diff options
Diffstat (limited to 'fs')
1043 files changed, 13570 insertions, 15532 deletions
diff --git a/fs/9p/Kconfig b/fs/9p/Kconfig index 11045d8e356a..ac2ec4543fe1 100644 --- a/fs/9p/Kconfig +++ b/fs/9p/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config 9P_FS tristate "Plan 9 Resource Sharing Support (9P2000)" depends on INET && NET_9P diff --git a/fs/9p/cache.c b/fs/9p/cache.c index 9eb34701a566..995e332eee5c 100644 --- a/fs/9p/cache.c +++ b/fs/9p/cache.c @@ -1,23 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * V9FS cache definitions. * * Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/jiffies.h> diff --git a/fs/9p/cache.h b/fs/9p/cache.h index 247e47e54bcc..00f107af443e 100644 --- a/fs/9p/cache.h +++ b/fs/9p/cache.h @@ -1,23 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * V9FS cache definitions. * * Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #ifndef _9P_CACHE_H diff --git a/fs/9p/fid.c b/fs/9p/fid.c index a9ef46f02354..3d681a2c2731 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -1,24 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * V9FS FID Management * * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net> * Copyright (C) 2005, 2006 by Eric Van Hensbergen <ericvh@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/module.h> diff --git a/fs/9p/fid.h b/fs/9p/fid.h index 4491bcaf42b8..928b1093f511 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -1,23 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * V9FS FID Management * * Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #ifndef FS_9P_FID_H #define FS_9P_FID_H diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 619128b55837..15a99f9c7253 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/v9fs.c * @@ -5,22 +6,6 @@ * * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 129e5243a6bf..7b763776306e 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -1,24 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * V9FS definitions. * * Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #ifndef FS_9P_V9FS_H #define FS_9P_V9FS_H diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 60cd4ba04afc..fd2a2b040250 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -1,24 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * V9FS VFS extensions. * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #ifndef FS_9P_V9FS_VFS_H #define FS_9P_V9FS_VFS_H diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 0bcbcc20f769..cce9ace651a2 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/vfs_addr.c * @@ -5,22 +6,6 @@ * * Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/module.h> @@ -50,8 +35,9 @@ * @page: structure to page * */ -static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) +static int v9fs_fid_readpage(void *data, struct page *page) { + struct p9_fid *fid = data; struct inode *inode = page->mapping->host; struct bio_vec bvec = {.bv_page = page, .bv_len = PAGE_SIZE}; struct iov_iter to; @@ -122,7 +108,8 @@ static int v9fs_vfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) return ret; - ret = read_cache_pages(mapping, pages, (void *)v9fs_vfs_readpage, filp); + ret = read_cache_pages(mapping, pages, v9fs_fid_readpage, + filp->private_data); p9_debug(P9_DEBUG_VFS, " = %d\n", ret); return ret; } diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index bd456c668d39..7d6f69aefd45 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/vfs_dentry.c * @@ -5,22 +6,6 @@ * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/module.h> diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 00745147329d..674d22bf4f6f 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/vfs_dir.c * @@ -5,22 +6,6 @@ * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/module.h> diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 9a1125305d84..4cc966a31cb3 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/vfs_file.c * @@ -5,22 +6,6 @@ * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/module.h> diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 24050e866e64..b82423a72f68 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/vfs_inode.c * @@ -5,22 +6,6 @@ * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index a950a927a626..60328b21c5fb 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/vfs_inode_dotl.c * @@ -5,22 +6,6 @@ * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/module.h> diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 67d1b965adcd..08112fbcaece 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/9p/vfs_super.c * @@ -6,22 +7,6 @@ * * Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include <linux/kernel.h> diff --git a/fs/Kconfig b/fs/Kconfig index cbbffc8b9ef5..bfb1c6095c7a 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # File system configuration # @@ -10,7 +11,6 @@ config DCACHE_WORD_ACCESS config VALIDATE_FS_PARSER bool "Validate filesystem parameter description" - default y help Enable this to perform validation of the parameter description for a filesystem when it is registered. diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index b795f8da81f3..62dc4f577ba1 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only menu "Executable file formats" @@ -90,12 +91,28 @@ config BINFMT_SCRIPT Most systems will not boot if you say M or N here. If unsure, say Y. +config ARCH_HAS_BINFMT_FLAT + bool + config BINFMT_FLAT bool "Kernel support for flat binaries" - depends on !MMU || ARM || M68K + depends on ARCH_HAS_BINFMT_FLAT help Support uClinux FLAT format binaries. +config BINFMT_FLAT_ARGVP_ENVP_ON_STACK + bool + +config BINFMT_FLAT_OLD_ALWAYS_RAM + bool + +config BINFMT_FLAT_OLD + bool "Enable support for very old legacy flat binaries" + depends on BINFMT_FLAT + help + Support decade old uClinux FLAT format binaries. Unless you know + you have some of those say N here. + config BINFMT_ZFLAT bool "Enable ZFLAT support" depends on BINFMT_FLAT diff --git a/fs/adfs/Kconfig b/fs/adfs/Kconfig index c5a7787dd5e9..df4650dccf68 100644 --- a/fs/adfs/Kconfig +++ b/fs/adfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config ADFS_FS tristate "ADFS file system support" depends on BLOCK diff --git a/fs/adfs/Makefile b/fs/adfs/Makefile index 9b2d71a9a35c..cf7de6ece659 100644 --- a/fs/adfs/Makefile +++ b/fs/adfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux adfs filesystem routines. # diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h index c76db75f02aa..804c6a77c5db 100644 --- a/fs/adfs/adfs.h +++ b/fs/adfs/adfs.h @@ -113,19 +113,6 @@ struct object_info { __u16 filetype; }; -/* RISC OS 12-bit filetype converts to ,xyz hex filename suffix */ -static inline int append_filetype_suffix(char *buf, __u16 filetype) -{ - if (filetype == 0xffff) /* no explicit 12-bit file type was set */ - return 0; - - *buf++ = ','; - *buf++ = hex_asc_lo(filetype >> 8); - *buf++ = hex_asc_lo(filetype >> 4); - *buf++ = hex_asc_lo(filetype >> 0); - return 4; -} - struct adfs_dir_ops { int (*read)(struct super_block *sb, unsigned int id, unsigned int sz, struct adfs_dir *dir); int (*setpos)(struct adfs_dir *dir, unsigned int fpos); @@ -172,6 +159,7 @@ extern const struct dentry_operations adfs_dentry_operations; extern const struct adfs_dir_ops adfs_f_dir_ops; extern const struct adfs_dir_ops adfs_fplus_dir_ops; +void adfs_object_fixup(struct adfs_dir *dir, struct object_info *obj); extern int adfs_dir_update(struct super_block *sb, struct object_info *obj, int wait); diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c index e18eff854e1a..35a4d9f4c3ae 100644 --- a/fs/adfs/dir.c +++ b/fs/adfs/dir.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/adfs/dir.c * * Copyright (C) 1999-2000 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Common directory handling for ADFS */ #include "adfs.h" @@ -16,6 +13,50 @@ */ static DEFINE_RWLOCK(adfs_dir_lock); +void adfs_object_fixup(struct adfs_dir *dir, struct object_info *obj) +{ + unsigned int dots, i; + + /* + * RISC OS allows the use of '/' in directory entry names, so we need + * to fix these up. '/' is typically used for FAT compatibility to + * represent '.', so do the same conversion here. In any case, '.' + * will never be in a RISC OS name since it is used as the pathname + * separator. Handle the case where we may generate a '.' or '..' + * name, replacing the first character with '^' (the RISC OS "parent + * directory" character.) + */ + for (i = dots = 0; i < obj->name_len; i++) + if (obj->name[i] == '/') { + obj->name[i] = '.'; + dots++; + } + + if (obj->name_len <= 2 && dots == obj->name_len) + obj->name[0] = '^'; + + obj->filetype = -1; + + /* + * object is a file and is filetyped and timestamped? + * RISC OS 12-bit filetype is stored in load_address[19:8] + */ + if ((0 == (obj->attr & ADFS_NDA_DIRECTORY)) && + (0xfff00000 == (0xfff00000 & obj->loadaddr))) { + obj->filetype = (__u16) ((0x000fff00 & obj->loadaddr) >> 8); + + /* optionally append the ,xyz hex filetype suffix */ + if (ADFS_SB(dir->sb)->s_ftsuffix) { + __u16 filetype = obj->filetype; + + obj->name[obj->name_len++] = ','; + obj->name[obj->name_len++] = hex_asc_lo(filetype >> 8); + obj->name[obj->name_len++] = hex_asc_lo(filetype >> 4); + obj->name[obj->name_len++] = hex_asc_lo(filetype >> 0); + } + } +} + static int adfs_readdir(struct file *file, struct dir_context *ctx) { @@ -100,37 +141,36 @@ out: return ret; } -static int -adfs_match(const struct qstr *name, struct object_info *obj) +static unsigned char adfs_tolower(unsigned char c) { - int i; - - if (name->len != obj->name_len) - return 0; + if (c >= 'A' && c <= 'Z') + c += 'a' - 'A'; + return c; +} - for (i = 0; i < name->len; i++) { - char c1, c2; +static int __adfs_compare(const unsigned char *qstr, u32 qlen, + const char *str, u32 len) +{ + u32 i; - c1 = name->name[i]; - c2 = obj->name[i]; + if (qlen != len) + return 1; - if (c1 >= 'A' && c1 <= 'Z') - c1 += 'a' - 'A'; - if (c2 >= 'A' && c2 <= 'Z') - c2 += 'a' - 'A'; + for (i = 0; i < qlen; i++) + if (adfs_tolower(qstr[i]) != adfs_tolower(str[i])) + return 1; - if (c1 != c2) - return 0; - } - return 1; + return 0; } -static int -adfs_dir_lookup_byname(struct inode *inode, const struct qstr *name, struct object_info *obj) +static int adfs_dir_lookup_byname(struct inode *inode, const struct qstr *qstr, + struct object_info *obj) { struct super_block *sb = inode->i_sb; const struct adfs_dir_ops *ops = ADFS_SB(sb)->s_dir; + const unsigned char *name; struct adfs_dir dir; + u32 name_len; int ret; ret = ops->read(sb, inode->i_ino, inode->i_size, &dir); @@ -153,8 +193,10 @@ adfs_dir_lookup_byname(struct inode *inode, const struct qstr *name, struct obje goto unlock_out; ret = -ENOENT; + name = qstr->name; + name_len = qstr->len; while (ops->getnext(&dir, obj) == 0) { - if (adfs_match(name, obj)) { + if (!__adfs_compare(name, name_len, obj->name, obj->name_len)) { ret = 0; break; } @@ -179,30 +221,18 @@ const struct file_operations adfs_dir_operations = { static int adfs_hash(const struct dentry *parent, struct qstr *qstr) { - const unsigned int name_len = ADFS_SB(parent->d_sb)->s_namelen; const unsigned char *name; unsigned long hash; - int i; + u32 len; - if (qstr->len < name_len) - return 0; + if (qstr->len > ADFS_SB(parent->d_sb)->s_namelen) + return -ENAMETOOLONG; - /* - * Truncate the name in place, avoids - * having to define a compare function. - */ - qstr->len = i = name_len; + len = qstr->len; name = qstr->name; hash = init_name_hash(parent); - while (i--) { - char c; - - c = *name++; - if (c >= 'A' && c <= 'Z') - c += 'a' - 'A'; - - hash = partial_name_hash(c, hash); - } + while (len--) + hash = partial_name_hash(adfs_tolower(*name++), hash); qstr->hash = end_name_hash(hash); return 0; @@ -212,30 +242,10 @@ adfs_hash(const struct dentry *parent, struct qstr *qstr) * Compare two names, taking note of the name length * requirements of the underlying filesystem. */ -static int -adfs_compare(const struct dentry *dentry, - unsigned int len, const char *str, const struct qstr *name) +static int adfs_compare(const struct dentry *dentry, unsigned int len, + const char *str, const struct qstr *qstr) { - int i; - - if (len != name->len) - return 1; - - for (i = 0; i < name->len; i++) { - char a, b; - - a = str[i]; - b = name->name[i]; - - if (a >= 'A' && a <= 'Z') - a += 'a' - 'A'; - if (b >= 'A' && b <= 'Z') - b += 'a' - 'A'; - - if (a != b) - return 1; - } - return 0; + return __adfs_compare(qstr->name, qstr->len, str, len); } const struct dentry_operations adfs_dentry_operations = { diff --git a/fs/adfs/dir_f.c b/fs/adfs/dir_f.c index 382c9d7ad375..7557378e58b3 100644 --- a/fs/adfs/dir_f.c +++ b/fs/adfs/dir_f.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/adfs/dir_f.c * * Copyright (C) 1997-1999 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * E and F format directory handling */ #include <linux/buffer_head.h> @@ -47,21 +44,6 @@ static inline void adfs_writeval(unsigned char *p, int len, unsigned int val) } } -static inline int adfs_readname(char *buf, char *ptr, int maxlen) -{ - char *old_buf = buf; - - while ((unsigned char)*ptr >= ' ' && maxlen--) { - if (*ptr == '/') - *buf++ = '.'; - else - *buf++ = *ptr; - ptr++; - } - - return buf - old_buf; -} - #define ror13(v) ((v >> 13) | (v << 19)) #define dir_u8(idx) \ @@ -216,29 +198,23 @@ static inline void adfs_dir2obj(struct adfs_dir *dir, struct object_info *obj, struct adfs_direntry *de) { - obj->name_len = adfs_readname(obj->name, de->dirobname, ADFS_F_NAME_LEN); + unsigned int name_len; + + for (name_len = 0; name_len < ADFS_F_NAME_LEN; name_len++) { + if (de->dirobname[name_len] < ' ') + break; + + obj->name[name_len] = de->dirobname[name_len]; + } + + obj->name_len = name_len; obj->file_id = adfs_readval(de->dirinddiscadd, 3); obj->loadaddr = adfs_readval(de->dirload, 4); obj->execaddr = adfs_readval(de->direxec, 4); obj->size = adfs_readval(de->dirlen, 4); obj->attr = de->newdiratts; - obj->filetype = -1; - /* - * object is a file and is filetyped and timestamped? - * RISC OS 12-bit filetype is stored in load_address[19:8] - */ - if ((0 == (obj->attr & ADFS_NDA_DIRECTORY)) && - (0xfff00000 == (0xfff00000 & obj->loadaddr))) { - obj->filetype = (__u16) ((0x000fff00 & obj->loadaddr) >> 8); - - /* optionally append the ,xyz hex filetype suffix */ - if (ADFS_SB(dir->sb)->s_ftsuffix) - obj->name_len += - append_filetype_suffix( - &obj->name[obj->name_len], - obj->filetype); - } + adfs_object_fixup(dir, obj); } /* diff --git a/fs/adfs/dir_f.h b/fs/adfs/dir_f.h index e4713404096c..5aec332b90f5 100644 --- a/fs/adfs/dir_f.h +++ b/fs/adfs/dir_f.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/fs/adfs/dir_f.h * * Copyright (C) 1999 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Structures of directories on the F format disk */ #ifndef ADFS_DIR_F_H diff --git a/fs/adfs/dir_fplus.c b/fs/adfs/dir_fplus.c index c92cfb638c18..6c5fbb0259c9 100644 --- a/fs/adfs/dir_fplus.c +++ b/fs/adfs/dir_fplus.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/adfs/dir_fplus.c * * Copyright (C) 1997-1999 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/buffer_head.h> #include <linux/slab.h> @@ -169,7 +166,7 @@ adfs_fplus_getnext(struct adfs_dir *dir, struct object_info *obj) (struct adfs_bigdirheader *) dir->bh_fplus[0]->b_data; struct adfs_bigdirentry bde; unsigned int offset; - int i, ret = -ENOENT; + int ret = -ENOENT; if (dir->pos >= le32_to_cpu(h->bigdirentries)) goto out; @@ -193,27 +190,7 @@ adfs_fplus_getnext(struct adfs_dir *dir, struct object_info *obj) offset += le32_to_cpu(bde.bigdirobnameptr); dir_memcpy(dir, offset, obj->name, obj->name_len); - for (i = 0; i < obj->name_len; i++) - if (obj->name[i] == '/') - obj->name[i] = '.'; - - obj->filetype = -1; - - /* - * object is a file and is filetyped and timestamped? - * RISC OS 12-bit filetype is stored in load_address[19:8] - */ - if ((0 == (obj->attr & ADFS_NDA_DIRECTORY)) && - (0xfff00000 == (0xfff00000 & obj->loadaddr))) { - obj->filetype = (__u16) ((0x000fff00 & obj->loadaddr) >> 8); - - /* optionally append the ,xyz hex filetype suffix */ - if (ADFS_SB(dir->sb)->s_ftsuffix) - obj->name_len += - append_filetype_suffix( - &obj->name[obj->name_len], - obj->filetype); - } + adfs_object_fixup(dir, obj); dir->pos += 1; ret = 0; diff --git a/fs/adfs/dir_fplus.h b/fs/adfs/dir_fplus.h index b55aa41a68fe..4ec0931e36ad 100644 --- a/fs/adfs/dir_fplus.h +++ b/fs/adfs/dir_fplus.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/fs/adfs/dir_fplus.h * * Copyright (C) 1999 Russell King * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Structures of directories on the F+ format disk */ diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 66621e96f9af..904d624541ad 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/adfs/inode.c * * Copyright (C) 1997-1999 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/buffer_head.h> #include <linux/writeback.h> diff --git a/fs/adfs/map.c b/fs/adfs/map.c index 6935f05202ac..4d34338c6176 100644 --- a/fs/adfs/map.c +++ b/fs/adfs/map.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/adfs/map.c * * Copyright (C) 1997-2002 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/buffer_head.h> #include <asm/unaligned.h> diff --git a/fs/adfs/super.c b/fs/adfs/super.c index 2a83655c408f..ffb669f9bba7 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/adfs/super.c * * Copyright (C) 1997-1999 Russell King - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/module.h> #include <linux/init.h> diff --git a/fs/affs/Kconfig b/fs/affs/Kconfig index a04d9e848d05..84c46b9025c5 100644 --- a/fs/affs/Kconfig +++ b/fs/affs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config AFFS_FS tristate "Amiga FFS file system support" depends on BLOCK diff --git a/fs/affs/Makefile b/fs/affs/Makefile index 3988b4a78339..f2c811429a4e 100644 --- a/fs/affs/Makefile +++ b/fs/affs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux affs filesystem routines. # diff --git a/fs/affs/super.c b/fs/affs/super.c index 7370228eefb2..e7d036efbaa1 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/affs/inode.c * diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig index 701aaa9b1899..3fb1f559e317 100644 --- a/fs/afs/Kconfig +++ b/fs/afs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config AFS_FS tristate "Andrew File System support (AFS)" depends on INET diff --git a/fs/afs/Makefile b/fs/afs/Makefile index cbf31f6cd177..10359bea7070 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -29,7 +29,6 @@ kafs-y := \ server.o \ server_list.o \ super.o \ - netdevices.o \ vlclient.o \ vl_list.o \ vl_probe.o \ diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 967db336d11a..df415c05939e 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Server address list management * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/slab.h> @@ -250,8 +246,8 @@ struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry _enter("%s", cell->name); - ret = dns_query("afsdb", cell->name, cell->name_len, "srv=1", - &result, _expiry); + ret = dns_query(cell->net->net, "afsdb", cell->name, cell->name_len, + "srv=1", &result, _expiry, true); if (ret < 0) { _leave(" = %d [dns]", ret); return ERR_PTR(ret); diff --git a/fs/afs/afs.h b/fs/afs/afs.h index d12ffb457e47..b6d49d646ade 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* AFS common types * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #ifndef AFS_H @@ -23,6 +19,9 @@ #define AFSPATHMAX 1024 /* Maximum length of a pathname plus NUL */ #define AFSOPAQUEMAX 1024 /* Maximum length of an opaque field */ +#define AFS_VL_MAX_LIFESPAN (120 * HZ) +#define AFS_PROBE_MAX_LIFESPAN (30 * HZ) + typedef u64 afs_volid_t; typedef u64 afs_vnodeid_t; typedef u64 afs_dataversion_t; @@ -69,8 +68,8 @@ typedef enum { struct afs_callback { time64_t expires_at; /* Time at which expires */ - unsigned version; /* Callback version */ - afs_callback_type_t type; /* Type of callback */ + //unsigned version; /* Callback version */ + //afs_callback_type_t type; /* Type of callback */ }; struct afs_callback_break { @@ -144,6 +143,15 @@ struct afs_file_status { u32 abort_code; /* Abort if bulk-fetching this failed */ }; +struct afs_status_cb { + struct afs_file_status status; + struct afs_callback callback; + unsigned int cb_break; /* Pre-op callback break counter */ + bool have_status; /* True if status record was retrieved */ + bool have_cb; /* True if cb record was retrieved */ + bool have_error; /* True if status.abort_code indicates an error */ +}; + /* * AFS file status change request */ diff --git a/fs/afs/afs_cm.h b/fs/afs/afs_cm.h index 255f5dd6040c..565cbe0a8af6 100644 --- a/fs/afs/afs_cm.h +++ b/fs/afs/afs_cm.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* AFS Cache Manager definitions * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #ifndef AFS_CM_H diff --git a/fs/afs/afs_fs.h b/fs/afs/afs_fs.h index 18a54ca422f8..20ab344baf9d 100644 --- a/fs/afs/afs_fs.h +++ b/fs/afs/afs_fs.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* AFS File Service definitions * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #ifndef AFS_FS_H diff --git a/fs/afs/afs_vl.h b/fs/afs/afs_vl.h index e3c4688f573b..e9b8029920ec 100644 --- a/fs/afs/afs_vl.h +++ b/fs/afs/afs_vl.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* AFS Volume Location Service client interface * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #ifndef AFS_VL_H diff --git a/fs/afs/cache.c b/fs/afs/cache.c index f6d0a21e8052..037af93e3aba 100644 --- a/fs/afs/cache.c +++ b/fs/afs/cache.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS caching stuff * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/sched.h> diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 128f2dbe256a..6cdd7047c809 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -48,7 +48,7 @@ static struct afs_cb_interest *afs_create_interest(struct afs_server *server, refcount_set(&new->usage, 1); new->sb = vnode->vfs_inode.i_sb; new->vid = vnode->volume->vid; - new->server = afs_get_server(server); + new->server = afs_get_server(server, afs_server_trace_get_new_cbi); INIT_HLIST_NODE(&new->cb_vlink); write_lock(&server->cb_break_lock); @@ -94,15 +94,15 @@ int afs_register_server_cb_interest(struct afs_vnode *vnode, struct afs_server *server = entry->server; again: - if (vnode->cb_interest && - likely(vnode->cb_interest == entry->cb_interest)) + vcbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock)); + if (vcbi && likely(vcbi == entry->cb_interest)) return 0; read_lock(&slist->lock); cbi = afs_get_cb_interest(entry->cb_interest); read_unlock(&slist->lock); - vcbi = vnode->cb_interest; if (vcbi) { if (vcbi == cbi) { afs_put_cb_interest(afs_v2net(vnode), cbi); @@ -114,8 +114,9 @@ again: */ if (cbi && vcbi->server == cbi->server) { write_seqlock(&vnode->cb_lock); - old = vnode->cb_interest; - vnode->cb_interest = cbi; + old = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + rcu_assign_pointer(vnode->cb_interest, cbi); write_sequnlock(&vnode->cb_lock); afs_put_cb_interest(afs_v2net(vnode), old); return 0; @@ -160,8 +161,9 @@ again: */ write_seqlock(&vnode->cb_lock); - old = vnode->cb_interest; - vnode->cb_interest = cbi; + old = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + rcu_assign_pointer(vnode->cb_interest, cbi); vnode->cb_s_break = cbi->server->cb_s_break; vnode->cb_v_break = vnode->volume->cb_v_break; clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); @@ -191,10 +193,11 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi) vi = NULL; write_unlock(&cbi->server->cb_break_lock); - kfree(vi); - afs_put_server(net, cbi->server); + if (vi) + kfree_rcu(vi, rcu); + afs_put_server(net, cbi->server, afs_server_trace_put_cbi); } - kfree(cbi); + kfree_rcu(cbi, rcu); } } @@ -209,7 +212,7 @@ void afs_init_callback_state(struct afs_server *server) /* * actually break a callback */ -void __afs_break_callback(struct afs_vnode *vnode) +void __afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reason) { _enter(""); @@ -218,21 +221,19 @@ void __afs_break_callback(struct afs_vnode *vnode) vnode->cb_break++; afs_clear_permits(vnode); - spin_lock(&vnode->lock); - - _debug("break callback"); - - if (list_empty(&vnode->granted_locks) && - !list_empty(&vnode->pending_locks)) + if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB) afs_lock_may_be_available(vnode); - spin_unlock(&vnode->lock); + + trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, true); + } else { + trace_afs_cb_break(&vnode->fid, vnode->cb_break, reason, false); } } -void afs_break_callback(struct afs_vnode *vnode) +void afs_break_callback(struct afs_vnode *vnode, enum afs_cb_break_reason reason) { write_seqlock(&vnode->cb_lock); - __afs_break_callback(vnode); + __afs_break_callback(vnode, reason); write_sequnlock(&vnode->cb_lock); } @@ -278,9 +279,11 @@ static void afs_break_one_callback(struct afs_server *server, struct afs_super_info *as = AFS_FS_S(cbi->sb); struct afs_volume *volume = as->volume; - write_lock(&volume->cb_break_lock); + write_lock(&volume->cb_v_break_lock); volume->cb_v_break++; - write_unlock(&volume->cb_break_lock); + trace_afs_cb_break(fid, volume->cb_v_break, + afs_cb_break_for_volume_callback, false); + write_unlock(&volume->cb_v_break_lock); } else { data.volume = NULL; data.fid = *fid; @@ -288,8 +291,10 @@ static void afs_break_one_callback(struct afs_server *server, afs_iget5_test, &data); if (inode) { vnode = AFS_FS_I(inode); - afs_break_callback(vnode); + afs_break_callback(vnode, afs_cb_break_for_callback); iput(inode); + } else { + trace_afs_cb_miss(fid, afs_cb_break_for_callback); } } } diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 9de46116c749..a2a87117d262 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS cell and server record management * * Copyright (C) 2002, 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/slab.h> @@ -123,6 +119,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, const char *name, unsigned int namelen, const char *addresses) { + struct afs_vlserver_list *vllist; struct afs_cell *cell; int i, ret; @@ -151,18 +148,14 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, atomic_set(&cell->usage, 2); INIT_WORK(&cell->manager, afs_manage_cell); - cell->flags = ((1 << AFS_CELL_FL_NOT_READY) | - (1 << AFS_CELL_FL_NO_LOOKUP_YET)); INIT_LIST_HEAD(&cell->proc_volumes); rwlock_init(&cell->proc_lock); rwlock_init(&cell->vl_servers_lock); - /* Fill in the VL server list if we were given a list of addresses to - * use. + /* Provide a VL server list, filling it in if we were given a list of + * addresses to use. */ if (addresses) { - struct afs_vlserver_list *vllist; - vllist = afs_parse_text_addrs(net, addresses, strlen(addresses), ':', VL_SERVICE, AFS_VL_PORT); @@ -171,19 +164,32 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, goto parse_failed; } - rcu_assign_pointer(cell->vl_servers, vllist); + vllist->source = DNS_RECORD_FROM_CONFIG; + vllist->status = DNS_LOOKUP_NOT_DONE; cell->dns_expiry = TIME64_MAX; - __clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags); } else { + ret = -ENOMEM; + vllist = afs_alloc_vlserver_list(0); + if (!vllist) + goto error; + vllist->source = DNS_RECORD_UNAVAILABLE; + vllist->status = DNS_LOOKUP_NOT_DONE; cell->dns_expiry = ktime_get_real_seconds(); } + rcu_assign_pointer(cell->vl_servers, vllist); + + cell->dns_source = vllist->source; + cell->dns_status = vllist->status; + smp_store_release(&cell->dns_lookup_count, 1); /* vs source/status */ + _leave(" = %p", cell); return cell; parse_failed: if (ret == -EINVAL) printk(KERN_ERR "kAFS: bad VL server IP address\n"); +error: kfree(cell); _leave(" = %d", ret); return ERR_PTR(ret); @@ -208,6 +214,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, { struct afs_cell *cell, *candidate, *cursor; struct rb_node *parent, **pp; + enum afs_cell_state state; int ret, n; _enter("%s,%s", name, vllist); @@ -267,18 +274,16 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net, wait_for_cell: _debug("wait_for_cell"); - ret = wait_on_bit(&cell->flags, AFS_CELL_FL_NOT_READY, TASK_INTERRUPTIBLE); - smp_rmb(); - - switch (READ_ONCE(cell->state)) { - case AFS_CELL_FAILED: + wait_var_event(&cell->state, + ({ + state = smp_load_acquire(&cell->state); /* vs error */ + state == AFS_CELL_ACTIVE || state == AFS_CELL_FAILED; + })); + + /* Check the state obtained from the wait check. */ + if (state == AFS_CELL_FAILED) { ret = cell->error; goto error; - default: - _debug("weird %u %d", cell->state, cell->error); - goto error; - case AFS_CELL_ACTIVE: - break; } _leave(" = %p [cell]", cell); @@ -360,16 +365,46 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) /* * Update a cell's VL server address list from the DNS. */ -static void afs_update_cell(struct afs_cell *cell) +static int afs_update_cell(struct afs_cell *cell) { - struct afs_vlserver_list *vllist, *old; + struct afs_vlserver_list *vllist, *old = NULL, *p; unsigned int min_ttl = READ_ONCE(afs_cell_min_ttl); unsigned int max_ttl = READ_ONCE(afs_cell_max_ttl); time64_t now, expiry = 0; + int ret = 0; _enter("%s", cell->name); vllist = afs_dns_query(cell, &expiry); + if (IS_ERR(vllist)) { + ret = PTR_ERR(vllist); + + _debug("%s: fail %d", cell->name, ret); + if (ret == -ENOMEM) + goto out_wake; + + ret = -ENOMEM; + vllist = afs_alloc_vlserver_list(0); + if (!vllist) + goto out_wake; + + switch (ret) { + case -ENODATA: + case -EDESTADDRREQ: + vllist->status = DNS_LOOKUP_GOT_NOT_FOUND; + break; + case -EAGAIN: + case -ECONNREFUSED: + vllist->status = DNS_LOOKUP_GOT_TEMP_FAILURE; + break; + default: + vllist->status = DNS_LOOKUP_GOT_LOCAL_FAILURE; + break; + } + } + + _debug("%s: got list %d %d", cell->name, vllist->source, vllist->status); + cell->dns_status = vllist->status; now = ktime_get_real_seconds(); if (min_ttl > max_ttl) @@ -379,48 +414,47 @@ static void afs_update_cell(struct afs_cell *cell) else if (expiry > now + max_ttl) expiry = now + max_ttl; - if (IS_ERR(vllist)) { - switch (PTR_ERR(vllist)) { - case -ENODATA: - case -EDESTADDRREQ: + _debug("%s: status %d", cell->name, vllist->status); + if (vllist->source == DNS_RECORD_UNAVAILABLE) { + switch (vllist->status) { + case DNS_LOOKUP_GOT_NOT_FOUND: /* The DNS said that the cell does not exist or there * weren't any addresses to be had. */ - set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags); - clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); cell->dns_expiry = expiry; break; - case -EAGAIN: - case -ECONNREFUSED: + case DNS_LOOKUP_BAD: + case DNS_LOOKUP_GOT_LOCAL_FAILURE: + case DNS_LOOKUP_GOT_TEMP_FAILURE: + case DNS_LOOKUP_GOT_NS_FAILURE: default: - set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); cell->dns_expiry = now + 10; break; } - - cell->error = -EDESTADDRREQ; } else { - clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); - clear_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags); - - /* Exclusion on changing vl_addrs is achieved by a - * non-reentrant work item. - */ - old = rcu_dereference_protected(cell->vl_servers, true); - rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = expiry; - - if (old) - afs_put_vlserverlist(cell->net, old); } - if (test_and_clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags)) - wake_up_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET); + /* Replace the VL server list if the new record has servers or the old + * record doesn't. + */ + write_lock(&cell->vl_servers_lock); + p = rcu_dereference_protected(cell->vl_servers, true); + if (vllist->nr_servers > 0 || p->nr_servers == 0) { + rcu_assign_pointer(cell->vl_servers, vllist); + cell->dns_source = vllist->source; + old = p; + } + write_unlock(&cell->vl_servers_lock); + afs_put_vlserverlist(cell->net, old); - now = ktime_get_real_seconds(); - afs_set_cell_timer(cell->net, cell->dns_expiry - now); - _leave(""); +out_wake: + smp_store_release(&cell->dns_lookup_count, + cell->dns_lookup_count + 1); /* vs source/status */ + wake_up_var(&cell->dns_lookup_count); + _leave(" = %d", ret); + return ret; } /* @@ -491,8 +525,7 @@ void afs_put_cell(struct afs_net *net, struct afs_cell *cell) now = ktime_get_real_seconds(); cell->last_inactive = now; expire_delay = 0; - if (!test_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags) && - !test_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags)) + if (cell->vl_servers->nr_servers) expire_delay = afs_cell_gc_delay; if (atomic_dec_return(&cell->usage) > 1) @@ -623,11 +656,13 @@ again: goto final_destruction; if (cell->state == AFS_CELL_FAILED) goto done; - cell->state = AFS_CELL_UNSET; + smp_store_release(&cell->state, AFS_CELL_UNSET); + wake_up_var(&cell->state); goto again; case AFS_CELL_UNSET: - cell->state = AFS_CELL_ACTIVATING; + smp_store_release(&cell->state, AFS_CELL_ACTIVATING); + wake_up_var(&cell->state); goto again; case AFS_CELL_ACTIVATING: @@ -635,28 +670,29 @@ again: if (ret < 0) goto activation_failed; - cell->state = AFS_CELL_ACTIVE; - smp_wmb(); - clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags); - wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY); + smp_store_release(&cell->state, AFS_CELL_ACTIVE); + wake_up_var(&cell->state); goto again; case AFS_CELL_ACTIVE: if (atomic_read(&cell->usage) > 1) { - time64_t now = ktime_get_real_seconds(); - if (cell->dns_expiry <= now && net->live) - afs_update_cell(cell); + if (test_and_clear_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags)) { + ret = afs_update_cell(cell); + if (ret < 0) + cell->error = ret; + } goto done; } - cell->state = AFS_CELL_DEACTIVATING; + smp_store_release(&cell->state, AFS_CELL_DEACTIVATING); + wake_up_var(&cell->state); goto again; case AFS_CELL_DEACTIVATING: - set_bit(AFS_CELL_FL_NOT_READY, &cell->flags); if (atomic_read(&cell->usage) > 1) goto reverse_deactivation; afs_deactivate_cell(net, cell); - cell->state = AFS_CELL_INACTIVE; + smp_store_release(&cell->state, AFS_CELL_INACTIVE); + wake_up_var(&cell->state); goto again; default: @@ -669,17 +705,13 @@ activation_failed: cell->error = ret; afs_deactivate_cell(net, cell); - cell->state = AFS_CELL_FAILED; - smp_wmb(); - if (test_and_clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags)) - wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY); + smp_store_release(&cell->state, AFS_CELL_FAILED); /* vs error */ + wake_up_var(&cell->state); goto again; reverse_deactivation: - cell->state = AFS_CELL_ACTIVE; - smp_wmb(); - clear_bit(AFS_CELL_FL_NOT_READY, &cell->flags); - wake_up_bit(&cell->flags, AFS_CELL_FL_NOT_READY); + smp_store_release(&cell->state, AFS_CELL_ACTIVE); + wake_up_var(&cell->state); _leave(" [deact->act]"); return; @@ -739,11 +771,16 @@ void afs_manage_cells(struct work_struct *work) } if (usage == 1) { + struct afs_vlserver_list *vllist; time64_t expire_at = cell->last_inactive; - if (!test_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags) && - !test_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags)) + read_lock(&cell->vl_servers_lock); + vllist = rcu_dereference_protected( + cell->vl_servers, + lockdep_is_held(&cell->vl_servers_lock)); + if (vllist->nr_servers > 0) expire_at += afs_cell_gc_delay; + read_unlock(&cell->vl_servers_lock); if (purging || expire_at <= now) sched_cell = true; else if (expire_at < next_manage) @@ -751,10 +788,8 @@ void afs_manage_cells(struct work_struct *work) } if (!purging) { - if (cell->dns_expiry <= now) + if (test_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags)) sched_cell = true; - else if (cell->dns_expiry <= next_manage) - next_manage = cell->dns_expiry; } if (sched_cell) diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 748090014519..4f1b6f466ff5 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS Cache Manager Service * * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> @@ -213,7 +209,7 @@ static int afs_find_cm_server_by_peer(struct afs_call *call) return 0; } - call->cm_server = server; + call->server = server; return afs_record_cm_probe(call, server); } @@ -234,7 +230,7 @@ static int afs_find_cm_server_by_uuid(struct afs_call *call, return 0; } - call->cm_server = server; + call->server = server; return afs_record_cm_probe(call, server); } @@ -260,8 +256,11 @@ static void SRXAFSCB_CallBack(struct work_struct *work) * server holds up change visibility till it receives our reply so as * to maintain cache coherency. */ - if (call->cm_server) - afs_break_callbacks(call->cm_server, call->count, call->request); + if (call->server) { + trace_afs_server(call->server, atomic_read(&call->server->usage), + afs_server_trace_callback); + afs_break_callbacks(call->server, call->count, call->request); + } afs_send_empty_reply(call); afs_put_call(call); @@ -376,10 +375,10 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) { struct afs_call *call = container_of(work, struct afs_call, work); - _enter("{%p}", call->cm_server); + _enter("{%p}", call->server); - if (call->cm_server) - afs_init_callback_state(call->cm_server); + if (call->server) + afs_init_callback_state(call->server); afs_send_empty_reply(call); afs_put_call(call); _leave(""); @@ -584,9 +583,8 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) */ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) { - struct afs_interface *ifs; struct afs_call *call = container_of(work, struct afs_call, work); - int loop, nifs; + int loop; struct { struct /* InterfaceAddr */ { @@ -604,19 +602,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) _enter(""); - nifs = 0; - ifs = kcalloc(32, sizeof(*ifs), GFP_KERNEL); - if (ifs) { - nifs = afs_get_ipv4_interfaces(call->net, ifs, 32, false); - if (nifs < 0) { - kfree(ifs); - ifs = NULL; - nifs = 0; - } - } - memset(&reply, 0, sizeof(reply)); - reply.ia.nifs = htonl(nifs); reply.ia.uuid[0] = call->net->uuid.time_low; reply.ia.uuid[1] = htonl(ntohs(call->net->uuid.time_mid)); @@ -626,15 +612,6 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) for (loop = 0; loop < 6; loop++) reply.ia.uuid[loop + 5] = htonl((s8) call->net->uuid.node[loop]); - if (ifs) { - for (loop = 0; loop < nifs; loop++) { - reply.ia.ifaddr[loop] = ifs[loop].address.s_addr; - reply.ia.netmask[loop] = ifs[loop].netmask.s_addr; - reply.ia.mtu[loop] = htonl(ifs[loop].mtu); - } - kfree(ifs); - } - reply.cap.capcount = htonl(1); reply.cap.caps[0] = htonl(AFS_CAP_ERROR_TRANSLATION); afs_send_simple_reply(call, &reply, sizeof(reply)); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 9a466be583d2..e640d67274be 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* dir.c: AFS filesystem directory handling * * Copyright (C) 2002, 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> @@ -18,6 +14,7 @@ #include <linux/sched.h> #include <linux/task_io_accounting_ops.h> #include "internal.h" +#include "afs_fs.h" #include "xdr_fs.h" static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, @@ -102,8 +99,8 @@ struct afs_lookup_cookie { bool found; bool one_only; unsigned short nr_fids; - struct afs_file_status *statuses; - struct afs_callback *callbacks; + struct inode **inodes; + struct afs_status_cb *statuses; struct afs_fid fids[50]; }; @@ -241,8 +238,7 @@ retry: if (nr_inline > (PAGE_SIZE - sizeof(*req)) / sizeof(struct page *)) nr_inline = 0; - req = kzalloc(sizeof(*req) + sizeof(struct page *) * nr_inline, - GFP_KERNEL); + req = kzalloc(struct_size(req, array, nr_inline), GFP_KERNEL); if (!req) return ERR_PTR(-ENOMEM); @@ -638,12 +634,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, struct key *key) { struct afs_lookup_cookie *cookie; - struct afs_cb_interest *cbi = NULL; + struct afs_cb_interest *dcbi, *cbi = NULL; struct afs_super_info *as = dir->i_sb->s_fs_info; - struct afs_iget_data data; + struct afs_status_cb *scb; + struct afs_iget_data iget_data; struct afs_fs_cursor fc; - struct afs_vnode *dvnode = AFS_FS_I(dir); - struct inode *inode = NULL; + struct afs_server *server; + struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; + struct inode *inode = NULL, *ti; int ret, i; _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); @@ -657,10 +655,14 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, cookie->nr_fids = 1; /* slot 0 is saved for the fid we actually want */ read_seqlock_excl(&dvnode->cb_lock); - if (dvnode->cb_interest && - dvnode->cb_interest->server && - test_bit(AFS_SERVER_FL_NO_IBULK, &dvnode->cb_interest->server->flags)) - cookie->one_only = true; + dcbi = rcu_dereference_protected(dvnode->cb_interest, + lockdep_is_held(&dvnode->cb_lock.lock)); + if (dcbi) { + server = dcbi->server; + if (server && + test_bit(AFS_SERVER_FL_NO_IBULK, &server->flags)) + cookie->one_only = true; + } read_sequnlock_excl(&dvnode->cb_lock); for (i = 0; i < 50; i++) @@ -678,24 +680,43 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, goto out; /* Check to see if we already have an inode for the primary fid. */ - data.volume = dvnode->volume; - data.fid = cookie->fids[0]; - inode = ilookup5(dir->i_sb, cookie->fids[0].vnode, afs_iget5_test, &data); + iget_data.fid = cookie->fids[0]; + iget_data.volume = dvnode->volume; + iget_data.cb_v_break = dvnode->volume->cb_v_break; + iget_data.cb_s_break = 0; + inode = ilookup5(dir->i_sb, cookie->fids[0].vnode, + afs_iget5_test, &iget_data); if (inode) goto out; /* Need space for examining all the selected files */ inode = ERR_PTR(-ENOMEM); - cookie->statuses = kcalloc(cookie->nr_fids, sizeof(struct afs_file_status), - GFP_KERNEL); + cookie->statuses = kvcalloc(cookie->nr_fids, sizeof(struct afs_status_cb), + GFP_KERNEL); if (!cookie->statuses) goto out; - cookie->callbacks = kcalloc(cookie->nr_fids, sizeof(struct afs_callback), - GFP_KERNEL); - if (!cookie->callbacks) + cookie->inodes = kcalloc(cookie->nr_fids, sizeof(struct inode *), + GFP_KERNEL); + if (!cookie->inodes) goto out_s; + for (i = 1; i < cookie->nr_fids; i++) { + scb = &cookie->statuses[i]; + + /* Find any inodes that already exist and get their + * callback counters. + */ + iget_data.fid = cookie->fids[i]; + ti = ilookup5_nowait(dir->i_sb, iget_data.fid.vnode, + afs_iget5_test, &iget_data); + if (!IS_ERR_OR_NULL(ti)) { + vnode = AFS_FS_I(ti); + scb->cb_break = afs_calc_vnode_cb_break(vnode); + cookie->inodes[i] = ti; + } + } + /* Try FS.InlineBulkStatus first. Abort codes for the individual * lookups contained therein are stored in the reply without aborting * the whole operation. @@ -704,7 +725,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, goto no_inline_bulk_status; inode = ERR_PTR(-ERESTARTSYS); - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { while (afs_select_fileserver(&fc)) { if (test_bit(AFS_SERVER_FL_NO_IBULK, &fc.cbi->server->flags)) { @@ -712,11 +733,12 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, fc.ac.error = -ECONNABORTED; break; } + iget_data.cb_v_break = dvnode->volume->cb_v_break; + iget_data.cb_s_break = fc.cbi->server->cb_s_break; afs_fs_inline_bulk_status(&fc, afs_v2net(dvnode), cookie->fids, cookie->statuses, - cookie->callbacks, cookie->nr_fids, NULL); } @@ -737,15 +759,16 @@ no_inline_bulk_status: * any of the lookups fails - so, for the moment, revert to * FS.FetchStatus for just the primary fid. */ - cookie->nr_fids = 1; inode = ERR_PTR(-ERESTARTSYS); - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { while (afs_select_fileserver(&fc)) { + iget_data.cb_v_break = dvnode->volume->cb_v_break; + iget_data.cb_s_break = fc.cbi->server->cb_s_break; + scb = &cookie->statuses[0]; afs_fs_fetch_status(&fc, afs_v2net(dvnode), cookie->fids, - cookie->statuses, - cookie->callbacks, + scb, NULL); } @@ -757,26 +780,36 @@ no_inline_bulk_status: if (IS_ERR(inode)) goto out_c; - for (i = 0; i < cookie->nr_fids; i++) - cookie->statuses[i].abort_code = 0; - success: /* Turn all the files into inodes and save the first one - which is the * one we actually want. */ - if (cookie->statuses[0].abort_code != 0) - inode = ERR_PTR(afs_abort_to_error(cookie->statuses[0].abort_code)); + scb = &cookie->statuses[0]; + if (scb->status.abort_code != 0) + inode = ERR_PTR(afs_abort_to_error(scb->status.abort_code)); for (i = 0; i < cookie->nr_fids; i++) { - struct inode *ti; + struct afs_status_cb *scb = &cookie->statuses[i]; + + if (!scb->have_status && !scb->have_error) + continue; - if (cookie->statuses[i].abort_code != 0) + if (cookie->inodes[i]) { + afs_vnode_commit_status(&fc, AFS_FS_I(cookie->inodes[i]), + scb->cb_break, NULL, scb); + continue; + } + + if (scb->status.abort_code != 0) continue; - ti = afs_iget(dir->i_sb, key, &cookie->fids[i], - &cookie->statuses[i], - &cookie->callbacks[i], - cbi, dvnode); + iget_data.fid = cookie->fids[i]; + ti = afs_iget(dir->i_sb, key, &iget_data, scb, cbi, dvnode); + if (!IS_ERR(ti)) + afs_cache_permit(AFS_FS_I(ti), key, + 0 /* Assume vnode->cb_break is 0 */ + + iget_data.cb_v_break, + scb); if (i == 0) { inode = ti; } else { @@ -787,9 +820,13 @@ success: out_c: afs_put_cb_interest(afs_v2net(dvnode), cbi); - kfree(cookie->callbacks); + if (cookie->inodes) { + for (i = 0; i < cookie->nr_fids; i++) + iput(cookie->inodes[i]); + kfree(cookie->inodes); + } out_s: - kfree(cookie->statuses); + kvfree(cookie->statuses); out: kfree(cookie); return inode; @@ -1114,9 +1151,8 @@ void afs_d_release(struct dentry *dentry) */ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, struct dentry *new_dentry, - struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_iget_data *new_data, + struct afs_status_cb *new_scb) { struct afs_vnode *vnode; struct inode *inode; @@ -1125,7 +1161,7 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, return; inode = afs_iget(fc->vnode->vfs_inode.i_sb, fc->key, - newfid, newstatus, newcb, fc->cbi, fc->vnode); + new_data, new_scb, fc->cbi, fc->vnode); if (IS_ERR(inode)) { /* ENOMEM or EINTR at a really inconvenient time - just abandon * the new directory on the server. @@ -1136,22 +1172,29 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); - afs_vnode_commit_status(fc, vnode, 0); + if (fc->ac.error == 0) + afs_cache_permit(vnode, fc->key, vnode->cb_break, new_scb); d_instantiate(new_dentry, inode); } +static void afs_prep_for_new_inode(struct afs_fs_cursor *fc, + struct afs_iget_data *iget_data) +{ + iget_data->volume = fc->vnode->volume; + iget_data->cb_v_break = fc->vnode->volume->cb_v_break; + iget_data->cb_s_break = fc->cbi->server->cb_s_break; +} + /* * create a directory on an AFS filesystem */ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { - struct afs_file_status newstatus; + struct afs_iget_data iget_data; + struct afs_status_cb *scb; struct afs_fs_cursor fc; - struct afs_callback newcb; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_fid newfid; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; mode |= S_IFDIR; @@ -1159,23 +1202,32 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) _enter("{%llx:%llu},{%pd},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_create(&fc, dentry->d_name.name, mode, data_version, - &newfid, &newstatus, &newcb); + afs_prep_for_new_inode(&fc, &iget_data); + afs_fs_create(&fc, dentry->d_name.name, mode, + &scb[0], &iget_data.fid, &scb[1]); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, &newcb); + afs_check_for_remote_deletion(&fc, dvnode); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) goto error_key; @@ -1185,15 +1237,18 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) if (ret == 0 && test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_add(dvnode, &dentry->d_name, &newfid, + afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_create); key_put(key); + kfree(scb); _leave(" = 0"); return 0; error_key: key_put(key); +error_scb: + kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); @@ -1220,15 +1275,19 @@ static void afs_dir_remove_subdir(struct dentry *dentry) */ static int afs_rmdir(struct inode *dir, struct dentry *dentry) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; _enter("{%llx:%llu},{%pd}", dvnode->fid.vid, dvnode->fid.vnode, dentry); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); @@ -1250,14 +1309,16 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_remove(&fc, vnode, dentry->d_name.name, true, - data_version); + afs_fs_remove(&fc, vnode, dentry->d_name.name, true, scb); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); if (ret == 0) { afs_dir_remove_subdir(dentry); @@ -1272,6 +1333,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) error_key: key_put(key); error: + kfree(scb); return ret; } @@ -1285,32 +1347,27 @@ error: * However, if we didn't have a callback promise outstanding, or it was * outstanding on a different server, then it won't break it either... */ -int afs_dir_remove_link(struct dentry *dentry, struct key *key, - unsigned long d_version_before, - unsigned long d_version_after) +static int afs_dir_remove_link(struct afs_vnode *dvnode, struct dentry *dentry, + struct key *key) { - bool dir_valid; int ret = 0; - /* There were no intervening changes on the server if the version - * number we got back was incremented by exactly 1. - */ - dir_valid = (d_version_after == d_version_before + 1); - if (d_really_is_positive(dentry)) { struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { /* Already done */ - } else if (dir_valid) { + } else if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { + write_seqlock(&vnode->cb_lock); drop_nlink(&vnode->vfs_inode); if (vnode->vfs_inode.i_nlink == 0) { set_bit(AFS_VNODE_DELETED, &vnode->flags); - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + __afs_break_callback(vnode, afs_cb_break_for_unlink); } + write_sequnlock(&vnode->cb_lock); ret = 0; } else { - clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + afs_break_callback(vnode, afs_cb_break_for_unlink); if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) kdebug("AFS_VNODE_DELETED"); @@ -1331,11 +1388,11 @@ int afs_dir_remove_link(struct dentry *dentry, struct key *key, static int afs_unlink(struct inode *dir, struct dentry *dentry) { struct afs_fs_cursor fc; - struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; + struct afs_status_cb *scb; + struct afs_vnode *dvnode = AFS_FS_I(dir); + struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); struct key *key; - unsigned long d_version = (unsigned long)dentry->d_fsdata; bool need_rehash = false; - u64 data_version = dvnode->status.data_version; int ret; _enter("{%llx:%llu},{%pd}", @@ -1344,22 +1401,24 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) if (dentry->d_name.len >= AFSNAMEMAX) return -ENAMETOOLONG; + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } /* Try to make sure we have a callback promise on the victim. */ - if (d_really_is_positive(dentry)) { - vnode = AFS_FS_I(d_inode(dentry)); - ret = afs_validate(vnode, key); - if (ret < 0) - goto error_key; - } + ret = afs_validate(vnode, key); + if (ret < 0) + goto error_key; spin_lock(&dentry->d_lock); - if (vnode && d_count(dentry) > 1) { + if (d_count(dentry) > 1) { spin_unlock(&dentry->d_lock); /* Start asynchronous writeout of the inode */ write_inode_now(d_inode(dentry), 0); @@ -1374,30 +1433,34 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) spin_unlock(&dentry->d_lock); ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + afs_dataversion_t data_version_2 = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); + fc.cb_break_2 = afs_calc_vnode_cb_break(vnode); if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) && !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) { yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name, - data_version); + &scb[0], &scb[1]); if (fc.ac.error != -ECONNABORTED || fc.ac.abort_code != RXGEN_OPCODE) continue; set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags); } - afs_fs_remove(&fc, vnode, dentry->d_name.name, false, - data_version); + afs_fs_remove(&fc, vnode, dentry->d_name.name, false, &scb[0]); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, + &data_version_2, &scb[1]); ret = afs_end_vnode_operation(&fc); - if (ret == 0) - ret = afs_dir_remove_link( - dentry, key, d_version, - (unsigned long)dvnode->status.data_version); + if (ret == 0 && !(scb[1].have_status || scb[1].have_error)) + ret = afs_dir_remove_link(dvnode, dentry, key); if (ret == 0 && test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_edit_dir_remove(dvnode, &dentry->d_name, @@ -1409,6 +1472,8 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) error_key: key_put(key); +error_scb: + kfree(scb); error: _leave(" = %d", ret); return ret; @@ -1420,13 +1485,11 @@ error: static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { + struct afs_iget_data iget_data; struct afs_fs_cursor fc; - struct afs_file_status newstatus; - struct afs_callback newcb; + struct afs_status_cb *scb; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_fid newfid; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; mode |= S_IFREG; @@ -1444,17 +1507,26 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, goto error; } + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error_scb; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_create(&fc, dentry->d_name.name, mode, data_version, - &newfid, &newstatus, &newcb); + afs_prep_for_new_inode(&fc, &iget_data); + afs_fs_create(&fc, dentry->d_name.name, mode, + &scb[0], &iget_data.fid, &scb[1]); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, &newcb); + afs_check_for_remote_deletion(&fc, dvnode); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) goto error_key; @@ -1463,13 +1535,16 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, } if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_add(dvnode, &dentry->d_name, &newfid, + afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_create); + kfree(scb); key_put(key); _leave(" = 0"); return 0; +error_scb: + kfree(scb); error_key: key_put(key); error: @@ -1485,15 +1560,12 @@ static int afs_link(struct dentry *from, struct inode *dir, struct dentry *dentry) { struct afs_fs_cursor fc; - struct afs_vnode *dvnode, *vnode; + struct afs_status_cb *scb; + struct afs_vnode *dvnode = AFS_FS_I(dir); + struct afs_vnode *vnode = AFS_FS_I(d_inode(from)); struct key *key; - u64 data_version; int ret; - vnode = AFS_FS_I(d_inode(from)); - dvnode = AFS_FS_I(dir); - data_version = dvnode->status.data_version; - _enter("{%llx:%llu},{%llx:%llu},{%pd}", vnode->fid.vid, vnode->fid.vnode, dvnode->fid.vid, dvnode->fid.vnode, @@ -1503,14 +1575,21 @@ static int afs_link(struct dentry *from, struct inode *dir, if (dentry->d_name.len >= AFSNAMEMAX) goto error; + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + if (mutex_lock_interruptible_nested(&vnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); goto error_key; @@ -1519,11 +1598,14 @@ static int afs_link(struct dentry *from, struct inode *dir, while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); fc.cb_break_2 = afs_calc_vnode_cb_break(vnode); - afs_fs_link(&fc, vnode, dentry->d_name.name, data_version); + afs_fs_link(&fc, vnode, dentry->d_name.name, + &scb[0], &scb[1]); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_commit_status(&fc, vnode, fc.cb_break_2); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_commit_status(&fc, vnode, fc.cb_break_2, + NULL, &scb[1]); ihold(&vnode->vfs_inode); d_instantiate(dentry, &vnode->vfs_inode); @@ -1540,11 +1622,14 @@ static int afs_link(struct dentry *from, struct inode *dir, afs_edit_dir_for_link); key_put(key); + kfree(scb); _leave(" = 0"); return 0; error_key: key_put(key); +error_scb: + kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); @@ -1557,12 +1642,11 @@ error: static int afs_symlink(struct inode *dir, struct dentry *dentry, const char *content) { + struct afs_iget_data iget_data; struct afs_fs_cursor fc; - struct afs_file_status newstatus; + struct afs_status_cb *scb; struct afs_vnode *dvnode = AFS_FS_I(dir); - struct afs_fid newfid; struct key *key; - u64 data_version = dvnode->status.data_version; int ret; _enter("{%llx:%llu},{%pd},%s", @@ -1577,24 +1661,32 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, if (strlen(content) >= AFSPATHMAX) goto error; + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_symlink(&fc, dentry->d_name.name, - content, data_version, - &newfid, &newstatus); + afs_prep_for_new_inode(&fc, &iget_data); + afs_fs_symlink(&fc, dentry->d_name.name, content, + &scb[0], &iget_data.fid, &scb[1]); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); - afs_vnode_new_inode(&fc, dentry, &newfid, &newstatus, NULL); + afs_check_for_remote_deletion(&fc, dvnode); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &data_version, &scb[0]); + afs_vnode_new_inode(&fc, dentry, &iget_data, &scb[1]); ret = afs_end_vnode_operation(&fc); if (ret < 0) goto error_key; @@ -1603,15 +1695,18 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, } if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - afs_edit_dir_add(dvnode, &dentry->d_name, &newfid, + afs_edit_dir_add(dvnode, &dentry->d_name, &iget_data.fid, afs_edit_dir_for_symlink); key_put(key); + kfree(scb); _leave(" = 0"); return 0; error_key: key_put(key); +error_scb: + kfree(scb); error: d_drop(dentry); _leave(" = %d", ret); @@ -1626,11 +1721,11 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, unsigned int flags) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *orig_dvnode, *new_dvnode, *vnode; struct dentry *tmp = NULL, *rehash = NULL; struct inode *new_inode; struct key *key; - u64 orig_data_version, new_data_version; bool new_negative = d_is_negative(new_dentry); int ret; @@ -1644,8 +1739,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, vnode = AFS_FS_I(d_inode(old_dentry)); orig_dvnode = AFS_FS_I(old_dir); new_dvnode = AFS_FS_I(new_dir); - orig_data_version = orig_dvnode->status.data_version; - new_data_version = new_dvnode->status.data_version; _enter("{%llx:%llu},{%llx:%llu},{%llx:%llu},{%pd}", orig_dvnode->fid.vid, orig_dvnode->fid.vnode, @@ -1653,10 +1746,15 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dvnode->fid.vid, new_dvnode->fid.vnode, new_dentry); + ret = -ENOMEM; + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + key = afs_request_key(orig_dvnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } /* For non-directories, check whether the target is busy and if so, @@ -1690,31 +1788,43 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, new_dentry = tmp; rehash = NULL; new_negative = true; - orig_data_version = orig_dvnode->status.data_version; - new_data_version = new_dvnode->status.data_version; } } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, orig_dvnode, key)) { + if (afs_begin_vnode_operation(&fc, orig_dvnode, key, true)) { + afs_dataversion_t orig_data_version; + afs_dataversion_t new_data_version; + struct afs_status_cb *new_scb = &scb[1]; + + orig_data_version = orig_dvnode->status.data_version + 1; + if (orig_dvnode != new_dvnode) { if (mutex_lock_interruptible_nested(&new_dvnode->io_lock, 1) < 0) { afs_end_vnode_operation(&fc); goto error_rehash; } + new_data_version = new_dvnode->status.data_version; + } else { + new_data_version = orig_data_version; + new_scb = &scb[0]; } + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode); fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode); afs_fs_rename(&fc, old_dentry->d_name.name, new_dvnode, new_dentry->d_name.name, - orig_data_version, new_data_version); + &scb[0], new_scb); } - afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break); - afs_vnode_commit_status(&fc, new_dvnode, fc.cb_break_2); - if (orig_dvnode != new_dvnode) + afs_vnode_commit_status(&fc, orig_dvnode, fc.cb_break, + &orig_data_version, &scb[0]); + if (new_dvnode != orig_dvnode) { + afs_vnode_commit_status(&fc, new_dvnode, fc.cb_break_2, + &new_data_version, &scb[1]); mutex_unlock(&new_dvnode->io_lock); + } ret = afs_end_vnode_operation(&fc); if (ret < 0) goto error_rehash; @@ -1754,6 +1864,8 @@ error_tmp: if (tmp) dput(tmp); key_put(key); +error_scb: + kfree(scb); error: _leave(" = %d", ret); return ret; diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c index 8b400f5aead5..d4fbe5f85f1b 100644 --- a/fs/afs/dir_edit.c +++ b/fs/afs/dir_edit.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS filesystem directory editing * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/kernel.h> diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c index f6f89fdab6b2..361088a5edb9 100644 --- a/fs/afs/dir_silly.c +++ b/fs/afs/dir_silly.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS silly rename handling * * Copyright (C) 2019 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * - Derived from NFS's sillyrename. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/kernel.h> @@ -24,21 +20,28 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode struct key *key) { struct afs_fs_cursor fc; - u64 dir_data_version = dvnode->status.data_version; + struct afs_status_cb *scb; int ret = -ERESTARTSYS; _enter("%pd,%pd", old, new); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + trace_afs_silly_rename(vnode, false); - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, true)) { + afs_dataversion_t dir_data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); afs_fs_rename(&fc, old->d_name.name, dvnode, new->d_name.name, - dir_data_version, dir_data_version); + scb, scb); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &dir_data_version, scb); ret = afs_end_vnode_operation(&fc); } @@ -57,13 +60,9 @@ static int afs_do_silly_rename(struct afs_vnode *dvnode, struct afs_vnode *vnode if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) afs_edit_dir_add(dvnode, &new->d_name, &vnode->fid, afs_edit_dir_for_silly_1); - - /* vfs_unlink and the like do not issue this when a file is - * sillyrenamed, so do it here. - */ - fsnotify_nameremove(old, 0); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -143,31 +142,37 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode struct dentry *dentry, struct key *key) { struct afs_fs_cursor fc; - u64 dir_data_version = dvnode->status.data_version; + struct afs_status_cb *scb; int ret = -ERESTARTSYS; _enter(""); + scb = kcalloc(2, sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + trace_afs_silly_rename(vnode, true); - if (afs_begin_vnode_operation(&fc, dvnode, key)) { + if (afs_begin_vnode_operation(&fc, dvnode, key, false)) { + afs_dataversion_t dir_data_version = dvnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) && !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) { yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name, - dir_data_version); + &scb[0], &scb[1]); if (fc.ac.error != -ECONNABORTED || fc.ac.abort_code != RXGEN_OPCODE) continue; set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags); } - afs_fs_remove(&fc, vnode, dentry->d_name.name, false, - dir_data_version); + afs_fs_remove(&fc, vnode, dentry->d_name.name, false, &scb[0]); } - afs_vnode_commit_status(&fc, dvnode, fc.cb_break); + afs_vnode_commit_status(&fc, dvnode, fc.cb_break, + &dir_data_version, &scb[0]); ret = afs_end_vnode_operation(&fc); if (ret == 0) { drop_nlink(&vnode->vfs_inode); @@ -182,6 +187,7 @@ static int afs_do_silly_unlink(struct afs_vnode *dvnode, struct afs_vnode *vnode afs_edit_dir_for_unlink); } + kfree(scb); _leave(" = %d", ret); return ret; } diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index a9ba81ddf154..bcd1bafb0278 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS dynamic root handling * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/fs.h> @@ -28,6 +24,7 @@ const struct file_operations afs_dynroot_file_operations = { static int afs_probe_cell_name(struct dentry *dentry) { struct afs_cell *cell; + struct afs_net *net = afs_d2net(dentry); const char *name = dentry->d_name.name; size_t len = dentry->d_name.len; int ret; @@ -40,13 +37,14 @@ static int afs_probe_cell_name(struct dentry *dentry) len--; } - cell = afs_lookup_cell_rcu(afs_d2net(dentry), name, len); + cell = afs_lookup_cell_rcu(net, name, len); if (!IS_ERR(cell)) { - afs_put_cell(afs_d2net(dentry), cell); + afs_put_cell(net, cell); return 0; } - ret = dns_query("afsdb", name, len, "srv=1", NULL, NULL); + ret = dns_query(net->net, "afsdb", name, len, "srv=1", + NULL, NULL, false); if (ret == -ENODATA) ret = -EDESTADDRREQ; return ret; @@ -261,8 +259,7 @@ int afs_dynroot_populate(struct super_block *sb) struct afs_net *net = afs_sb2net(sb); int ret; - if (mutex_lock_interruptible(&net->proc_cells_lock) < 0) - return -ERESTARTSYS; + mutex_lock(&net->proc_cells_lock); net->dynroot_sb = sb; hlist_for_each_entry(cell, &net->proc_cells, proc_link) { diff --git a/fs/afs/file.c b/fs/afs/file.c index e8d6619890a9..56b69576274d 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS filesystem file handling * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> @@ -170,11 +166,12 @@ int afs_release(struct inode *inode, struct file *file) { struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_file *af = file->private_data; + int ret = 0; _enter("{%llx:%llu},", vnode->fid.vid, vnode->fid.vnode); if ((file->f_mode & FMODE_WRITE)) - return vfs_fsync(file, 0); + ret = vfs_fsync(file, 0); file->private_data = NULL; if (af->wb) @@ -182,8 +179,8 @@ int afs_release(struct inode *inode, struct file *file) key_put(af->key); kfree(af); afs_prune_wb_keys(vnode); - _leave(" = 0"); - return 0; + _leave(" = %d", ret); + return ret; } /* @@ -227,6 +224,7 @@ static void afs_file_readpage_read_complete(struct page *page, int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *desc) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; int ret; _enter("%s{%llx:%llu.%u},%x,,,", @@ -236,15 +234,22 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de vnode->fid.unique, key_serial(key)); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_fetch_data(&fc, desc); + afs_fs_fetch_data(&fc, scb, desc); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } @@ -254,6 +259,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de &afs_v2net(vnode)->n_fetch_bytes); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -304,8 +310,7 @@ int afs_page_filler(void *data, struct page *page) /* fall through */ default: go_on: - req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), - GFP_KERNEL); + req = kzalloc(struct_size(req, array, 1), GFP_KERNEL); if (!req) goto enomem; @@ -404,10 +409,10 @@ static int afs_readpage(struct file *file, struct page *page) /* * Make pages available as they're filled. */ -static void afs_readpages_page_done(struct afs_call *call, struct afs_read *req) +static void afs_readpages_page_done(struct afs_read *req) { #ifdef CONFIG_AFS_FSCACHE - struct afs_vnode *vnode = call->reply[0]; + struct afs_vnode *vnode = req->vnode; #endif struct page *page = req->pages[req->index]; @@ -455,12 +460,12 @@ static int afs_readpages_one(struct file *file, struct address_space *mapping, n++; } - req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *) * n, - GFP_NOFS); + req = kzalloc(struct_size(req, array, n), GFP_NOFS); if (!req) return -ENOMEM; refcount_set(&req->usage, 1); + req->vnode = vnode; req->page_done = afs_readpages_page_done; req->pos = first->index; req->pos <<= PAGE_SHIFT; diff --git a/fs/afs/flock.c b/fs/afs/flock.c index adc88eff7849..d5e5a6ddc847 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS file locking support * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include "internal.h" @@ -41,9 +37,6 @@ void afs_lock_may_be_available(struct afs_vnode *vnode) { _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - if (vnode->lock_state != AFS_VNODE_LOCK_WAITING_FOR_CB) - return; - spin_lock(&vnode->lock); if (vnode->lock_state == AFS_VNODE_LOCK_WAITING_FOR_CB) afs_next_locker(vnode, 0); @@ -77,7 +70,7 @@ static void afs_schedule_lock_extension(struct afs_vnode *vnode) */ void afs_lock_op_done(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; + struct afs_vnode *vnode = call->lvnode; if (call->error == 0) { spin_lock(&vnode->lock); @@ -185,6 +178,7 @@ static void afs_kill_lockers_enoent(struct afs_vnode *vnode) static int afs_set_lock(struct afs_vnode *vnode, struct key *key, afs_lock_type_t type) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -195,18 +189,23 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, vnode->fid.unique, key_serial(key), type); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_set_lock(&fc, type); + afs_fs_set_lock(&fc, type, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); ret = afs_end_vnode_operation(&fc); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -216,6 +215,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, */ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -226,18 +226,23 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) vnode->fid.unique, key_serial(key)); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, false)) { while (afs_select_current_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_extend_lock(&fc); + afs_fs_extend_lock(&fc, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); ret = afs_end_vnode_operation(&fc); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -247,6 +252,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) */ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -257,18 +263,23 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) vnode->fid.unique, key_serial(key)); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, false)) { while (afs_select_current_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_release_lock(&fc); + afs_fs_release_lock(&fc, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, NULL, scb); ret = afs_end_vnode_operation(&fc); } + kfree(scb); _leave(" = %d", ret); return ret; } @@ -736,7 +747,7 @@ static int afs_do_getlk(struct file *file, struct file_lock *fl) posix_test_lock(file, fl); if (fl->fl_type == F_UNLCK) { /* no local locks; consult the server */ - ret = afs_fetch_status(vnode, key, false); + ret = afs_fetch_status(vnode, key, false, NULL); if (ret < 0) goto error; diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 5d3abde52a0f..cfe62b154f68 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS fileserver probing * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/sched.h> @@ -33,8 +29,8 @@ static bool afs_fs_probe_done(struct afs_server *server) void afs_fileserver_probe_result(struct afs_call *call) { struct afs_addr_list *alist = call->alist; - struct afs_server *server = call->reply[0]; - unsigned int server_index = (long)call->reply[1]; + struct afs_server *server = call->server; + unsigned int server_index = call->server_index; unsigned int index = call->addr_ix; unsigned int rtt = UINT_MAX; bool have_result = false; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 1296f5dc4c1e..1ce73e014139 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS File Server client stubs * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/init.h> @@ -60,78 +56,17 @@ static void xdr_dump_bad(const __be32 *bp) } /* - * Update the core inode struct from a returned status record. - */ -void afs_update_inode_from_status(struct afs_vnode *vnode, - struct afs_file_status *status, - const afs_dataversion_t *expected_version, - u8 flags) -{ - struct timespec64 t; - umode_t mode; - - t = status->mtime_client; - vnode->vfs_inode.i_ctime = t; - vnode->vfs_inode.i_mtime = t; - vnode->vfs_inode.i_atime = t; - - if (flags & (AFS_VNODE_META_CHANGED | AFS_VNODE_NOT_YET_SET)) { - vnode->vfs_inode.i_uid = make_kuid(&init_user_ns, status->owner); - vnode->vfs_inode.i_gid = make_kgid(&init_user_ns, status->group); - set_nlink(&vnode->vfs_inode, status->nlink); - - mode = vnode->vfs_inode.i_mode; - mode &= ~S_IALLUGO; - mode |= status->mode; - barrier(); - vnode->vfs_inode.i_mode = mode; - } - - if (!(flags & AFS_VNODE_NOT_YET_SET)) { - if (expected_version && - *expected_version != status->data_version) { - _debug("vnode modified %llx on {%llx:%llu} [exp %llx]", - (unsigned long long) status->data_version, - vnode->fid.vid, vnode->fid.vnode, - (unsigned long long) *expected_version); - vnode->invalid_before = status->data_version; - if (vnode->status.type == AFS_FTYPE_DIR) { - if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - afs_stat_v(vnode, n_inval); - } else { - set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); - } - } else if (vnode->status.type == AFS_FTYPE_DIR) { - /* Expected directory change is handled elsewhere so - * that we can locally edit the directory and save on a - * download. - */ - if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) - flags &= ~AFS_VNODE_DATA_CHANGED; - } - } - - if (flags & (AFS_VNODE_DATA_CHANGED | AFS_VNODE_NOT_YET_SET)) { - inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); - i_size_write(&vnode->vfs_inode, status->size); - } -} - -/* * decode an AFSFetchStatus block */ -static int xdr_decode_AFSFetchStatus(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) +static int xdr_decode_AFSFetchStatus(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp; + struct afs_file_status *status = &scb->status; bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus); u64 data_version, size; u32 type, abort_code; - u8 flags = 0; abort_code = ntohl(xdr->abort_code); @@ -144,6 +79,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, * case. */ status->abort_code = abort_code; + scb->have_error = true; return 0; } @@ -161,44 +97,25 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, case AFS_FTYPE_FILE: case AFS_FTYPE_DIR: case AFS_FTYPE_SYMLINK: - if (type != status->type && - vnode && - !test_bit(AFS_VNODE_UNSET, &vnode->flags)) { - pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", - vnode->fid.vid, - vnode->fid.vnode, - vnode->fid.unique, - status->type, type); - goto bad; - } status->type = type; break; default: goto bad; } -#define EXTRACT_M(FIELD) \ - do { \ - u32 x = ntohl(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_META_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - - EXTRACT_M(nlink); - EXTRACT_M(author); - EXTRACT_M(owner); - EXTRACT_M(caller_access); /* call ticket dependent */ - EXTRACT_M(anon_access); - EXTRACT_M(mode); - EXTRACT_M(group); + status->nlink = ntohl(xdr->nlink); + status->author = ntohl(xdr->author); + status->owner = ntohl(xdr->owner); + status->caller_access = ntohl(xdr->caller_access); /* Ticket dependent */ + status->anon_access = ntohl(xdr->anon_access); + status->mode = ntohl(xdr->mode) & S_IALLUGO; + status->group = ntohl(xdr->group); + status->lock_count = ntohl(xdr->lock_count); status->mtime_client.tv_sec = ntohl(xdr->mtime_client); status->mtime_client.tv_nsec = 0; status->mtime_server.tv_sec = ntohl(xdr->mtime_server); status->mtime_server.tv_nsec = 0; - status->lock_count = ntohl(xdr->lock_count); size = (u64)ntohl(xdr->size_lo); size |= (u64)ntohl(xdr->size_hi) << 32; @@ -206,25 +123,10 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, data_version = (u64)ntohl(xdr->data_version_lo); data_version |= (u64)ntohl(xdr->data_version_hi) << 32; - if (data_version != status->data_version) { - status->data_version = data_version; - flags |= AFS_VNODE_DATA_CHANGED; - } - - if (read_req) { - read_req->data_version = data_version; - read_req->file_size = size; - } + status->data_version = data_version; + scb->have_status = true; *_bp = (const void *)*_bp + sizeof(*xdr); - - if (vnode) { - if (test_bit(AFS_VNODE_UNSET, &vnode->flags)) - flags |= AFS_VNODE_NOT_YET_SET; - afs_update_inode_from_status(vnode, status, expected_version, - flags); - } - return 0; bad: @@ -232,77 +134,22 @@ bad: return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); } -/* - * Decode the file status. We need to lock the target vnode if we're going to - * update its status so that stat() sees the attributes update atomically. - */ -static int afs_decode_status(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) +static time64_t xdr_decode_expiry(struct afs_call *call, u32 expiry) { - int ret; - - if (!vnode) - return xdr_decode_AFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - - write_seqlock(&vnode->cb_lock); - ret = xdr_decode_AFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - write_sequnlock(&vnode->cb_lock); - return ret; + return ktime_divns(call->reply_time, NSEC_PER_SEC) + expiry; } -/* - * decode an AFSCallBack block - */ -static void xdr_decode_AFSCallBack(struct afs_call *call, - struct afs_vnode *vnode, - const __be32 **_bp) +static void xdr_decode_AFSCallBack(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { - struct afs_cb_interest *old, *cbi = call->cbi; + struct afs_callback *cb = &scb->callback; const __be32 *bp = *_bp; - u32 cb_expiry; - - write_seqlock(&vnode->cb_lock); - - if (!afs_cb_is_broken(call->cb_break, vnode, cbi)) { - vnode->cb_version = ntohl(*bp++); - cb_expiry = ntohl(*bp++); - vnode->cb_type = ntohl(*bp++); - vnode->cb_expires_at = cb_expiry + ktime_get_real_seconds(); - old = vnode->cb_interest; - if (old != call->cbi) { - vnode->cb_interest = cbi; - cbi = old; - } - set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } else { - bp += 3; - } - write_sequnlock(&vnode->cb_lock); - call->cbi = cbi; - *_bp = bp; -} - -static ktime_t xdr_decode_expiry(struct afs_call *call, u32 expiry) -{ - return ktime_add_ns(call->reply_time, expiry * NSEC_PER_SEC); -} - -static void xdr_decode_AFSCallBack_raw(struct afs_call *call, - const __be32 **_bp, - struct afs_callback *cb) -{ - const __be32 *bp = *_bp; - - cb->version = ntohl(*bp++); + bp++; /* version */ cb->expires_at = xdr_decode_expiry(call, ntohl(*bp++)); - cb->type = ntohl(*bp++); + bp++; /* type */ + scb->have_cb = true; *_bp = bp; } @@ -395,7 +242,6 @@ static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp, */ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -403,16 +249,13 @@ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) if (ret < 0) return ret; - _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack(call, vnode, &bp); - xdr_decode_AFSVolSync(&bp, call->reply[1]); + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -431,8 +274,8 @@ static const struct afs_call_type afs_RXFSFetchStatus_vnode = { /* * fetch the status information for a file */ -int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsync, - bool new_inode) +int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb, + struct afs_volsync *volsync) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -440,7 +283,7 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_file_status(fc, volsync, new_inode); + return yfs_fs_fetch_file_status(fc, scb, volsync); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -453,10 +296,8 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy } call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = volsync; - call->expected_version = new_inode ? 1 : vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -465,10 +306,10 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -478,8 +319,7 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy */ static int afs_deliver_fs_fetch_data(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; - struct afs_read *req = call->reply[2]; + struct afs_read *req = call->read_request; const __be32 *bp; unsigned int size; int ret; @@ -541,7 +381,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) if (req->offset == PAGE_SIZE) { req->offset = 0; if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->index++; if (req->remain > 0) goto begin_page; @@ -575,12 +415,14 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) return ret; bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &vnode->status.data_version, req); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack(call, vnode, &bp); - xdr_decode_AFSVolSync(&bp, call->reply[1]); + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); + + req->data_version = call->out_scb->status.data_version; + req->file_size = call->out_scb->status.size; call->unmarshall++; @@ -593,7 +435,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) zero_user_segment(req->pages[req->index], req->offset, PAGE_SIZE); if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->offset = 0; } @@ -603,7 +445,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) static void afs_fetch_data_destructor(struct afs_call *call) { - struct afs_read *req = call->reply[2]; + struct afs_read *req = call->read_request; afs_put_read(req); afs_flat_call_destructor(call); @@ -629,7 +471,9 @@ static const struct afs_call_type afs_RXFSFetchData64 = { /* * fetch data from a very large file */ -static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) +static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, + struct afs_status_cb *scb, + struct afs_read *req) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -643,11 +487,9 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = NULL; /* volsync */ - call->reply[2] = req; - call->expected_version = vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = NULL; + call->read_request = req; /* marshall the parameters */ bp = call->request; @@ -661,9 +503,9 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) bp[7] = htonl(lower_32_bits(req->len)); refcount_inc(&req->usage); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -671,7 +513,9 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) /* * fetch data from a file */ -int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) +int afs_fs_fetch_data(struct afs_fs_cursor *fc, + struct afs_status_cb *scb, + struct afs_read *req) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -679,12 +523,12 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_data(fc, req); + return yfs_fs_fetch_data(fc, scb, req); if (upper_32_bits(req->pos) || upper_32_bits(req->len) || upper_32_bits(req->pos + req->len)) - return afs_fs_fetch_data64(fc, req); + return afs_fs_fetch_data64(fc, scb, req); _enter(""); @@ -693,11 +537,9 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = NULL; /* volsync */ - call->reply[2] = req; - call->expected_version = vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = NULL; + call->read_request = req; /* marshall the parameters */ bp = call->request; @@ -709,9 +551,9 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) bp[5] = htonl(lower_32_bits(req->len)); refcount_inc(&req->usage); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -721,28 +563,24 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) */ static int afs_deliver_fs_create_vnode(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; - _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call); if (ret < 0) return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_AFSFid(&bp, call->reply[1]); - ret = afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_AFSFid(&bp, call->out_fid); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack_raw(call, &bp, call->reply[3]); - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -771,24 +609,23 @@ static const struct afs_call_type afs_RXFSMakeDir = { int afs_fs_create(struct afs_fs_cursor *fc, const char *name, umode_t mode, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz; __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)){ if (S_ISDIR(mode)) - return yfs_fs_make_dir(fc, name, mode, current_data_version, - newfid, newstatus, newcb); + return yfs_fs_make_dir(fc, name, mode, dvnode_scb, + newfid, new_scb); else - return yfs_fs_create_file(fc, name, mode, current_data_version, - newfid, newstatus, newcb); + return yfs_fs_create_file(fc, name, mode, dvnode_scb, + newfid, new_scb); } _enter(""); @@ -804,19 +641,16 @@ int afs_fs_create(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->reply[3] = newcb; - call->expected_version = current_data_version + 1; - call->want_reply_time = true; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; *bp++ = htonl(S_ISDIR(mode) ? FSMAKEDIR : FSCREATEFILE); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(dvnode->fid.vid); + *bp++ = htonl(dvnode->fid.vnode); + *bp++ = htonl(dvnode->fid.unique); *bp++ = htonl(namesz); memcpy(bp, name, namesz); bp = (void *) bp + namesz; @@ -825,41 +659,38 @@ int afs_fs_create(struct afs_fs_cursor *fc, bp = (void *) bp + padsz; } *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); - *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(dvnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(mode & S_IALLUGO); /* unix mode */ *bp++ = 0; /* segment size */ afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &vnode->fid, name); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } /* - * Deliver reply data to any operation that returns file status and volume + * Deliver reply data to any operation that returns directory status and volume * sync. */ -static int afs_deliver_fs_status_and_vol(struct afs_call *call) +static int afs_deliver_fs_dir_status_and_vol(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; - _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call); if (ret < 0) return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -871,14 +702,14 @@ static int afs_deliver_fs_status_and_vol(struct afs_call *call) static const struct afs_call_type afs_RXFSRemoveFile = { .name = "FS.RemoveFile", .op = afs_FS_RemoveFile, - .deliver = afs_deliver_fs_status_and_vol, + .deliver = afs_deliver_fs_dir_status_and_vol, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type afs_RXFSRemoveDir = { .name = "FS.RemoveDir", .op = afs_FS_RemoveDir, - .deliver = afs_deliver_fs_status_and_vol, + .deliver = afs_deliver_fs_dir_status_and_vol, .destructor = afs_flat_call_destructor, }; @@ -886,7 +717,7 @@ static const struct afs_call_type afs_RXFSRemoveDir = { * remove a file or directory */ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, bool isdir, u64 current_data_version) + const char *name, bool isdir, struct afs_status_cb *dvnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -895,7 +726,7 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_remove(fc, vnode, name, isdir, current_data_version); + return yfs_fs_remove(fc, vnode, name, isdir, dvnode_scb); _enter(""); @@ -910,9 +741,7 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -930,6 +759,7 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -939,7 +769,6 @@ int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int afs_deliver_fs_link(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0], *vnode = call->reply[1]; const __be32 *bp; int ret; @@ -951,14 +780,13 @@ static int afs_deliver_fs_link(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = afs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -978,7 +806,9 @@ static const struct afs_call_type afs_RXFSLink = { * make a hard link */ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, u64 current_data_version) + const char *name, + struct afs_status_cb *dvnode_scb, + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -987,7 +817,7 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_link(fc, vnode, name, current_data_version); + return yfs_fs_link(fc, vnode, name, dvnode_scb, vnode_scb); _enter(""); @@ -1000,9 +830,8 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -1023,6 +852,7 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call1(call, &vnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1032,7 +862,6 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int afs_deliver_fs_symlink(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1044,15 +873,14 @@ static int afs_deliver_fs_symlink(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_AFSFid(&bp, call->reply[1]); - ret = afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_AFSFid(&bp, call->out_fid); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1074,19 +902,19 @@ static const struct afs_call_type afs_RXFSSymlink = { int afs_fs_symlink(struct afs_fs_cursor *fc, const char *name, const char *contents, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz, c_namesz, c_padsz; __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_symlink(fc, name, contents, current_data_version, - newfid, newstatus); + return yfs_fs_symlink(fc, name, contents, dvnode_scb, + newfid, new_scb); _enter(""); @@ -1104,17 +932,16 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; *bp++ = htonl(FSSYMLINK); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(dvnode->fid.vid); + *bp++ = htonl(dvnode->fid.vnode); + *bp++ = htonl(dvnode->fid.unique); *bp++ = htonl(namesz); memcpy(bp, name, namesz); bp = (void *) bp + namesz; @@ -1130,14 +957,15 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, bp = (void *) bp + c_padsz; } *bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME); - *bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */ + *bp++ = htonl(dvnode->vfs_inode.i_mtime.tv_sec); /* mtime */ *bp++ = 0; /* owner */ *bp++ = 0; /* group */ *bp++ = htonl(S_IRWXUGO); /* unix mode */ *bp++ = 0; /* segment size */ afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &vnode->fid, name); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1147,29 +975,24 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_rename(struct afs_call *call) { - struct afs_vnode *orig_dvnode = call->reply[0], *new_dvnode = call->reply[1]; const __be32 *bp; int ret; - _enter("{%u}", call->unmarshall); - ret = afs_transfer_reply(call); if (ret < 0) return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - if (new_dvnode != orig_dvnode) { - ret = afs_decode_status(call, &bp, &new_dvnode->status, new_dvnode, - &call->expected_version_2, NULL); + if (call->out_dir_scb != call->out_scb) { + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; } - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1186,14 +1009,14 @@ static const struct afs_call_type afs_RXFSRename = { }; /* - * create a symbolic link + * Rename/move a file or directory. */ int afs_fs_rename(struct afs_fs_cursor *fc, const char *orig_name, struct afs_vnode *new_dvnode, const char *new_name, - u64 current_orig_data_version, - u64 current_new_data_version) + struct afs_status_cb *orig_dvnode_scb, + struct afs_status_cb *new_dvnode_scb) { struct afs_vnode *orig_dvnode = fc->vnode; struct afs_call *call; @@ -1204,8 +1027,8 @@ int afs_fs_rename(struct afs_fs_cursor *fc, if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) return yfs_fs_rename(fc, orig_name, new_dvnode, new_name, - current_orig_data_version, - current_new_data_version); + orig_dvnode_scb, + new_dvnode_scb); _enter(""); @@ -1225,10 +1048,8 @@ int afs_fs_rename(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = orig_dvnode; - call->reply[1] = new_dvnode; - call->expected_version = current_orig_data_version + 1; - call->expected_version_2 = current_new_data_version + 1; + call->out_dir_scb = orig_dvnode_scb; + call->out_scb = new_dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -1257,6 +1078,7 @@ int afs_fs_rename(struct afs_fs_cursor *fc, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call2(call, &orig_dvnode->fid, orig_name, new_name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1266,7 +1088,6 @@ int afs_fs_rename(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_store_data(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1278,13 +1099,10 @@ static int afs_deliver_fs_store_data(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ - - afs_pages_written_back(vnode, call); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1314,7 +1132,8 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, struct address_space *mapping, pgoff_t first, pgoff_t last, unsigned offset, unsigned to, - loff_t size, loff_t pos, loff_t i_size) + loff_t size, loff_t pos, loff_t i_size, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1332,13 +1151,12 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, call->key = fc->key; call->mapping = mapping; - call->reply[0] = vnode; call->first = first; call->last = last; call->first_offset = offset; call->last_to = to; call->send_pages = true; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1362,6 +1180,7 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, *bp++ = htonl((u32) i_size); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1371,7 +1190,8 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, */ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, pgoff_t first, pgoff_t last, - unsigned offset, unsigned to) + unsigned offset, unsigned to, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1380,7 +1200,7 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_store_data(fc, mapping, first, last, offset, to); + return yfs_fs_store_data(fc, mapping, first, last, offset, to, scb); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -1401,7 +1221,7 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32) return afs_fs_store_data64(fc, mapping, first, last, offset, to, - size, pos, i_size); + size, pos, i_size, scb); call = afs_alloc_flat_call(net, &afs_RXFSStoreData, (4 + 6 + 3) * 4, @@ -1411,13 +1231,12 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, call->key = fc->key; call->mapping = mapping; - call->reply[0] = vnode; call->first = first; call->last = last; call->first_offset = offset; call->last_to = to; call->send_pages = true; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1439,6 +1258,7 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1448,7 +1268,6 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, */ static int afs_deliver_fs_store_status(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1460,11 +1279,10 @@ static int afs_deliver_fs_store_status(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1498,7 +1316,8 @@ static const struct afs_call_type afs_RXFSStoreData64_as_Status = { * set the attributes on a very large file, using FS.StoreData rather than * FS.StoreStatus so as to alter the file size also */ -static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) +static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1517,8 +1336,7 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1538,6 +1356,7 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1546,7 +1365,8 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) * set the attributes on a file, using FS.StoreData rather than FS.StoreStatus * so as to alter the file size also */ -static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) +static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1558,7 +1378,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) ASSERT(attr->ia_valid & ATTR_SIZE); if (attr->ia_size >> 32) - return afs_fs_setattr_size64(fc, attr); + return afs_fs_setattr_size64(fc, attr, scb); call = afs_alloc_flat_call(net, &afs_RXFSStoreData_as_Status, (4 + 6 + 3) * 4, @@ -1567,8 +1387,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1585,6 +1404,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1593,7 +1413,8 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) * set the attributes on a file, using FS.StoreData if there's a change in file * size, and FS.StoreStatus otherwise */ -int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) +int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1601,10 +1422,10 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_setattr(fc, attr); + return yfs_fs_setattr(fc, attr, scb); if (attr->ia_valid & ATTR_SIZE) - return afs_fs_setattr_size(fc, attr); + return afs_fs_setattr_size(fc, attr, scb); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -1616,8 +1437,7 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1630,6 +1450,7 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1659,7 +1480,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_AFSFetchVolumeStatus(&bp, call->reply[1]); + xdr_decode_AFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); @@ -1675,7 +1496,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_volname_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; /* Fall through - and extract the volume name */ @@ -1685,7 +1506,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("volname '%s'", p); afs_extract_to_tmp(call); @@ -1703,7 +1524,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_offline_msg_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; /* Fall through - and extract the offline message */ @@ -1713,7 +1534,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("offline '%s'", p); @@ -1732,7 +1553,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_motd_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; /* Fall through - and extract the message of the day */ @@ -1742,7 +1563,7 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("motd '%s'", p); @@ -1757,23 +1578,13 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) } /* - * destroy an FS.GetVolumeStatus call - */ -static void afs_get_volume_status_call_destructor(struct afs_call *call) -{ - kfree(call->reply[2]); - call->reply[2] = NULL; - afs_flat_call_destructor(call); -} - -/* * FS.GetVolumeStatus operation type */ static const struct afs_call_type afs_RXFSGetVolumeStatus = { .name = "FS.GetVolumeStatus", .op = afs_FS_GetVolumeStatus, .deliver = afs_deliver_fs_get_volume_status, - .destructor = afs_get_volume_status_call_destructor, + .destructor = afs_flat_call_destructor, }; /* @@ -1786,27 +1597,19 @@ int afs_fs_get_volume_status(struct afs_fs_cursor *fc, struct afs_call *call; struct afs_net *net = afs_v2net(vnode); __be32 *bp; - void *tmpbuf; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) return yfs_fs_get_volume_status(fc, vs); _enter(""); - tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL); - if (!tmpbuf) + call = afs_alloc_flat_call(net, &afs_RXFSGetVolumeStatus, 2 * 4, + max(12 * 4, AFSOPAQUEMAX + 1)); + if (!call) return -ENOMEM; - call = afs_alloc_flat_call(net, &afs_RXFSGetVolumeStatus, 2 * 4, 12 * 4); - if (!call) { - kfree(tmpbuf); - return -ENOMEM; - } - call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = vs; - call->reply[2] = tmpbuf; + call->out_volstatus = vs; /* marshall the parameters */ bp = call->request; @@ -1815,6 +1618,7 @@ int afs_fs_get_volume_status(struct afs_fs_cursor *fc, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1835,7 +1639,7 @@ static int afs_deliver_fs_xxxx_lock(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1876,7 +1680,8 @@ static const struct afs_call_type afs_RXFSReleaseLock = { /* * Set a lock on a file */ -int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) +int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1884,7 +1689,7 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_set_lock(fc, type); + return yfs_fs_set_lock(fc, type, scb); _enter(""); @@ -1893,8 +1698,8 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->want_reply_time = true; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1906,6 +1711,7 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_calli(call, &vnode->fid, type); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1913,7 +1719,7 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) /* * extend a lock on a file */ -int afs_fs_extend_lock(struct afs_fs_cursor *fc) +int afs_fs_extend_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1921,7 +1727,7 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_extend_lock(fc); + return yfs_fs_extend_lock(fc, scb); _enter(""); @@ -1930,8 +1736,8 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->want_reply_time = true; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1942,6 +1748,7 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1949,7 +1756,7 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) /* * release a lock on a file */ -int afs_fs_release_lock(struct afs_fs_cursor *fc) +int afs_fs_release_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1957,7 +1764,7 @@ int afs_fs_release_lock(struct afs_fs_cursor *fc) __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_release_lock(fc); + return yfs_fs_release_lock(fc, scb); _enter(""); @@ -1966,7 +1773,8 @@ int afs_fs_release_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1977,6 +1785,7 @@ int afs_fs_release_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -2071,14 +1880,6 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) return 0; } -static void afs_destroy_fs_get_capabilities(struct afs_call *call) -{ - struct afs_server *server = call->reply[0]; - - afs_put_server(call->net, server); - afs_flat_call_destructor(call); -} - /* * FS.GetCapabilities operation type */ @@ -2087,7 +1888,7 @@ static const struct afs_call_type afs_RXFSGetCapabilities = { .op = afs_FS_GetCapabilities, .deliver = afs_deliver_fs_get_capabilities, .done = afs_fileserver_probe_result, - .destructor = afs_destroy_fs_get_capabilities, + .destructor = afs_flat_call_destructor, }; /* @@ -2110,11 +1911,11 @@ struct afs_call *afs_fs_get_capabilities(struct afs_net *net, return ERR_PTR(-ENOMEM); call->key = key; - call->reply[0] = afs_get_server(server); - call->reply[1] = (void *)(long)server_index; + call->server = afs_get_server(server, afs_server_trace_get_caps); + call->server_index = server_index; call->upgrade = true; - call->want_reply_time = true; call->async = true; + call->max_lifespan = AFS_PROBE_MAX_LIFESPAN; /* marshall the parameters */ bp = call->request; @@ -2131,10 +1932,6 @@ struct afs_call *afs_fs_get_capabilities(struct afs_net *net, */ static int afs_deliver_fs_fetch_status(struct afs_call *call) { - struct afs_file_status *status = call->reply[1]; - struct afs_callback *callback = call->reply[2]; - struct afs_volsync *volsync = call->reply[3]; - struct afs_fid *fid = call->reply[0]; const __be32 *bp; int ret; @@ -2142,16 +1939,13 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call) if (ret < 0) return ret; - _enter("{%llx:%llu}", fid->vid, fid->vnode); - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = afs_decode_status(call, &bp, status, NULL, - &call->expected_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_AFSCallBack_raw(call, &bp, callback); - xdr_decode_AFSVolSync(&bp, volsync); + xdr_decode_AFSCallBack(&bp, call, call->out_scb); + xdr_decode_AFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -2173,15 +1967,14 @@ static const struct afs_call_type afs_RXFSFetchStatus = { int afs_fs_fetch_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fid, - struct afs_file_status *status, - struct afs_callback *callback, + struct afs_status_cb *scb, struct afs_volsync *volsync) { struct afs_call *call; __be32 *bp; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_fetch_status(fc, net, fid, status, callback, volsync); + return yfs_fs_fetch_status(fc, net, fid, scb, volsync); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), fid->vid, fid->vnode); @@ -2193,12 +1986,9 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = fid; - call->reply[1] = status; - call->reply[2] = callback; - call->reply[3] = volsync; - call->expected_version = 1; /* vnode->status.data_version */ - call->want_reply_time = true; + call->out_fid = fid; + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -2207,9 +1997,9 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, bp[2] = htonl(fid->vnode); bp[3] = htonl(fid->unique); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -2219,9 +2009,7 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) { - struct afs_file_status *statuses; - struct afs_callback *callbacks; - struct afs_vnode *vnode = call->reply[0]; + struct afs_status_cb *scb; const __be32 *bp; u32 tmp; int ret; @@ -2260,10 +2048,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - statuses = call->reply[1]; - ret = afs_decode_status(call, &bp, &statuses[call->count], - call->count == 0 ? vnode : NULL, - NULL, NULL); + scb = &call->out_scb[call->count]; + ret = xdr_decode_AFSFetchStatus(&bp, call, scb); if (ret < 0) return ret; @@ -2302,13 +2088,8 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) _debug("unmarshall CB array"); bp = call->buffer; - callbacks = call->reply[2]; - callbacks[call->count].version = ntohl(bp[0]); - callbacks[call->count].expires_at = xdr_decode_expiry(call, ntohl(bp[1])); - callbacks[call->count].type = ntohl(bp[2]); - statuses = call->reply[1]; - if (call->count == 0 && vnode && statuses[0].abort_code == 0) - xdr_decode_AFSCallBack(call, vnode, &bp); + scb = &call->out_scb[call->count]; + xdr_decode_AFSCallBack(&bp, call, scb); call->count++; if (call->count < call->count2) goto more_cbs; @@ -2323,7 +2104,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_AFSVolSync(&bp, call->reply[3]); + xdr_decode_AFSVolSync(&bp, call->out_volsync); call->unmarshall++; @@ -2351,8 +2132,7 @@ static const struct afs_call_type afs_RXFSInlineBulkStatus = { int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fids, - struct afs_file_status *statuses, - struct afs_callback *callbacks, + struct afs_status_cb *statuses, unsigned int nr_fids, struct afs_volsync *volsync) { @@ -2361,7 +2141,7 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, int i; if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) - return yfs_fs_inline_bulk_status(fc, net, fids, statuses, callbacks, + return yfs_fs_inline_bulk_status(fc, net, fids, statuses, nr_fids, volsync); _enter(",%x,{%llx:%llu},%u", @@ -2376,12 +2156,9 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = NULL; /* vnode for fid[0] */ - call->reply[1] = statuses; - call->reply[2] = callbacks; - call->reply[3] = volsync; + call->out_scb = statuses; + call->out_volsync = volsync; call->count2 = nr_fids; - call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -2393,9 +2170,9 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, *bp++ = htonl(fids[i].unique); } - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &fids[0]); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -2405,7 +2182,6 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, */ static int afs_deliver_fs_fetch_acl(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[1]; struct afs_acl *acl; const __be32 *bp; unsigned int size; @@ -2430,7 +2206,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) acl = kmalloc(struct_size(acl, data, size), GFP_KERNEL); if (!acl) return -ENOMEM; - call->reply[0] = acl; + call->ret_acl = acl; acl->size = call->count2; afs_extract_begin(call, acl->data, size); call->unmarshall++; @@ -2451,11 +2227,10 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) return ret; bp = call->buffer; - ret = afs_decode_status(call, &bp, &vnode->status, vnode, - &vnode->status.data_version, NULL); + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_AFSVolSync(&bp, call->reply[2]); + xdr_decode_AFSVolSync(&bp, call->out_volsync); call->unmarshall++; @@ -2469,7 +2244,7 @@ static int afs_deliver_fs_fetch_acl(struct afs_call *call) static void afs_destroy_fs_fetch_acl(struct afs_call *call) { - kfree(call->reply[0]); + kfree(call->ret_acl); afs_flat_call_destructor(call); } @@ -2486,7 +2261,8 @@ static const struct afs_call_type afs_RXFSFetchACL = { /* * Fetch the ACL for a file. */ -struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *fc) +struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *fc, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -2503,10 +2279,9 @@ struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *fc) } call->key = fc->key; - call->reply[0] = NULL; - call->reply[1] = vnode; - call->reply[2] = NULL; /* volsync */ - call->ret_reply0 = true; + call->ret_acl = NULL; + call->out_scb = scb; + call->out_volsync = NULL; /* marshall the parameters */ bp = call->request; @@ -2515,7 +2290,6 @@ struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *fc) bp[2] = htonl(vnode->fid.vnode); bp[3] = htonl(vnode->fid.unique); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); afs_make_call(&fc->ac, call, GFP_KERNEL); @@ -2523,19 +2297,43 @@ struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *fc) } /* + * Deliver reply data to any operation that returns file status and volume + * sync. + */ +static int afs_deliver_fs_file_status_and_vol(struct afs_call *call) +{ + const __be32 *bp; + int ret; + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + bp = call->buffer; + ret = xdr_decode_AFSFetchStatus(&bp, call, call->out_scb); + if (ret < 0) + return ret; + xdr_decode_AFSVolSync(&bp, call->out_volsync); + + _leave(" = 0 [done]"); + return 0; +} + +/* * FS.StoreACL operation type */ static const struct afs_call_type afs_RXFSStoreACL = { .name = "FS.StoreACL", .op = afs_FS_StoreACL, - .deliver = afs_deliver_fs_status_and_vol, + .deliver = afs_deliver_fs_file_status_and_vol, .destructor = afs_flat_call_destructor, }; /* * Fetch the ACL for a file. */ -int afs_fs_store_acl(struct afs_fs_cursor *fc, const struct afs_acl *acl) +int afs_fs_store_acl(struct afs_fs_cursor *fc, const struct afs_acl *acl, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -2555,8 +2353,8 @@ int afs_fs_store_acl(struct afs_fs_cursor *fc, const struct afs_acl *acl) } call->key = fc->key; - call->reply[0] = vnode; - call->reply[2] = NULL; /* volsync */ + call->out_scb = scb; + call->out_volsync = NULL; /* marshall the parameters */ bp = call->request; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index c4652b42d545..7b1c18c32f48 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -23,6 +23,7 @@ #include <linux/namei.h> #include <linux/iversion.h> #include "internal.h" +#include "afs_fs.h" static const struct inode_operations afs_symlink_inode_operations = { .get_link = page_get_link, @@ -55,41 +56,63 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren } /* + * Set the file size and block count. Estimate the number of 512 bytes blocks + * used, rounded up to nearest 1K for consistency with other AFS clients. + */ +static void afs_set_i_size(struct afs_vnode *vnode, u64 size) +{ + i_size_write(&vnode->vfs_inode, size); + vnode->vfs_inode.i_blocks = ((size + 1023) >> 10) << 1; +} + +/* * Initialise an inode from the vnode status. */ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, - struct afs_vnode *parent_vnode) + struct afs_cb_interest *cbi, + struct afs_vnode *parent_vnode, + struct afs_status_cb *scb) { + struct afs_cb_interest *old_cbi = NULL; + struct afs_file_status *status = &scb->status; struct inode *inode = AFS_VNODE_TO_I(vnode); + struct timespec64 t; _debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu", - vnode->status.type, - vnode->status.nlink, - (unsigned long long) vnode->status.size, - vnode->status.data_version, - vnode->status.mode); + status->type, + status->nlink, + (unsigned long long) status->size, + status->data_version, + status->mode); + + write_seqlock(&vnode->cb_lock); - read_seqlock_excl(&vnode->cb_lock); + vnode->status = *status; - afs_update_inode_from_status(vnode, &vnode->status, NULL, - AFS_VNODE_NOT_YET_SET); + t = status->mtime_client; + inode->i_ctime = t; + inode->i_mtime = t; + inode->i_atime = t; + inode->i_uid = make_kuid(&init_user_ns, status->owner); + inode->i_gid = make_kgid(&init_user_ns, status->group); + set_nlink(&vnode->vfs_inode, status->nlink); - switch (vnode->status.type) { + switch (status->type) { case AFS_FTYPE_FILE: - inode->i_mode = S_IFREG | vnode->status.mode; + inode->i_mode = S_IFREG | status->mode; inode->i_op = &afs_file_inode_operations; inode->i_fop = &afs_file_operations; inode->i_mapping->a_ops = &afs_fs_aops; break; case AFS_FTYPE_DIR: - inode->i_mode = S_IFDIR | vnode->status.mode; + inode->i_mode = S_IFDIR | status->mode; inode->i_op = &afs_dir_inode_operations; inode->i_fop = &afs_dir_file_operations; inode->i_mapping->a_ops = &afs_dir_aops; break; case AFS_FTYPE_SYMLINK: /* Symlinks with a mode of 0644 are actually mountpoints. */ - if ((vnode->status.mode & 0777) == 0644) { + if ((status->mode & 0777) == 0644) { inode->i_flags |= S_AUTOMOUNT; set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags); @@ -99,7 +122,7 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, inode->i_fop = &afs_mntpt_file_operations; inode->i_mapping->a_ops = &afs_fs_aops; } else { - inode->i_mode = S_IFLNK | vnode->status.mode; + inode->i_mode = S_IFLNK | status->mode; inode->i_op = &afs_symlink_inode_operations; inode->i_mapping->a_ops = &afs_fs_aops; } @@ -107,26 +130,181 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, break; default: dump_vnode(vnode, parent_vnode); - read_sequnlock_excl(&vnode->cb_lock); + write_sequnlock(&vnode->cb_lock); return afs_protocol_error(NULL, -EBADMSG, afs_eproto_file_type); } - /* - * Estimate 512 bytes blocks used, rounded up to nearest 1K - * for consistency with other AFS clients. - */ - inode->i_blocks = ((i_size_read(inode) + 1023) >> 10) << 1; - vnode->invalid_before = vnode->status.data_version; + afs_set_i_size(vnode, status->size); - read_sequnlock_excl(&vnode->cb_lock); + vnode->invalid_before = status->data_version; + inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); + + if (!scb->have_cb) { + /* it's a symlink we just created (the fileserver + * didn't give us a callback) */ + vnode->cb_expires_at = ktime_get_real_seconds(); + } else { + vnode->cb_expires_at = scb->callback.expires_at; + old_cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + if (cbi != old_cbi) + rcu_assign_pointer(vnode->cb_interest, afs_get_cb_interest(cbi)); + else + old_cbi = NULL; + set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } + + write_sequnlock(&vnode->cb_lock); + afs_put_cb_interest(afs_v2net(vnode), old_cbi); return 0; } /* + * Update the core inode struct from a returned status record. + */ +static void afs_apply_status(struct afs_fs_cursor *fc, + struct afs_vnode *vnode, + struct afs_status_cb *scb, + const afs_dataversion_t *expected_version) +{ + struct afs_file_status *status = &scb->status; + struct timespec64 t; + umode_t mode; + bool data_changed = false; + + BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags)); + + if (status->type != vnode->status.type) { + pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", + vnode->fid.vid, + vnode->fid.vnode, + vnode->fid.unique, + status->type, vnode->status.type); + afs_protocol_error(NULL, -EBADMSG, afs_eproto_bad_status); + return; + } + + if (status->nlink != vnode->status.nlink) + set_nlink(&vnode->vfs_inode, status->nlink); + + if (status->owner != vnode->status.owner) + vnode->vfs_inode.i_uid = make_kuid(&init_user_ns, status->owner); + + if (status->group != vnode->status.group) + vnode->vfs_inode.i_gid = make_kgid(&init_user_ns, status->group); + + if (status->mode != vnode->status.mode) { + mode = vnode->vfs_inode.i_mode; + mode &= ~S_IALLUGO; + mode |= status->mode; + WRITE_ONCE(vnode->vfs_inode.i_mode, mode); + } + + t = status->mtime_client; + vnode->vfs_inode.i_ctime = t; + vnode->vfs_inode.i_mtime = t; + vnode->vfs_inode.i_atime = t; + + if (vnode->status.data_version != status->data_version) + data_changed = true; + + vnode->status = *status; + + if (expected_version && + *expected_version != status->data_version) { + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) + pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s\n", + vnode->fid.vid, vnode->fid.vnode, + (unsigned long long)*expected_version, + (unsigned long long)status->data_version, + fc->type ? fc->type->name : "???"); + + vnode->invalid_before = status->data_version; + if (vnode->status.type == AFS_FTYPE_DIR) { + if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + afs_stat_v(vnode, n_inval); + } else { + set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); + } + } else if (vnode->status.type == AFS_FTYPE_DIR) { + /* Expected directory change is handled elsewhere so + * that we can locally edit the directory and save on a + * download. + */ + if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) + data_changed = false; + } + + if (data_changed) { + inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); + afs_set_i_size(vnode, status->size); + } +} + +/* + * Apply a callback to a vnode. + */ +static void afs_apply_callback(struct afs_fs_cursor *fc, + struct afs_vnode *vnode, + struct afs_status_cb *scb, + unsigned int cb_break) +{ + struct afs_cb_interest *old; + struct afs_callback *cb = &scb->callback; + + if (!afs_cb_is_broken(cb_break, vnode, fc->cbi)) { + vnode->cb_expires_at = cb->expires_at; + old = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + if (old != fc->cbi) { + rcu_assign_pointer(vnode->cb_interest, afs_get_cb_interest(fc->cbi)); + afs_put_cb_interest(afs_v2net(vnode), old); + } + set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } +} + +/* + * Apply the received status and callback to an inode all in the same critical + * section to avoid races with afs_validate(). + */ +void afs_vnode_commit_status(struct afs_fs_cursor *fc, + struct afs_vnode *vnode, + unsigned int cb_break, + const afs_dataversion_t *expected_version, + struct afs_status_cb *scb) +{ + if (fc->ac.error != 0) + return; + + write_seqlock(&vnode->cb_lock); + + if (scb->have_error) { + if (scb->status.abort_code == VNOVNODE) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + clear_nlink(&vnode->vfs_inode); + __afs_break_callback(vnode, afs_cb_break_for_deleted); + } + } else { + if (scb->have_status) + afs_apply_status(fc, vnode, scb, expected_version); + if (scb->have_cb) + afs_apply_callback(fc, vnode, scb, cb_break); + } + + write_sequnlock(&vnode->cb_lock); + + if (fc->ac.error == 0 && scb->have_status) + afs_cache_permit(vnode, fc->key, cb_break, scb); +} + +/* * Fetch file status from the volume. */ -int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) +int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool is_new, + afs_access_t *_caller_access) { + struct afs_status_cb *scb; struct afs_fs_cursor fc; int ret; @@ -135,18 +313,38 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, vnode->flags); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + return -ENOMEM; + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_fetch_file_status(&fc, NULL, new_inode); + afs_fs_fetch_file_status(&fc, scb, NULL); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + if (fc.error) { + /* Do nothing. */ + } else if (is_new) { + ret = afs_inode_init_from_status(vnode, key, fc.cbi, + NULL, scb); + fc.error = ret; + if (ret == 0) + afs_cache_permit(vnode, key, fc.cb_break, scb); + } else { + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + } + afs_check_for_remote_deletion(&fc, vnode); ret = afs_end_vnode_operation(&fc); } + if (ret == 0 && _caller_access) + *_caller_access = scb->status.caller_access; + kfree(scb); _leave(" = %d", ret); return ret; } @@ -156,10 +354,10 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) */ int afs_iget5_test(struct inode *inode, void *opaque) { - struct afs_iget_data *data = opaque; + struct afs_iget_data *iget_data = opaque; struct afs_vnode *vnode = AFS_FS_I(inode); - return memcmp(&vnode->fid, &data->fid, sizeof(data->fid)) == 0; + return memcmp(&vnode->fid, &iget_data->fid, sizeof(iget_data->fid)) == 0; } /* @@ -177,17 +375,19 @@ static int afs_iget5_pseudo_dir_test(struct inode *inode, void *opaque) */ static int afs_iget5_set(struct inode *inode, void *opaque) { - struct afs_iget_data *data = opaque; + struct afs_iget_data *iget_data = opaque; struct afs_vnode *vnode = AFS_FS_I(inode); - vnode->fid = data->fid; - vnode->volume = data->volume; + vnode->fid = iget_data->fid; + vnode->volume = iget_data->volume; + vnode->cb_v_break = iget_data->cb_v_break; + vnode->cb_s_break = iget_data->cb_s_break; /* YFS supports 96-bit vnode IDs, but Linux only supports * 64-bit inode numbers. */ - inode->i_ino = data->fid.vnode; - inode->i_generation = data->fid.unique; + inode->i_ino = iget_data->fid.vnode; + inode->i_generation = iget_data->fid.unique; return 0; } @@ -197,38 +397,42 @@ static int afs_iget5_set(struct inode *inode, void *opaque) */ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) { - struct afs_iget_data data; struct afs_super_info *as; struct afs_vnode *vnode; struct inode *inode; static atomic_t afs_autocell_ino; + struct afs_iget_data iget_data = { + .cb_v_break = 0, + .cb_s_break = 0, + }; + _enter(""); as = sb->s_fs_info; if (as->volume) { - data.volume = as->volume; - data.fid.vid = as->volume->vid; + iget_data.volume = as->volume; + iget_data.fid.vid = as->volume->vid; } if (root) { - data.fid.vnode = 1; - data.fid.unique = 1; + iget_data.fid.vnode = 1; + iget_data.fid.unique = 1; } else { - data.fid.vnode = atomic_inc_return(&afs_autocell_ino); - data.fid.unique = 0; + iget_data.fid.vnode = atomic_inc_return(&afs_autocell_ino); + iget_data.fid.unique = 0; } - inode = iget5_locked(sb, data.fid.vnode, + inode = iget5_locked(sb, iget_data.fid.vnode, afs_iget5_pseudo_dir_test, afs_iget5_set, - &data); + &iget_data); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); } _debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }", - inode, inode->i_ino, data.fid.vid, data.fid.vnode, - data.fid.unique); + inode, inode->i_ino, iget_data.fid.vid, iget_data.fid.vnode, + iget_data.fid.unique); vnode = AFS_FS_I(inode); @@ -299,23 +503,24 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) * inode retrieval */ struct inode *afs_iget(struct super_block *sb, struct key *key, - struct afs_fid *fid, struct afs_file_status *status, - struct afs_callback *cb, struct afs_cb_interest *cbi, + struct afs_iget_data *iget_data, + struct afs_status_cb *scb, + struct afs_cb_interest *cbi, struct afs_vnode *parent_vnode) { - struct afs_iget_data data = { .fid = *fid }; struct afs_super_info *as; struct afs_vnode *vnode; + struct afs_fid *fid = &iget_data->fid; struct inode *inode; int ret; _enter(",{%llx:%llu.%u},,", fid->vid, fid->vnode, fid->unique); as = sb->s_fs_info; - data.volume = as->volume; + iget_data->volume = as->volume; inode = iget5_locked(sb, fid->vnode, afs_iget5_test, afs_iget5_set, - &data); + iget_data); if (!inode) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); @@ -332,43 +537,25 @@ struct inode *afs_iget(struct super_block *sb, struct key *key, return inode; } - if (!status) { + if (!scb) { /* it's a remotely extant inode */ - ret = afs_fetch_status(vnode, key, true); + ret = afs_fetch_status(vnode, key, true, NULL); if (ret < 0) goto bad_inode; } else { - /* it's an inode we just created */ - memcpy(&vnode->status, status, sizeof(vnode->status)); - - if (!cb) { - /* it's a symlink we just created (the fileserver - * didn't give us a callback) */ - vnode->cb_version = 0; - vnode->cb_type = 0; - vnode->cb_expires_at = ktime_get(); - } else { - vnode->cb_version = cb->version; - vnode->cb_type = cb->type; - vnode->cb_expires_at = cb->expires_at; - vnode->cb_interest = afs_get_cb_interest(cbi); - set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } - - vnode->cb_expires_at += ktime_get_real_seconds(); + ret = afs_inode_init_from_status(vnode, key, cbi, parent_vnode, + scb); + if (ret < 0) + goto bad_inode; } - ret = afs_inode_init_from_status(vnode, key, parent_vnode); - if (ret < 0) - goto bad_inode; - afs_get_inode_cache(vnode); /* success */ clear_bit(AFS_VNODE_UNSET, &vnode->flags); inode->i_flags |= S_NOATIME; unlock_new_inode(inode); - _leave(" = %p [CB { v=%u t=%u }]", inode, vnode->cb_version, vnode->cb_type); + _leave(" = %p", inode); return inode; /* failure */ @@ -400,6 +587,69 @@ void afs_zap_data(struct afs_vnode *vnode) } /* + * Check the validity of a vnode/inode. + */ +bool afs_check_validity(struct afs_vnode *vnode) +{ + struct afs_cb_interest *cbi; + struct afs_server *server; + struct afs_volume *volume = vnode->volume; + enum afs_cb_break_reason need_clear = afs_cb_break_no_break; + time64_t now = ktime_get_real_seconds(); + bool valid; + unsigned int cb_break, cb_s_break, cb_v_break; + int seq = 0; + + do { + read_seqbegin_or_lock(&vnode->cb_lock, &seq); + cb_v_break = READ_ONCE(volume->cb_v_break); + cb_break = vnode->cb_break; + + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { + cbi = rcu_dereference(vnode->cb_interest); + server = rcu_dereference(cbi->server); + cb_s_break = READ_ONCE(server->cb_s_break); + + if (vnode->cb_s_break != cb_s_break || + vnode->cb_v_break != cb_v_break) { + vnode->cb_s_break = cb_s_break; + vnode->cb_v_break = cb_v_break; + need_clear = afs_cb_break_for_vsbreak; + valid = false; + } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) { + need_clear = afs_cb_break_for_zap; + valid = false; + } else if (vnode->cb_expires_at - 10 <= now) { + need_clear = afs_cb_break_for_lapsed; + valid = false; + } else { + valid = true; + } + } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { + valid = true; + } else { + vnode->cb_v_break = cb_v_break; + valid = false; + } + + } while (need_seqretry(&vnode->cb_lock, seq)); + + done_seqretry(&vnode->cb_lock, seq); + + if (need_clear != afs_cb_break_no_break) { + write_seqlock(&vnode->cb_lock); + if (cb_break == vnode->cb_break) + __afs_break_callback(vnode, need_clear); + else + trace_afs_cb_miss(&vnode->fid, need_clear); + write_sequnlock(&vnode->cb_lock); + valid = false; + } + + return valid; +} + +/* * validate a vnode/inode * - there are several things we need to check * - parent dir data changes (rm, rmdir, rename, mkdir, create, link, @@ -410,7 +660,6 @@ void afs_zap_data(struct afs_vnode *vnode) */ int afs_validate(struct afs_vnode *vnode, struct key *key) { - time64_t now = ktime_get_real_seconds(); bool valid; int ret; @@ -418,36 +667,9 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->fid.vid, vnode->fid.vnode, vnode->flags, key_serial(key)); - /* Quickly check the callback state. Ideally, we'd use read_seqbegin - * here, but we have no way to pass the net namespace to the RCU - * cleanup for the server record. - */ - read_seqlock_excl(&vnode->cb_lock); - - if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { - if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break || - vnode->cb_v_break != vnode->volume->cb_v_break) { - vnode->cb_s_break = vnode->cb_interest->server->cb_s_break; - vnode->cb_v_break = vnode->volume->cb_v_break; - valid = false; - } else if (vnode->status.type == AFS_FTYPE_DIR && - (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) || - vnode->cb_expires_at - 10 <= now)) { - valid = false; - } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) || - vnode->cb_expires_at - 10 <= now) { - valid = false; - } else { - valid = true; - } - } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { - valid = true; - } else { - vnode->cb_v_break = vnode->volume->cb_v_break; - valid = false; - } - - read_sequnlock_excl(&vnode->cb_lock); + rcu_read_lock(); + valid = afs_check_validity(vnode); + rcu_read_unlock(); if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) clear_nlink(&vnode->vfs_inode); @@ -463,7 +685,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) * access */ if (!test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { _debug("not promised"); - ret = afs_fetch_status(vnode, key, false); + ret = afs_fetch_status(vnode, key, false, NULL); if (ret < 0) { if (ret == -ENOENT) { set_bit(AFS_VNODE_DELETED, &vnode->flags); @@ -534,6 +756,7 @@ int afs_drop_inode(struct inode *inode) */ void afs_evict_inode(struct inode *inode) { + struct afs_cb_interest *cbi; struct afs_vnode *vnode; vnode = AFS_FS_I(inode); @@ -550,10 +773,14 @@ void afs_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); clear_inode(inode); - if (vnode->cb_interest) { - afs_put_cb_interest(afs_i2net(inode), vnode->cb_interest); - vnode->cb_interest = NULL; + write_seqlock(&vnode->cb_lock); + cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->cb_lock.lock)); + if (cbi) { + afs_put_cb_interest(afs_i2net(inode), cbi); + rcu_assign_pointer(vnode->cb_interest, NULL); } + write_sequnlock(&vnode->cb_lock); while (!list_empty(&vnode->wb_keys)) { struct afs_wb_key *wbk = list_entry(vnode->wb_keys.next, @@ -573,6 +800,7 @@ void afs_evict_inode(struct inode *inode) } #endif + afs_prune_wb_keys(vnode); afs_put_permits(rcu_access_pointer(vnode->permit_cache)); key_put(vnode->silly_key); vnode->silly_key = NULL; @@ -587,9 +815,10 @@ void afs_evict_inode(struct inode *inode) int afs_setattr(struct dentry *dentry, struct iattr *attr) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); struct key *key; - int ret; + int ret = -ENOMEM; _enter("{%llx:%llu},{n=%pd},%x", vnode->fid.vid, vnode->fid.vnode, dentry, @@ -601,6 +830,10 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) return 0; } + scb = kzalloc(sizeof(struct afs_status_cb), GFP_KERNEL); + if (!scb) + goto error; + /* flush any dirty data outstanding on a regular file */ if (S_ISREG(vnode->vfs_inode.i_mode)) filemap_write_and_wait(vnode->vfs_inode.i_mapping); @@ -611,25 +844,33 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) key = afs_request_key(vnode->volume->cell); if (IS_ERR(key)) { ret = PTR_ERR(key); - goto error; + goto error_scb; } } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, false)) { + afs_dataversion_t data_version = vnode->status.data_version; + + if (attr->ia_valid & ATTR_SIZE) + data_version++; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_setattr(&fc, attr); + afs_fs_setattr(&fc, attr, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } if (!(attr->ia_valid & ATTR_FILE)) key_put(key); +error_scb: + kfree(scb); error: _leave(" = %d", ret); return ret; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index b3cd6e8ad59d..f66a3be12fd6 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal AFS stuff * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/compiler.h> @@ -66,6 +62,8 @@ struct afs_fs_context { struct afs_iget_data { struct afs_fid fid; struct afs_volume *volume; /* volume on which resides */ + unsigned int cb_v_break; /* Pre-fetch volume break count */ + unsigned int cb_s_break; /* Pre-fetch server break count */ }; enum afs_call_state { @@ -111,8 +109,10 @@ struct afs_call { struct rxrpc_call *rxcall; /* RxRPC call handle */ struct key *key; /* security for this call */ struct afs_net *net; /* The network namespace */ - struct afs_server *cm_server; /* Server affected by incoming CM call */ + struct afs_server *server; /* The fileserver record if fs op (pins ref) */ + struct afs_vlserver *vlserver; /* The vlserver record if vl op */ struct afs_cb_interest *cbi; /* Callback interest for server used */ + struct afs_vnode *lvnode; /* vnode being locked */ void *request; /* request data (first part) */ struct address_space *mapping; /* Pages being written from */ struct iov_iter iter; /* Buffer iterator */ @@ -122,7 +122,20 @@ struct afs_call { struct bio_vec bvec[1]; }; void *buffer; /* reply receive buffer */ - void *reply[4]; /* Where to put the reply */ + union { + long ret0; /* Value to reply with instead of 0 */ + struct afs_addr_list *ret_alist; + struct afs_vldb_entry *ret_vldb; + struct afs_acl *ret_acl; + }; + struct afs_fid *out_fid; + struct afs_status_cb *out_dir_scb; + struct afs_status_cb *out_scb; + struct yfs_acl *out_yacl; + struct afs_volsync *out_volsync; + struct afs_volume_status *out_volstatus; + struct afs_read *read_request; + unsigned int server_index; pgoff_t first; /* first page in mapping to deal with */ pgoff_t last; /* last page in mapping to deal with */ atomic_t usage; @@ -131,10 +144,10 @@ struct afs_call { int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ u32 epoch; + unsigned int max_lifespan; /* Maximum lifespan to set if not 0 */ unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ unsigned first_offset; /* offset into mapping[first] */ - unsigned int cb_break; /* cb_break + cb_s_break before the call */ union { unsigned last_to; /* amount of mapping[last] */ unsigned count2; /* count used in unmarshalling */ @@ -145,9 +158,9 @@ struct afs_call { bool send_pages; /* T if data from mapping should be sent */ bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ - bool ret_reply0; /* T if should return reply[0] on success */ bool upgrade; /* T to request service upgrade */ - bool want_reply_time; /* T if want reply_time */ + bool have_reply_time; /* T if have got reply_time */ + bool intr; /* T if interruptible */ u16 service_id; /* Actual service ID (after upgrade) */ unsigned int debug_id; /* Trace ID */ u32 operation_ID; /* operation ID for an incoming call */ @@ -159,8 +172,6 @@ struct afs_call { } __attribute__((packed)); __be64 tmp64; }; - afs_dataversion_t expected_version; /* Updated version expected from store */ - afs_dataversion_t expected_version_2; /* 2nd updated version expected from store */ ktime_t reply_time; /* Time of first reply packet */ }; @@ -221,7 +232,8 @@ struct afs_read { unsigned int index; /* Which page we're reading into */ unsigned int nr_pages; unsigned int offset; /* offset into current page */ - void (*page_done)(struct afs_call *, struct afs_read *); + struct afs_vnode *vnode; + void (*page_done)(struct afs_read *); struct page **pages; struct page *array[]; }; @@ -367,13 +379,13 @@ struct afs_cell { time64_t last_inactive; /* Time of last drop of usage count */ atomic_t usage; unsigned long flags; -#define AFS_CELL_FL_NOT_READY 0 /* The cell record is not ready for use */ -#define AFS_CELL_FL_NO_GC 1 /* The cell was added manually, don't auto-gc */ -#define AFS_CELL_FL_NOT_FOUND 2 /* Permanent DNS error */ -#define AFS_CELL_FL_DNS_FAIL 3 /* Failed to access DNS */ -#define AFS_CELL_FL_NO_LOOKUP_YET 4 /* Not completed first DNS lookup yet */ +#define AFS_CELL_FL_NO_GC 0 /* The cell was added manually, don't auto-gc */ +#define AFS_CELL_FL_DO_LOOKUP 1 /* DNS lookup requested */ enum afs_cell_state state; short error; + enum dns_record_source dns_source:8; /* Latest source of data from lookup */ + enum dns_lookup_status dns_status:8; /* Latest status of data from lookup */ + unsigned int dns_lookup_count; /* Counter of DNS lookups */ /* Active fileserver interaction state. */ struct list_head proc_volumes; /* procfs volume list */ @@ -502,6 +514,7 @@ struct afs_server { atomic_t usage; u32 addr_version; /* Address list version */ u32 cm_epoch; /* Server RxRPC epoch */ + unsigned int debug_id; /* Debugging ID for traces */ /* file service access */ rwlock_t fs_lock; /* access lock */ @@ -538,7 +551,10 @@ struct afs_server { struct afs_vol_interest { struct hlist_node srv_link; /* Link in server->cb_volumes */ struct hlist_head cb_interests; /* List of callback interests on the server */ - afs_volid_t vid; /* Volume ID to match */ + union { + struct rcu_head rcu; + afs_volid_t vid; /* Volume ID to match */ + }; unsigned int usage; }; @@ -550,7 +566,10 @@ struct afs_cb_interest { struct afs_vol_interest *vol_interest; struct afs_server *server; /* Server on which this interest resides */ struct super_block *sb; /* Superblock on which inodes reside */ - afs_volid_t vid; /* Volume ID to match */ + union { + struct rcu_head rcu; + afs_volid_t vid; /* Volume ID to match */ + }; refcount_t usage; }; @@ -596,7 +615,7 @@ struct afs_volume { unsigned int servers_seq; /* Incremented each time ->servers changes */ unsigned cb_v_break; /* Break-everything counter. */ - rwlock_t cb_break_lock; + rwlock_t cb_v_break_lock; afs_voltype_t type; /* type of volume */ short error; @@ -660,15 +679,13 @@ struct afs_vnode { afs_lock_type_t lock_type : 8; /* outstanding callback notification on this file */ - struct afs_cb_interest *cb_interest; /* Server on which this resides */ + struct afs_cb_interest __rcu *cb_interest; /* Server on which this resides */ unsigned int cb_s_break; /* Mass break counter on ->server */ unsigned int cb_v_break; /* Mass break counter on ->volume */ unsigned int cb_break; /* Break counter on vnode */ seqlock_t cb_lock; /* Lock for ->cb_interest, ->status, ->cb_*break */ time64_t cb_expires_at; /* time at which callback expires */ - unsigned cb_version; /* callback version */ - afs_callback_type_t cb_type; /* type of callback */ }; static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode) @@ -703,15 +720,6 @@ struct afs_permits { }; /* - * record of one of a system's set of network interfaces - */ -struct afs_interface { - struct in_addr address; /* IPv4 address bound to interface */ - struct in_addr netmask; /* netmask applied to address */ - unsigned mtu; /* MTU of interface */ -}; - -/* * Error prioritisation and accumulation. */ struct afs_error { @@ -755,6 +763,7 @@ struct afs_vl_cursor { * Cursor for iterating over a set of fileservers. */ struct afs_fs_cursor { + const struct afs_call_type *type; /* Type of call done */ struct afs_addr_cursor ac; struct afs_vnode *vnode; struct afs_server_list *server_list; /* Current server list (pins ref) */ @@ -772,6 +781,7 @@ struct afs_fs_cursor { #define AFS_FS_CURSOR_VNOVOL 0x0008 /* Set if seen VNOVOL */ #define AFS_FS_CURSOR_CUR_ONLY 0x0010 /* Set if current server only (file lock held) */ #define AFS_FS_CURSOR_NO_VSLEEP 0x0020 /* Set to prevent sleep on VBUSY, VOFFLINE, ... */ +#define AFS_FS_CURSOR_INTR 0x0040 /* Set if op is interruptible */ unsigned short nr_iterations; /* Number of server iterations */ }; @@ -826,9 +836,9 @@ extern struct fscache_cookie_def afs_vnode_cache_index_def; * callback.c */ extern void afs_init_callback_state(struct afs_server *); -extern void __afs_break_callback(struct afs_vnode *); -extern void afs_break_callback(struct afs_vnode *); -extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*); +extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); +extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); +extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break *); extern int afs_register_server_cb_interest(struct afs_vnode *, struct afs_server_list *, unsigned int); @@ -882,7 +892,6 @@ extern const struct address_space_operations afs_dir_aops; extern const struct dentry_operations afs_fs_dentry_operations; extern void afs_d_release(struct dentry *); -extern int afs_dir_remove_link(struct dentry *, struct key *, unsigned long, unsigned long); /* * dir_edit.c @@ -940,50 +949,48 @@ extern int afs_flock(struct file *, int, struct file_lock *); /* * fsclient.c */ -#define AFS_VNODE_NOT_YET_SET 0x01 -#define AFS_VNODE_META_CHANGED 0x02 -#define AFS_VNODE_DATA_CHANGED 0x04 -extern void afs_update_inode_from_status(struct afs_vnode *, struct afs_file_status *, - const afs_dataversion_t *, u8); - -extern int afs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_volsync *, bool); +extern int afs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_status_cb *, + struct afs_volsync *); extern int afs_fs_give_up_callbacks(struct afs_net *, struct afs_server *); -extern int afs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *); -extern int afs_fs_create(struct afs_fs_cursor *, const char *, umode_t, u64, - struct afs_fid *, struct afs_file_status *, struct afs_callback *); -extern int afs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64); -extern int afs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); -extern int afs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64, - struct afs_fid *, struct afs_file_status *); +extern int afs_fs_fetch_data(struct afs_fs_cursor *, struct afs_status_cb *, struct afs_read *); +extern int afs_fs_create(struct afs_fs_cursor *, const char *, umode_t, + struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); +extern int afs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, + struct afs_status_cb *); +extern int afs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); +extern int afs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, + struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); extern int afs_fs_rename(struct afs_fs_cursor *, const char *, - struct afs_vnode *, const char *, u64, u64); + struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); extern int afs_fs_store_data(struct afs_fs_cursor *, struct address_space *, - pgoff_t, pgoff_t, unsigned, unsigned); -extern int afs_fs_setattr(struct afs_fs_cursor *, struct iattr *); + pgoff_t, pgoff_t, unsigned, unsigned, struct afs_status_cb *); +extern int afs_fs_setattr(struct afs_fs_cursor *, struct iattr *, struct afs_status_cb *); extern int afs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *); -extern int afs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t); -extern int afs_fs_extend_lock(struct afs_fs_cursor *); -extern int afs_fs_release_lock(struct afs_fs_cursor *); +extern int afs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t, struct afs_status_cb *); +extern int afs_fs_extend_lock(struct afs_fs_cursor *, struct afs_status_cb *); +extern int afs_fs_release_lock(struct afs_fs_cursor *, struct afs_status_cb *); extern int afs_fs_give_up_all_callbacks(struct afs_net *, struct afs_server *, struct afs_addr_cursor *, struct key *); extern struct afs_call *afs_fs_get_capabilities(struct afs_net *, struct afs_server *, struct afs_addr_cursor *, struct key *, unsigned int); extern int afs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, unsigned int, - struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + unsigned int, struct afs_volsync *); extern int afs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + struct afs_volsync *); struct afs_acl { u32 size; u8 data[]; }; -extern struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *); -extern int afs_fs_store_acl(struct afs_fs_cursor *, const struct afs_acl *); +extern struct afs_acl *afs_fs_fetch_acl(struct afs_fs_cursor *, struct afs_status_cb *); +extern int afs_fs_store_acl(struct afs_fs_cursor *, const struct afs_acl *, + struct afs_status_cb *); /* * fs_probe.c @@ -995,15 +1002,20 @@ extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long); /* * inode.c */ -extern int afs_fetch_status(struct afs_vnode *, struct key *, bool); +extern void afs_vnode_commit_status(struct afs_fs_cursor *, + struct afs_vnode *, + unsigned int, + const afs_dataversion_t *, + struct afs_status_cb *); +extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); extern int afs_iget5_test(struct inode *, void *); extern struct inode *afs_iget_pseudo_dir(struct super_block *, bool); extern struct inode *afs_iget(struct super_block *, struct key *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, + struct afs_iget_data *, struct afs_status_cb *, struct afs_cb_interest *, struct afs_vnode *); extern void afs_zap_data(struct afs_vnode *); +extern bool afs_check_validity(struct afs_vnode *); extern int afs_validate(struct afs_vnode *, struct key *); extern int afs_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int afs_setattr(struct dentry *, struct iattr *); @@ -1070,12 +1082,6 @@ extern struct vfsmount *afs_d_automount(struct path *); extern void afs_mntpt_kill_timer(void); /* - * netdevices.c - */ -extern int afs_get_ipv4_interfaces(struct afs_net *, struct afs_interface *, - size_t, bool); - -/* * proc.c */ #ifdef CONFIG_PROC_FS @@ -1096,7 +1102,7 @@ static inline void afs_put_sysnames(struct afs_sysnames *sysnames) {} * rotate.c */ extern bool afs_begin_vnode_operation(struct afs_fs_cursor *, struct afs_vnode *, - struct key *); + struct key *, bool); extern bool afs_select_fileserver(struct afs_fs_cursor *); extern bool afs_select_current_fileserver(struct afs_fs_cursor *); extern int afs_end_vnode_operation(struct afs_fs_cursor *); @@ -1121,6 +1127,12 @@ extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); extern int afs_extract_data(struct afs_call *, bool); extern int afs_protocol_error(struct afs_call *, int, enum afs_eproto_cause); +static inline void afs_set_fc_call(struct afs_call *call, struct afs_fs_cursor *fc) +{ + call->intr = fc->flags & AFS_FS_CURSOR_INTR; + fc->type = call->type; +} + static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size) { call->kvec[0].iov_base = buf; @@ -1201,7 +1213,8 @@ static inline void afs_set_call_complete(struct afs_call *call, */ extern void afs_put_permits(struct afs_permits *); extern void afs_clear_permits(struct afs_vnode *); -extern void afs_cache_permit(struct afs_vnode *, struct key *, unsigned int); +extern void afs_cache_permit(struct afs_vnode *, struct key *, unsigned int, + struct afs_status_cb *); extern void afs_zap_permits(struct rcu_head *); extern struct key *afs_request_key(struct afs_cell *); extern int afs_check_permit(struct afs_vnode *, struct key *, afs_access_t *); @@ -1213,17 +1226,12 @@ extern void __exit afs_clean_up_permit_cache(void); */ extern spinlock_t afs_server_peer_lock; -static inline struct afs_server *afs_get_server(struct afs_server *server) -{ - atomic_inc(&server->usage); - return server; -} - extern struct afs_server *afs_find_server(struct afs_net *, const struct sockaddr_rxrpc *); extern struct afs_server *afs_find_server_by_uuid(struct afs_net *, const uuid_t *); extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *); -extern void afs_put_server(struct afs_net *, struct afs_server *); +extern struct afs_server *afs_get_server(struct afs_server *, enum afs_server_trace); +extern void afs_put_server(struct afs_net *, struct afs_server *, enum afs_server_trace); extern void afs_manage_servers(struct work_struct *); extern void afs_servers_timer(struct timer_list *); extern void __net_exit afs_purge_servers(struct afs_net *); @@ -1327,7 +1335,6 @@ extern int afs_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata); extern int afs_writepage(struct page *, struct writeback_control *); extern int afs_writepages(struct address_space *, struct writeback_control *); -extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *); extern int afs_fsync(struct file *, loff_t, loff_t, int); extern vm_fault_t afs_page_mkwrite(struct vm_fault *vmf); @@ -1343,33 +1350,36 @@ extern ssize_t afs_listxattr(struct dentry *, char *, size_t); /* * yfsclient.c */ -extern int yfs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_volsync *, bool); -extern int yfs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *); -extern int yfs_fs_create_file(struct afs_fs_cursor *, const char *, umode_t, u64, - struct afs_fid *, struct afs_file_status *, struct afs_callback *); -extern int yfs_fs_make_dir(struct afs_fs_cursor *, const char *, umode_t, u64, - struct afs_fid *, struct afs_file_status *, struct afs_callback *); -extern int yfs_fs_remove_file2(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); -extern int yfs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64); -extern int yfs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); -extern int yfs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64, - struct afs_fid *, struct afs_file_status *); -extern int yfs_fs_rename(struct afs_fs_cursor *, const char *, - struct afs_vnode *, const char *, u64, u64); +extern int yfs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_status_cb *, + struct afs_volsync *); +extern int yfs_fs_fetch_data(struct afs_fs_cursor *, struct afs_status_cb *, struct afs_read *); +extern int yfs_fs_create_file(struct afs_fs_cursor *, const char *, umode_t, struct afs_status_cb *, + struct afs_fid *, struct afs_status_cb *); +extern int yfs_fs_make_dir(struct afs_fs_cursor *, const char *, umode_t, struct afs_status_cb *, + struct afs_fid *, struct afs_status_cb *); +extern int yfs_fs_remove_file2(struct afs_fs_cursor *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); +extern int yfs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, + struct afs_status_cb *); +extern int yfs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); +extern int yfs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, + struct afs_status_cb *, struct afs_fid *, struct afs_status_cb *); +extern int yfs_fs_rename(struct afs_fs_cursor *, const char *, struct afs_vnode *, const char *, + struct afs_status_cb *, struct afs_status_cb *); extern int yfs_fs_store_data(struct afs_fs_cursor *, struct address_space *, - pgoff_t, pgoff_t, unsigned, unsigned); -extern int yfs_fs_setattr(struct afs_fs_cursor *, struct iattr *); + pgoff_t, pgoff_t, unsigned, unsigned, struct afs_status_cb *); +extern int yfs_fs_setattr(struct afs_fs_cursor *, struct iattr *, struct afs_status_cb *); extern int yfs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *); -extern int yfs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t); -extern int yfs_fs_extend_lock(struct afs_fs_cursor *); -extern int yfs_fs_release_lock(struct afs_fs_cursor *); +extern int yfs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t, struct afs_status_cb *); +extern int yfs_fs_extend_lock(struct afs_fs_cursor *, struct afs_status_cb *); +extern int yfs_fs_release_lock(struct afs_fs_cursor *, struct afs_status_cb *); extern int yfs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + struct afs_volsync *); extern int yfs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, - struct afs_fid *, struct afs_file_status *, - struct afs_callback *, unsigned int, - struct afs_volsync *); + struct afs_fid *, struct afs_status_cb *, + unsigned int, struct afs_volsync *); struct yfs_acl { struct afs_acl *acl; /* Dir/file/symlink ACL */ @@ -1382,8 +1392,10 @@ struct yfs_acl { }; extern void yfs_free_opaque_acl(struct yfs_acl *); -extern struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *, unsigned int); -extern int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *, const struct afs_acl *); +extern struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *, struct yfs_acl *, + struct afs_status_cb *); +extern int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *, const struct afs_acl *, + struct afs_status_cb *); /* * Miscellaneous inline functions. @@ -1398,20 +1410,12 @@ static inline struct inode *AFS_VNODE_TO_I(struct afs_vnode *vnode) return &vnode->vfs_inode; } -static inline void afs_vnode_commit_status(struct afs_fs_cursor *fc, - struct afs_vnode *vnode, - unsigned int cb_break) -{ - if (fc->ac.error == 0) - afs_cache_permit(vnode, fc->key, cb_break); -} - static inline void afs_check_for_remote_deletion(struct afs_fs_cursor *fc, struct afs_vnode *vnode) { if (fc->ac.error == -ENOENT) { set_bit(AFS_VNODE_DELETED, &vnode->flags); - afs_break_callback(vnode); + afs_break_callback(vnode, afs_cb_break_for_deleted); } } diff --git a/fs/afs/main.c b/fs/afs/main.c index 107427688edd..c9c45d7078bd 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS client file system * * Copyright (C) 2002,5 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 7f2af061ea06..52b19e9c1535 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* miscellaneous bits * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> @@ -14,6 +10,7 @@ #include <linux/errno.h> #include "internal.h" #include "afs_fs.h" +#include "protocol_uae.h" /* * convert an AFS abort code to a Linux error number @@ -69,34 +66,25 @@ int afs_abort_to_error(u32 abort_code) case AFSVL_PERM: return -EACCES; case AFSVL_NOMEM: return -EREMOTEIO; - /* Unified AFS error table; ET "uae" == 0x2f6df00 */ - case 0x2f6df00: return -EPERM; - case 0x2f6df01: return -ENOENT; - case 0x2f6df04: return -EIO; - case 0x2f6df0a: return -EAGAIN; - case 0x2f6df0b: return -ENOMEM; - case 0x2f6df0c: return -EACCES; - case 0x2f6df0f: return -EBUSY; - case 0x2f6df10: return -EEXIST; - case 0x2f6df11: return -EXDEV; - case 0x2f6df12: return -ENODEV; - case 0x2f6df13: return -ENOTDIR; - case 0x2f6df14: return -EISDIR; - case 0x2f6df15: return -EINVAL; - case 0x2f6df1a: return -EFBIG; - case 0x2f6df1b: return -ENOSPC; - case 0x2f6df1d: return -EROFS; - case 0x2f6df1e: return -EMLINK; - case 0x2f6df20: return -EDOM; - case 0x2f6df21: return -ERANGE; - case 0x2f6df22: return -EDEADLK; - case 0x2f6df23: return -ENAMETOOLONG; - case 0x2f6df24: return -ENOLCK; - case 0x2f6df26: return -ENOTEMPTY; - case 0x2f6df28: return -EWOULDBLOCK; - case 0x2f6df69: return -ENOTCONN; - case 0x2f6df6c: return -ETIMEDOUT; - case 0x2f6df78: return -EDQUOT; + /* Unified AFS error table */ + case UAEPERM: return -EPERM; + case UAENOENT: return -ENOENT; + case UAEACCES: return -EACCES; + case UAEBUSY: return -EBUSY; + case UAEEXIST: return -EEXIST; + case UAENOTDIR: return -ENOTDIR; + case UAEISDIR: return -EISDIR; + case UAEFBIG: return -EFBIG; + case UAENOSPC: return -ENOSPC; + case UAEROFS: return -EROFS; + case UAEMLINK: return -EMLINK; + case UAEDEADLK: return -EDEADLK; + case UAENAMETOOLONG: return -ENAMETOOLONG; + case UAENOLCK: return -ENOLCK; + case UAENOTEMPTY: return -ENOTEMPTY; + case UAELOOP: return -ELOOP; + case UAENOMEDIUM: return -ENOMEDIUM; + case UAEDQUOT: return -EDQUOT; /* RXKAD abort codes; from include/rxrpc/packet.h. ET "RXK" == 0x1260B00 */ case RXKADINCONSISTENCY: return -EPROTO; diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index eecd8b699186..f532d6d3bd28 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* mountpoint management * * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> diff --git a/fs/afs/netdevices.c b/fs/afs/netdevices.c deleted file mode 100644 index 2a009d1939d7..000000000000 --- a/fs/afs/netdevices.c +++ /dev/null @@ -1,48 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* AFS network device helpers - * - * Copyright (c) 2007 Patrick McHardy <kaber@trash.net> - */ - -#include <linux/string.h> -#include <linux/rtnetlink.h> -#include <linux/inetdevice.h> -#include <linux/netdevice.h> -#include <linux/if_arp.h> -#include <net/net_namespace.h> -#include "internal.h" - -/* - * get a list of this system's interface IPv4 addresses, netmasks and MTUs - * - maxbufs must be at least 1 - * - returns the number of interface records in the buffer - */ -int afs_get_ipv4_interfaces(struct afs_net *net, struct afs_interface *bufs, - size_t maxbufs, bool wantloopback) -{ - struct net_device *dev; - struct in_device *idev; - int n = 0; - - ASSERT(maxbufs > 0); - - rtnl_lock(); - for_each_netdev(net->net, dev) { - if (dev->type == ARPHRD_LOOPBACK && !wantloopback) - continue; - idev = __in_dev_get_rtnl(dev); - if (!idev) - continue; - for_primary_ifa(idev) { - bufs[n].address.s_addr = ifa->ifa_address; - bufs[n].netmask.s_addr = ifa->ifa_mask; - bufs[n].mtu = dev->mtu; - n++; - if (n >= maxbufs) - goto out; - } endfor_ifa(idev); - } -out: - rtnl_unlock(); - return n; -} diff --git a/fs/afs/proc.c b/fs/afs/proc.c index be2ee3bbd0a9..fba2ec3a3a9c 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* /proc interface for AFS * * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/slab.h> @@ -53,7 +49,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v) seq_printf(m, "%3u %6lld %2u %s\n", atomic_read(&cell->usage), cell->dns_expiry - ktime_get_real_seconds(), - vllist ? vllist->nr_servers : 0, + vllist->nr_servers, cell->name); return 0; } @@ -296,8 +292,8 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v) if (v == SEQ_START_TOKEN) { seq_printf(m, "# source %s, status %s\n", - dns_record_sources[vllist->source], - dns_lookup_statuses[vllist->status]); + dns_record_sources[vllist ? vllist->source : 0], + dns_lookup_statuses[vllist ? vllist->status : 0]); return 0; } @@ -336,7 +332,7 @@ static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos) if (pos == 0) return SEQ_START_TOKEN; - if (!vllist || pos - 1 >= vllist->nr_servers) + if (pos - 1 >= vllist->nr_servers) return NULL; return &vllist->servers[pos - 1]; diff --git a/fs/afs/protocol_uae.h b/fs/afs/protocol_uae.h new file mode 100644 index 000000000000..1b3d1060bd34 --- /dev/null +++ b/fs/afs/protocol_uae.h @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Universal AFS Error codes (UAE). + * + * Copyright (C) 2003, Daria Phoebe Brashear + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + */ + +enum { + UAEPERM = 0x2f6df00, /* Operation not permitted */ + UAENOENT = 0x2f6df01, /* No such file or directory */ + UAESRCH = 0x2f6df02, /* No such process */ + UAEINTR = 0x2f6df03, /* Interrupted system call */ + UAEIO = 0x2f6df04, /* I/O error */ + UAENXIO = 0x2f6df05, /* No such device or address */ + UAE2BIG = 0x2f6df06, /* Arg list too long */ + UAENOEXEC = 0x2f6df07, /* Exec format error */ + UAEBADF = 0x2f6df08, /* Bad file number */ + UAECHILD = 0x2f6df09, /* No child processes */ + UAEAGAIN = 0x2f6df0a, /* Try again */ + UAENOMEM = 0x2f6df0b, /* Out of memory */ + UAEACCES = 0x2f6df0c, /* Permission denied */ + UAEFAULT = 0x2f6df0d, /* Bad address */ + UAENOTBLK = 0x2f6df0e, /* Block device required */ + UAEBUSY = 0x2f6df0f, /* Device or resource busy */ + UAEEXIST = 0x2f6df10, /* File exists */ + UAEXDEV = 0x2f6df11, /* Cross-device link */ + UAENODEV = 0x2f6df12, /* No such device */ + UAENOTDIR = 0x2f6df13, /* Not a directory */ + UAEISDIR = 0x2f6df14, /* Is a directory */ + UAEINVAL = 0x2f6df15, /* Invalid argument */ + UAENFILE = 0x2f6df16, /* File table overflow */ + UAEMFILE = 0x2f6df17, /* Too many open files */ + UAENOTTY = 0x2f6df18, /* Not a typewriter */ + UAETXTBSY = 0x2f6df19, /* Text file busy */ + UAEFBIG = 0x2f6df1a, /* File too large */ + UAENOSPC = 0x2f6df1b, /* No space left on device */ + UAESPIPE = 0x2f6df1c, /* Illegal seek */ + UAEROFS = 0x2f6df1d, /* Read-only file system */ + UAEMLINK = 0x2f6df1e, /* Too many links */ + UAEPIPE = 0x2f6df1f, /* Broken pipe */ + UAEDOM = 0x2f6df20, /* Math argument out of domain of func */ + UAERANGE = 0x2f6df21, /* Math result not representable */ + UAEDEADLK = 0x2f6df22, /* Resource deadlock would occur */ + UAENAMETOOLONG = 0x2f6df23, /* File name too long */ + UAENOLCK = 0x2f6df24, /* No record locks available */ + UAENOSYS = 0x2f6df25, /* Function not implemented */ + UAENOTEMPTY = 0x2f6df26, /* Directory not empty */ + UAELOOP = 0x2f6df27, /* Too many symbolic links encountered */ + UAEWOULDBLOCK = 0x2f6df28, /* Operation would block */ + UAENOMSG = 0x2f6df29, /* No message of desired type */ + UAEIDRM = 0x2f6df2a, /* Identifier removed */ + UAECHRNG = 0x2f6df2b, /* Channel number out of range */ + UAEL2NSYNC = 0x2f6df2c, /* Level 2 not synchronized */ + UAEL3HLT = 0x2f6df2d, /* Level 3 halted */ + UAEL3RST = 0x2f6df2e, /* Level 3 reset */ + UAELNRNG = 0x2f6df2f, /* Link number out of range */ + UAEUNATCH = 0x2f6df30, /* Protocol driver not attached */ + UAENOCSI = 0x2f6df31, /* No CSI structure available */ + UAEL2HLT = 0x2f6df32, /* Level 2 halted */ + UAEBADE = 0x2f6df33, /* Invalid exchange */ + UAEBADR = 0x2f6df34, /* Invalid request descriptor */ + UAEXFULL = 0x2f6df35, /* Exchange full */ + UAENOANO = 0x2f6df36, /* No anode */ + UAEBADRQC = 0x2f6df37, /* Invalid request code */ + UAEBADSLT = 0x2f6df38, /* Invalid slot */ + UAEBFONT = 0x2f6df39, /* Bad font file format */ + UAENOSTR = 0x2f6df3a, /* Device not a stream */ + UAENODATA = 0x2f6df3b, /* No data available */ + UAETIME = 0x2f6df3c, /* Timer expired */ + UAENOSR = 0x2f6df3d, /* Out of streams resources */ + UAENONET = 0x2f6df3e, /* Machine is not on the network */ + UAENOPKG = 0x2f6df3f, /* Package not installed */ + UAEREMOTE = 0x2f6df40, /* Object is remote */ + UAENOLINK = 0x2f6df41, /* Link has been severed */ + UAEADV = 0x2f6df42, /* Advertise error */ + UAESRMNT = 0x2f6df43, /* Srmount error */ + UAECOMM = 0x2f6df44, /* Communication error on send */ + UAEPROTO = 0x2f6df45, /* Protocol error */ + UAEMULTIHOP = 0x2f6df46, /* Multihop attempted */ + UAEDOTDOT = 0x2f6df47, /* RFS specific error */ + UAEBADMSG = 0x2f6df48, /* Not a data message */ + UAEOVERFLOW = 0x2f6df49, /* Value too large for defined data type */ + UAENOTUNIQ = 0x2f6df4a, /* Name not unique on network */ + UAEBADFD = 0x2f6df4b, /* File descriptor in bad state */ + UAEREMCHG = 0x2f6df4c, /* Remote address changed */ + UAELIBACC = 0x2f6df4d, /* Can not access a needed shared library */ + UAELIBBAD = 0x2f6df4e, /* Accessing a corrupted shared library */ + UAELIBSCN = 0x2f6df4f, /* .lib section in a.out corrupted */ + UAELIBMAX = 0x2f6df50, /* Attempting to link in too many shared libraries */ + UAELIBEXEC = 0x2f6df51, /* Cannot exec a shared library directly */ + UAEILSEQ = 0x2f6df52, /* Illegal byte sequence */ + UAERESTART = 0x2f6df53, /* Interrupted system call should be restarted */ + UAESTRPIPE = 0x2f6df54, /* Streams pipe error */ + UAEUSERS = 0x2f6df55, /* Too many users */ + UAENOTSOCK = 0x2f6df56, /* Socket operation on non-socket */ + UAEDESTADDRREQ = 0x2f6df57, /* Destination address required */ + UAEMSGSIZE = 0x2f6df58, /* Message too long */ + UAEPROTOTYPE = 0x2f6df59, /* Protocol wrong type for socket */ + UAENOPROTOOPT = 0x2f6df5a, /* Protocol not available */ + UAEPROTONOSUPPORT = 0x2f6df5b, /* Protocol not supported */ + UAESOCKTNOSUPPORT = 0x2f6df5c, /* Socket type not supported */ + UAEOPNOTSUPP = 0x2f6df5d, /* Operation not supported on transport endpoint */ + UAEPFNOSUPPORT = 0x2f6df5e, /* Protocol family not supported */ + UAEAFNOSUPPORT = 0x2f6df5f, /* Address family not supported by protocol */ + UAEADDRINUSE = 0x2f6df60, /* Address already in use */ + UAEADDRNOTAVAIL = 0x2f6df61, /* Cannot assign requested address */ + UAENETDOWN = 0x2f6df62, /* Network is down */ + UAENETUNREACH = 0x2f6df63, /* Network is unreachable */ + UAENETRESET = 0x2f6df64, /* Network dropped connection because of reset */ + UAECONNABORTED = 0x2f6df65, /* Software caused connection abort */ + UAECONNRESET = 0x2f6df66, /* Connection reset by peer */ + UAENOBUFS = 0x2f6df67, /* No buffer space available */ + UAEISCONN = 0x2f6df68, /* Transport endpoint is already connected */ + UAENOTCONN = 0x2f6df69, /* Transport endpoint is not connected */ + UAESHUTDOWN = 0x2f6df6a, /* Cannot send after transport endpoint shutdown */ + UAETOOMANYREFS = 0x2f6df6b, /* Too many references: cannot splice */ + UAETIMEDOUT = 0x2f6df6c, /* Connection timed out */ + UAECONNREFUSED = 0x2f6df6d, /* Connection refused */ + UAEHOSTDOWN = 0x2f6df6e, /* Host is down */ + UAEHOSTUNREACH = 0x2f6df6f, /* No route to host */ + UAEALREADY = 0x2f6df70, /* Operation already in progress */ + UAEINPROGRESS = 0x2f6df71, /* Operation now in progress */ + UAESTALE = 0x2f6df72, /* Stale NFS file handle */ + UAEUCLEAN = 0x2f6df73, /* Structure needs cleaning */ + UAENOTNAM = 0x2f6df74, /* Not a XENIX named type file */ + UAENAVAIL = 0x2f6df75, /* No XENIX semaphores available */ + UAEISNAM = 0x2f6df76, /* Is a named type file */ + UAEREMOTEIO = 0x2f6df77, /* Remote I/O error */ + UAEDQUOT = 0x2f6df78, /* Quota exceeded */ + UAENOMEDIUM = 0x2f6df79, /* No medium found */ + UAEMEDIUMTYPE = 0x2f6df7a, /* Wrong medium type */ +}; diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h index 915b9d10cdf3..32be9c698348 100644 --- a/fs/afs/protocol_yfs.h +++ b/fs/afs/protocol_yfs.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* YFS protocol bits * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #define YFS_FS_SERVICE 2500 diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index c3ae324781f8..172ba569cd60 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Handle fileserver selection and rotation. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/kernel.h> @@ -25,7 +21,7 @@ * them here also using the io_lock. */ bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - struct key *key) + struct key *key, bool intr) { memset(fc, 0, sizeof(*fc)); fc->vnode = vnode; @@ -33,10 +29,15 @@ bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode fc->ac.error = SHRT_MAX; fc->error = -EDESTADDRREQ; - if (mutex_lock_interruptible(&vnode->io_lock) < 0) { - fc->error = -EINTR; - fc->flags |= AFS_FS_CURSOR_STOP; - return false; + if (intr) { + fc->flags |= AFS_FS_CURSOR_INTR; + if (mutex_lock_interruptible(&vnode->io_lock) < 0) { + fc->error = -EINTR; + fc->flags |= AFS_FS_CURSOR_STOP; + return false; + } + } else { + mutex_lock(&vnode->io_lock); } if (vnode->lock_state != AFS_VNODE_LOCK_NONE) @@ -61,7 +62,8 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, fc->untried = (1UL << fc->server_list->nr_servers) - 1; fc->index = READ_ONCE(fc->server_list->preferred); - cbi = vnode->cb_interest; + cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock)); if (cbi) { /* See if the vnode's preferred record is still available */ for (i = 0; i < fc->server_list->nr_servers; i++) { @@ -82,8 +84,8 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, /* Note that the callback promise is effectively broken */ write_seqlock(&vnode->cb_lock); - ASSERTCMP(cbi, ==, vnode->cb_interest); - vnode->cb_interest = NULL; + ASSERTCMP(cbi, ==, rcu_access_pointer(vnode->cb_interest)); + rcu_assign_pointer(vnode->cb_interest, NULL); if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) vnode->cb_break++; write_sequnlock(&vnode->cb_lock); @@ -118,10 +120,14 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code) */ static bool afs_sleep_and_retry(struct afs_fs_cursor *fc) { - msleep_interruptible(1000); - if (signal_pending(current)) { - fc->error = -ERESTARTSYS; - return false; + if (fc->flags & AFS_FS_CURSOR_INTR) { + msleep_interruptible(1000); + if (signal_pending(current)) { + fc->error = -ERESTARTSYS; + return false; + } + } else { + msleep(1000); } return true; @@ -408,7 +414,9 @@ selected_server: if (error < 0) goto failed_set_error; - fc->cbi = afs_get_cb_interest(vnode->cb_interest); + fc->cbi = afs_get_cb_interest( + rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock))); read_lock(&server->fs_lock); alist = rcu_dereference_protected(server->addresses, @@ -459,6 +467,8 @@ no_more_servers: s->probe.abort_code); } + error = e.error; + failed_set_error: fc->error = error; failed: @@ -476,12 +486,15 @@ failed: bool afs_select_current_fileserver(struct afs_fs_cursor *fc) { struct afs_vnode *vnode = fc->vnode; - struct afs_cb_interest *cbi = vnode->cb_interest; + struct afs_cb_interest *cbi; struct afs_addr_list *alist; int error = fc->ac.error; _enter(""); + cbi = rcu_dereference_protected(vnode->cb_interest, + lockdep_is_held(&vnode->io_lock)); + switch (error) { case SHRT_MAX: if (!cbi) { @@ -490,7 +503,7 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) return false; } - fc->cbi = afs_get_cb_interest(vnode->cb_interest); + fc->cbi = afs_get_cb_interest(cbi); read_lock(&cbi->server->fs_lock); alist = rcu_dereference_protected(cbi->server->addresses, diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index a34a89c75c6a..0e5269374ac1 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Maintain an RxRPC server socket to do AFS communications through * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/slab.h> @@ -188,7 +184,7 @@ void afs_put_call(struct afs_call *call) if (call->type->destructor) call->type->destructor(call); - afs_put_server(call->net, call->cm_server); + afs_put_server(call->net, call->server, afs_server_trace_put_call); afs_put_cb_interest(call->net, call->cbi); afs_put_addrlist(call->alist); kfree(call->request); @@ -417,6 +413,7 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) afs_wake_up_async_call : afs_wake_up_call_waiter), call->upgrade, + call->intr, call->debug_id); if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); @@ -426,6 +423,10 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) call->rxcall = rxcall; + if (call->max_lifespan) + rxrpc_kernel_set_max_life(call->net->socket, rxcall, + call->max_lifespan); + /* send the request */ iov[0].iov_base = call->request; iov[0].iov_len = call->request_size; @@ -529,11 +530,11 @@ static void afs_deliver_to_call(struct afs_call *call) return; } - if (call->want_reply_time && + if (!call->have_reply_time && rxrpc_kernel_get_reply_time(call->net->socket, call->rxcall, &call->reply_time)) - call->want_reply_time = false; + call->have_reply_time = true; ret = call->type->deliver(call); state = READ_ONCE(call->state); @@ -648,7 +649,7 @@ long afs_wait_for_call_to_complete(struct afs_call *call, break; } - if (timeout == 0 && + if (call->intr && timeout == 0 && life == last_life && signal_pending(current)) { if (stalled) break; @@ -691,10 +692,9 @@ long afs_wait_for_call_to_complete(struct afs_call *call, ret = ac->error; switch (ret) { case 0: - if (call->ret_reply0) { - ret = (long)call->reply[0]; - call->reply[0] = NULL; - } + ret = call->ret0; + call->ret0 = 0; + /* Fall through */ case -ECONNABORTED: ac->responded = true; diff --git a/fs/afs/security.c b/fs/afs/security.c index 5f58a9a17e69..71e71c07568f 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS security handling * * Copyright (C) 2007, 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/init.h> @@ -87,11 +83,9 @@ void afs_clear_permits(struct afs_vnode *vnode) permits = rcu_dereference_protected(vnode->permit_cache, lockdep_is_held(&vnode->lock)); RCU_INIT_POINTER(vnode->permit_cache, NULL); - vnode->cb_break++; spin_unlock(&vnode->lock); - if (permits) - afs_put_permits(permits); + afs_put_permits(permits); } /* @@ -118,10 +112,10 @@ static void afs_hash_permits(struct afs_permits *permits) * as the ACL *may* have changed. */ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, - unsigned int cb_break) + unsigned int cb_break, struct afs_status_cb *scb) { struct afs_permits *permits, *xpermits, *replacement, *zap, *new = NULL; - afs_access_t caller_access = READ_ONCE(vnode->status.caller_access); + afs_access_t caller_access = scb->status.caller_access; size_t size = 0; bool changed = false; int i, j; @@ -148,7 +142,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, } if (afs_cb_is_broken(cb_break, vnode, - vnode->cb_interest)) { + rcu_dereference(vnode->cb_interest))) { changed = true; break; } @@ -178,7 +172,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, } } - if (afs_cb_is_broken(cb_break, vnode, vnode->cb_interest)) + if (afs_cb_is_broken(cb_break, vnode, rcu_dereference(vnode->cb_interest))) goto someone_else_changed_it; /* We need a ref on any permits list we want to copy as we'll have to @@ -255,14 +249,16 @@ found: kfree(new); + rcu_read_lock(); spin_lock(&vnode->lock); zap = rcu_access_pointer(vnode->permit_cache); - if (!afs_cb_is_broken(cb_break, vnode, vnode->cb_interest) && + if (!afs_cb_is_broken(cb_break, vnode, rcu_dereference(vnode->cb_interest)) && zap == permits) rcu_assign_pointer(vnode->permit_cache, replacement); else zap = replacement; spin_unlock(&vnode->lock); + rcu_read_unlock(); afs_put_permits(zap); out_put: afs_put_permits(permits); @@ -322,13 +318,12 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key, */ _debug("no valid permit"); - ret = afs_fetch_status(vnode, key, false); + ret = afs_fetch_status(vnode, key, false, _access); if (ret < 0) { *_access = 0; _leave(" = %d", ret); return ret; } - *_access = vnode->status.caller_access; } _leave(" = 0 [access %x]", *_access); diff --git a/fs/afs/server.c b/fs/afs/server.c index 65b33b6da48b..64d440aaabc0 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS server record management * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/sched.h> @@ -17,6 +13,7 @@ static unsigned afs_server_gc_delay = 10; /* Server record timeout in seconds */ static unsigned afs_server_update_delay = 30; /* Time till VLDB recheck in secs */ +static atomic_t afs_server_debug_id; static void afs_inc_servers_outstanding(struct afs_net *net) { @@ -51,7 +48,7 @@ struct afs_server *afs_find_server(struct afs_net *net, do { if (server) - afs_put_server(net, server); + afs_put_server(net, server, afs_server_trace_put_find_rsq); server = NULL; read_seqbegin_or_lock(&net->fs_addr_lock, &seq); @@ -116,7 +113,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu * changes. */ if (server) - afs_put_server(net, server); + afs_put_server(net, server, afs_server_trace_put_uuid_rsq); server = NULL; read_seqbegin_or_lock(&net->fs_lock, &seq); @@ -131,7 +128,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu } else if (diff > 0) { p = p->rb_right; } else { - afs_get_server(server); + afs_get_server(server, afs_server_trace_get_by_uuid); break; } @@ -202,7 +199,7 @@ static struct afs_server *afs_install_server(struct afs_net *net, ret = 0; exists: - afs_get_server(server); + afs_get_server(server, afs_server_trace_get_install); write_sequnlock(&net->fs_lock); return server; } @@ -223,6 +220,7 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, goto enomem; atomic_set(&server->usage, 1); + server->debug_id = atomic_inc_return(&afs_server_debug_id); RCU_INIT_POINTER(server->addresses, alist); server->addr_version = alist->version; server->uuid = *uuid; @@ -234,6 +232,7 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, spin_lock_init(&server->probe_lock); afs_inc_servers_outstanding(net); + trace_afs_server(server, 1, afs_server_trace_alloc); _leave(" = %p", server); return server; @@ -329,9 +328,22 @@ void afs_servers_timer(struct timer_list *timer) } /* + * Get a reference on a server object. + */ +struct afs_server *afs_get_server(struct afs_server *server, + enum afs_server_trace reason) +{ + unsigned int u = atomic_inc_return(&server->usage); + + trace_afs_server(server, u, reason); + return server; +} + +/* * Release a reference on a server record. */ -void afs_put_server(struct afs_net *net, struct afs_server *server) +void afs_put_server(struct afs_net *net, struct afs_server *server, + enum afs_server_trace reason) { unsigned int usage; @@ -342,7 +354,7 @@ void afs_put_server(struct afs_net *net, struct afs_server *server) usage = atomic_dec_return(&server->usage); - _enter("{%u}", usage); + trace_afs_server(server, usage, reason); if (likely(usage > 0)) return; @@ -354,6 +366,8 @@ static void afs_server_rcu(struct rcu_head *rcu) { struct afs_server *server = container_of(rcu, struct afs_server, rcu); + trace_afs_server(server, atomic_read(&server->usage), + afs_server_trace_free); afs_put_addrlist(rcu_access_pointer(server->addresses)); kfree(server); } @@ -369,7 +383,9 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) .index = alist->preferred, .error = 0, }; - _enter("%p", server); + + trace_afs_server(server, atomic_read(&server->usage), + afs_server_trace_give_up_cb); if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags)) afs_fs_give_up_all_callbacks(net, server, &ac, NULL); @@ -377,6 +393,8 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) wait_var_event(&server->probe_outstanding, atomic_read(&server->probe_outstanding) == 0); + trace_afs_server(server, atomic_read(&server->usage), + afs_server_trace_destroy); call_rcu(&server->rcu, afs_server_rcu); afs_dec_servers_outstanding(net); } @@ -396,6 +414,7 @@ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list) write_seqlock(&net->fs_lock); usage = 1; deleted = atomic_try_cmpxchg(&server->usage, &usage, 0); + trace_afs_server(server, usage, afs_server_trace_gc); if (deleted) { rb_erase(&server->uuid_rb, &net->fs_servers); hlist_del_rcu(&server->proc_link); @@ -518,11 +537,20 @@ static noinline bool afs_update_server_record(struct afs_fs_cursor *fc, struct a _enter(""); + trace_afs_server(server, atomic_read(&server->usage), afs_server_trace_update); + alist = afs_vl_lookup_addrs(fc->vnode->volume->cell, fc->key, &server->uuid); if (IS_ERR(alist)) { - fc->ac.error = PTR_ERR(alist); - _leave(" = f [%d]", fc->ac.error); + if ((PTR_ERR(alist) == -ERESTARTSYS || + PTR_ERR(alist) == -EINTR) && + !(fc->flags & AFS_FS_CURSOR_INTR) && + server->addresses) { + _leave(" = t [intr]"); + return true; + } + fc->error = PTR_ERR(alist); + _leave(" = f [%d]", fc->error); return false; } @@ -574,7 +602,11 @@ retry: ret = wait_on_bit(&server->flags, AFS_SERVER_FL_UPDATING, TASK_INTERRUPTIBLE); if (ret == -ERESTARTSYS) { - fc->ac.error = ret; + if (!(fc->flags & AFS_FS_CURSOR_INTR) && server->addresses) { + _leave(" = t [intr]"); + return true; + } + fc->error = ret; _leave(" = f [intr]"); return false; } diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 155dc14caef9..888d91d195d9 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS fileserver list management. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> @@ -20,7 +16,8 @@ void afs_put_serverlist(struct afs_net *net, struct afs_server_list *slist) if (slist && refcount_dec_and_test(&slist->usage)) { for (i = 0; i < slist->nr_servers; i++) { afs_put_cb_interest(net, slist->servers[i].cb_interest); - afs_put_server(net, slist->servers[i].server); + afs_put_server(net, slist->servers[i].server, + afs_server_trace_put_slist); } kfree(slist); } @@ -71,7 +68,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, break; if (j < slist->nr_servers) { if (slist->servers[j].server == server) { - afs_put_server(cell->net, server); + afs_put_server(cell->net, server, + afs_server_trace_put_slist_isort); continue; } diff --git a/fs/afs/super.c b/fs/afs/super.c index 783c68cd1a35..f18911e8d770 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -426,7 +426,7 @@ static int afs_set_super(struct super_block *sb, struct fs_context *fc) static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) { struct afs_super_info *as = AFS_FS_S(sb); - struct afs_fid fid; + struct afs_iget_data iget_data; struct inode *inode = NULL; int ret; @@ -451,11 +451,13 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx) } else { sprintf(sb->s_id, "%llu", as->volume->vid); afs_activate_volume(as->volume); - fid.vid = as->volume->vid; - fid.vnode = 1; - fid.vnode_hi = 0; - fid.unique = 1; - inode = afs_iget(sb, ctx->key, &fid, NULL, NULL, NULL, NULL); + iget_data.fid.vid = as->volume->vid; + iget_data.fid.vnode = 1; + iget_data.fid.vnode_hi = 0; + iget_data.fid.unique = 1; + iget_data.cb_v_break = as->volume->cb_v_break; + iget_data.cb_s_break = 0; + inode = afs_iget(sb, ctx->key, &iget_data, NULL, NULL, NULL); } if (IS_ERR(inode)) @@ -677,13 +679,12 @@ static struct inode *afs_alloc_inode(struct super_block *sb) vnode->volume = NULL; vnode->lock_key = NULL; vnode->permit_cache = NULL; - vnode->cb_interest = NULL; + RCU_INIT_POINTER(vnode->cb_interest, NULL); #ifdef CONFIG_AFS_FSCACHE vnode->cache = NULL; #endif vnode->flags = 1 << AFS_VNODE_UNSET; - vnode->cb_type = 0; vnode->lock_state = AFS_VNODE_LOCK_NONE; init_rwsem(&vnode->rmdir_lock); @@ -708,7 +709,7 @@ static void afs_destroy_inode(struct inode *inode) _debug("DESTROY INODE %p", inode); - ASSERTCMP(vnode->cb_interest, ==, NULL); + ASSERTCMP(rcu_access_pointer(vnode->cb_interest), ==, NULL); atomic_dec(&afs_count_active_inodes); } @@ -741,7 +742,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) return PTR_ERR(key); ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { fc.flags |= AFS_FS_CURSOR_NO_VSLEEP; while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); @@ -749,7 +750,6 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) } afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); ret = afs_end_vnode_operation(&fc); } diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c index b4f1a84519b9..21eb0c0be912 100644 --- a/fs/afs/vl_list.c +++ b/fs/afs/vl_list.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS vlserver list management. * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> @@ -232,18 +228,16 @@ struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell, if (bs.status > NR__dns_lookup_status) bs.status = NR__dns_lookup_status; + /* See if we can update an old server record */ server = NULL; - if (previous) { - /* See if we can update an old server record */ - for (i = 0; i < previous->nr_servers; i++) { - struct afs_vlserver *p = previous->servers[i].server; - - if (p->name_len == bs.name_len && - p->port == bs.port && - strncasecmp(b, p->name, bs.name_len) == 0) { - server = afs_get_vlserver(p); - break; - } + for (i = 0; i < previous->nr_servers; i++) { + struct afs_vlserver *p = previous->servers[i].server; + + if (p->name_len == bs.name_len && + p->port == bs.port && + strncasecmp(b, p->name, bs.name_len) == 0) { + server = afs_get_vlserver(p); + break; } } diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index b05e0de04f42..858498cc1b05 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS vlserver probing * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/sched.h> @@ -33,8 +29,8 @@ static bool afs_vl_probe_done(struct afs_vlserver *server) void afs_vlserver_probe_result(struct afs_call *call) { struct afs_addr_list *alist = call->alist; - struct afs_vlserver *server = call->reply[0]; - unsigned int server_index = (long)call->reply[1]; + struct afs_vlserver *server = call->vlserver; + unsigned int server_index = call->server_index; unsigned int index = call->addr_ix; unsigned int rtt = UINT_MAX; bool have_result = false; diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index 7adde83a0648..9a5ce9687779 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Handle vlserver selection and rotation. * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/kernel.h> @@ -43,11 +39,29 @@ bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cel static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) { struct afs_cell *cell = vc->cell; + unsigned int dns_lookup_count; + + if (cell->dns_source == DNS_RECORD_UNAVAILABLE || + cell->dns_expiry <= ktime_get_real_seconds()) { + dns_lookup_count = smp_load_acquire(&cell->dns_lookup_count); + set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags); + queue_work(afs_wq, &cell->manager); + + if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { + if (wait_var_event_interruptible( + &cell->dns_lookup_count, + smp_load_acquire(&cell->dns_lookup_count) + != dns_lookup_count) < 0) { + vc->error = -ERESTARTSYS; + return false; + } + } - if (wait_on_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET, - TASK_INTERRUPTIBLE)) { - vc->error = -ERESTARTSYS; - return false; + /* Status load is ordered after lookup counter load */ + if (cell->dns_source == DNS_RECORD_UNAVAILABLE) { + vc->error = -EDESTADDRREQ; + return false; + } } read_lock(&cell->vl_servers_lock); @@ -55,7 +69,7 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) rcu_dereference_protected(cell->vl_servers, lockdep_is_held(&cell->vl_servers_lock))); read_unlock(&cell->vl_servers_lock); - if (!vc->server_list || !vc->server_list->nr_servers) + if (!vc->server_list->nr_servers) return false; vc->untried = (1UL << vc->server_list->nr_servers) - 1; diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index dd9ba4e96fb3..d7e0fd3c00df 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS Volume Location Service client * * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/gfp.h> @@ -34,7 +30,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) /* unmarshall the reply once we've received all of it */ uvldb = call->buffer; - entry = call->reply[0]; + entry = call->ret_vldb; nr_servers = ntohl(uvldb->nServers); if (nr_servers > AFS_NMAXNSERVERS) @@ -110,7 +106,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call) static void afs_destroy_vl_get_entry_by_name_u(struct afs_call *call) { - kfree(call->reply[0]); + kfree(call->ret_vldb); afs_flat_call_destructor(call); } @@ -155,8 +151,8 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc, } call->key = vc->key; - call->reply[0] = entry; - call->ret_reply0 = true; + call->ret_vldb = entry; + call->max_lifespan = AFS_VL_MAX_LIFESPAN; /* Marshall the parameters */ bp = call->request; @@ -214,7 +210,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) if (!alist) return -ENOMEM; alist->version = uniquifier; - call->reply[0] = alist; + call->ret_alist = alist; call->count = count; call->count2 = nentries; call->unmarshall++; @@ -229,7 +225,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) if (ret < 0) return ret; - alist = call->reply[0]; + alist = call->ret_alist; bp = call->buffer; count = min(call->count, 4U); for (i = 0; i < count; i++) @@ -249,8 +245,7 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) static void afs_vl_get_addrs_u_destructor(struct afs_call *call) { - afs_put_server(call->net, (struct afs_server *)call->reply[0]); - kfree(call->reply[1]); + afs_put_addrlist(call->ret_alist); return afs_flat_call_destructor(call); } @@ -287,8 +282,8 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc, return ERR_PTR(-ENOMEM); call->key = vc->key; - call->reply[0] = NULL; - call->ret_reply0 = true; + call->ret_alist = NULL; + call->max_lifespan = AFS_VL_MAX_LIFESPAN; /* Marshall the parameters */ bp = call->request; @@ -358,9 +353,7 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call) static void afs_destroy_vl_get_capabilities(struct afs_call *call) { - struct afs_vlserver *server = call->reply[0]; - - afs_put_vlserver(call->net, server); + afs_put_vlserver(call->net, call->vlserver); afs_flat_call_destructor(call); } @@ -398,11 +391,11 @@ struct afs_call *afs_vl_get_capabilities(struct afs_net *net, return ERR_PTR(-ENOMEM); call->key = key; - call->reply[0] = afs_get_vlserver(server); - call->reply[1] = (void *)(long)server_index; + call->vlserver = afs_get_vlserver(server); + call->server_index = server_index; call->upgrade = true; - call->want_reply_time = true; call->async = true; + call->max_lifespan = AFS_PROBE_MAX_LIFESPAN; /* marshall the parameters */ bp = call->request; @@ -460,7 +453,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) if (!alist) return -ENOMEM; alist->version = uniquifier; - call->reply[0] = alist; + call->ret_alist = alist; if (call->count == 0) goto extract_volendpoints; @@ -488,7 +481,7 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) if (ret < 0) return ret; - alist = call->reply[0]; + alist = call->ret_alist; bp = call->buffer; switch (call->count2) { case YFS_ENDPOINT_IPV4: @@ -609,7 +602,6 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) break; } - alist = call->reply[0]; _leave(" = 0 [done]"); return 0; } @@ -644,8 +636,8 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc, return ERR_PTR(-ENOMEM); call->key = vc->key; - call->reply[0] = NULL; - call->ret_reply0 = true; + call->ret_alist = NULL; + call->max_lifespan = AFS_VL_MAX_LIFESPAN; /* Marshall the parameters */ bp = call->request; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index f6eba2def0a1..1a414300b654 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* AFS volume management * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> @@ -47,6 +43,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, atomic_set(&volume->usage, 1); INIT_LIST_HEAD(&volume->proc_link); rwlock_init(&volume->servers_lock); + rwlock_init(&volume->cb_v_break_lock); memcpy(volume->name, vldb->name, vldb->name_len + 1); slist = afs_alloc_server_list(params->cell, params->key, vldb, type_mask); diff --git a/fs/afs/write.c b/fs/afs/write.c index 0122d7445fba..cb76566763db 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* handling of writes to regular files and writing back to the server * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/backing-dev.h> @@ -48,8 +44,7 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key, return 0; } - req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), - GFP_KERNEL); + req = kzalloc(struct_size(req, array, 1), GFP_KERNEL); if (!req) return -ENOMEM; @@ -314,6 +309,46 @@ static void afs_redirty_pages(struct writeback_control *wbc, } /* + * completion of write to server + */ +static void afs_pages_written_back(struct afs_vnode *vnode, + pgoff_t first, pgoff_t last) +{ + struct pagevec pv; + unsigned long priv; + unsigned count, loop; + + _enter("{%llx:%llu},{%lx-%lx}", + vnode->fid.vid, vnode->fid.vnode, first, last); + + pagevec_init(&pv); + + do { + _debug("done %lx-%lx", first, last); + + count = last - first + 1; + if (count > PAGEVEC_SIZE) + count = PAGEVEC_SIZE; + pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping, + first, count, pv.pages); + ASSERTCMP(pv.nr, ==, count); + + for (loop = 0; loop < count; loop++) { + priv = page_private(pv.pages[loop]); + trace_afs_page_dirty(vnode, tracepoint_string("clear"), + pv.pages[loop]->index, priv); + set_page_private(pv.pages[loop], 0); + end_page_writeback(pv.pages[loop]); + } + first += count; + __pagevec_release(&pv); + } while (first <= last); + + afs_prune_wb_keys(vnode); + _leave(""); +} + +/* * write to a file */ static int afs_store_data(struct address_space *mapping, @@ -322,6 +357,7 @@ static int afs_store_data(struct address_space *mapping, { struct afs_vnode *vnode = AFS_FS_I(mapping->host); struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_wb_key *wbk = NULL; struct list_head *p; int ret = -ENOKEY, ret2; @@ -333,6 +369,10 @@ static int afs_store_data(struct address_space *mapping, vnode->fid.unique, first, last, offset, to); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + return -ENOMEM; + spin_lock(&vnode->wb_lock); p = vnode->wb_keys.next; @@ -351,6 +391,7 @@ try_next_key: spin_unlock(&vnode->wb_lock); afs_put_wb_key(wbk); + kfree(scb); _leave(" = %d [no keys]", ret); return ret; @@ -361,14 +402,19 @@ found_key: _debug("USE WB KEY %u", key_serial(wbk->key)); ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) { + if (afs_begin_vnode_operation(&fc, vnode, wbk->key, false)) { + afs_dataversion_t data_version = vnode->status.data_version + 1; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_store_data(&fc, mapping, first, last, offset, to); + afs_fs_store_data(&fc, mapping, first, last, offset, to, scb); } - afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_check_for_remote_deletion(&fc, vnode); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); + if (fc.ac.error == 0) + afs_pages_written_back(vnode, first, last); ret = afs_end_vnode_operation(&fc); } @@ -393,6 +439,7 @@ found_key: } afs_put_wb_key(wbk); + kfree(scb); _leave(" = %d", ret); return ret; } @@ -679,46 +726,6 @@ int afs_writepages(struct address_space *mapping, } /* - * completion of write to server - */ -void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call) -{ - struct pagevec pv; - unsigned long priv; - unsigned count, loop; - pgoff_t first = call->first, last = call->last; - - _enter("{%llx:%llu},{%lx-%lx}", - vnode->fid.vid, vnode->fid.vnode, first, last); - - pagevec_init(&pv); - - do { - _debug("done %lx-%lx", first, last); - - count = last - first + 1; - if (count > PAGEVEC_SIZE) - count = PAGEVEC_SIZE; - pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping, - first, count, pv.pages); - ASSERTCMP(pv.nr, ==, count); - - for (loop = 0; loop < count; loop++) { - priv = page_private(pv.pages[loop]); - trace_afs_page_dirty(vnode, tracepoint_string("clear"), - pv.pages[loop]->index, priv); - set_page_private(pv.pages[loop], 0); - end_page_writeback(pv.pages[loop]); - } - first += count; - __pagevec_release(&pv); - } while (first <= last); - - afs_prune_wb_keys(vnode); - _leave(""); -} - -/* * write to an AFS file */ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index c81f85003fc7..5552d034090a 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Extended attribute handling for AFS. We use xattrs to get and set metadata * instead of providing pioctl(). * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/slab.h> @@ -47,40 +43,52 @@ static int afs_xattr_get_acl(const struct xattr_handler *handler, void *buffer, size_t size) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_acl *acl = NULL; struct key *key; - int ret; + int ret = -ENOMEM; + + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error; key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) - return PTR_ERR(key); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_scb; + } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - acl = afs_fs_fetch_acl(&fc); + acl = afs_fs_fetch_acl(&fc, scb); } afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } if (ret == 0) { ret = acl->size; if (size > 0) { - ret = -ERANGE; - if (acl->size > size) - return -ERANGE; - memcpy(buffer, acl->data, acl->size); - ret = acl->size; + if (acl->size <= size) + memcpy(buffer, acl->data, acl->size); + else + ret = -ERANGE; } kfree(acl); } key_put(key); +error_scb: + kfree(scb); +error: return ret; } @@ -93,41 +101,53 @@ static int afs_xattr_set_acl(const struct xattr_handler *handler, const void *buffer, size_t size, int flags) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_acl *acl = NULL; struct key *key; - int ret; + int ret = -ENOMEM; if (flags == XATTR_CREATE) return -EINVAL; - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) - return PTR_ERR(key); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error; acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL); - if (!acl) { - key_put(key); - return -ENOMEM; + if (!acl) + goto error_scb; + + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_acl; } acl->size = size; memcpy(acl->data, buffer, size); ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - afs_fs_store_acl(&fc, acl); + afs_fs_store_acl(&fc, acl, scb); } afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } - kfree(acl); key_put(key); +error_acl: + kfree(acl); +error_scb: + kfree(scb); +error: return ret; } @@ -146,12 +166,12 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler, void *buffer, size_t size) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *vnode = AFS_FS_I(inode); struct yfs_acl *yacl = NULL; struct key *key; - unsigned int flags = 0; char buf[16], *data; - int which = 0, dsize, ret; + int which = 0, dsize, ret = -ENOMEM; if (strcmp(name, "acl") == 0) which = 0; @@ -164,65 +184,81 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler, else return -EOPNOTSUPP; + yacl = kzalloc(sizeof(struct yfs_acl), GFP_KERNEL); + if (!yacl) + goto error; + if (which == 0) - flags |= YFS_ACL_WANT_ACL; + yacl->flags |= YFS_ACL_WANT_ACL; else if (which == 3) - flags |= YFS_ACL_WANT_VOL_ACL; + yacl->flags |= YFS_ACL_WANT_VOL_ACL; + + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error_yacl; key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) - return PTR_ERR(key); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_scb; + } ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - yacl = yfs_fs_fetch_opaque_acl(&fc, flags); + yfs_fs_fetch_opaque_acl(&fc, yacl, scb); } afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } - if (ret == 0) { - switch (which) { - case 0: - data = yacl->acl->data; - dsize = yacl->acl->size; - break; - case 1: - data = buf; - dsize = snprintf(buf, sizeof(buf), "%u", - yacl->inherit_flag); - break; - case 2: - data = buf; - dsize = snprintf(buf, sizeof(buf), "%u", - yacl->num_cleaned); - break; - case 3: - data = yacl->vol_acl->data; - dsize = yacl->vol_acl->size; - break; - default: - ret = -EOPNOTSUPP; - goto out; - } + if (ret < 0) + goto error_key; + + switch (which) { + case 0: + data = yacl->acl->data; + dsize = yacl->acl->size; + break; + case 1: + data = buf; + dsize = snprintf(buf, sizeof(buf), "%u", yacl->inherit_flag); + break; + case 2: + data = buf; + dsize = snprintf(buf, sizeof(buf), "%u", yacl->num_cleaned); + break; + case 3: + data = yacl->vol_acl->data; + dsize = yacl->vol_acl->size; + break; + default: + ret = -EOPNOTSUPP; + goto error_key; + } - ret = dsize; - if (size > 0) { - if (dsize > size) { - ret = -ERANGE; - goto out; - } - memcpy(buffer, data, dsize); + ret = dsize; + if (size > 0) { + if (dsize > size) { + ret = -ERANGE; + goto error_key; } + memcpy(buffer, data, dsize); } -out: - yfs_free_opaque_acl(yacl); +error_key: key_put(key); +error_scb: + kfree(scb); +error_yacl: + yfs_free_opaque_acl(yacl); +error: return ret; } @@ -235,42 +271,54 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler, const void *buffer, size_t size, int flags) { struct afs_fs_cursor fc; + struct afs_status_cb *scb; struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_acl *acl = NULL; struct key *key; - int ret; + int ret = -ENOMEM; if (flags == XATTR_CREATE || strcmp(name, "acl") != 0) return -EINVAL; - key = afs_request_key(vnode->volume->cell); - if (IS_ERR(key)) - return PTR_ERR(key); + scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS); + if (!scb) + goto error; acl = kmalloc(sizeof(*acl) + size, GFP_KERNEL); - if (!acl) { - key_put(key); - return -ENOMEM; - } + if (!acl) + goto error_scb; acl->size = size; memcpy(acl->data, buffer, size); + key = afs_request_key(vnode->volume->cell); + if (IS_ERR(key)) { + ret = PTR_ERR(key); + goto error_acl; + } + ret = -ERESTARTSYS; - if (afs_begin_vnode_operation(&fc, vnode, key)) { + if (afs_begin_vnode_operation(&fc, vnode, key, true)) { + afs_dataversion_t data_version = vnode->status.data_version; + while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(vnode); - yfs_fs_store_opaque_acl2(&fc, acl); + yfs_fs_store_opaque_acl2(&fc, acl, scb); } afs_check_for_remote_deletion(&fc, fc.vnode); - afs_vnode_commit_status(&fc, vnode, fc.cb_break); + afs_vnode_commit_status(&fc, vnode, fc.cb_break, + &data_version, scb); ret = afs_end_vnode_operation(&fc); } +error_acl: kfree(acl); key_put(key); +error_scb: + kfree(scb); +error: return ret; } diff --git a/fs/afs/xdr_fs.h b/fs/afs/xdr_fs.h index aa21f3068d52..94f1f398eefa 100644 --- a/fs/afs/xdr_fs.h +++ b/fs/afs/xdr_fs.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* AFS fileserver XDR types * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #ifndef XDR_FS_H diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 6cf7d161baa1..18722aaeda33 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* YFS File Server client stubs * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/init.h> @@ -183,24 +179,19 @@ static void xdr_dump_bad(const __be32 *bp) /* * Decode a YFSFetchStatus block */ -static int xdr_decode_YFSFetchStatus(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) +static int xdr_decode_YFSFetchStatus(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { const struct yfs_xdr_YFSFetchStatus *xdr = (const void *)*_bp; + struct afs_file_status *status = &scb->status; u32 type; - u8 flags = 0; status->abort_code = ntohl(xdr->abort_code); if (status->abort_code != 0) { - if (vnode && status->abort_code == VNOVNODE) { - set_bit(AFS_VNODE_DELETED, &vnode->flags); + if (status->abort_code == VNOVNODE) status->nlink = 0; - __afs_break_callback(vnode); - } + scb->have_error = true; return 0; } @@ -209,77 +200,28 @@ static int xdr_decode_YFSFetchStatus(struct afs_call *call, case AFS_FTYPE_FILE: case AFS_FTYPE_DIR: case AFS_FTYPE_SYMLINK: - if (type != status->type && - vnode && - !test_bit(AFS_VNODE_UNSET, &vnode->flags)) { - pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", - vnode->fid.vid, - vnode->fid.vnode, - vnode->fid.unique, - status->type, type); - goto bad; - } status->type = type; break; default: goto bad; } -#define EXTRACT_M4(FIELD) \ - do { \ - u32 x = ntohl(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_META_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - -#define EXTRACT_M8(FIELD) \ - do { \ - u64 x = xdr_to_u64(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_META_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - -#define EXTRACT_D8(FIELD) \ - do { \ - u64 x = xdr_to_u64(xdr->FIELD); \ - if (status->FIELD != x) { \ - flags |= AFS_VNODE_DATA_CHANGED; \ - status->FIELD = x; \ - } \ - } while (0) - - EXTRACT_M4(nlink); - EXTRACT_D8(size); - EXTRACT_D8(data_version); - EXTRACT_M8(author); - EXTRACT_M8(owner); - EXTRACT_M8(group); - EXTRACT_M4(mode); - EXTRACT_M4(caller_access); /* call ticket dependent */ - EXTRACT_M4(anon_access); - - status->mtime_client = xdr_to_time(xdr->mtime_client); - status->mtime_server = xdr_to_time(xdr->mtime_server); - status->lock_count = ntohl(xdr->lock_count); - - if (read_req) { - read_req->data_version = status->data_version; - read_req->file_size = status->size; - } + status->nlink = ntohl(xdr->nlink); + status->author = xdr_to_u64(xdr->author); + status->owner = xdr_to_u64(xdr->owner); + status->caller_access = ntohl(xdr->caller_access); /* Ticket dependent */ + status->anon_access = ntohl(xdr->anon_access); + status->mode = ntohl(xdr->mode) & S_IALLUGO; + status->group = xdr_to_u64(xdr->group); + status->lock_count = ntohl(xdr->lock_count); + + status->mtime_client = xdr_to_time(xdr->mtime_client); + status->mtime_server = xdr_to_time(xdr->mtime_server); + status->size = xdr_to_u64(xdr->size); + status->data_version = xdr_to_u64(xdr->data_version); + scb->have_status = true; *_bp += xdr_size(xdr); - - if (vnode) { - if (test_bit(AFS_VNODE_UNSET, &vnode->flags)) - flags |= AFS_VNODE_NOT_YET_SET; - afs_update_inode_from_status(vnode, status, expected_version, - flags); - } - return 0; bad: @@ -288,73 +230,20 @@ bad: } /* - * Decode the file status. We need to lock the target vnode if we're going to - * update its status so that stat() sees the attributes update atomically. - */ -static int yfs_decode_status(struct afs_call *call, - const __be32 **_bp, - struct afs_file_status *status, - struct afs_vnode *vnode, - const afs_dataversion_t *expected_version, - struct afs_read *read_req) -{ - int ret; - - if (!vnode) - return xdr_decode_YFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - - write_seqlock(&vnode->cb_lock); - ret = xdr_decode_YFSFetchStatus(call, _bp, status, vnode, - expected_version, read_req); - write_sequnlock(&vnode->cb_lock); - return ret; -} - -/* * Decode a YFSCallBack block */ -static void xdr_decode_YFSCallBack(struct afs_call *call, - struct afs_vnode *vnode, - const __be32 **_bp) -{ - struct yfs_xdr_YFSCallBack *xdr = (void *)*_bp; - struct afs_cb_interest *old, *cbi = call->cbi; - u64 cb_expiry; - - write_seqlock(&vnode->cb_lock); - - if (!afs_cb_is_broken(call->cb_break, vnode, cbi)) { - cb_expiry = xdr_to_u64(xdr->expiration_time); - do_div(cb_expiry, 10 * 1000 * 1000); - vnode->cb_version = ntohl(xdr->version); - vnode->cb_type = ntohl(xdr->type); - vnode->cb_expires_at = cb_expiry + ktime_get_real_seconds(); - old = vnode->cb_interest; - if (old != call->cbi) { - vnode->cb_interest = cbi; - cbi = old; - } - set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); - } - - write_sequnlock(&vnode->cb_lock); - call->cbi = cbi; - *_bp += xdr_size(xdr); -} - -static void xdr_decode_YFSCallBack_raw(const __be32 **_bp, - struct afs_callback *cb) +static void xdr_decode_YFSCallBack(const __be32 **_bp, + struct afs_call *call, + struct afs_status_cb *scb) { struct yfs_xdr_YFSCallBack *x = (void *)*_bp; - u64 cb_expiry; - - cb_expiry = xdr_to_u64(x->expiration_time); - do_div(cb_expiry, 10 * 1000 * 1000); - cb->version = ntohl(x->version); - cb->type = ntohl(x->type); - cb->expires_at = cb_expiry + ktime_get_real_seconds(); + struct afs_callback *cb = &scb->callback; + ktime_t cb_expiry; + cb_expiry = call->reply_time; + cb_expiry = ktime_add(cb_expiry, xdr_to_u64(x->expiration_time) * 100); + cb->expires_at = ktime_divns(cb_expiry, NSEC_PER_SEC); + scb->have_cb = true; *_bp += xdr_size(x); } @@ -442,11 +331,10 @@ static void xdr_decode_YFSFetchVolumeStatus(const __be32 **_bp, } /* - * deliver reply data to an FS.FetchStatus + * Deliver a reply that's a status, callback and volsync. */ -static int yfs_deliver_fs_fetch_status_vnode(struct afs_call *call) +static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -454,16 +342,36 @@ static int yfs_deliver_fs_fetch_status_vnode(struct afs_call *call) if (ret < 0) return ret; - _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_YFSCallBack(call, vnode, &bp); - xdr_decode_YFSVolSync(&bp, call->reply[1]); + xdr_decode_YFSCallBack(&bp, call, call->out_scb); + xdr_decode_YFSVolSync(&bp, call->out_volsync); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * Deliver reply data to operations that just return a file status and a volume + * sync record. + */ +static int yfs_deliver_status_and_volsync(struct afs_call *call) +{ + const __be32 *bp; + int ret; + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + bp = call->buffer; + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); + if (ret < 0) + return ret; + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -475,15 +383,15 @@ static int yfs_deliver_fs_fetch_status_vnode(struct afs_call *call) static const struct afs_call_type yfs_RXYFSFetchStatus_vnode = { .name = "YFS.FetchStatus(vnode)", .op = yfs_FS_FetchStatus, - .deliver = yfs_deliver_fs_fetch_status_vnode, + .deliver = yfs_deliver_fs_status_cb_and_volsync, .destructor = afs_flat_call_destructor, }; /* * Fetch the status information for a file. */ -int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsync, - bool new_inode) +int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_status_cb *scb, + struct afs_volsync *volsync) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -505,9 +413,8 @@ int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy } call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = volsync; - call->expected_version = new_inode ? 1 : vnode->status.data_version; + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -516,9 +423,9 @@ int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy bp = xdr_encode_YFSFid(bp, &vnode->fid); yfs_check_req(call, bp); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -528,8 +435,7 @@ int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy */ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; - struct afs_read *req = call->reply[2]; + struct afs_read *req = call->read_request; const __be32 *bp; unsigned int size; int ret; @@ -586,7 +492,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) if (req->offset == PAGE_SIZE) { req->offset = 0; if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->index++; if (req->remain > 0) goto begin_page; @@ -623,12 +529,14 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) return ret; bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &vnode->status.data_version, req); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_YFSCallBack(call, vnode, &bp); - xdr_decode_YFSVolSync(&bp, call->reply[1]); + xdr_decode_YFSCallBack(&bp, call, call->out_scb); + xdr_decode_YFSVolSync(&bp, call->out_volsync); + + req->data_version = call->out_scb->status.data_version; + req->file_size = call->out_scb->status.size; call->unmarshall++; @@ -642,7 +550,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) zero_user_segment(req->pages[req->index], req->offset, PAGE_SIZE); if (req->page_done) - req->page_done(call, req); + req->page_done(req); req->offset = 0; } @@ -652,9 +560,7 @@ static int yfs_deliver_fs_fetch_data64(struct afs_call *call) static void yfs_fetch_data_destructor(struct afs_call *call) { - struct afs_read *req = call->reply[2]; - - afs_put_read(req); + afs_put_read(call->read_request); afs_flat_call_destructor(call); } @@ -671,7 +577,8 @@ static const struct afs_call_type yfs_RXYFSFetchData64 = { /* * Fetch data from a file. */ -int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) +int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_status_cb *scb, + struct afs_read *req) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -693,11 +600,9 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = NULL; /* volsync */ - call->reply[2] = req; - call->expected_version = vnode->status.data_version; - call->want_reply_time = true; + call->out_scb = scb; + call->out_volsync = NULL; + call->read_request = req; /* marshall the parameters */ bp = call->request; @@ -709,9 +614,9 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) yfs_check_req(call, bp); refcount_inc(&req->usage); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -721,7 +626,6 @@ int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) */ static int yfs_deliver_fs_create_vnode(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -733,16 +637,15 @@ static int yfs_deliver_fs_create_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_YFSFid(&bp, call->reply[1]); - ret = yfs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_YFSFid(&bp, call->out_fid); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSCallBack_raw(&bp, call->reply[3]); - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSCallBack(&bp, call, call->out_scb); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -764,14 +667,13 @@ static const struct afs_call_type afs_RXFSCreateFile = { int yfs_fs_create_file(struct afs_fs_cursor *fc, const char *name, umode_t mode, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, rplsz; __be32 *bp; @@ -795,24 +697,23 @@ int yfs_fs_create_file(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->reply[3] = newcb; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSCREATEFILE); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &dvnode->fid); bp = xdr_encode_string(bp, name, namesz); bp = xdr_encode_YFSStoreStatus_mode(bp, mode); bp = xdr_encode_u32(bp, yfs_LockNone); /* ViceLockType */ yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &vnode->fid, name); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -830,14 +731,13 @@ static const struct afs_call_type yfs_RXFSMakeDir = { int yfs_fs_make_dir(struct afs_fs_cursor *fc, const char *name, umode_t mode, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus, - struct afs_callback *newcb) + struct afs_status_cb *new_scb) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, rplsz; __be32 *bp; @@ -860,23 +760,22 @@ int yfs_fs_make_dir(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->reply[3] = newcb; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = new_scb; /* marshall the parameters */ bp = call->request; bp = xdr_encode_u32(bp, YFSMAKEDIR); bp = xdr_encode_u32(bp, 0); /* RPC flags */ - bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSFid(bp, &dvnode->fid); bp = xdr_encode_string(bp, name, namesz); bp = xdr_encode_YFSStoreStatus_mode(bp, mode); yfs_check_req(call, bp); afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call1(call, &vnode->fid, name); + trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -886,8 +785,6 @@ int yfs_fs_make_dir(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_remove_file2(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0]; - struct afs_vnode *vnode = call->reply[1]; struct afs_fid fid; const __be32 *bp; int ret; @@ -898,20 +795,18 @@ static int yfs_deliver_fs_remove_file2(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; xdr_decode_YFSFid(&bp, &fid); - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; /* Was deleted if vnode->status.abort_code == VNOVNODE. */ - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); return 0; } @@ -929,7 +824,8 @@ static const struct afs_call_type yfs_RXYFSRemoveFile2 = { * Remove a file and retrieve new file status. */ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, u64 current_data_version) + const char *name, struct afs_status_cb *dvnode_scb, + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -954,9 +850,8 @@ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -968,6 +863,7 @@ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -977,7 +873,6 @@ int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_remove(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0]; const __be32 *bp; int ret; @@ -987,14 +882,12 @@ static int yfs_deliver_fs_remove(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); return 0; } @@ -1019,7 +912,8 @@ static const struct afs_call_type yfs_RXYFSRemoveDir = { * remove a file or directory */ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, bool isdir, u64 current_data_version) + const char *name, bool isdir, + struct afs_status_cb *dvnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -1042,9 +936,7 @@ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -1056,6 +948,7 @@ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1065,7 +958,6 @@ int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_link(struct afs_call *call) { - struct afs_vnode *dvnode = call->reply[0], *vnode = call->reply[1]; const __be32 *bp; int ret; @@ -1075,16 +967,14 @@ static int yfs_deliver_fs_link(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; } @@ -1103,7 +993,9 @@ static const struct afs_call_type yfs_RXYFSLink = { * Make a hard link. */ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, - const char *name, u64 current_data_version) + const char *name, + struct afs_status_cb *dvnode_scb, + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -1127,9 +1019,8 @@ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = vnode; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -1142,6 +1033,7 @@ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call1(call, &vnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1151,7 +1043,6 @@ int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, */ static int yfs_deliver_fs_symlink(struct afs_call *call) { - struct afs_vnode *vnode = call->reply[0]; const __be32 *bp; int ret; @@ -1163,15 +1054,14 @@ static int yfs_deliver_fs_symlink(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - xdr_decode_YFSFid(&bp, call->reply[1]); - ret = yfs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + xdr_decode_YFSFid(&bp, call->out_fid); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; @@ -1193,9 +1083,9 @@ static const struct afs_call_type yfs_RXYFSSymlink = { int yfs_fs_symlink(struct afs_fs_cursor *fc, const char *name, const char *contents, - u64 current_data_version, + struct afs_status_cb *dvnode_scb, struct afs_fid *newfid, - struct afs_file_status *newstatus) + struct afs_status_cb *vnode_scb) { struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; @@ -1222,10 +1112,9 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = dvnode; - call->reply[1] = newfid; - call->reply[2] = newstatus; - call->expected_version = current_data_version + 1; + call->out_dir_scb = dvnode_scb; + call->out_fid = newfid; + call->out_scb = vnode_scb; /* marshall the parameters */ bp = call->request; @@ -1239,6 +1128,7 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call1(call, &dvnode->fid, name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1248,8 +1138,6 @@ int yfs_fs_symlink(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_rename(struct afs_call *call) { - struct afs_vnode *orig_dvnode = call->reply[0]; - struct afs_vnode *new_dvnode = call->reply[1]; const __be32 *bp; int ret; @@ -1259,20 +1147,17 @@ static int yfs_deliver_fs_rename(struct afs_call *call) if (ret < 0) return ret; - /* unmarshall the reply once we've received all of it */ bp = call->buffer; - ret = yfs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_dir_scb); if (ret < 0) return ret; - if (new_dvnode != orig_dvnode) { - ret = yfs_decode_status(call, &bp, &new_dvnode->status, new_dvnode, - &call->expected_version_2, NULL); + if (call->out_dir_scb != call->out_scb) { + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; } - xdr_decode_YFSVolSync(&bp, NULL); + xdr_decode_YFSVolSync(&bp, call->out_volsync); _leave(" = 0 [done]"); return 0; } @@ -1294,8 +1179,8 @@ int yfs_fs_rename(struct afs_fs_cursor *fc, const char *orig_name, struct afs_vnode *new_dvnode, const char *new_name, - u64 current_orig_data_version, - u64 current_new_data_version) + struct afs_status_cb *orig_dvnode_scb, + struct afs_status_cb *new_dvnode_scb) { struct afs_vnode *orig_dvnode = fc->vnode; struct afs_call *call; @@ -1321,10 +1206,8 @@ int yfs_fs_rename(struct afs_fs_cursor *fc, return -ENOMEM; call->key = fc->key; - call->reply[0] = orig_dvnode; - call->reply[1] = new_dvnode; - call->expected_version = current_orig_data_version + 1; - call->expected_version_2 = current_new_data_version + 1; + call->out_dir_scb = orig_dvnode_scb; + call->out_scb = new_dvnode_scb; /* marshall the parameters */ bp = call->request; @@ -1338,46 +1221,18 @@ int yfs_fs_rename(struct afs_fs_cursor *fc, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call2(call, &orig_dvnode->fid, orig_name, new_name); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } /* - * Deliver reply data to a YFS.StoreData64 operation. - */ -static int yfs_deliver_fs_store_data(struct afs_call *call) -{ - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - _enter(""); - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, NULL); - - afs_pages_written_back(vnode, call); - - _leave(" = 0 [done]"); - return 0; -} - -/* * YFS.StoreData64 operation type. */ static const struct afs_call_type yfs_RXYFSStoreData64 = { .name = "YFS.StoreData64", .op = yfs_FS_StoreData64, - .deliver = yfs_deliver_fs_store_data, + .deliver = yfs_deliver_status_and_volsync, .destructor = afs_flat_call_destructor, }; @@ -1386,7 +1241,8 @@ static const struct afs_call_type yfs_RXYFSStoreData64 = { */ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, pgoff_t first, pgoff_t last, - unsigned offset, unsigned to) + unsigned offset, unsigned to, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1424,13 +1280,12 @@ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, call->key = fc->key; call->mapping = mapping; - call->reply[0] = vnode; call->first = first; call->last = last; call->first_offset = offset; call->last_to = to; call->send_pages = true; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1445,51 +1300,25 @@ int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } /* - * deliver reply data to an FS.StoreStatus - */ -static int yfs_deliver_fs_store_status(struct afs_call *call) -{ - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - _enter(""); - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, NULL); - - _leave(" = 0 [done]"); - return 0; -} - -/* * YFS.StoreStatus operation type */ static const struct afs_call_type yfs_RXYFSStoreStatus = { .name = "YFS.StoreStatus", .op = yfs_FS_StoreStatus, - .deliver = yfs_deliver_fs_store_status, + .deliver = yfs_deliver_status_and_volsync, .destructor = afs_flat_call_destructor, }; static const struct afs_call_type yfs_RXYFSStoreData64_as_Status = { .name = "YFS.StoreData64", .op = yfs_FS_StoreData64, - .deliver = yfs_deliver_fs_store_status, + .deliver = yfs_deliver_status_and_volsync, .destructor = afs_flat_call_destructor, }; @@ -1497,7 +1326,8 @@ static const struct afs_call_type yfs_RXYFSStoreData64_as_Status = { * Set the attributes on a file, using YFS.StoreData64 rather than * YFS.StoreStatus so as to alter the file size also. */ -static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) +static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1518,8 +1348,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version + 1; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1534,6 +1363,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1542,7 +1372,8 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) * Set the attributes on a file, using YFS.StoreData64 if there's a change in * file size, and YFS.StoreStatus otherwise. */ -int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) +int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1550,7 +1381,7 @@ int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) __be32 *bp; if (attr->ia_valid & ATTR_SIZE) - return yfs_fs_setattr_size(fc, attr); + return yfs_fs_setattr_size(fc, attr, scb); _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); @@ -1565,8 +1396,7 @@ int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->expected_version = vnode->status.data_version; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1578,6 +1408,7 @@ int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1607,7 +1438,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_YFSFetchVolumeStatus(&bp, call->reply[1]); + xdr_decode_YFSFetchVolumeStatus(&bp, call->out_volstatus); call->unmarshall++; afs_extract_to_tmp(call); @@ -1623,7 +1454,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_volname_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; /* Fall through - and extract the volume name */ @@ -1633,7 +1464,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("volname '%s'", p); afs_extract_to_tmp(call); @@ -1651,7 +1482,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_offline_msg_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; /* Fall through - and extract the offline message */ @@ -1661,7 +1492,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("offline '%s'", p); @@ -1680,7 +1511,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) return afs_protocol_error(call, -EBADMSG, afs_eproto_motd_len); size = (call->count + 3) & ~3; /* It's padded */ - afs_extract_begin(call, call->reply[2], size); + afs_extract_to_buf(call, size); call->unmarshall++; /* Fall through - and extract the message of the day */ @@ -1690,7 +1521,7 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) if (ret < 0) return ret; - p = call->reply[2]; + p = call->buffer; p[call->count] = 0; _debug("motd '%s'", p); @@ -1706,23 +1537,13 @@ static int yfs_deliver_fs_get_volume_status(struct afs_call *call) } /* - * Destroy a YFS.GetVolumeStatus call. - */ -static void yfs_get_volume_status_call_destructor(struct afs_call *call) -{ - kfree(call->reply[2]); - call->reply[2] = NULL; - afs_flat_call_destructor(call); -} - -/* * YFS.GetVolumeStatus operation type */ static const struct afs_call_type yfs_RXYFSGetVolumeStatus = { .name = "YFS.GetVolumeStatus", .op = yfs_FS_GetVolumeStatus, .deliver = yfs_deliver_fs_get_volume_status, - .destructor = yfs_get_volume_status_call_destructor, + .destructor = afs_flat_call_destructor, }; /* @@ -1735,28 +1556,21 @@ int yfs_fs_get_volume_status(struct afs_fs_cursor *fc, struct afs_call *call; struct afs_net *net = afs_v2net(vnode); __be32 *bp; - void *tmpbuf; _enter(""); - tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL); - if (!tmpbuf) - return -ENOMEM; - call = afs_alloc_flat_call(net, &yfs_RXYFSGetVolumeStatus, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_u64), - sizeof(struct yfs_xdr_YFSFetchVolumeStatus) + - sizeof(__be32)); - if (!call) { - kfree(tmpbuf); + max_t(size_t, + sizeof(struct yfs_xdr_YFSFetchVolumeStatus) + + sizeof(__be32), + AFSOPAQUEMAX + 1)); + if (!call) return -ENOMEM; - } call->key = fc->key; - call->reply[0] = vnode; - call->reply[1] = vs; - call->reply[2] = tmpbuf; + call->out_volstatus = vs; /* marshall the parameters */ bp = call->request; @@ -1767,39 +1581,12 @@ int yfs_fs_get_volume_status(struct afs_fs_cursor *fc, afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } /* - * Deliver reply data to operations that just return a file status and a volume - * sync record. - */ -static int yfs_deliver_status_and_volsync(struct afs_call *call) -{ - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - _enter("{%u}", call->unmarshall); - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSVolSync(&bp, NULL); - - _leave(" = 0 [done]"); - return 0; -} - -/* * YFS.SetLock operation type */ static const struct afs_call_type yfs_RXYFSSetLock = { @@ -1834,7 +1621,8 @@ static const struct afs_call_type yfs_RXYFSReleaseLock = { /* * Set a lock on a file */ -int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) +int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1853,8 +1641,8 @@ int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->want_reply_time = true; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1866,6 +1654,7 @@ int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_calli(call, &vnode->fid, type); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1873,7 +1662,7 @@ int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) /* * extend a lock on a file */ -int yfs_fs_extend_lock(struct afs_fs_cursor *fc) +int yfs_fs_extend_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1891,8 +1680,8 @@ int yfs_fs_extend_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; - call->want_reply_time = true; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1903,6 +1692,7 @@ int yfs_fs_extend_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -1910,7 +1700,7 @@ int yfs_fs_extend_lock(struct afs_fs_cursor *fc) /* * release a lock on a file */ -int yfs_fs_release_lock(struct afs_fs_cursor *fc) +int yfs_fs_release_lock(struct afs_fs_cursor *fc, struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -1928,7 +1718,8 @@ int yfs_fs_release_lock(struct afs_fs_cursor *fc) return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->lvnode = vnode; + call->out_scb = scb; /* marshall the parameters */ bp = call->request; @@ -1939,48 +1730,18 @@ int yfs_fs_release_lock(struct afs_fs_cursor *fc) afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } /* - * Deliver reply data to an FS.FetchStatus with no vnode. - */ -static int yfs_deliver_fs_fetch_status(struct afs_call *call) -{ - struct afs_file_status *status = call->reply[1]; - struct afs_callback *callback = call->reply[2]; - struct afs_volsync *volsync = call->reply[3]; - struct afs_vnode *vnode = call->reply[0]; - const __be32 *bp; - int ret; - - ret = afs_transfer_reply(call); - if (ret < 0) - return ret; - - _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); - - /* unmarshall the reply once we've received all of it */ - bp = call->buffer; - ret = yfs_decode_status(call, &bp, status, vnode, - &call->expected_version, NULL); - if (ret < 0) - return ret; - xdr_decode_YFSCallBack_raw(&bp, callback); - xdr_decode_YFSVolSync(&bp, volsync); - - _leave(" = 0 [done]"); - return 0; -} - -/* * YFS.FetchStatus operation type */ static const struct afs_call_type yfs_RXYFSFetchStatus = { .name = "YFS.FetchStatus", .op = yfs_FS_FetchStatus, - .deliver = yfs_deliver_fs_fetch_status, + .deliver = yfs_deliver_fs_status_cb_and_volsync, .destructor = afs_flat_call_destructor, }; @@ -1990,8 +1751,7 @@ static const struct afs_call_type yfs_RXYFSFetchStatus = { int yfs_fs_fetch_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fid, - struct afs_file_status *status, - struct afs_callback *callback, + struct afs_status_cb *scb, struct afs_volsync *volsync) { struct afs_call *call; @@ -2012,11 +1772,8 @@ int yfs_fs_fetch_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = NULL; /* vnode for fid[0] */ - call->reply[1] = status; - call->reply[2] = callback; - call->reply[3] = volsync; - call->expected_version = 1; /* vnode->status.data_version */ + call->out_scb = scb; + call->out_volsync = volsync; /* marshall the parameters */ bp = call->request; @@ -2025,9 +1782,9 @@ int yfs_fs_fetch_status(struct afs_fs_cursor *fc, bp = xdr_encode_YFSFid(bp, fid); yfs_check_req(call, bp); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, fid); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -2037,9 +1794,7 @@ int yfs_fs_fetch_status(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) { - struct afs_file_status *statuses; - struct afs_callback *callbacks; - struct afs_vnode *vnode = call->reply[0]; + struct afs_status_cb *scb; const __be32 *bp; u32 tmp; int ret; @@ -2078,10 +1833,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - statuses = call->reply[1]; - ret = yfs_decode_status(call, &bp, &statuses[call->count], - call->count == 0 ? vnode : NULL, - NULL, NULL); + scb = &call->out_scb[call->count]; + ret = xdr_decode_YFSFetchStatus(&bp, call, scb); if (ret < 0) return ret; @@ -2120,13 +1873,8 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) _debug("unmarshall CB array"); bp = call->buffer; - callbacks = call->reply[2]; - xdr_decode_YFSCallBack_raw(&bp, &callbacks[call->count]); - statuses = call->reply[1]; - if (call->count == 0 && vnode && statuses[0].abort_code == 0) { - bp = call->buffer; - xdr_decode_YFSCallBack(call, vnode, &bp); - } + scb = &call->out_scb[call->count]; + xdr_decode_YFSCallBack(&bp, call, scb); call->count++; if (call->count < call->count2) goto more_cbs; @@ -2141,7 +1889,7 @@ static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) return ret; bp = call->buffer; - xdr_decode_YFSVolSync(&bp, call->reply[3]); + xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; @@ -2170,8 +1918,7 @@ static const struct afs_call_type yfs_RXYFSInlineBulkStatus = { int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, struct afs_net *net, struct afs_fid *fids, - struct afs_file_status *statuses, - struct afs_callback *callbacks, + struct afs_status_cb *statuses, unsigned int nr_fids, struct afs_volsync *volsync) { @@ -2194,10 +1941,8 @@ int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = NULL; /* vnode for fid[0] */ - call->reply[1] = statuses; - call->reply[2] = callbacks; - call->reply[3] = volsync; + call->out_scb = statuses; + call->out_volsync = volsync; call->count2 = nr_fids; /* marshall the parameters */ @@ -2209,9 +1954,9 @@ int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, bp = xdr_encode_YFSFid(bp, &fids[i]); yfs_check_req(call, bp); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &fids[0]); + afs_set_fc_call(call, fc); afs_make_call(&fc->ac, call, GFP_NOFS); return afs_wait_for_call_to_complete(call, &fc->ac); } @@ -2221,9 +1966,7 @@ int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, */ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) { - struct afs_volsync *volsync = call->reply[2]; - struct afs_vnode *vnode = call->reply[1]; - struct yfs_acl *yacl = call->reply[0]; + struct yfs_acl *yacl = call->out_yacl; struct afs_acl *acl; const __be32 *bp; unsigned int size; @@ -2308,11 +2051,10 @@ static int yfs_deliver_fs_fetch_opaque_acl(struct afs_call *call) bp = call->buffer; yacl->inherit_flag = ntohl(*bp++); yacl->num_cleaned = ntohl(*bp++); - ret = yfs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL); + ret = xdr_decode_YFSFetchStatus(&bp, call, call->out_scb); if (ret < 0) return ret; - xdr_decode_YFSVolSync(&bp, volsync); + xdr_decode_YFSVolSync(&bp, call->out_volsync); call->unmarshall++; @@ -2333,12 +2075,6 @@ void yfs_free_opaque_acl(struct yfs_acl *yacl) } } -static void yfs_destroy_fs_fetch_opaque_acl(struct afs_call *call) -{ - yfs_free_opaque_acl(call->reply[0]); - afs_flat_call_destructor(call); -} - /* * YFS.FetchOpaqueACL operation type */ @@ -2346,18 +2082,18 @@ static const struct afs_call_type yfs_RXYFSFetchOpaqueACL = { .name = "YFS.FetchOpaqueACL", .op = yfs_FS_FetchOpaqueACL, .deliver = yfs_deliver_fs_fetch_opaque_acl, - .destructor = yfs_destroy_fs_fetch_opaque_acl, + .destructor = afs_flat_call_destructor, }; /* * Fetch the YFS advanced ACLs for a file. */ struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *fc, - unsigned int flags) + struct yfs_acl *yacl, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; - struct yfs_acl *yacl; struct afs_net *net = afs_v2net(vnode); __be32 *bp; @@ -2370,19 +2106,15 @@ struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *fc, sizeof(__be32) * 2 + sizeof(struct yfs_xdr_YFSFetchStatus) + sizeof(struct yfs_xdr_YFSVolSync)); - if (!call) - goto nomem; - - yacl = kzalloc(sizeof(struct yfs_acl), GFP_KERNEL); - if (!yacl) - goto nomem_call; + if (!call) { + fc->ac.error = -ENOMEM; + return ERR_PTR(-ENOMEM); + } - yacl->flags = flags; call->key = fc->key; - call->reply[0] = yacl; - call->reply[1] = vnode; - call->reply[2] = NULL; /* volsync */ - call->ret_reply0 = true; + call->out_yacl = yacl; + call->out_scb = scb; + call->out_volsync = NULL; /* marshall the parameters */ bp = call->request; @@ -2391,17 +2123,10 @@ struct yfs_acl *yfs_fs_fetch_opaque_acl(struct afs_fs_cursor *fc, bp = xdr_encode_YFSFid(bp, &vnode->fid); yfs_check_req(call, bp); - call->cb_break = fc->cb_break; afs_use_fs_server(call, fc->cbi); trace_afs_make_fs_call(call, &vnode->fid); afs_make_call(&fc->ac, call, GFP_KERNEL); return (struct yfs_acl *)afs_wait_for_call_to_complete(call, &fc->ac); - -nomem_call: - afs_put_call(call); -nomem: - fc->ac.error = -ENOMEM; - return ERR_PTR(-ENOMEM); } /* @@ -2417,7 +2142,8 @@ static const struct afs_call_type yfs_RXYFSStoreOpaqueACL2 = { /* * Fetch the YFS ACL for a file. */ -int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl) +int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl, + struct afs_status_cb *scb) { struct afs_vnode *vnode = fc->vnode; struct afs_call *call; @@ -2441,8 +2167,8 @@ int yfs_fs_store_opaque_acl2(struct afs_fs_cursor *fc, const struct afs_acl *acl } call->key = fc->key; - call->reply[0] = vnode; - call->reply[2] = NULL; /* volsync */ + call->out_scb = scb; + call->out_volsync = NULL; /* marshall the parameters */ bp = call->request; @@ -2095,6 +2095,7 @@ SYSCALL_DEFINE6(io_pgetevents, struct __aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 ts; + bool interrupted; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) @@ -2108,8 +2109,10 @@ SYSCALL_DEFINE6(io_pgetevents, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2128,6 +2131,7 @@ SYSCALL_DEFINE6(io_pgetevents_time32, struct __aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 ts; + bool interrupted; int ret; if (timeout && unlikely(get_old_timespec32(&ts, timeout))) @@ -2142,8 +2146,10 @@ SYSCALL_DEFINE6(io_pgetevents_time32, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2193,6 +2199,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, struct __compat_aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 t; + bool interrupted; int ret; if (timeout && get_old_timespec32(&t, timeout)) @@ -2206,8 +2213,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2226,6 +2235,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, struct __compat_aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 t; + bool interrupted; int ret; if (timeout && get_timespec64(&t, timeout)) @@ -2239,8 +2249,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 91262c34b797..c2b8663f5b00 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/anon_inodes.c * diff --git a/fs/autofs/Kconfig b/fs/autofs/Kconfig index eaebcd430cc3..3b3a6b1423c6 100644 --- a/fs/autofs/Kconfig +++ b/fs/autofs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config AUTOFS4_FS tristate "Old Kconfig name for Kernel automounter support" select AUTOFS_FS diff --git a/fs/autofs/Makefile b/fs/autofs/Makefile index 1f85d35ec8b7..495ac542e172 100644 --- a/fs/autofs/Makefile +++ b/fs/autofs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux autofs-filesystem routines. # diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h index e1091312abe1..8c0c11181fad 100644 --- a/fs/autofs/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright 1997-1998 Transmeta Corporation - All Rights Reserved * Copyright 2005-2006 Ian Kent <raven@themaw.net> - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ /* Internal header file for autofs */ diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c index e9fe74d1541b..a3cdb0036c5d 100644 --- a/fs/autofs/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 2008 Red Hat, Inc. All rights reserved. * Copyright 2008 Ian Kent <raven@themaw.net> - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ #include <linux/miscdevice.h> diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index 28d9c2b1b3bb..cdff0567aacb 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org> * Copyright 2001-2006 Ian Kent <raven@themaw.net> - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ #include "autofs_i.h" diff --git a/fs/autofs/init.c b/fs/autofs/init.c index c0c1db2cc6ea..d3f55e874338 100644 --- a/fs/autofs/init.c +++ b/fs/autofs/init.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ #include <linux/module.h> diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index fb0225f21c12..9edf243713eb 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 2005-2006 Ian Kent <raven@themaw.net> - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ #include <linux/seq_file.h> diff --git a/fs/autofs/root.c b/fs/autofs/root.c index 1246f396bf0e..e646569c75ed 100644 --- a/fs/autofs/root.c +++ b/fs/autofs/root.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 1999-2000 Jeremy Fitzhardinge <jeremy@goop.org> * Copyright 2001-2006 Ian Kent <raven@themaw.net> - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ #include <linux/capability.h> diff --git a/fs/autofs/symlink.c b/fs/autofs/symlink.c index aad3902c0cc1..7ac67dc76039 100644 --- a/fs/autofs/symlink.c +++ b/fs/autofs/symlink.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ #include "autofs_i.h" diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index 15a3e31d0904..b04c528b19d3 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 1997-1998 Transmeta Corporation -- All Rights Reserved * Copyright 2001-2006 Ian Kent <raven@themaw.net> - * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. */ #include <linux/sched/signal.h> diff --git a/fs/befs/Kconfig b/fs/befs/Kconfig index edc5cc2aefad..9550b6462b81 100644 --- a/fs/befs/Kconfig +++ b/fs/befs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config BEFS_FS tristate "BeOS file system (BeFS) support (read only)" depends on BLOCK diff --git a/fs/befs/Makefile b/fs/befs/Makefile index 8b9f66642a83..6c9c3cbc556e 100644 --- a/fs/befs/Makefile +++ b/fs/befs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux BeOS filesystem routines. # diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index e273850c95af..462d096ff3e9 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/befs/linuxvfs.c * diff --git a/fs/bfs/Kconfig b/fs/bfs/Kconfig index 3728a6479c64..3e1247f07913 100644 --- a/fs/bfs/Kconfig +++ b/fs/bfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config BFS_FS tristate "BFS file system support" depends on BLOCK diff --git a/fs/bfs/Makefile b/fs/bfs/Makefile index c787b36d940c..2b6bc5eb4de9 100644 --- a/fs/bfs/Makefile +++ b/fs/bfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for BFS filesystem. # diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index dc0cd2aa3d65..5e97bed073d7 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/bfs/inode.c * BFS superblock and inode operations. diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 1fefd87eb4b4..8e8346a81723 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/binfmt_aout.c * diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7d09d125f148..8264b468f283 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/binfmt_elf.c * @@ -524,6 +525,19 @@ static inline int arch_check_elf(struct elfhdr *ehdr, bool has_interp, #endif /* !CONFIG_ARCH_BINFMT_ELF_STATE */ +static inline int make_prot(u32 p_flags) +{ + int prot = 0; + + if (p_flags & PF_R) + prot |= PROT_READ; + if (p_flags & PF_W) + prot |= PROT_WRITE; + if (p_flags & PF_X) + prot |= PROT_EXEC; + return prot; +} + /* This is much more generalized than the library routine read function, so we keep this separate. Technically the library read function is only provided so that we can read a.out libraries that have @@ -563,16 +577,10 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) { if (eppnt->p_type == PT_LOAD) { int elf_type = MAP_PRIVATE | MAP_DENYWRITE; - int elf_prot = 0; + int elf_prot = make_prot(eppnt->p_flags); unsigned long vaddr = 0; unsigned long k, map_addr; - if (eppnt->p_flags & PF_R) - elf_prot = PROT_READ; - if (eppnt->p_flags & PF_W) - elf_prot |= PROT_WRITE; - if (eppnt->p_flags & PF_X) - elf_prot |= PROT_EXEC; vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) elf_type |= MAP_FIXED_NOREPLACE; @@ -687,7 +695,6 @@ static int load_elf_binary(struct linux_binprm *bprm) struct file *interpreter = NULL; /* to shut gcc up */ unsigned long load_addr = 0, load_bias = 0; int load_addr_set = 0; - char * elf_interpreter = NULL; unsigned long error; struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL; unsigned long elf_bss, elf_brk; @@ -698,13 +705,12 @@ static int load_elf_binary(struct linux_binprm *bprm) unsigned long start_code, end_code, start_data, end_data; unsigned long reloc_func_desc __maybe_unused = 0; int executable_stack = EXSTACK_DEFAULT; - struct pt_regs *regs = current_pt_regs(); struct { struct elfhdr elf_ex; struct elfhdr interp_elf_ex; } *loc; struct arch_elf_state arch_state = INIT_ARCH_ELF_STATE; - loff_t pos; + struct pt_regs *regs; loc = kmalloc(sizeof(*loc), GFP_KERNEL); if (!loc) { @@ -734,69 +740,66 @@ static int load_elf_binary(struct linux_binprm *bprm) goto out; elf_ppnt = elf_phdata; - elf_bss = 0; - elf_brk = 0; + for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { + char *elf_interpreter; + loff_t pos; - start_code = ~0UL; - end_code = 0; - start_data = 0; - end_data = 0; + if (elf_ppnt->p_type != PT_INTERP) + continue; - for (i = 0; i < loc->elf_ex.e_phnum; i++) { - if (elf_ppnt->p_type == PT_INTERP) { - /* This is the program interpreter used for - * shared libraries - for now assume that this - * is an a.out format binary - */ - retval = -ENOEXEC; - if (elf_ppnt->p_filesz > PATH_MAX || - elf_ppnt->p_filesz < 2) - goto out_free_ph; - - retval = -ENOMEM; - elf_interpreter = kmalloc(elf_ppnt->p_filesz, - GFP_KERNEL); - if (!elf_interpreter) - goto out_free_ph; - - pos = elf_ppnt->p_offset; - retval = kernel_read(bprm->file, elf_interpreter, - elf_ppnt->p_filesz, &pos); - if (retval != elf_ppnt->p_filesz) { - if (retval >= 0) - retval = -EIO; - goto out_free_interp; - } - /* make sure path is NULL terminated */ - retval = -ENOEXEC; - if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0') - goto out_free_interp; + /* + * This is the program interpreter used for shared libraries - + * for now assume that this is an a.out format binary. + */ + retval = -ENOEXEC; + if (elf_ppnt->p_filesz > PATH_MAX || elf_ppnt->p_filesz < 2) + goto out_free_ph; - interpreter = open_exec(elf_interpreter); - retval = PTR_ERR(interpreter); - if (IS_ERR(interpreter)) - goto out_free_interp; + retval = -ENOMEM; + elf_interpreter = kmalloc(elf_ppnt->p_filesz, GFP_KERNEL); + if (!elf_interpreter) + goto out_free_ph; - /* - * If the binary is not readable then enforce - * mm->dumpable = 0 regardless of the interpreter's - * permissions. - */ - would_dump(bprm, interpreter); - - /* Get the exec headers */ - pos = 0; - retval = kernel_read(interpreter, &loc->interp_elf_ex, - sizeof(loc->interp_elf_ex), &pos); - if (retval != sizeof(loc->interp_elf_ex)) { - if (retval >= 0) - retval = -EIO; - goto out_free_dentry; - } + pos = elf_ppnt->p_offset; + retval = kernel_read(bprm->file, elf_interpreter, + elf_ppnt->p_filesz, &pos); + if (retval != elf_ppnt->p_filesz) { + if (retval >= 0) + retval = -EIO; + goto out_free_interp; + } + /* make sure path is NULL terminated */ + retval = -ENOEXEC; + if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0') + goto out_free_interp; - break; + interpreter = open_exec(elf_interpreter); + kfree(elf_interpreter); + retval = PTR_ERR(interpreter); + if (IS_ERR(interpreter)) + goto out_free_ph; + + /* + * If the binary is not readable then enforce mm->dumpable = 0 + * regardless of the interpreter's permissions. + */ + would_dump(bprm, interpreter); + + /* Get the exec headers */ + pos = 0; + retval = kernel_read(interpreter, &loc->interp_elf_ex, + sizeof(loc->interp_elf_ex), &pos); + if (retval != sizeof(loc->interp_elf_ex)) { + if (retval >= 0) + retval = -EIO; + goto out_free_dentry; } - elf_ppnt++; + + break; + +out_free_interp: + kfree(elf_interpreter); + goto out_free_ph; } elf_ppnt = elf_phdata; @@ -819,7 +822,7 @@ static int load_elf_binary(struct linux_binprm *bprm) } /* Some simple consistency checks for the interpreter */ - if (elf_interpreter) { + if (interpreter) { retval = -ELIBBAD; /* Not an ELF interpreter */ if (memcmp(loc->interp_elf_ex.e_ident, ELFMAG, SELFMAG) != 0) @@ -884,13 +887,19 @@ static int load_elf_binary(struct linux_binprm *bprm) if (retval < 0) goto out_free_dentry; - current->mm->start_stack = bprm->p; + elf_bss = 0; + elf_brk = 0; + + start_code = ~0UL; + end_code = 0; + start_data = 0; + end_data = 0; /* Now we do a little grungy work by mmapping the ELF image into the correct location in memory. */ for(i = 0, elf_ppnt = elf_phdata; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { - int elf_prot = 0, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE; + int elf_prot, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE; unsigned long k, vaddr; unsigned long total_size = 0; @@ -931,12 +940,7 @@ static int load_elf_binary(struct linux_binprm *bprm) elf_fixed = MAP_FIXED; } - if (elf_ppnt->p_flags & PF_R) - elf_prot |= PROT_READ; - if (elf_ppnt->p_flags & PF_W) - elf_prot |= PROT_WRITE; - if (elf_ppnt->p_flags & PF_X) - elf_prot |= PROT_EXEC; + elf_prot = make_prot(elf_ppnt->p_flags); elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; @@ -978,7 +982,7 @@ static int load_elf_binary(struct linux_binprm *bprm) * independently randomized mmap region (0 load_bias * without MAP_FIXED). */ - if (elf_interpreter) { + if (interpreter) { load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); @@ -1076,7 +1080,7 @@ static int load_elf_binary(struct linux_binprm *bprm) goto out_free_dentry; } - if (elf_interpreter) { + if (interpreter) { unsigned long interp_map_addr = 0; elf_entry = load_elf_interp(&loc->interp_elf_ex, @@ -1100,7 +1104,6 @@ static int load_elf_binary(struct linux_binprm *bprm) allow_write_access(interpreter); fput(interpreter); - kfree(elf_interpreter); } else { elf_entry = loc->elf_ex.e_entry; if (BAD_ADDR(elf_entry)) { @@ -1115,7 +1118,7 @@ static int load_elf_binary(struct linux_binprm *bprm) set_binfmt(&elf_format); #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES - retval = arch_setup_additional_pages(bprm, !!elf_interpreter); + retval = arch_setup_additional_pages(bprm, !!interpreter); if (retval < 0) goto out; #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */ @@ -1132,6 +1135,17 @@ static int load_elf_binary(struct linux_binprm *bprm) current->mm->start_stack = bprm->p; if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) { + /* + * For architectures with ELF randomization, when executing + * a loader directly (i.e. no interpreter listed in ELF + * headers), move the brk area out of the mmap region + * (since it grows up, and may collide early with the stack + * growing down), and into the unused ELF_ET_DYN_BASE region. + */ + if (IS_ENABLED(CONFIG_ARCH_HAS_ELF_RANDOMIZE) && !interpreter) + current->mm->brk = current->mm->start_brk = + ELF_ET_DYN_BASE; + current->mm->brk = current->mm->start_brk = arch_randomize_brk(current->mm); #ifdef compat_brk_randomized @@ -1148,6 +1162,7 @@ static int load_elf_binary(struct linux_binprm *bprm) MAP_FIXED | MAP_PRIVATE, 0); } + regs = current_pt_regs(); #ifdef ELF_PLAT_INIT /* * The ABI may specify that certain registers be set up in special @@ -1176,8 +1191,6 @@ out_free_dentry: allow_write_access(interpreter); if (interpreter) fput(interpreter); -out_free_interp: - kfree(elf_interpreter); out_free_ph: kfree(elf_phdata); goto out; @@ -1456,8 +1469,6 @@ static void fill_elf_header(struct elfhdr *elf, int segs, elf->e_ehsize = sizeof(struct elfhdr); elf->e_phentsize = sizeof(struct elf_phdr); elf->e_phnum = segs; - - return; } static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) @@ -1470,7 +1481,6 @@ static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) phdr->p_memsz = 0; phdr->p_flags = 0; phdr->p_align = 0; - return; } static void fill_note(struct memelfnote *note, const char *name, int type, @@ -1480,7 +1490,6 @@ static void fill_note(struct memelfnote *note, const char *name, int type, note->type = type; note->datasz = sz; note->data = data; - return; } /* diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index b53bb3729ac1..d86ebd0dcc3d 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* binfmt_elf_fdpic.c: FDPIC ELF binary format * * Copyright (C) 2003, 2004, 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * Derived from binfmt_elf.c - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c index dd2d3f0cd55d..466497860c62 100644 --- a/fs/binfmt_em86.c +++ b/fs/binfmt_em86.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/binfmt_em86.c * diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 82a48e830018..8c6b50f34466 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -42,6 +42,11 @@ #include <asm/unaligned.h> #include <asm/cacheflush.h> #include <asm/page.h> +#include <asm/flat.h> + +#ifndef flat_get_relocate_addr +#define flat_get_relocate_addr(rel) (rel) +#endif /****************************************************************************/ @@ -63,6 +68,12 @@ #define RELOC_FAILED 0xff00ff01 /* Relocation incorrect somewhere */ #define UNLOADED_LIB 0x7ff000ff /* Placeholder for unused library */ +#ifdef CONFIG_BINFMT_SHARED_FLAT +#define MAX_SHARED_LIBS (4) +#else +#define MAX_SHARED_LIBS (1) +#endif + struct lib_info { struct { unsigned long start_code; /* Start of text segment */ @@ -120,14 +131,15 @@ static int create_flat_tables(struct linux_binprm *bprm, unsigned long arg_start sp -= bprm->envc + 1; sp -= bprm->argc + 1; - sp -= flat_argvp_envp_on_stack() ? 2 : 0; + if (IS_ENABLED(CONFIG_BINFMT_FLAT_ARGVP_ENVP_ON_STACK)) + sp -= 2; /* argvp + envp */ sp -= 1; /* &argc */ current->mm->start_stack = (unsigned long)sp & -FLAT_STACK_ALIGN; sp = (unsigned long __user *)current->mm->start_stack; __put_user(bprm->argc, sp++); - if (flat_argvp_envp_on_stack()) { + if (IS_ENABLED(CONFIG_BINFMT_FLAT_ARGVP_ENVP_ON_STACK)) { unsigned long argv, envp; argv = (unsigned long)(sp + 2); envp = (unsigned long)(sp + 2 + bprm->argc + 1); @@ -345,7 +357,7 @@ calc_reloc(unsigned long r, struct lib_info *p, int curid, int internalp) start_code = p->lib_list[id].start_code; text_len = p->lib_list[id].text_len; - if (!flat_reloc_valid(r, start_brk - start_data + text_len)) { + if (r > start_brk - start_data + text_len) { pr_err("reloc outside program 0x%lx (0 - 0x%lx/0x%lx)", r, start_brk-start_data+text_len, text_len); goto failed; @@ -368,6 +380,7 @@ failed: /****************************************************************************/ +#ifdef CONFIG_BINFMT_FLAT_OLD static void old_reloc(unsigned long rl) { static const char *segment[] = { "TEXT", "DATA", "BSS", "*UNKNOWN*" }; @@ -405,6 +418,7 @@ static void old_reloc(unsigned long rl) pr_debug("Relocation became %lx\n", val); } +#endif /* CONFIG_BINFMT_FLAT_OLD */ /****************************************************************************/ @@ -415,7 +429,8 @@ static int load_flat_file(struct linux_binprm *bprm, unsigned long textpos, datapos, realdatastart; u32 text_len, data_len, bss_len, stack_len, full_data, flags; unsigned long len, memp, memp_size, extra, rlim; - u32 __user *reloc, *rp; + __be32 __user *reloc; + u32 __user *rp; struct inode *inode; int i, rev, relocs; loff_t fpos; @@ -454,6 +469,7 @@ static int load_flat_file(struct linux_binprm *bprm, if (flags & FLAT_FLAG_KTRACE) pr_info("Loading file: %s\n", bprm->filename); +#ifdef CONFIG_BINFMT_FLAT_OLD if (rev != FLAT_VERSION && rev != OLD_FLAT_VERSION) { pr_err("bad flat file version 0x%x (supported 0x%lx and 0x%lx)\n", rev, FLAT_VERSION, OLD_FLAT_VERSION); @@ -470,6 +486,23 @@ static int load_flat_file(struct linux_binprm *bprm, } /* + * fix up the flags for the older format, there were all kinds + * of endian hacks, this only works for the simple cases + */ + if (rev == OLD_FLAT_VERSION && + (flags || IS_ENABLED(CONFIG_BINFMT_FLAT_OLD_ALWAYS_RAM))) + flags = FLAT_FLAG_RAM; + +#else /* CONFIG_BINFMT_FLAT_OLD */ + if (rev != FLAT_VERSION) { + pr_err("bad flat file version 0x%x (supported 0x%lx)\n", + rev, FLAT_VERSION); + ret = -ENOEXEC; + goto err; + } +#endif /* !CONFIG_BINFMT_FLAT_OLD */ + + /* * Make sure the header params are sane. * 28 bits (256 MB) is way more than reasonable in this case. * If some top bits are set we have probable binary corruption. @@ -480,13 +513,6 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - /* - * fix up the flags for the older format, there were all kinds - * of endian hacks, this only works for the simple cases - */ - if (rev == OLD_FLAT_VERSION && flat_old_ram_flag(flags)) - flags = FLAT_FLAG_RAM; - #ifndef CONFIG_BINFMT_ZFLAT if (flags & (FLAT_FLAG_GZIP|FLAT_FLAG_GZDATA)) { pr_err("Support for ZFLAT executables is not enabled.\n"); @@ -547,7 +573,7 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - len = data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long); + len = data_len + extra; len = PAGE_ALIGN(len); realdatastart = vm_mmap(NULL, 0, len, PROT_READ|PROT_WRITE|PROT_EXEC, MAP_PRIVATE, 0); @@ -561,9 +587,7 @@ static int load_flat_file(struct linux_binprm *bprm, vm_munmap(textpos, text_len); goto err; } - datapos = ALIGN(realdatastart + - MAX_SHARED_LIBS * sizeof(unsigned long), - FLAT_DATA_ALIGN); + datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN); pr_debug("Allocated data+bss+stack (%u bytes): %lx\n", data_len + bss_len + stack_len, datapos); @@ -587,13 +611,13 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } - reloc = (u32 __user *) + reloc = (__be32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = realdatastart; memp_size = len; } else { - len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32); + len = text_len + data_len + extra; len = PAGE_ALIGN(len); textpos = vm_mmap(NULL, 0, len, PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0); @@ -608,11 +632,9 @@ static int load_flat_file(struct linux_binprm *bprm, } realdatastart = textpos + ntohl(hdr->data_start); - datapos = ALIGN(realdatastart + - MAX_SHARED_LIBS * sizeof(u32), - FLAT_DATA_ALIGN); + datapos = ALIGN(realdatastart, FLAT_DATA_ALIGN); - reloc = (u32 __user *) + reloc = (__be32 __user *) (datapos + (ntohl(hdr->reloc_start) - text_len)); memp = textpos; memp_size = len; @@ -627,8 +649,9 @@ static int load_flat_file(struct linux_binprm *bprm, (text_len + full_data - sizeof(struct flat_hdr)), 0); - memmove((void *) datapos, (void *) realdatastart, - full_data); + if (datapos != realdatastart) + memmove((void *)datapos, (void *)realdatastart, + full_data); #else /* * This is used on MMU systems mainly for testing. @@ -684,8 +707,7 @@ static int load_flat_file(struct linux_binprm *bprm, if (IS_ERR_VALUE(result)) { ret = result; pr_err("Unable to read code+data+bss, errno %d\n", ret); - vm_munmap(textpos, text_len + data_len + extra + - MAX_SHARED_LIBS * sizeof(u32)); + vm_munmap(textpos, text_len + data_len + extra); goto err; } } @@ -775,20 +797,18 @@ static int load_flat_file(struct linux_binprm *bprm, * __start to address 4 so that is okay). */ if (rev > OLD_FLAT_VERSION) { - u32 __maybe_unused persistent = 0; for (i = 0; i < relocs; i++) { u32 addr, relval; + __be32 tmp; /* * Get the address of the pointer to be * relocated (of course, the address has to be * relocated first). */ - if (get_user(relval, reloc + i)) + if (get_user(tmp, reloc + i)) return -EFAULT; - relval = ntohl(relval); - if (flat_set_persistent(relval, &persistent)) - continue; + relval = ntohl(tmp); addr = flat_get_relocate_addr(relval); rp = (u32 __user *)calc_reloc(addr, libinfo, id, 1); if (rp == (u32 __user *)RELOC_FAILED) { @@ -797,8 +817,7 @@ static int load_flat_file(struct linux_binprm *bprm, } /* Get the pointer's value. */ - ret = flat_get_addr_from_rp(rp, relval, flags, - &addr, &persistent); + ret = flat_get_addr_from_rp(rp, relval, flags, &addr); if (unlikely(ret)) goto err; @@ -807,8 +826,13 @@ static int load_flat_file(struct linux_binprm *bprm, * Do the relocation. PIC relocs in the data section are * already in target order */ - if ((flags & FLAT_FLAG_GOTPIC) == 0) - addr = ntohl(addr); + if ((flags & FLAT_FLAG_GOTPIC) == 0) { + /* + * Meh, the same value can have a different + * byte order based on a flag.. + */ + addr = ntohl((__force __be32)addr); + } addr = calc_reloc(addr, libinfo, id, 0); if (addr == RELOC_FAILED) { ret = -ENOEXEC; @@ -821,14 +845,15 @@ static int load_flat_file(struct linux_binprm *bprm, goto err; } } +#ifdef CONFIG_BINFMT_FLAT_OLD } else { for (i = 0; i < relocs; i++) { - u32 relval; + __be32 relval; if (get_user(relval, reloc + i)) return -EFAULT; - relval = ntohl(relval); - old_reloc(relval); + old_reloc(ntohl(relval)); } +#endif /* CONFIG_BINFMT_FLAT_OLD */ } flush_icache_range(start_code, end_code); @@ -856,9 +881,14 @@ err: static int load_flat_shared_library(int id, struct lib_info *libs) { + /* + * This is a fake bprm struct; only the members "buf", "file" and + * "filename" are actually used. + */ struct linux_binprm bprm; int res; char buf[16]; + loff_t pos = 0; memset(&bprm, 0, sizeof(bprm)); @@ -872,25 +902,11 @@ static int load_flat_shared_library(int id, struct lib_info *libs) if (IS_ERR(bprm.file)) return res; - bprm.cred = prepare_exec_creds(); - res = -ENOMEM; - if (!bprm.cred) - goto out; - - /* We don't really care about recalculating credentials at this point - * as we're past the point of no return and are dealing with shared - * libraries. - */ - bprm.called_set_creds = 1; - - res = prepare_binprm(&bprm); + res = kernel_read(bprm.file, bprm.buf, BINPRM_BUF_SIZE, &pos); - if (!res) + if (res >= 0) res = load_flat_file(&bprm, libs, id, NULL); - abort_creds(bprm.cred); - -out: allow_write_access(bprm.file); fput(bprm.file); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index aa4a7a23ff99..b8e145552ec7 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * binfmt_misc.c * diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index e996174cbfc0..e9e6a6f4a35f 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/binfmt_script.c * diff --git a/fs/block_dev.c b/fs/block_dev.c index f80045048bb7..f00b569a9f89 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/block_dev.c * @@ -29,7 +30,6 @@ #include <linux/namei.h> #include <linux/log2.h> #include <linux/cleancache.h> -#include <linux/dax.h> #include <linux/task_io_accounting_ops.h> #include <linux/falloc.h> #include <linux/uaccess.h> @@ -203,13 +203,12 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, { struct file *file = iocb->ki_filp; struct block_device *bdev = I_BDEV(bdev_file_inode(file)); - struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs, *bvec; + struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs; loff_t pos = iocb->ki_pos; bool should_dirty = false; struct bio bio; ssize_t ret; blk_qc_t qc; - struct bvec_iter_all iter_all; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) @@ -259,13 +258,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, } __set_current_state(TASK_RUNNING); - bio_for_each_segment_all(bvec, &bio, iter_all) { - if (should_dirty && !PageCompound(bvec->bv_page)) - set_page_dirty_lock(bvec->bv_page); - if (!bio_flagged(&bio, BIO_NO_PAGE_REF)) - put_page(bvec->bv_page); - } - + bio_release_pages(&bio, should_dirty); if (unlikely(bio.bi_status)) ret = blk_status_to_errno(bio.bi_status); @@ -335,13 +328,7 @@ static void blkdev_bio_end_io(struct bio *bio) if (should_dirty) { bio_check_pages_dirty(bio); } else { - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { - struct bvec_iter_all iter_all; - struct bio_vec *bvec; - - bio_for_each_segment_all(bvec, bio, iter_all) - put_page(bvec->bv_page); - } + bio_release_pages(bio, false); bio_put(bio); } } @@ -1406,20 +1393,27 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev, */ int revalidate_disk(struct gendisk *disk) { - struct block_device *bdev; int ret = 0; if (disk->fops->revalidate_disk) ret = disk->fops->revalidate_disk(disk); - bdev = bdget_disk(disk, 0); - if (!bdev) - return ret; - mutex_lock(&bdev->bd_mutex); - check_disk_size_change(disk, bdev, ret == 0); - bdev->bd_invalidated = 0; - mutex_unlock(&bdev->bd_mutex); - bdput(bdev); + /* + * Hidden disks don't have associated bdev so there's no point in + * revalidating it. + */ + if (!(disk->flags & GENHD_FL_HIDDEN)) { + struct block_device *bdev = bdget_disk(disk, 0); + + if (!bdev) + return ret; + + mutex_lock(&bdev->bd_mutex); + check_disk_size_change(disk, bdev, ret == 0); + bdev->bd_invalidated = 0; + mutex_unlock(&bdev->bd_mutex); + bdput(bdev); + } return ret; } EXPORT_SYMBOL(revalidate_disk); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index daf7908d1e35..84dd4a8980c5 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -1008,6 +1008,7 @@ int btrfs_compress_pages(unsigned int type_level, struct address_space *mapping, struct list_head *workspace; int ret; + level = btrfs_compress_op[type]->set_level(level); workspace = get_workspace(type, level); ret = btrfs_compress_op[type]->compress_pages(workspace, mapping, start, pages, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 55c15f31d00d..ee0989c7e3a9 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -603,17 +603,33 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, } btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); - return PTR_ERR(trans); + /* + * We have to use this loop approach because at this point src_device + * has to be available for transaction commit to complete, yet new + * chunks shouldn't be allocated on the device. + */ + while (1) { + trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); + return PTR_ERR(trans); + } + ret = btrfs_commit_transaction(trans); + WARN_ON(ret); + + /* Prevent write_all_supers() during the finishing procedure */ + mutex_lock(&fs_info->fs_devices->device_list_mutex); + /* Prevent new chunks being allocated on the source device */ + mutex_lock(&fs_info->chunk_mutex); + + if (!list_empty(&src_device->post_commit_list)) { + mutex_unlock(&fs_info->fs_devices->device_list_mutex); + mutex_unlock(&fs_info->chunk_mutex); + } else { + break; + } } - ret = btrfs_commit_transaction(trans); - WARN_ON(ret); - /* keep away write_all_supers() during the finishing procedure */ - mutex_lock(&fs_info->fs_devices->device_list_mutex); - mutex_lock(&fs_info->chunk_mutex); down_write(&dev_replace->rwsem); dev_replace->replace_state = scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED @@ -662,7 +678,6 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, btrfs_device_set_disk_total_bytes(tgt_device, src_device->disk_total_bytes); btrfs_device_set_bytes_used(tgt_device, src_device->bytes_used); - ASSERT(list_empty(&src_device->post_commit_list)); tgt_device->commit_total_bytes = src_device->commit_total_bytes; tgt_device->commit_bytes_used = src_device->bytes_used; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f79e477a378e..5faf057f6f37 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -757,12 +757,14 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info, } static void add_pinned_bytes(struct btrfs_fs_info *fs_info, - struct btrfs_ref *ref) + struct btrfs_ref *ref, int sign) { struct btrfs_space_info *space_info; - s64 num_bytes = -ref->len; + s64 num_bytes; u64 flags; + ASSERT(sign == 1 || sign == -1); + num_bytes = sign * ref->len; if (ref->type == BTRFS_REF_METADATA) { if (ref->tree_ref.root == BTRFS_CHUNK_TREE_OBJECTID) flags = BTRFS_BLOCK_GROUP_SYSTEM; @@ -2063,7 +2065,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, btrfs_ref_tree_mod(fs_info, generic_ref); if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0) - add_pinned_bytes(fs_info, generic_ref); + add_pinned_bytes(fs_info, generic_ref, -1); return ret; } @@ -3882,8 +3884,7 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) info->space_info_kobj, "%s", alloc_name(space_info->flags)); if (ret) { - percpu_counter_destroy(&space_info->total_bytes_pinned); - kfree(space_info); + kobject_put(&space_info->kobj); return ret; } @@ -7190,7 +7191,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, } out: if (pin) - add_pinned_bytes(fs_info, &generic_ref); + add_pinned_bytes(fs_info, &generic_ref, 1); if (last_ref) { /* @@ -7238,7 +7239,7 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref) btrfs_ref_tree_mod(fs_info, ref); if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0) - add_pinned_bytes(fs_info, ref); + add_pinned_bytes(fs_info, ref, 1); return ret; } @@ -10830,17 +10831,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, remove_em = (atomic_read(&block_group->trimming) == 0); spin_unlock(&block_group->lock); - if (remove_em) { - struct extent_map_tree *em_tree; - - em_tree = &fs_info->mapping_tree.map_tree; - write_lock(&em_tree->lock); - remove_extent_mapping(em_tree, em); - write_unlock(&em_tree->lock); - /* once for the tree */ - free_extent_map(em); - } - mutex_unlock(&fs_info->chunk_mutex); ret = remove_block_group_free_space(trans, block_group); @@ -10857,6 +10847,19 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, goto out; ret = btrfs_del_item(trans, root, path); + if (ret) + goto out; + + if (remove_em) { + struct extent_map_tree *em_tree; + + em_tree = &fs_info->mapping_tree.map_tree; + write_lock(&em_tree->lock); + remove_extent_mapping(em_tree, em); + write_unlock(&em_tree->lock); + /* once for the tree */ + free_extent_map(em); + } out: if (remove_rsv) btrfs_delayed_refs_rsv_release(fs_info, 1); @@ -11136,13 +11139,11 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info, * it while performing the free space search since we have already * held back allocations. */ -static int btrfs_trim_free_extents(struct btrfs_device *device, - struct fstrim_range *range, u64 *trimmed) +static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed) { - u64 start, len = 0, end = 0; + u64 start = SZ_1M, len = 0, end = 0; int ret; - start = max_t(u64, range->start, SZ_1M); *trimmed = 0; /* Discard not supported = nothing to do. */ @@ -11185,22 +11186,6 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, break; } - /* Keep going until we satisfy minlen or reach end of space */ - if (len < range->minlen) { - mutex_unlock(&fs_info->chunk_mutex); - start += len; - continue; - } - - /* If we are out of the passed range break */ - if (start > range->start + range->len - 1) { - mutex_unlock(&fs_info->chunk_mutex); - break; - } - - start = max(range->start, start); - len = min(range->len, len); - ret = btrfs_issue_discard(device->bdev, start, len, &bytes); if (!ret) @@ -11215,10 +11200,6 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, start += len; *trimmed += bytes; - /* We've trimmed enough */ - if (*trimmed >= range->len) - break; - if (fatal_signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -11302,7 +11283,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) mutex_lock(&fs_info->fs_devices->device_list_mutex); devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { - ret = btrfs_trim_free_extents(device, range, &group_trimmed); + ret = btrfs_trim_free_extents(device, &group_trimmed); if (ret) { dev_failed++; dev_ret = ret; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7e85dca0e6f2..89f5be2bfb43 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2068,6 +2068,18 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) u64 len; /* + * If the inode needs a full sync, make sure we use a full range to + * avoid log tree corruption, due to hole detection racing with ordered + * extent completion for adjacent ranges, and assertion failures during + * hole detection. + */ + if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, + &BTRFS_I(inode)->runtime_flags)) { + start = 0; + end = LLONG_MAX; + } + + /* * The range length can be represented by u64, we have to do the typecasts * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync() */ @@ -2554,10 +2566,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend, &cached_state); - if (ret) { - inode_unlock(inode); + if (ret) goto out_only_mutex; - } path = btrfs_alloc_path(); if (!path) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9aba9660efe5..a2aabdb85226 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6433,8 +6433,18 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size + name_len * 2); inode_inc_iversion(&parent_inode->vfs_inode); - parent_inode->vfs_inode.i_mtime = parent_inode->vfs_inode.i_ctime = - current_time(&parent_inode->vfs_inode); + /* + * If we are replaying a log tree, we do not want to update the mtime + * and ctime of the parent directory with the current time, since the + * log replay procedure is responsible for setting them to their correct + * values (the ones it had when the fsync was done). + */ + if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags)) { + struct timespec64 now = current_time(&parent_inode->vfs_inode); + + parent_inode->vfs_inode.i_mtime = now; + parent_inode->vfs_inode.i_ctime = now; + } ret = btrfs_update_inode(trans, root, &parent_inode->vfs_inode); if (ret) btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 6dafa857bbb9..cfeff1b8dce0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -187,7 +187,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) struct btrfs_inode *binode = BTRFS_I(inode); struct btrfs_root *root = binode->root; struct btrfs_trans_handle *trans; - unsigned int fsflags; + unsigned int fsflags, old_fsflags; int ret; const char *comp = NULL; u32 binode_flags = binode->flags; @@ -212,13 +212,10 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) inode_lock(inode); fsflags = btrfs_mask_fsflags_for_type(inode, fsflags); - if ((fsflags ^ btrfs_inode_flags_to_fsflags(binode->flags)) & - (FS_APPEND_FL | FS_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - ret = -EPERM; - goto out_unlock; - } - } + old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); + if (ret) + goto out_unlock; if (fsflags & FS_SYNC_FL) binode_flags |= BTRFS_INODE_SYNC; @@ -312,8 +309,6 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) btrfs_abort_transaction(trans, ret); goto out_end_trans; } - set_bit(BTRFS_INODE_COPY_EVERYTHING, - &BTRFS_I(inode)->runtime_flags); } else { ret = btrfs_set_prop(trans, inode, "btrfs.compression", NULL, 0, 0); @@ -378,9 +373,7 @@ static int btrfs_ioctl_fsgetxattr(struct file *file, void __user *arg) struct btrfs_inode *binode = BTRFS_I(file_inode(file)); struct fsxattr fa; - memset(&fa, 0, sizeof(fa)); - fa.fsx_xflags = btrfs_inode_flags_to_xflags(binode->flags); - + simple_fill_fsxattr(&fa, btrfs_inode_flags_to_xflags(binode->flags)); if (copy_to_user(arg, &fa, sizeof(fa))) return -EFAULT; @@ -393,7 +386,7 @@ static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg) struct btrfs_inode *binode = BTRFS_I(inode); struct btrfs_root *root = binode->root; struct btrfs_trans_handle *trans; - struct fsxattr fa; + struct fsxattr fa, old_fa; unsigned old_flags; unsigned old_i_flags; int ret = 0; @@ -404,7 +397,6 @@ static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg) if (btrfs_root_readonly(root)) return -EROFS; - memset(&fa, 0, sizeof(fa)); if (copy_from_user(&fa, arg, sizeof(fa))) return -EFAULT; @@ -424,13 +416,11 @@ static int btrfs_ioctl_fssetxattr(struct file *file, void __user *arg) old_flags = binode->flags; old_i_flags = inode->i_flags; - /* We need the capabilities to change append-only or immutable inode */ - if (((old_flags & (BTRFS_INODE_APPEND | BTRFS_INODE_IMMUTABLE)) || - (fa.fsx_xflags & (FS_XFLAG_APPEND | FS_XFLAG_IMMUTABLE))) && - !capable(CAP_LINUX_IMMUTABLE)) { - ret = -EPERM; + simple_fill_fsxattr(&old_fa, + btrfs_inode_flags_to_xflags(binode->flags)); + ret = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa); + if (ret) goto out_unlock; - } if (fa.fsx_xflags & FS_XFLAG_SYNC) binode->flags |= BTRFS_INODE_SYNC; @@ -2930,8 +2920,10 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, inode_lock(inode); err = btrfs_delete_subvolume(dir, dentry); inode_unlock(inode); - if (!err) + if (!err) { + fsnotify_rmdir(dir, dentry); d_delete(dentry); + } out_dput: dput(dentry); diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c index ca2716917e37..a9e2e66152ee 100644 --- a/fs/btrfs/props.c +++ b/fs/btrfs/props.c @@ -332,6 +332,7 @@ static int inherit_props(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info = root->fs_info; int ret; int i; + bool need_reserve = false; if (!test_bit(BTRFS_INODE_HAS_PROPS, &BTRFS_I(parent)->runtime_flags)) @@ -357,11 +358,20 @@ static int inherit_props(struct btrfs_trans_handle *trans, if (ret) continue; - num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); - ret = btrfs_block_rsv_add(root, trans->block_rsv, - num_bytes, BTRFS_RESERVE_NO_FLUSH); - if (ret) - return ret; + /* + * Currently callers should be reserving 1 item for properties, + * since we only have 1 property that we currently support. If + * we add more in the future we need to try and reserve more + * space for them. But we should also revisit how we do space + * reservations if we do add more properties in the future. + */ + if (need_reserve) { + num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); + ret = btrfs_block_rsv_add(root, trans->block_rsv, + num_bytes, BTRFS_RESERVE_NO_FLUSH); + if (ret) + return ret; + } ret = btrfs_setxattr(trans, inode, h->xattr_name, value, strlen(value), 0); @@ -375,9 +385,13 @@ static int inherit_props(struct btrfs_trans_handle *trans, &BTRFS_I(inode)->runtime_flags); } - btrfs_block_rsv_release(fs_info, trans->block_rsv, num_bytes); - if (ret) - return ret; + if (need_reserve) { + btrfs_block_rsv_release(fs_info, trans->block_rsv, + num_bytes); + if (ret) + return ret; + } + need_reserve = true; } return 0; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 2f708f2c4e67..3e6ffbbd8b0a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3830,7 +3830,13 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans, subvol_slot); block->last_snapshot = last_snapshot; block->level = level; - if (bg->flags & BTRFS_BLOCK_GROUP_DATA) + + /* + * If we have bg == NULL, we're called from btrfs_recover_relocation(), + * no one else can modify tree blocks thus we qgroup will not change + * no matter the value of trace_leaf. + */ + if (bg && bg->flags & BTRFS_BLOCK_GROUP_DATA) block->trace_leaf = true; else block->trace_leaf = false; diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 10d9589001a9..bb5bd49573b4 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -747,6 +747,7 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info) u64 total = 0; int i; +again: do { enqueued = 0; mutex_lock(&fs_devices->device_list_mutex); @@ -758,6 +759,10 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info) mutex_unlock(&fs_devices->device_list_mutex); total += enqueued; } while (enqueued && total < 10000); + if (fs_devices->seed) { + fs_devices = fs_devices->seed; + goto again; + } if (enqueued == 0) return; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index a459ecddcce4..22a3c69864fa 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2177,22 +2177,30 @@ static int clean_dirty_subvols(struct reloc_control *rc) struct btrfs_root *root; struct btrfs_root *next; int ret = 0; + int ret2; list_for_each_entry_safe(root, next, &rc->dirty_subvol_roots, reloc_dirty_list) { - struct btrfs_root *reloc_root = root->reloc_root; + if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) { + /* Merged subvolume, cleanup its reloc root */ + struct btrfs_root *reloc_root = root->reloc_root; - clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); - list_del_init(&root->reloc_dirty_list); - root->reloc_root = NULL; - if (reloc_root) { - int ret2; + clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state); + list_del_init(&root->reloc_dirty_list); + root->reloc_root = NULL; + if (reloc_root) { - ret2 = btrfs_drop_snapshot(reloc_root, NULL, 0, 1); + ret2 = btrfs_drop_snapshot(reloc_root, NULL, 0, 1); + if (ret2 < 0 && !ret) + ret = ret2; + } + btrfs_put_fs_root(root); + } else { + /* Orphan reloc tree, just clean it up */ + ret2 = btrfs_drop_snapshot(root, NULL, 0, 1); if (ret2 < 0 && !ret) ret = ret2; } - btrfs_put_fs_root(root); } return ret; } @@ -2480,6 +2488,9 @@ again: } } else { list_del_init(&reloc_root->root_list); + /* Don't forget to queue this reloc root for cleanup */ + list_add_tail(&reloc_root->reloc_dirty_list, + &rc->dirty_subvol_roots); } } diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 1b9a5d0de139..22124122728c 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -132,10 +132,8 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root return -ENOMEM; ret = btrfs_search_slot(trans, root, key, path, 0, 1); - if (ret < 0) { - btrfs_abort_transaction(trans, ret); + if (ret < 0) goto out; - } if (ret > 0) { btrfs_crit(fs_info, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index dd38dfe174df..f7fe4770f0e5 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4999,6 +4999,12 @@ static int send_hole(struct send_ctx *sctx, u64 end) if (offset >= sctx->cur_inode_size) return 0; + /* + * Don't go beyond the inode's i_size due to prealloc extents that start + * after the i_size. + */ + end = min_t(u64, end, sctx->cur_inode_size); + if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) return send_update_extent(sctx, offset, end - offset); @@ -5218,10 +5224,50 @@ static int clone_range(struct send_ctx *sctx, clone_len = min_t(u64, ext_len, len); if (btrfs_file_extent_disk_bytenr(leaf, ei) == disk_byte && - clone_data_offset == data_offset) - ret = send_clone(sctx, offset, clone_len, clone_root); - else + clone_data_offset == data_offset) { + const u64 src_end = clone_root->offset + clone_len; + const u64 sectorsize = SZ_64K; + + /* + * We can't clone the last block, when its size is not + * sector size aligned, into the middle of a file. If we + * do so, the receiver will get a failure (-EINVAL) when + * trying to clone or will silently corrupt the data in + * the destination file if it's on a kernel without the + * fix introduced by commit ac765f83f1397646 + * ("Btrfs: fix data corruption due to cloning of eof + * block). + * + * So issue a clone of the aligned down range plus a + * regular write for the eof block, if we hit that case. + * + * Also, we use the maximum possible sector size, 64K, + * because we don't know what's the sector size of the + * filesystem that receives the stream, so we have to + * assume the largest possible sector size. + */ + if (src_end == clone_src_i_size && + !IS_ALIGNED(src_end, sectorsize) && + offset + clone_len < sctx->cur_inode_size) { + u64 slen; + + slen = ALIGN_DOWN(src_end - clone_root->offset, + sectorsize); + if (slen > 0) { + ret = send_clone(sctx, offset, slen, + clone_root); + if (ret < 0) + goto out; + } + ret = send_extent_data(sctx, offset + slen, + clone_len - slen); + } else { + ret = send_clone(sctx, offset, clone_len, + clone_root); + } + } else { ret = send_extent_data(sctx, offset, clone_len); + } if (ret < 0) goto out; diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 5a5930e3d32b..c1dfc97893ba 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -303,11 +303,12 @@ static ssize_t raid_bytes_show(struct kobject *kobj, return snprintf(buf, PAGE_SIZE, "%llu\n", val); } -static struct attribute *raid_attributes[] = { +static struct attribute *raid_attrs[] = { BTRFS_ATTR_PTR(raid, total_bytes), BTRFS_ATTR_PTR(raid, used_bytes), NULL }; +ATTRIBUTE_GROUPS(raid); static void release_raid_kobj(struct kobject *kobj) { @@ -317,7 +318,7 @@ static void release_raid_kobj(struct kobject *kobj) struct kobj_type btrfs_raid_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = release_raid_kobj, - .default_attrs = raid_attributes, + .default_groups = raid_groups, }; #define SPACE_INFO_ATTR(field) \ @@ -364,6 +365,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, total_bytes_pinned), NULL, }; +ATTRIBUTE_GROUPS(space_info); static void space_info_release(struct kobject *kobj) { @@ -375,7 +377,7 @@ static void space_info_release(struct kobject *kobj) struct kobj_type space_info_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = space_info_release, - .default_attrs = space_info_attrs, + .default_groups = space_info_groups, }; static const struct attribute *allocation_attrs[] = { @@ -825,7 +827,12 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, fs_devs->fsid_kobj.kset = btrfs_kset; error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, parent, "%pU", fs_devs->fsid); - return error; + if (error) { + kobject_put(&fs_devs->fsid_kobj); + return error; + } + + return 0; } int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info) @@ -905,12 +912,10 @@ void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info, ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group); } -static int btrfs_init_debugfs(void) +static void btrfs_init_debugfs(void) { #ifdef CONFIG_DEBUG_FS btrfs_debugfs_root_dentry = debugfs_create_dir("btrfs", NULL); - if (!btrfs_debugfs_root_dentry) - return -ENOMEM; /* * Example code, how to export data through debugfs. @@ -924,7 +929,6 @@ static int btrfs_init_debugfs(void) #endif #endif - return 0; } int __init btrfs_init_sysfs(void) @@ -935,9 +939,7 @@ int __init btrfs_init_sysfs(void) if (!btrfs_kset) return -ENOMEM; - ret = btrfs_init_debugfs(); - if (ret) - goto out1; + btrfs_init_debugfs(); init_feature_attrs(); ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group); @@ -954,7 +956,6 @@ out_remove_group: sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group); out2: debugfs_remove_recursive(btrfs_debugfs_root_dentry); -out1: kset_unregister(btrfs_kset); return ret; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 748cd1598255..96fce4bef4e7 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -107,8 +107,26 @@ static void file_extent_err(const struct extent_buffer *eb, int slot, (!IS_ALIGNED(btrfs_file_extent_##name((leaf), (fi)), (alignment))); \ }) +static u64 file_extent_end(struct extent_buffer *leaf, + struct btrfs_key *key, + struct btrfs_file_extent_item *extent) +{ + u64 end; + u64 len; + + if (btrfs_file_extent_type(leaf, extent) == BTRFS_FILE_EXTENT_INLINE) { + len = btrfs_file_extent_ram_bytes(leaf, extent); + end = ALIGN(key->offset + len, leaf->fs_info->sectorsize); + } else { + len = btrfs_file_extent_num_bytes(leaf, extent); + end = key->offset + len; + } + return end; +} + static int check_extent_data_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) { struct btrfs_fs_info *fs_info = leaf->fs_info; struct btrfs_file_extent_item *fi; @@ -188,6 +206,28 @@ static int check_extent_data_item(struct extent_buffer *leaf, CHECK_FE_ALIGNED(leaf, slot, fi, offset, sectorsize) || CHECK_FE_ALIGNED(leaf, slot, fi, num_bytes, sectorsize)) return -EUCLEAN; + + /* + * Check that no two consecutive file extent items, in the same leaf, + * present ranges that overlap each other. + */ + if (slot > 0 && + prev_key->objectid == key->objectid && + prev_key->type == BTRFS_EXTENT_DATA_KEY) { + struct btrfs_file_extent_item *prev_fi; + u64 prev_end; + + prev_fi = btrfs_item_ptr(leaf, slot - 1, + struct btrfs_file_extent_item); + prev_end = file_extent_end(leaf, prev_key, prev_fi); + if (prev_end > key->offset) { + file_extent_err(leaf, slot - 1, +"file extent end range (%llu) goes beyond start offset (%llu) of the next file extent", + prev_end, key->offset); + return -EUCLEAN; + } + } + return 0; } @@ -774,14 +814,15 @@ static int check_inode_item(struct extent_buffer *leaf, * Common point to switch the item-specific validation. */ static int check_leaf_item(struct extent_buffer *leaf, - struct btrfs_key *key, int slot) + struct btrfs_key *key, int slot, + struct btrfs_key *prev_key) { int ret = 0; struct btrfs_chunk *chunk; switch (key->type) { case BTRFS_EXTENT_DATA_KEY: - ret = check_extent_data_item(leaf, key, slot); + ret = check_extent_data_item(leaf, key, slot, prev_key); break; case BTRFS_EXTENT_CSUM_KEY: ret = check_csum_item(leaf, key, slot); @@ -928,7 +969,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) * Check if the item size and content meet other * criteria */ - ret = check_leaf_item(leaf, &key, slot); + ret = check_leaf_item(leaf, &key, slot, &prev_key); if (ret < 0) return ret; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 6adcd8a2c5c7..3fc8d854d7fb 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3110,6 +3110,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, log->log_transid = root->log_transid; root->log_start_pid = 0; /* + * Update or create log root item under the root's log_mutex to prevent + * races with concurrent log syncs that can lead to failure to update + * log root item because it was not created yet. + */ + ret = update_log_root(trans, log); + /* * IO has been started, blocks of the log tree have WRITTEN flag set * in their headers. new modifications of the log will be written to * new positions. so it's safe to allow log writers to go in. @@ -3128,8 +3134,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&log_root_tree->log_mutex); - ret = update_log_root(trans, log); - mutex_lock(&log_root_tree->log_mutex); if (atomic_dec_and_test(&log_root_tree->log_writers)) { /* atomic_dec_and_test implies a barrier */ @@ -4182,6 +4186,7 @@ fill_holes: *last_extent, 0, 0, len, 0, len, 0, 0, 0); + *last_extent += len; } } } @@ -5477,7 +5482,6 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, { int ret = 0; struct dentry *old_parent = NULL; - struct btrfs_inode *orig_inode = inode; /* * for regular files, if its inode is already on disk, we don't @@ -5497,16 +5501,6 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, } while (1) { - /* - * If we are logging a directory then we start with our inode, - * not our parent's inode, so we need to skip setting the - * logged_trans so that further down in the log code we don't - * think this inode has already been logged. - */ - if (inode != orig_inode) - inode->logged_trans = trans->transid; - smp_mb(); - if (btrfs_must_commit_transaction(trans, inode)) { ret = 1; break; @@ -6383,7 +6377,6 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, * if this directory was already logged any new * names for this file/dir will get recorded */ - smp_mb(); if (dir->logged_trans == trans->transid) return; diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 78b6ba2029e8..95d9aebff2c4 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -213,6 +213,9 @@ int btrfs_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, } out: btrfs_free_path(path); + if (!ret) + set_bit(BTRFS_INODE_COPY_EVERYTHING, + &BTRFS_I(inode)->runtime_flags); return ret; } @@ -236,7 +239,6 @@ int btrfs_setxattr_trans(struct inode *inode, const char *name, inode_inc_iversion(inode); inode->i_ctime = current_time(inode); - set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); out: @@ -388,8 +390,6 @@ static int btrfs_xattr_handler_set_prop(const struct xattr_handler *handler, if (!ret) { inode_inc_iversion(inode); inode->i_ctime = current_time(inode); - set_bit(BTRFS_INODE_COPY_EVERYTHING, - &BTRFS_I(inode)->runtime_flags); ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); } diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index a6ff07cf11d5..3837ca180d52 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -105,10 +105,10 @@ static void zstd_reclaim_timer_fn(struct timer_list *timer) unsigned long reclaim_threshold = jiffies - ZSTD_BTRFS_RECLAIM_JIFFIES; struct list_head *pos, *next; - spin_lock(&wsm.lock); + spin_lock_bh(&wsm.lock); if (list_empty(&wsm.lru_list)) { - spin_unlock(&wsm.lock); + spin_unlock_bh(&wsm.lock); return; } @@ -137,7 +137,7 @@ static void zstd_reclaim_timer_fn(struct timer_list *timer) if (!list_empty(&wsm.lru_list)) mod_timer(&wsm.timer, jiffies + ZSTD_BTRFS_RECLAIM_JIFFIES); - spin_unlock(&wsm.lock); + spin_unlock_bh(&wsm.lock); } /* @@ -198,7 +198,7 @@ static void zstd_cleanup_workspace_manager(void) struct workspace *workspace; int i; - spin_lock(&wsm.lock); + spin_lock_bh(&wsm.lock); for (i = 0; i < ZSTD_BTRFS_MAX_LEVEL; i++) { while (!list_empty(&wsm.idle_ws[i])) { workspace = container_of(wsm.idle_ws[i].next, @@ -208,7 +208,7 @@ static void zstd_cleanup_workspace_manager(void) zstd_free_workspace(&workspace->list); } } - spin_unlock(&wsm.lock); + spin_unlock_bh(&wsm.lock); del_timer_sync(&wsm.timer); } @@ -230,7 +230,7 @@ static struct list_head *zstd_find_workspace(unsigned int level) struct workspace *workspace; int i = level - 1; - spin_lock(&wsm.lock); + spin_lock_bh(&wsm.lock); for_each_set_bit_from(i, &wsm.active_map, ZSTD_BTRFS_MAX_LEVEL) { if (!list_empty(&wsm.idle_ws[i])) { ws = wsm.idle_ws[i].next; @@ -242,11 +242,11 @@ static struct list_head *zstd_find_workspace(unsigned int level) list_del(&workspace->lru_list); if (list_empty(&wsm.idle_ws[i])) clear_bit(i, &wsm.active_map); - spin_unlock(&wsm.lock); + spin_unlock_bh(&wsm.lock); return ws; } } - spin_unlock(&wsm.lock); + spin_unlock_bh(&wsm.lock); return NULL; } @@ -305,7 +305,7 @@ static void zstd_put_workspace(struct list_head *ws) { struct workspace *workspace = list_to_workspace(ws); - spin_lock(&wsm.lock); + spin_lock_bh(&wsm.lock); /* A node is only taken off the lru if we are the corresponding level */ if (workspace->req_level == workspace->level) { @@ -325,7 +325,7 @@ static void zstd_put_workspace(struct list_head *ws) list_add(&workspace->list, &wsm.idle_ws[workspace->level - 1]); workspace->req_level = 0; - spin_unlock(&wsm.lock); + spin_unlock_bh(&wsm.lock); if (workspace->level == ZSTD_BTRFS_MAX_LEVEL) cond_wake_up(&wsm.wait); diff --git a/fs/buffer.c b/fs/buffer.c index 0faa41fb4c88..49a871570092 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * @@ -2085,38 +2086,6 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, } EXPORT_SYMBOL(block_write_begin); -void __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, - struct page *page) -{ - loff_t old_size = inode->i_size; - bool i_size_changed = false; - - /* - * No need to use i_size_read() here, the i_size cannot change under us - * because we hold i_rwsem. - * - * But it's important to update i_size while still holding page lock: - * page writeout could otherwise come in and zero beyond i_size. - */ - if (pos + copied > inode->i_size) { - i_size_write(inode, pos + copied); - i_size_changed = true; - } - - unlock_page(page); - - if (old_size < pos) - pagecache_isize_extended(inode, old_size, pos); - /* - * Don't mark the inode dirty under page lock. First, it unnecessarily - * makes the holding time of page lock longer. Second, it forces lock - * ordering of page lock and transaction start for journaling - * filesystems. - */ - if (i_size_changed) - mark_inode_dirty(inode); -} - int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) @@ -2157,9 +2126,37 @@ int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { + struct inode *inode = mapping->host; + loff_t old_size = inode->i_size; + bool i_size_changed = false; + copied = block_write_end(file, mapping, pos, len, copied, page, fsdata); - __generic_write_end(mapping->host, pos, copied, page); + + /* + * No need to use i_size_read() here, the i_size cannot change under us + * because we hold i_rwsem. + * + * But it's important to update i_size while still holding page lock: + * page writeout could otherwise come in and zero beyond i_size. + */ + if (pos + copied > inode->i_size) { + i_size_write(inode, pos + copied); + i_size_changed = true; + } + + unlock_page(page); put_page(page); + + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); + /* + * Don't mark the inode dirty under page lock. First, it unnecessarily + * makes the holding time of page lock longer. Second, it forces lock + * ordering of page lock and transaction start for journaling + * filesystems. + */ + if (i_size_changed) + mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig index 80e9c6167f0b..ae559ed5b3b3 100644 --- a/fs/cachefiles/Kconfig +++ b/fs/cachefiles/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config CACHEFILES tristate "Filesystem caching on files" diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index 4a717d400807..dfb14dbddf51 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Bind and unbind a cache from the filesystem backing it * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 3fdee214a5bb..752c1e43416f 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Daemon interface * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 222bc5d8b62c..4cea5fbf695e 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache interface to CacheFiles * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/slab.h> diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index d2f6f996e65a..cf9bd6401c2d 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* General netfs cache on cache files internal defs * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #ifdef pr_fmt diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c index 33b58c60f2d1..be96f5fc5cac 100644 --- a/fs/cachefiles/key.c +++ b/fs/cachefiles/key.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Key to pathname encoder * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/slab.h> diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c index f54d3f5b2e40..ddf0cd58d60c 100644 --- a/fs/cachefiles/main.c +++ b/fs/cachefiles/main.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Network filesystem caching backend to use cache files on a premounted * filesystem * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 1645fcfd9691..ecc8ecbbfa5a 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles path walking and related routines * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/module.h> @@ -20,7 +16,6 @@ #include <linux/namei.h> #include <linux/security.h> #include <linux/slab.h> -#include <linux/xattr.h> #include "internal.h" #define CACHEFILES_KEYBUF_SIZE 512 diff --git a/fs/cachefiles/proc.c b/fs/cachefiles/proc.c index 0ce1aa56b67f..6e67aea0f24e 100644 --- a/fs/cachefiles/proc.c +++ b/fs/cachefiles/proc.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles statistics * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 8a577409d030..44a3ce1e4ce4 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Storage object read/write * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/mount.h> diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c index 31bbc0528b11..aec13fd94692 100644 --- a/fs/cachefiles/security.c +++ b/fs/cachefiles/security.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles security management * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/fs.h> diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 511e6c68156a..72e42438f3d7 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* CacheFiles extended attribute management * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig index 52095f473464..7f7d92d6b024 100644 --- a/fs/ceph/Kconfig +++ b/fs/ceph/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config CEPH_FS tristate "Ceph distributed file system" depends on INET diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 5f0103f40079..8a19c249036c 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -1,21 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/ceph/acl.c * * Copyright (C) 2013 Guangliang Zhao, <lucienchao@gmail.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License v2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/ceph/ceph_debug.h> diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 1bf3502bdd6f..bc90cf6ad7ed 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -1,24 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Ceph cache definitions. * * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved. * Written by Milosz Tanski (milosz@adfin.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #include "super.h" diff --git a/fs/ceph/cache.h b/fs/ceph/cache.h index 7e72c7594f0c..e486fac3434d 100644 --- a/fs/ceph/cache.h +++ b/fs/ceph/cache.h @@ -1,24 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Ceph cache definitions. * * Copyright (C) 2013 by Adfin Solutions, Inc. All Rights Reserved. * Written by Milosz Tanski (milosz@adfin.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to: - * Free Software Foundation - * 51 Franklin Street, Fifth Floor - * Boston, MA 02111-1301 USA - * */ #ifndef _CEPH_CACHE_H diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 36a8dc699448..0176241eaea7 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -892,8 +892,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) int have = ci->i_snap_caps; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask %p snap issued %s" - " (mask %s)\n", &ci->vfs_inode, + dout("__ceph_caps_issued_mask ino 0x%lx snap issued %s" + " (mask %s)\n", ci->vfs_inode.i_ino, ceph_cap_string(have), ceph_cap_string(mask)); return 1; @@ -904,8 +904,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) if (!__cap_is_valid(cap)) continue; if ((cap->issued & mask) == mask) { - dout("__ceph_caps_issued_mask %p cap %p issued %s" - " (mask %s)\n", &ci->vfs_inode, cap, + dout("__ceph_caps_issued_mask ino 0x%lx cap %p issued %s" + " (mask %s)\n", ci->vfs_inode.i_ino, cap, ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) @@ -916,8 +916,8 @@ int __ceph_caps_issued_mask(struct ceph_inode_info *ci, int mask, int touch) /* does a combination of caps satisfy mask? */ have |= cap->issued; if ((have & mask) == mask) { - dout("__ceph_caps_issued_mask %p combo issued %s" - " (mask %s)\n", &ci->vfs_inode, + dout("__ceph_caps_issued_mask ino 0x%lx combo issued %s" + " (mask %s)\n", ci->vfs_inode.i_ino, ceph_cap_string(cap->issued), ceph_cap_string(mask)); if (touch) { @@ -2257,8 +2257,6 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) if (datasync) goto out; - inode_lock(inode); - dirty = try_flush_caps(inode, &flush_tid); dout("fsync dirty caps are %s\n", ceph_cap_string(dirty)); @@ -2273,7 +2271,6 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = wait_event_interruptible(ci->i_cap_wq, caps_are_flushed(inode, flush_tid)); } - inode_unlock(inode); out: dout("fsync %p%s result=%d\n", inode, datasync ? " datasync" : "", ret); return ret; @@ -2528,9 +2525,14 @@ static void __take_cap_refs(struct ceph_inode_info *ci, int got, * to (when applicable), and check against max_size here as well. * Note that caller is responsible for ensuring max_size increases are * requested from the MDS. + * + * Returns 0 if caps were not able to be acquired (yet), a 1 if they were, + * or a negative error code. + * + * FIXME: how does a 0 return differ from -EAGAIN? */ static int try_get_cap_refs(struct ceph_inode_info *ci, int need, int want, - loff_t endoff, bool nonblock, int *got, int *err) + loff_t endoff, bool nonblock, int *got) { struct inode *inode = &ci->vfs_inode; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; @@ -2550,8 +2552,7 @@ again: if ((file_wanted & need) != need) { dout("try_get_cap_refs need %s file_wanted %s, EBADF\n", ceph_cap_string(need), ceph_cap_string(file_wanted)); - *err = -EBADF; - ret = 1; + ret = -EBADF; goto out_unlock; } @@ -2572,10 +2573,8 @@ again: if (endoff >= 0 && endoff > (loff_t)ci->i_max_size) { dout("get_cap_refs %p endoff %llu > maxsize %llu\n", inode, endoff, ci->i_max_size); - if (endoff > ci->i_requested_max_size) { - *err = -EAGAIN; - ret = 1; - } + if (endoff > ci->i_requested_max_size) + ret = -EAGAIN; goto out_unlock; } /* @@ -2610,8 +2609,7 @@ again: * task isn't in TASK_RUNNING state */ if (nonblock) { - *err = -EAGAIN; - ret = 1; + ret = -EAGAIN; goto out_unlock; } @@ -2640,8 +2638,7 @@ again: if (session_readonly) { dout("get_cap_refs %p needed %s but mds%d readonly\n", inode, ceph_cap_string(need), ci->i_auth_cap->mds); - *err = -EROFS; - ret = 1; + ret = -EROFS; goto out_unlock; } @@ -2650,16 +2647,14 @@ again: if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) { dout("get_cap_refs %p forced umount\n", inode); - *err = -EIO; - ret = 1; + ret = -EIO; goto out_unlock; } mds_wanted = __ceph_caps_mds_wanted(ci, false); if (need & ~(mds_wanted & need)) { dout("get_cap_refs %p caps were dropped" " (session killed?)\n", inode); - *err = -ESTALE; - ret = 1; + ret = -ESTALE; goto out_unlock; } if (!(file_wanted & ~mds_wanted)) @@ -2710,7 +2705,7 @@ static void check_max_size(struct inode *inode, loff_t endoff) int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, bool nonblock, int *got) { - int ret, err = 0; + int ret; BUG_ON(need & ~CEPH_CAP_FILE_RD); BUG_ON(want & ~(CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO|CEPH_CAP_FILE_SHARED)); @@ -2718,15 +2713,8 @@ int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, if (ret < 0) return ret; - ret = try_get_cap_refs(ci, need, want, 0, nonblock, got, &err); - if (ret) { - if (err == -EAGAIN) { - ret = 0; - } else if (err < 0) { - ret = err; - } - } - return ret; + ret = try_get_cap_refs(ci, need, want, 0, nonblock, got); + return ret == -EAGAIN ? 0 : ret; } /* @@ -2737,7 +2725,7 @@ int ceph_try_get_caps(struct ceph_inode_info *ci, int need, int want, int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, loff_t endoff, int *got, struct page **pinned_page) { - int _got, ret, err = 0; + int _got, ret; ret = ceph_pool_perm_check(ci, need); if (ret < 0) @@ -2747,21 +2735,17 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, if (endoff > 0) check_max_size(&ci->vfs_inode, endoff); - err = 0; _got = 0; ret = try_get_cap_refs(ci, need, want, endoff, - false, &_got, &err); - if (ret) { - if (err == -EAGAIN) - continue; - if (err < 0) - ret = err; - } else { + false, &_got); + if (ret == -EAGAIN) + continue; + if (!ret) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(&ci->i_cap_wq, &wait); - while (!try_get_cap_refs(ci, need, want, endoff, - true, &_got, &err)) { + while (!(ret = try_get_cap_refs(ci, need, want, endoff, + true, &_got))) { if (signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -2770,14 +2754,11 @@ int ceph_get_caps(struct ceph_inode_info *ci, int need, int want, } remove_wait_queue(&ci->i_cap_wq, &wait); - - if (err == -EAGAIN) + if (ret == -EAGAIN) continue; - if (err < 0) - ret = err; } if (ret < 0) { - if (err == -ESTALE) { + if (ret == -ESTALE) { /* session was killed, try renew caps */ ret = ceph_renew_caps(&ci->vfs_inode); if (ret == 0) @@ -3011,8 +2992,10 @@ void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr, } if (complete_capsnap) wake_up_all(&ci->i_cap_wq); - while (put-- > 0) - iput(inode); + while (put-- > 0) { + /* avoid calling iput_final() in osd dispatch threads */ + ceph_async_iput(inode); + } } /* @@ -3983,8 +3966,9 @@ void ceph_handle_caps(struct ceph_mds_session *session, done: mutex_unlock(&session->s_mutex); done_unlocked: - iput(inode); ceph_put_string(extra_info.pool_ns); + /* avoid calling iput_final() in mds dispatch threads */ + ceph_async_iput(inode); return; flush_cap_releases: @@ -4030,7 +4014,8 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc) if (inode) { dout("check_delayed_caps on %p\n", inode); ceph_check_caps(ci, flags, NULL); - iput(inode); + /* avoid calling iput_final() in tick thread */ + ceph_async_iput(inode); } } spin_unlock(&mdsc->cap_delay_lock); @@ -4099,7 +4084,7 @@ void ceph_put_fmode(struct ceph_inode_info *ci, int fmode) } /* - * For a soon-to-be unlinked file, drop the AUTH_RDCACHE caps. If it + * For a soon-to-be unlinked file, drop the LINK caps. If it * looks like the link count will hit 0, drop any other caps (other * than PIN) we don't specifically want (due to the file still being * open). diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 98365e74cb4a..83cd41fa2b01 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -37,7 +37,7 @@ static int mdsmap_show(struct seq_file *s, void *p) struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr; int state = mdsmap->m_info[i].state; seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, - ceph_pr_addr(&addr->in_addr), + ceph_pr_addr(addr), ceph_mds_state_name(state)); } return 0; @@ -88,7 +88,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_dentry, path ? path : ""); spin_unlock(&req->r_dentry->d_lock); - kfree(path); + ceph_mdsc_free_path(path, pathlen); } else if (req->r_path1) { seq_printf(s, " #%llx/%s", req->r_ino1.ino, req->r_path1); @@ -108,7 +108,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_old_dentry, path ? path : ""); spin_unlock(&req->r_old_dentry->d_lock); - kfree(path); + ceph_mdsc_free_path(path, pathlen); } else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) { if (req->r_ino2.ino) seq_printf(s, " #%llx/%s", req->r_ino2.ino, @@ -124,18 +124,48 @@ static int mdsc_show(struct seq_file *s, void *p) return 0; } +static int caps_show_cb(struct inode *inode, struct ceph_cap *cap, void *p) +{ + struct seq_file *s = p; + + seq_printf(s, "0x%-17lx%-17s%-17s\n", inode->i_ino, + ceph_cap_string(cap->issued), + ceph_cap_string(cap->implemented)); + return 0; +} + static int caps_show(struct seq_file *s, void *p) { struct ceph_fs_client *fsc = s->private; - int total, avail, used, reserved, min; + struct ceph_mds_client *mdsc = fsc->mdsc; + int total, avail, used, reserved, min, i; ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min); seq_printf(s, "total\t\t%d\n" "avail\t\t%d\n" "used\t\t%d\n" "reserved\t%d\n" - "min\t%d\n", + "min\t\t%d\n\n", total, avail, used, reserved, min); + seq_printf(s, "ino issued implemented\n"); + seq_printf(s, "-----------------------------------------------\n"); + + mutex_lock(&mdsc->mutex); + for (i = 0; i < mdsc->max_sessions; i++) { + struct ceph_mds_session *session; + + session = __ceph_lookup_mds_session(mdsc, i); + if (!session) + continue; + mutex_unlock(&mdsc->mutex); + mutex_lock(&session->s_mutex); + ceph_iterate_session_caps(session, caps_show_cb, s); + mutex_unlock(&session->s_mutex); + ceph_put_mds_session(session); + mutex_lock(&mdsc->mutex); + } + mutex_unlock(&mdsc->mutex); + return 0; } @@ -215,21 +245,17 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) debugfs_remove(fsc->debugfs_mdsc); } -int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) +void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) { char name[100]; - int err = -ENOMEM; dout("ceph_fs_debugfs_init\n"); - BUG_ON(!fsc->client->debugfs_dir); fsc->debugfs_congestion_kb = debugfs_create_file("writeback_congestion_kb", 0600, fsc->client->debugfs_dir, fsc, &congestion_kb_fops); - if (!fsc->debugfs_congestion_kb) - goto out; snprintf(name, sizeof(name), "../../bdi/%s", dev_name(fsc->sb->s_bdi->dev)); @@ -237,52 +263,36 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) debugfs_create_symlink("bdi", fsc->client->debugfs_dir, name); - if (!fsc->debugfs_bdi) - goto out; fsc->debugfs_mdsmap = debugfs_create_file("mdsmap", 0400, fsc->client->debugfs_dir, fsc, &mdsmap_show_fops); - if (!fsc->debugfs_mdsmap) - goto out; fsc->debugfs_mds_sessions = debugfs_create_file("mds_sessions", 0400, fsc->client->debugfs_dir, fsc, &mds_sessions_show_fops); - if (!fsc->debugfs_mds_sessions) - goto out; fsc->debugfs_mdsc = debugfs_create_file("mdsc", 0400, fsc->client->debugfs_dir, fsc, &mdsc_show_fops); - if (!fsc->debugfs_mdsc) - goto out; fsc->debugfs_caps = debugfs_create_file("caps", 0400, fsc->client->debugfs_dir, fsc, &caps_show_fops); - if (!fsc->debugfs_caps) - goto out; - - return 0; - -out: - ceph_fs_debugfs_cleanup(fsc); - return err; } #else /* CONFIG_DEBUG_FS */ -int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) +void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) { return 0; } diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 3c59ad180ef0..d3ef7ee429ec 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -22,18 +22,77 @@ struct ceph_nfs_confh { u64 ino, parent_ino; } __attribute__ ((packed)); +/* + * fh for snapped inode + */ +struct ceph_nfs_snapfh { + u64 ino; + u64 snapid; + u64 parent_ino; + u32 hash; +} __attribute__ ((packed)); + +static int ceph_encode_snapfh(struct inode *inode, u32 *rawfh, int *max_len, + struct inode *parent_inode) +{ + const static int snap_handle_length = + sizeof(struct ceph_nfs_snapfh) >> 2; + struct ceph_nfs_snapfh *sfh = (void *)rawfh; + u64 snapid = ceph_snap(inode); + int ret; + bool no_parent = true; + + if (*max_len < snap_handle_length) { + *max_len = snap_handle_length; + ret = FILEID_INVALID; + goto out; + } + + ret = -EINVAL; + if (snapid != CEPH_SNAPDIR) { + struct inode *dir; + struct dentry *dentry = d_find_alias(inode); + if (!dentry) + goto out; + + rcu_read_lock(); + dir = d_inode_rcu(dentry->d_parent); + if (ceph_snap(dir) != CEPH_SNAPDIR) { + sfh->parent_ino = ceph_ino(dir); + sfh->hash = ceph_dentry_hash(dir, dentry); + no_parent = false; + } + rcu_read_unlock(); + dput(dentry); + } + + if (no_parent) { + if (!S_ISDIR(inode->i_mode)) + goto out; + sfh->parent_ino = sfh->ino; + sfh->hash = 0; + } + sfh->ino = ceph_ino(inode); + sfh->snapid = snapid; + + *max_len = snap_handle_length; + ret = FILEID_BTRFS_WITH_PARENT; +out: + dout("encode_snapfh %llx.%llx ret=%d\n", ceph_vinop(inode), ret); + return ret; +} + static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, struct inode *parent_inode) { + const static int handle_length = + sizeof(struct ceph_nfs_fh) >> 2; + const static int connected_handle_length = + sizeof(struct ceph_nfs_confh) >> 2; int type; - struct ceph_nfs_fh *fh = (void *)rawfh; - struct ceph_nfs_confh *cfh = (void *)rawfh; - int connected_handle_length = sizeof(*cfh)/4; - int handle_length = sizeof(*fh)/4; - /* don't re-export snaps */ if (ceph_snap(inode) != CEPH_NOSNAP) - return -EINVAL; + return ceph_encode_snapfh(inode, rawfh, max_len, parent_inode); if (parent_inode && (*max_len < connected_handle_length)) { *max_len = connected_handle_length; @@ -44,6 +103,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, } if (parent_inode) { + struct ceph_nfs_confh *cfh = (void *)rawfh; dout("encode_fh %llx with parent %llx\n", ceph_ino(inode), ceph_ino(parent_inode)); cfh->ino = ceph_ino(inode); @@ -51,6 +111,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, *max_len = connected_handle_length; type = FILEID_INO32_GEN_PARENT; } else { + struct ceph_nfs_fh *fh = (void *)rawfh; dout("encode_fh %llx\n", ceph_ino(inode)); fh->ino = ceph_ino(inode); *max_len = handle_length; @@ -59,7 +120,7 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, return type; } -static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) +static struct inode *__lookup_inode(struct super_block *sb, u64 ino) { struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc; struct inode *inode; @@ -81,7 +142,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) mask = CEPH_STAT_CAP_INODE; if (ceph_security_xattr_wanted(d_inode(sb->s_root))) mask |= CEPH_CAP_XATTR_SHARED; - req->r_args.getattr.mask = cpu_to_le32(mask); + req->r_args.lookupino.mask = cpu_to_le32(mask); req->r_ino1 = vino; req->r_num_caps = 1; @@ -91,16 +152,114 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) ihold(inode); ceph_mdsc_put_request(req); if (!inode) - return ERR_PTR(-ESTALE); - if (inode->i_nlink == 0) { - iput(inode); - return ERR_PTR(-ESTALE); - } + return err < 0 ? ERR_PTR(err) : ERR_PTR(-ESTALE); } + return inode; +} + +struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino) +{ + struct inode *inode = __lookup_inode(sb, ino); + if (IS_ERR(inode)) + return inode; + if (inode->i_nlink == 0) { + iput(inode); + return ERR_PTR(-ESTALE); + } + return inode; +} +static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino) +{ + struct inode *inode = __lookup_inode(sb, ino); + if (IS_ERR(inode)) + return ERR_CAST(inode); + if (inode->i_nlink == 0) { + iput(inode); + return ERR_PTR(-ESTALE); + } return d_obtain_alias(inode); } +static struct dentry *__snapfh_to_dentry(struct super_block *sb, + struct ceph_nfs_snapfh *sfh, + bool want_parent) +{ + struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc; + struct ceph_mds_request *req; + struct inode *inode; + struct ceph_vino vino; + int mask; + int err; + bool unlinked = false; + + if (want_parent) { + vino.ino = sfh->parent_ino; + if (sfh->snapid == CEPH_SNAPDIR) + vino.snap = CEPH_NOSNAP; + else if (sfh->ino == sfh->parent_ino) + vino.snap = CEPH_SNAPDIR; + else + vino.snap = sfh->snapid; + } else { + vino.ino = sfh->ino; + vino.snap = sfh->snapid; + } + inode = ceph_find_inode(sb, vino); + if (inode) + return d_obtain_alias(inode); + + req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPINO, + USE_ANY_MDS); + if (IS_ERR(req)) + return ERR_CAST(req); + + mask = CEPH_STAT_CAP_INODE; + if (ceph_security_xattr_wanted(d_inode(sb->s_root))) + mask |= CEPH_CAP_XATTR_SHARED; + req->r_args.lookupino.mask = cpu_to_le32(mask); + if (vino.snap < CEPH_NOSNAP) { + req->r_args.lookupino.snapid = cpu_to_le64(vino.snap); + if (!want_parent && sfh->ino != sfh->parent_ino) { + req->r_args.lookupino.parent = + cpu_to_le64(sfh->parent_ino); + req->r_args.lookupino.hash = + cpu_to_le32(sfh->hash); + } + } + + req->r_ino1 = vino; + req->r_num_caps = 1; + err = ceph_mdsc_do_request(mdsc, NULL, req); + inode = req->r_target_inode; + if (inode) { + if (vino.snap == CEPH_SNAPDIR) { + if (inode->i_nlink == 0) + unlinked = true; + inode = ceph_get_snapdir(inode); + } else if (ceph_snap(inode) == vino.snap) { + ihold(inode); + } else { + /* mds does not support lookup snapped inode */ + err = -EOPNOTSUPP; + inode = NULL; + } + } + ceph_mdsc_put_request(req); + + if (want_parent) { + dout("snapfh_to_parent %llx.%llx\n err=%d\n", + vino.ino, vino.snap, err); + } else { + dout("snapfh_to_dentry %llx.%llx parent %llx hash %x err=%d", + vino.ino, vino.snap, sfh->parent_ino, sfh->hash, err); + } + if (!inode) + return ERR_PTR(-ESTALE); + /* see comments in ceph_get_parent() */ + return unlinked ? d_obtain_root(inode) : d_obtain_alias(inode); +} + /* * convert regular fh to dentry */ @@ -110,6 +269,11 @@ static struct dentry *ceph_fh_to_dentry(struct super_block *sb, { struct ceph_nfs_fh *fh = (void *)fid->raw; + if (fh_type == FILEID_BTRFS_WITH_PARENT) { + struct ceph_nfs_snapfh *sfh = (void *)fid->raw; + return __snapfh_to_dentry(sb, sfh, false); + } + if (fh_type != FILEID_INO32_GEN && fh_type != FILEID_INO32_GEN_PARENT) return NULL; @@ -163,13 +327,49 @@ static struct dentry *__get_parent(struct super_block *sb, static struct dentry *ceph_get_parent(struct dentry *child) { - /* don't re-export snaps */ - if (ceph_snap(d_inode(child)) != CEPH_NOSNAP) - return ERR_PTR(-EINVAL); - - dout("get_parent %p ino %llx.%llx\n", - child, ceph_vinop(d_inode(child))); - return __get_parent(child->d_sb, child, 0); + struct inode *inode = d_inode(child); + struct dentry *dn; + + if (ceph_snap(inode) != CEPH_NOSNAP) { + struct inode* dir; + bool unlinked = false; + /* do not support non-directory */ + if (!d_is_dir(child)) { + dn = ERR_PTR(-EINVAL); + goto out; + } + dir = __lookup_inode(inode->i_sb, ceph_ino(inode)); + if (IS_ERR(dir)) { + dn = ERR_CAST(dir); + goto out; + } + /* There can be multiple paths to access snapped inode. + * For simplicity, treat snapdir of head inode as parent */ + if (ceph_snap(inode) != CEPH_SNAPDIR) { + struct inode *snapdir = ceph_get_snapdir(dir); + if (dir->i_nlink == 0) + unlinked = true; + iput(dir); + if (IS_ERR(snapdir)) { + dn = ERR_CAST(snapdir); + goto out; + } + dir = snapdir; + } + /* If directory has already been deleted, futher get_parent + * will fail. Do not mark snapdir dentry as disconnected, + * this prevent exportfs from doing futher get_parent. */ + if (unlinked) + dn = d_obtain_root(dir); + else + dn = d_obtain_alias(dir); + } else { + dn = __get_parent(child->d_sb, child, 0); + } +out: + dout("get_parent %p ino %llx.%llx err=%ld\n", + child, ceph_vinop(inode), (IS_ERR(dn) ? PTR_ERR(dn) : 0)); + return dn; } /* @@ -182,6 +382,11 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, struct ceph_nfs_confh *cfh = (void *)fid->raw; struct dentry *dentry; + if (fh_type == FILEID_BTRFS_WITH_PARENT) { + struct ceph_nfs_snapfh *sfh = (void *)fid->raw; + return __snapfh_to_dentry(sb, sfh, true); + } + if (fh_type != FILEID_INO32_GEN_PARENT) return NULL; if (fh_len < sizeof(*cfh) / 4) @@ -194,14 +399,115 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, return dentry; } +static int __get_snap_name(struct dentry *parent, char *name, + struct dentry *child) +{ + struct inode *inode = d_inode(child); + struct inode *dir = d_inode(parent); + struct ceph_fs_client *fsc = ceph_inode_to_client(inode); + struct ceph_mds_request *req = NULL; + char *last_name = NULL; + unsigned next_offset = 2; + int err = -EINVAL; + + if (ceph_ino(inode) != ceph_ino(dir)) + goto out; + if (ceph_snap(inode) == CEPH_SNAPDIR) { + if (ceph_snap(dir) == CEPH_NOSNAP) { + strcpy(name, fsc->mount_options->snapdir_name); + err = 0; + } + goto out; + } + if (ceph_snap(dir) != CEPH_SNAPDIR) + goto out; + + while (1) { + struct ceph_mds_reply_info_parsed *rinfo; + struct ceph_mds_reply_dir_entry *rde; + int i; + + req = ceph_mdsc_create_request(fsc->mdsc, CEPH_MDS_OP_LSSNAP, + USE_AUTH_MDS); + if (IS_ERR(req)) { + err = PTR_ERR(req); + req = NULL; + goto out; + } + err = ceph_alloc_readdir_reply_buffer(req, inode); + if (err) + goto out; + + req->r_direct_mode = USE_AUTH_MDS; + req->r_readdir_offset = next_offset; + req->r_args.readdir.flags = + cpu_to_le16(CEPH_READDIR_REPLY_BITFLAGS); + if (last_name) { + req->r_path2 = last_name; + last_name = NULL; + } + + req->r_inode = dir; + ihold(dir); + req->r_dentry = dget(parent); + + inode_lock(dir); + err = ceph_mdsc_do_request(fsc->mdsc, NULL, req); + inode_unlock(dir); + + if (err < 0) + goto out; + + rinfo = &req->r_reply_info; + for (i = 0; i < rinfo->dir_nr; i++) { + rde = rinfo->dir_entries + i; + BUG_ON(!rde->inode.in); + if (ceph_snap(inode) == + le64_to_cpu(rde->inode.in->snapid)) { + memcpy(name, rde->name, rde->name_len); + name[rde->name_len] = '\0'; + err = 0; + goto out; + } + } + + if (rinfo->dir_end) + break; + + BUG_ON(rinfo->dir_nr <= 0); + rde = rinfo->dir_entries + (rinfo->dir_nr - 1); + next_offset += rinfo->dir_nr; + last_name = kstrndup(rde->name, rde->name_len, GFP_KERNEL); + if (!last_name) { + err = -ENOMEM; + goto out; + } + + ceph_mdsc_put_request(req); + req = NULL; + } + err = -ENOENT; +out: + if (req) + ceph_mdsc_put_request(req); + kfree(last_name); + dout("get_snap_name %p ino %llx.%llx err=%d\n", + child, ceph_vinop(inode), err); + return err; +} + static int ceph_get_name(struct dentry *parent, char *name, struct dentry *child) { struct ceph_mds_client *mdsc; struct ceph_mds_request *req; + struct inode *inode = d_inode(child); int err; - mdsc = ceph_inode_to_client(d_inode(child))->mdsc; + if (ceph_snap(inode) != CEPH_NOSNAP) + return __get_snap_name(parent, name, child); + + mdsc = ceph_inode_to_client(inode)->mdsc; req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_LOOKUPNAME, USE_ANY_MDS); if (IS_ERR(req)) @@ -209,8 +515,8 @@ static int ceph_get_name(struct dentry *parent, char *name, inode_lock(d_inode(parent)); - req->r_inode = d_inode(child); - ihold(d_inode(child)); + req->r_inode = inode; + ihold(inode); req->r_ino2 = ceph_vino(d_inode(parent)); req->r_parent = d_inode(parent); set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); @@ -224,10 +530,10 @@ static int ceph_get_name(struct dentry *parent, char *name, memcpy(name, rinfo->dname, rinfo->dname_len); name[rinfo->dname_len] = 0; dout("get_name %p ino %llx.%llx name %s\n", - child, ceph_vinop(d_inode(child)), name); + child, ceph_vinop(inode), name); } else { dout("get_name %p ino %llx.%llx err %d\n", - child, ceph_vinop(d_inode(child)), err); + child, ceph_vinop(inode), err); } ceph_mdsc_put_request(req); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 84725b53ac21..c5517ffeb11c 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -791,7 +791,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) if (aio_work) { INIT_WORK(&aio_work->work, ceph_aio_retry_work); aio_work->req = req; - queue_work(ceph_inode_to_client(inode)->wb_wq, + queue_work(ceph_inode_to_client(inode)->inode_wq, &aio_work->work); return; } @@ -929,7 +929,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, dout("sync_direct_%s on file %p %lld~%u snapc %p seq %lld\n", (write ? "write" : "read"), file, pos, (unsigned)count, - snapc, snapc->seq); + snapc, snapc ? snapc->seq : 0); ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + count - 1); @@ -1889,9 +1889,9 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode, return 0; } -static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, - struct file *dst_file, loff_t dst_off, - size_t len, unsigned int flags) +static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, + size_t len, unsigned int flags) { struct inode *src_inode = file_inode(src_file); struct inode *dst_inode = file_inode(dst_file); @@ -1909,6 +1909,8 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, if (src_inode == dst_inode) return -EINVAL; + if (src_inode->i_sb != dst_inode->i_sb) + return -EXDEV; if (ceph_snap(dst_inode) != CEPH_NOSNAP) return -EROFS; @@ -2100,6 +2102,21 @@ out: return ret; } +static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, + size_t len, unsigned int flags) +{ + ssize_t ret; + + ret = __ceph_copy_file_range(src_file, src_off, dst_file, dst_off, + len, flags); + + if (ret == -EOPNOTSUPP || ret == -EXDEV) + ret = generic_copy_file_range(src_file, src_off, dst_file, + dst_off, len, flags); + return ret; +} + const struct file_operations ceph_file_fops = { .open = ceph_open, .release = ceph_release, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 35dae6d5493a..761451f36e2d 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -33,9 +33,7 @@ static const struct inode_operations ceph_symlink_iops; -static void ceph_invalidate_work(struct work_struct *work); -static void ceph_writeback_work(struct work_struct *work); -static void ceph_vmtruncate_work(struct work_struct *work); +static void ceph_inode_work(struct work_struct *work); /* * find or create an inode, given the ceph ino number @@ -509,10 +507,8 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ci->i_snap_realm_item); INIT_LIST_HEAD(&ci->i_snap_flush_item); - INIT_WORK(&ci->i_wb_work, ceph_writeback_work); - INIT_WORK(&ci->i_pg_inv_work, ceph_invalidate_work); - - INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work); + INIT_WORK(&ci->i_work, ceph_inode_work); + ci->i_work_mask = 0; ceph_fscache_inode_init(ci); @@ -1480,7 +1476,8 @@ static int readdir_prepopulate_inodes_only(struct ceph_mds_request *req, pr_err("fill_inode badness on %p got %d\n", in, rc); err = rc; } - iput(in); + /* avoid calling iput_final() in mds dispatch threads */ + ceph_async_iput(in); } return err; @@ -1678,8 +1675,11 @@ retry_lookup: &req->r_caps_reservation); if (ret < 0) { pr_err("fill_inode badness on %p\n", in); - if (d_really_is_negative(dn)) - iput(in); + if (d_really_is_negative(dn)) { + /* avoid calling iput_final() in mds + * dispatch threads */ + ceph_async_iput(in); + } d_drop(dn); err = ret; goto next_item; @@ -1689,7 +1689,7 @@ retry_lookup: if (ceph_security_xattr_deadlock(in)) { dout(" skip splicing dn %p to inode %p" " (security xattr deadlock)\n", dn, in); - iput(in); + ceph_async_iput(in); skipped++; goto next_item; } @@ -1741,56 +1741,86 @@ bool ceph_inode_set_size(struct inode *inode, loff_t size) } /* + * Put reference to inode, but avoid calling iput_final() in current thread. + * iput_final() may wait for reahahead pages. The wait can cause deadlock in + * some contexts. + */ +void ceph_async_iput(struct inode *inode) +{ + if (!inode) + return; + for (;;) { + if (atomic_add_unless(&inode->i_count, -1, 1)) + break; + if (queue_work(ceph_inode_to_client(inode)->inode_wq, + &ceph_inode(inode)->i_work)) + break; + /* queue work failed, i_count must be at least 2 */ + } +} + +/* * Write back inode data in a worker thread. (This can't be done * in the message handler context.) */ void ceph_queue_writeback(struct inode *inode) { + struct ceph_inode_info *ci = ceph_inode(inode); + set_bit(CEPH_I_WORK_WRITEBACK, &ci->i_work_mask); + ihold(inode); - if (queue_work(ceph_inode_to_client(inode)->wb_wq, - &ceph_inode(inode)->i_wb_work)) { + if (queue_work(ceph_inode_to_client(inode)->inode_wq, + &ci->i_work)) { dout("ceph_queue_writeback %p\n", inode); } else { - dout("ceph_queue_writeback %p failed\n", inode); + dout("ceph_queue_writeback %p already queued, mask=%lx\n", + inode, ci->i_work_mask); iput(inode); } } -static void ceph_writeback_work(struct work_struct *work) -{ - struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, - i_wb_work); - struct inode *inode = &ci->vfs_inode; - - dout("writeback %p\n", inode); - filemap_fdatawrite(&inode->i_data); - iput(inode); -} - /* * queue an async invalidation */ void ceph_queue_invalidate(struct inode *inode) { + struct ceph_inode_info *ci = ceph_inode(inode); + set_bit(CEPH_I_WORK_INVALIDATE_PAGES, &ci->i_work_mask); + ihold(inode); - if (queue_work(ceph_inode_to_client(inode)->pg_inv_wq, - &ceph_inode(inode)->i_pg_inv_work)) { + if (queue_work(ceph_inode_to_client(inode)->inode_wq, + &ceph_inode(inode)->i_work)) { dout("ceph_queue_invalidate %p\n", inode); } else { - dout("ceph_queue_invalidate %p failed\n", inode); + dout("ceph_queue_invalidate %p already queued, mask=%lx\n", + inode, ci->i_work_mask); iput(inode); } } /* - * Invalidate inode pages in a worker thread. (This can't be done - * in the message handler context.) + * Queue an async vmtruncate. If we fail to queue work, we will handle + * the truncation the next time we call __ceph_do_pending_vmtruncate. */ -static void ceph_invalidate_work(struct work_struct *work) +void ceph_queue_vmtruncate(struct inode *inode) { - struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, - i_pg_inv_work); - struct inode *inode = &ci->vfs_inode; + struct ceph_inode_info *ci = ceph_inode(inode); + set_bit(CEPH_I_WORK_VMTRUNCATE, &ci->i_work_mask); + + ihold(inode); + if (queue_work(ceph_inode_to_client(inode)->inode_wq, + &ci->i_work)) { + dout("ceph_queue_vmtruncate %p\n", inode); + } else { + dout("ceph_queue_vmtruncate %p already queued, mask=%lx\n", + inode, ci->i_work_mask); + iput(inode); + } +} + +static void ceph_do_invalidate_pages(struct inode *inode) +{ + struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); u32 orig_gen; int check = 0; @@ -1842,44 +1872,6 @@ static void ceph_invalidate_work(struct work_struct *work) out: if (check) ceph_check_caps(ci, 0, NULL); - iput(inode); -} - - -/* - * called by trunc_wq; - * - * We also truncate in a separate thread as well. - */ -static void ceph_vmtruncate_work(struct work_struct *work) -{ - struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, - i_vmtruncate_work); - struct inode *inode = &ci->vfs_inode; - - dout("vmtruncate_work %p\n", inode); - __ceph_do_pending_vmtruncate(inode); - iput(inode); -} - -/* - * Queue an async vmtruncate. If we fail to queue work, we will handle - * the truncation the next time we call __ceph_do_pending_vmtruncate. - */ -void ceph_queue_vmtruncate(struct inode *inode) -{ - struct ceph_inode_info *ci = ceph_inode(inode); - - ihold(inode); - - if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq, - &ci->i_vmtruncate_work)) { - dout("ceph_queue_vmtruncate %p\n", inode); - } else { - dout("ceph_queue_vmtruncate %p failed, pending=%d\n", - inode, ci->i_truncate_pending); - iput(inode); - } } /* @@ -1943,6 +1935,25 @@ retry: wake_up_all(&ci->i_cap_wq); } +static void ceph_inode_work(struct work_struct *work) +{ + struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, + i_work); + struct inode *inode = &ci->vfs_inode; + + if (test_and_clear_bit(CEPH_I_WORK_WRITEBACK, &ci->i_work_mask)) { + dout("writeback %p\n", inode); + filemap_fdatawrite(&inode->i_data); + } + if (test_and_clear_bit(CEPH_I_WORK_INVALIDATE_PAGES, &ci->i_work_mask)) + ceph_do_invalidate_pages(inode); + + if (test_and_clear_bit(CEPH_I_WORK_VMTRUNCATE, &ci->i_work_mask)) + __ceph_do_pending_vmtruncate(inode); + + iput(inode); +} + /* * symlinks */ @@ -2266,43 +2277,72 @@ int ceph_permission(struct inode *inode, int mask) return err; } +/* Craft a mask of needed caps given a set of requested statx attrs. */ +static int statx_to_caps(u32 want) +{ + int mask = 0; + + if (want & (STATX_MODE|STATX_UID|STATX_GID|STATX_CTIME)) + mask |= CEPH_CAP_AUTH_SHARED; + + if (want & (STATX_NLINK|STATX_CTIME)) + mask |= CEPH_CAP_LINK_SHARED; + + if (want & (STATX_ATIME|STATX_MTIME|STATX_CTIME|STATX_SIZE| + STATX_BLOCKS)) + mask |= CEPH_CAP_FILE_SHARED; + + if (want & (STATX_CTIME)) + mask |= CEPH_CAP_XATTR_SHARED; + + return mask; +} + /* - * Get all attributes. Hopefully somedata we'll have a statlite() - * and can limit the fields we require to be accurate. + * Get all the attributes. If we have sufficient caps for the requested attrs, + * then we can avoid talking to the MDS at all. */ int ceph_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); struct ceph_inode_info *ci = ceph_inode(inode); - int err; + int err = 0; - err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL, false); - if (!err) { - generic_fillattr(inode, stat); - stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino); - if (ceph_snap(inode) == CEPH_NOSNAP) - stat->dev = inode->i_sb->s_dev; + /* Skip the getattr altogether if we're asked not to sync */ + if (!(flags & AT_STATX_DONT_SYNC)) { + err = ceph_do_getattr(inode, statx_to_caps(request_mask), + flags & AT_STATX_FORCE_SYNC); + if (err) + return err; + } + + generic_fillattr(inode, stat); + stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino); + if (ceph_snap(inode) == CEPH_NOSNAP) + stat->dev = inode->i_sb->s_dev; + else + stat->dev = ci->i_snapid_map ? ci->i_snapid_map->dev : 0; + + if (S_ISDIR(inode->i_mode)) { + if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), + RBYTES)) + stat->size = ci->i_rbytes; else - stat->dev = ci->i_snapid_map ? ci->i_snapid_map->dev : 0; - - if (S_ISDIR(inode->i_mode)) { - if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), - RBYTES)) - stat->size = ci->i_rbytes; - else - stat->size = ci->i_files + ci->i_subdirs; - stat->blocks = 0; - stat->blksize = 65536; - /* - * Some applications rely on the number of st_nlink - * value on directories to be either 0 (if unlinked) - * or 2 + number of subdirectories. - */ - if (stat->nlink == 1) - /* '.' + '..' + subdirs */ - stat->nlink = 1 + 1 + ci->i_subdirs; - } + stat->size = ci->i_files + ci->i_subdirs; + stat->blocks = 0; + stat->blksize = 65536; + /* + * Some applications rely on the number of st_nlink + * value on directories to be either 0 (if unlinked) + * or 2 + number of subdirectories. + */ + if (stat->nlink == 1) + /* '.' + '..' + subdirs */ + stat->nlink = 1 + 1 + ci->i_subdirs; } + + /* Mask off any higher bits (e.g. btime) until we have support */ + stat->result_mask = request_mask & STATX_BASIC_STATS; return err; } diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 9dae2ec7e1fa..ac9b53b89365 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -237,15 +237,6 @@ int ceph_lock(struct file *file, int cmd, struct file_lock *fl) spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { err = -EIO; - } else if (op == CEPH_MDS_OP_SETFILELOCK) { - /* - * increasing i_filelock_ref closes race window between - * handling request reply and adding file_lock struct to - * inode. Otherwise, i_auth_cap may get trimmed in the - * window. Caller function will decrease the counter. - */ - fl->fl_ops = &ceph_fl_lock_ops; - atomic_inc(&ci->i_filelock_ref); } spin_unlock(&ci->i_ceph_lock); if (err < 0) { @@ -299,10 +290,6 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl) spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { err = -EIO; - } else { - /* see comment in ceph_lock */ - fl->fl_ops = &ceph_fl_lock_ops; - atomic_inc(&ci->i_filelock_ref); } spin_unlock(&ci->i_ceph_lock); if (err < 0) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 9049c2a3e972..c8a9b89b922d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -550,15 +550,9 @@ void ceph_put_mds_session(struct ceph_mds_session *s) struct ceph_mds_session *__ceph_lookup_mds_session(struct ceph_mds_client *mdsc, int mds) { - struct ceph_mds_session *session; - if (mds >= mdsc->max_sessions || !mdsc->sessions[mds]) return NULL; - session = mdsc->sessions[mds]; - dout("lookup_mds_session %p %d\n", session, - refcount_read(&session->s_ref)); - get_session(session); - return session; + return get_session(mdsc->sessions[mds]); } static bool __have_session(struct ceph_mds_client *mdsc, int mds) @@ -696,11 +690,12 @@ void ceph_mdsc_release_request(struct kref *kref) ceph_msg_put(req->r_reply); if (req->r_inode) { ceph_put_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); - iput(req->r_inode); + /* avoid calling iput_final() in mds dispatch threads */ + ceph_async_iput(req->r_inode); } if (req->r_parent) ceph_put_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); - iput(req->r_target_inode); + ceph_async_iput(req->r_target_inode); if (req->r_dentry) dput(req->r_dentry); if (req->r_old_dentry) @@ -714,7 +709,7 @@ void ceph_mdsc_release_request(struct kref *kref) */ ceph_put_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); - iput(req->r_old_dentry_dir); + ceph_async_iput(req->r_old_dentry_dir); } kfree(req->r_path1); kfree(req->r_path2); @@ -824,7 +819,8 @@ static void __unregister_request(struct ceph_mds_client *mdsc, } if (req->r_unsafe_dir) { - iput(req->r_unsafe_dir); + /* avoid calling iput_final() in mds dispatch threads */ + ceph_async_iput(req->r_unsafe_dir); req->r_unsafe_dir = NULL; } @@ -989,7 +985,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc, cap = rb_entry(rb_first(&ci->i_caps), struct ceph_cap, ci_node); if (!cap) { spin_unlock(&ci->i_ceph_lock); - iput(inode); + ceph_async_iput(inode); goto random; } mds = cap->session->s_mds; @@ -998,7 +994,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc, cap == ci->i_auth_cap ? "auth " : "", cap); spin_unlock(&ci->i_ceph_lock); out: - iput(inode); + /* avoid calling iput_final() while holding mdsc->mutex or + * in mds dispatch threads */ + ceph_async_iput(inode); return mds; random: @@ -1284,9 +1282,9 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc, * * Caller must hold session s_mutex. */ -static int iterate_session_caps(struct ceph_mds_session *session, - int (*cb)(struct inode *, struct ceph_cap *, - void *), void *arg) +int ceph_iterate_session_caps(struct ceph_mds_session *session, + int (*cb)(struct inode *, struct ceph_cap *, + void *), void *arg) { struct list_head *p; struct ceph_cap *cap; @@ -1308,7 +1306,9 @@ static int iterate_session_caps(struct ceph_mds_session *session, spin_unlock(&session->s_cap_lock); if (last_inode) { - iput(last_inode); + /* avoid calling iput_final() while holding + * s_mutex or in mds dispatch threads */ + ceph_async_iput(last_inode); last_inode = NULL; } if (old_cap) { @@ -1341,7 +1341,7 @@ out: session->s_cap_iterator = NULL; spin_unlock(&session->s_cap_lock); - iput(last_inode); + ceph_async_iput(last_inode); if (old_cap) ceph_put_cap(session->s_mdsc, old_cap); @@ -1451,7 +1451,7 @@ static void remove_session_caps(struct ceph_mds_session *session) LIST_HEAD(dispose); dout("remove_session_caps on %p\n", session); - iterate_session_caps(session, remove_session_caps_cb, fsc); + ceph_iterate_session_caps(session, remove_session_caps_cb, fsc); wake_up_all(&fsc->mdsc->cap_flushing_wq); @@ -1477,7 +1477,8 @@ static void remove_session_caps(struct ceph_mds_session *session) spin_unlock(&session->s_cap_lock); inode = ceph_find_inode(sb, vino); - iput(inode); + /* avoid calling iput_final() while holding s_mutex */ + ceph_async_iput(inode); spin_lock(&session->s_cap_lock); } @@ -1534,8 +1535,8 @@ static int wake_up_session_cb(struct inode *inode, struct ceph_cap *cap, static void wake_up_session_caps(struct ceph_mds_session *session, int ev) { dout("wake_up_session_caps %p mds%d\n", session, session->s_mds); - iterate_session_caps(session, wake_up_session_cb, - (void *)(unsigned long)ev); + ceph_iterate_session_caps(session, wake_up_session_cb, + (void *)(unsigned long)ev); } /* @@ -1768,7 +1769,7 @@ int ceph_trim_caps(struct ceph_mds_client *mdsc, session->s_mds, session->s_nr_caps, max_caps, trim_caps); if (trim_caps > 0) { session->s_trim_caps = trim_caps; - iterate_session_caps(session, trim_caps_cb, session); + ceph_iterate_session_caps(session, trim_caps_cb, session); dout("trim_caps mds%d done: %d / %d, trimmed %d\n", session->s_mds, session->s_nr_caps, max_caps, trim_caps - session->s_trim_caps); @@ -1861,7 +1862,8 @@ again: num_cap_releases--; head = msg->front.iov_base; - le32_add_cpu(&head->num, 1); + put_unaligned_le32(get_unaligned_le32(&head->num) + 1, + &head->num); item = msg->front.iov_base + msg->front.iov_len; item->ino = cpu_to_le64(cap->cap_ino); item->cap_id = cpu_to_le64(cap->cap_id); @@ -2089,43 +2091,29 @@ static inline u64 __get_oldest_tid(struct ceph_mds_client *mdsc) * Encode hidden .snap dirs as a double /, i.e. * foo/.snap/bar -> foo//bar */ -char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base, +char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *pbase, int stop_on_nosnap) { struct dentry *temp; char *path; - int len, pos; + int pos; unsigned seq; + u64 base; if (!dentry) return ERR_PTR(-EINVAL); -retry: - len = 0; - seq = read_seqbegin(&rename_lock); - rcu_read_lock(); - for (temp = dentry; !IS_ROOT(temp);) { - struct inode *inode = d_inode(temp); - if (inode && ceph_snap(inode) == CEPH_SNAPDIR) - len++; /* slash only */ - else if (stop_on_nosnap && inode && - ceph_snap(inode) == CEPH_NOSNAP) - break; - else - len += 1 + temp->d_name.len; - temp = temp->d_parent; - } - rcu_read_unlock(); - if (len) - len--; /* no leading '/' */ - - path = kmalloc(len+1, GFP_NOFS); + path = __getname(); if (!path) return ERR_PTR(-ENOMEM); - pos = len; - path[pos] = 0; /* trailing null */ +retry: + pos = PATH_MAX - 1; + path[pos] = '\0'; + + seq = read_seqbegin(&rename_lock); rcu_read_lock(); - for (temp = dentry; !IS_ROOT(temp) && pos != 0; ) { + temp = dentry; + for (;;) { struct inode *inode; spin_lock(&temp->d_lock); @@ -2133,9 +2121,10 @@ retry: if (inode && ceph_snap(inode) == CEPH_SNAPDIR) { dout("build_path path+%d: %p SNAPDIR\n", pos, temp); - } else if (stop_on_nosnap && inode && + } else if (stop_on_nosnap && inode && dentry != temp && ceph_snap(inode) == CEPH_NOSNAP) { spin_unlock(&temp->d_lock); + pos++; /* get rid of any prepended '/' */ break; } else { pos -= temp->d_name.len; @@ -2143,83 +2132,54 @@ retry: spin_unlock(&temp->d_lock); break; } - strncpy(path + pos, temp->d_name.name, - temp->d_name.len); + memcpy(path + pos, temp->d_name.name, temp->d_name.len); } spin_unlock(&temp->d_lock); - if (pos) - path[--pos] = '/'; temp = temp->d_parent; + + /* Are we at the root? */ + if (IS_ROOT(temp)) + break; + + /* Are we out of buffer? */ + if (--pos < 0) + break; + + path[pos] = '/'; } + base = ceph_ino(d_inode(temp)); rcu_read_unlock(); - if (pos != 0 || read_seqretry(&rename_lock, seq)) { + if (pos < 0 || read_seqretry(&rename_lock, seq)) { pr_err("build_path did not end path lookup where " - "expected, namelen is %d, pos is %d\n", len, pos); + "expected, pos is %d\n", pos); /* presumably this is only possible if racing with a rename of one of the parent directories (we can not lock the dentries above us to prevent this, but retrying should be harmless) */ - kfree(path); goto retry; } - *base = ceph_ino(d_inode(temp)); - *plen = len; + *pbase = base; + *plen = PATH_MAX - 1 - pos; dout("build_path on %p %d built %llx '%.*s'\n", - dentry, d_count(dentry), *base, len, path); - return path; -} - -/* Duplicate the dentry->d_name.name safely */ -static int clone_dentry_name(struct dentry *dentry, const char **ppath, - int *ppathlen) -{ - u32 len; - char *name; - -retry: - len = READ_ONCE(dentry->d_name.len); - name = kmalloc(len + 1, GFP_NOFS); - if (!name) - return -ENOMEM; - - spin_lock(&dentry->d_lock); - if (dentry->d_name.len != len) { - spin_unlock(&dentry->d_lock); - kfree(name); - goto retry; - } - memcpy(name, dentry->d_name.name, len); - spin_unlock(&dentry->d_lock); - - name[len] = '\0'; - *ppath = name; - *ppathlen = len; - return 0; + dentry, d_count(dentry), base, *plen, path + pos); + return path + pos; } static int build_dentry_path(struct dentry *dentry, struct inode *dir, const char **ppath, int *ppathlen, u64 *pino, bool *pfreepath, bool parent_locked) { - int ret; char *path; rcu_read_lock(); if (!dir) dir = d_inode_rcu(dentry->d_parent); - if (dir && ceph_snap(dir) == CEPH_NOSNAP) { + if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP) { *pino = ceph_ino(dir); rcu_read_unlock(); - if (parent_locked) { - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; - } else { - ret = clone_dentry_name(dentry, ppath, ppathlen); - if (ret) - return ret; - *pfreepath = true; - } + *ppath = dentry->d_name.name; + *ppathlen = dentry->d_name.len; return 0; } rcu_read_unlock(); @@ -2331,9 +2291,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, (!!req->r_inode_drop + !!req->r_dentry_drop + !!req->r_old_inode_drop + !!req->r_old_dentry_drop); if (req->r_dentry_drop) - len += req->r_dentry->d_name.len; + len += pathlen1; if (req->r_old_dentry_drop) - len += req->r_old_dentry->d_name.len; + len += pathlen2; msg = ceph_msg_new2(CEPH_MSG_CLIENT_REQUEST, len, 1, GFP_NOFS, false); if (!msg) { @@ -2410,10 +2370,10 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, out_free2: if (freepath2) - kfree((char *)path2); + ceph_mdsc_free_path((char *)path2, pathlen2); out_free1: if (freepath1) - kfree((char *)path1); + ceph_mdsc_free_path((char *)path1, pathlen1); out: return msg; } @@ -2427,8 +2387,7 @@ static void complete_request(struct ceph_mds_client *mdsc, { if (req->r_callback) req->r_callback(mdsc, req); - else - complete_all(&req->r_completion); + complete_all(&req->r_completion); } /* @@ -2670,28 +2629,11 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds) } } -void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, +int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req) { - dout("submit_request on %p\n", req); - mutex_lock(&mdsc->mutex); - __register_request(mdsc, req, NULL); - __do_request(mdsc, req); - mutex_unlock(&mdsc->mutex); -} - -/* - * Synchrously perform an mds request. Take care of all of the - * session setup, forwarding, retry details. - */ -int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, - struct inode *dir, - struct ceph_mds_request *req) -{ int err; - dout("do_request on %p\n", req); - /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */ if (req->r_inode) ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); @@ -2701,18 +2643,21 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); - /* issue */ + dout("submit_request on %p for inode %p\n", req, dir); mutex_lock(&mdsc->mutex); __register_request(mdsc, req, dir); __do_request(mdsc, req); + err = req->r_err; + mutex_unlock(&mdsc->mutex); + return err; +} - if (req->r_err) { - err = req->r_err; - goto out; - } +static int ceph_mdsc_wait_request(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req) +{ + int err; /* wait */ - mutex_unlock(&mdsc->mutex); dout("do_request waiting\n"); if (!req->r_timeout && req->r_wait_for_completion) { err = req->r_wait_for_completion(mdsc, req); @@ -2753,8 +2698,26 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, err = req->r_err; } -out: mutex_unlock(&mdsc->mutex); + return err; +} + +/* + * Synchrously perform an mds request. Take care of all of the + * session setup, forwarding, retry details. + */ +int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, + struct inode *dir, + struct ceph_mds_request *req) +{ + int err; + + dout("do_request on %p\n", req); + + /* issue */ + err = ceph_mdsc_submit_request(mdsc, dir, req); + if (!err) + err = ceph_mdsc_wait_request(mdsc, req); dout("do_request %p done, result %d\n", req, err); return err; } @@ -3485,7 +3448,7 @@ out_freeflocks: ceph_pagelist_encode_string(pagelist, path, pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1)); out_freepath: - kfree(path); + ceph_mdsc_free_path(path, pathlen); } out_err: @@ -3642,7 +3605,7 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.msg_version = 2; } /* trsaverse this session's caps */ - err = iterate_session_caps(session, encode_caps_cb, &recon_state); + err = ceph_iterate_session_caps(session, encode_caps_cb, &recon_state); spin_lock(&session->s_cap_lock); session->s_cap_reconnect = 0; @@ -3957,8 +3920,9 @@ release: ceph_con_send(&session->s_con, msg); out: - iput(inode); mutex_unlock(&session->s_mutex); + /* avoid calling iput_final() in mds dispatch threads */ + ceph_async_iput(inode); return; bad: @@ -4125,6 +4089,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) mdsc->max_sessions = 0; mdsc->stopping = 0; atomic64_set(&mdsc->quotarealms_count, 0); + mdsc->quotarealms_inodes = RB_ROOT; + mutex_init(&mdsc->quotarealms_inodes_mutex); mdsc->last_snap_seq = 0; init_rwsem(&mdsc->snap_rwsem); mdsc->snap_realms = RB_ROOT; @@ -4216,6 +4182,8 @@ void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc) * their inode/dcache refs */ ceph_msgr_flush(); + + ceph_cleanup_quotarealms_inodes(mdsc); } /* diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 50385a481fdb..a83f28bc2387 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -326,6 +326,18 @@ struct ceph_snapid_map { }; /* + * node for list of quotarealm inodes that are not visible from the filesystem + * mountpoint, but required to handle, e.g. quotas. + */ +struct ceph_quotarealm_inode { + struct rb_node node; + u64 ino; + unsigned long timeout; /* last time a lookup failed for this inode */ + struct mutex mutex; + struct inode *inode; +}; + +/* * mds client state */ struct ceph_mds_client { @@ -344,6 +356,12 @@ struct ceph_mds_client { int stopping; /* true if shutting down */ atomic64_t quotarealms_count; /* # realms with quota */ + /* + * We keep a list of inodes we don't see in the mountpoint but that we + * need to track quota realms. + */ + struct rb_root quotarealms_inodes; + struct mutex quotarealms_inodes_mutex; /* * snap_rwsem will cover cap linkage into snaprealms, and @@ -447,8 +465,9 @@ extern int ceph_alloc_readdir_reply_buffer(struct ceph_mds_request *req, struct inode *dir); extern struct ceph_mds_request * ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode); -extern void ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, - struct ceph_mds_request *req); +extern int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, + struct inode *dir, + struct ceph_mds_request *req); extern int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, struct inode *dir, struct ceph_mds_request *req); @@ -468,8 +487,18 @@ extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc); extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr); +extern int ceph_iterate_session_caps(struct ceph_mds_session *session, + int (*cb)(struct inode *, + struct ceph_cap *, void *), + void *arg); extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); +static inline void ceph_mdsc_free_path(char *path, int len) +{ + if (path) + __putname(path - (PATH_MAX - 1 - len)); +} + extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base, int stop_on_nosnap); diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 1a2c5d390f7f..701b4fb0fb5a 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -205,7 +205,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end) dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n", i+1, n, global_id, mds, inc, - ceph_pr_addr(&addr.in_addr), + ceph_pr_addr(&addr), ceph_mds_state_name(state)); if (mds < 0 || state <= 0) diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 9455d3aef0c3..d629fc857450 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -22,7 +22,16 @@ void ceph_adjust_quota_realms_count(struct inode *inode, bool inc) static inline bool ceph_has_realms_with_quotas(struct inode *inode) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; - return atomic64_read(&mdsc->quotarealms_count) > 0; + struct super_block *sb = mdsc->fsc->sb; + + if (atomic64_read(&mdsc->quotarealms_count) > 0) + return true; + /* if root is the real CephFS root, we don't have quota realms */ + if (sb->s_root->d_inode && + (sb->s_root->d_inode->i_ino == CEPH_INO_ROOT)) + return false; + /* otherwise, we can't know for sure */ + return true; } void ceph_handle_quota(struct ceph_mds_client *mdsc, @@ -65,7 +74,110 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc, le64_to_cpu(h->max_files)); spin_unlock(&ci->i_ceph_lock); - iput(inode); + /* avoid calling iput_final() in dispatch thread */ + ceph_async_iput(inode); +} + +static struct ceph_quotarealm_inode * +find_quotarealm_inode(struct ceph_mds_client *mdsc, u64 ino) +{ + struct ceph_quotarealm_inode *qri = NULL; + struct rb_node **node, *parent = NULL; + + mutex_lock(&mdsc->quotarealms_inodes_mutex); + node = &(mdsc->quotarealms_inodes.rb_node); + while (*node) { + parent = *node; + qri = container_of(*node, struct ceph_quotarealm_inode, node); + + if (ino < qri->ino) + node = &((*node)->rb_left); + else if (ino > qri->ino) + node = &((*node)->rb_right); + else + break; + } + if (!qri || (qri->ino != ino)) { + /* Not found, create a new one and insert it */ + qri = kmalloc(sizeof(*qri), GFP_KERNEL); + if (qri) { + qri->ino = ino; + qri->inode = NULL; + qri->timeout = 0; + mutex_init(&qri->mutex); + rb_link_node(&qri->node, parent, node); + rb_insert_color(&qri->node, &mdsc->quotarealms_inodes); + } else + pr_warn("Failed to alloc quotarealms_inode\n"); + } + mutex_unlock(&mdsc->quotarealms_inodes_mutex); + + return qri; +} + +/* + * This function will try to lookup a realm inode which isn't visible in the + * filesystem mountpoint. A list of these kind of inodes (not visible) is + * maintained in the mdsc and freed only when the filesystem is umounted. + * + * Note that these inodes are kept in this list even if the lookup fails, which + * allows to prevent useless lookup requests. + */ +static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, + struct super_block *sb, + struct ceph_snap_realm *realm) +{ + struct ceph_quotarealm_inode *qri; + struct inode *in; + + qri = find_quotarealm_inode(mdsc, realm->ino); + if (!qri) + return NULL; + + mutex_lock(&qri->mutex); + if (qri->inode) { + /* A request has already returned the inode */ + mutex_unlock(&qri->mutex); + return qri->inode; + } + /* Check if this inode lookup has failed recently */ + if (qri->timeout && + time_before_eq(jiffies, qri->timeout)) { + mutex_unlock(&qri->mutex); + return NULL; + } + in = ceph_lookup_inode(sb, realm->ino); + if (IS_ERR(in)) { + pr_warn("Can't lookup inode %llx (err: %ld)\n", + realm->ino, PTR_ERR(in)); + qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ + } else { + qri->timeout = 0; + qri->inode = in; + } + mutex_unlock(&qri->mutex); + + return in; +} + +void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) +{ + struct ceph_quotarealm_inode *qri; + struct rb_node *node; + + /* + * It should now be safe to clean quotarealms_inode tree without holding + * mdsc->quotarealms_inodes_mutex... + */ + mutex_lock(&mdsc->quotarealms_inodes_mutex); + while (!RB_EMPTY_ROOT(&mdsc->quotarealms_inodes)) { + node = rb_first(&mdsc->quotarealms_inodes); + qri = rb_entry(node, struct ceph_quotarealm_inode, node); + rb_erase(node, &mdsc->quotarealms_inodes); + iput(qri->inode); + kfree(qri); + } + mutex_unlock(&mdsc->quotarealms_inodes_mutex); } /* @@ -76,9 +188,15 @@ void ceph_handle_quota(struct ceph_mds_client *mdsc, * * Note that the caller is responsible for calling ceph_put_snap_realm() on the * returned realm. + * + * Callers of this function need to hold mdsc->snap_rwsem. However, if there's + * a need to do an inode lookup, this rwsem will be temporarily dropped. Hence + * the 'retry' argument: if rwsem needs to be dropped and 'retry' is 'false' + * this function will return -EAGAIN; otherwise, the snaprealms walk-through + * will be restarted. */ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, - struct inode *inode) + struct inode *inode, bool retry) { struct ceph_inode_info *ci = NULL; struct ceph_snap_realm *realm, *next; @@ -88,6 +206,7 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, if (ceph_snap(inode) != CEPH_NOSNAP) return NULL; +restart: realm = ceph_inode(inode)->i_snap_realm; if (realm) ceph_get_snap_realm(mdsc, realm); @@ -95,15 +214,30 @@ static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, pr_err_ratelimited("get_quota_realm: ino (%llx.%llx) " "null i_snap_realm\n", ceph_vinop(inode)); while (realm) { + bool has_inode; + spin_lock(&realm->inodes_with_caps_lock); - in = realm->inode ? igrab(realm->inode) : NULL; + has_inode = realm->inode; + in = has_inode ? igrab(realm->inode) : NULL; spin_unlock(&realm->inodes_with_caps_lock); - if (!in) + if (has_inode && !in) break; + if (!in) { + up_read(&mdsc->snap_rwsem); + in = lookup_quotarealm_inode(mdsc, inode->i_sb, realm); + down_read(&mdsc->snap_rwsem); + if (IS_ERR_OR_NULL(in)) + break; + ceph_put_snap_realm(mdsc, realm); + if (!retry) + return ERR_PTR(-EAGAIN); + goto restart; + } ci = ceph_inode(in); has_quota = __ceph_has_any_quota(ci); - iput(in); + /* avoid calling iput_final() while holding mdsc->snap_rwsem */ + ceph_async_iput(in); next = realm->parent; if (has_quota || !next) @@ -125,9 +259,22 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) struct ceph_snap_realm *old_realm, *new_realm; bool is_same; +restart: + /* + * We need to lookup 2 quota realms atomically, i.e. with snap_rwsem. + * However, get_quota_realm may drop it temporarily. By setting the + * 'retry' parameter to 'false', we'll get -EAGAIN if the rwsem was + * dropped and we can then restart the whole operation. + */ down_read(&mdsc->snap_rwsem); - old_realm = get_quota_realm(mdsc, old); - new_realm = get_quota_realm(mdsc, new); + old_realm = get_quota_realm(mdsc, old, true); + new_realm = get_quota_realm(mdsc, new, false); + if (PTR_ERR(new_realm) == -EAGAIN) { + up_read(&mdsc->snap_rwsem); + if (old_realm) + ceph_put_snap_realm(mdsc, old_realm); + goto restart; + } is_same = (old_realm == new_realm); up_read(&mdsc->snap_rwsem); @@ -166,6 +313,7 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, return false; down_read(&mdsc->snap_rwsem); +restart: realm = ceph_inode(inode)->i_snap_realm; if (realm) ceph_get_snap_realm(mdsc, realm); @@ -173,12 +321,23 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, pr_err_ratelimited("check_quota_exceeded: ino (%llx.%llx) " "null i_snap_realm\n", ceph_vinop(inode)); while (realm) { + bool has_inode; + spin_lock(&realm->inodes_with_caps_lock); - in = realm->inode ? igrab(realm->inode) : NULL; + has_inode = realm->inode; + in = has_inode ? igrab(realm->inode) : NULL; spin_unlock(&realm->inodes_with_caps_lock); - if (!in) + if (has_inode && !in) break; - + if (!in) { + up_read(&mdsc->snap_rwsem); + in = lookup_quotarealm_inode(mdsc, inode->i_sb, realm); + down_read(&mdsc->snap_rwsem); + if (IS_ERR_OR_NULL(in)) + break; + ceph_put_snap_realm(mdsc, realm); + goto restart; + } ci = ceph_inode(in); spin_lock(&ci->i_ceph_lock); if (op == QUOTA_CHECK_MAX_FILES_OP) { @@ -215,7 +374,8 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, pr_warn("Invalid quota check op (%d)\n", op); exceeded = true; /* Just break the loop */ } - iput(in); + /* avoid calling iput_final() while holding mdsc->snap_rwsem */ + ceph_async_iput(in); next = realm->parent; if (exceeded || !next) @@ -314,7 +474,7 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf) bool is_updated = false; down_read(&mdsc->snap_rwsem); - realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root)); + realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root), true); up_read(&mdsc->snap_rwsem); if (!realm) return false; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index b26e12cd8ec3..72c6c022f02b 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -648,13 +648,15 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm) if (!inode) continue; spin_unlock(&realm->inodes_with_caps_lock); - iput(lastinode); + /* avoid calling iput_final() while holding + * mdsc->snap_rwsem or in mds dispatch threads */ + ceph_async_iput(lastinode); lastinode = inode; ceph_queue_cap_snap(ci); spin_lock(&realm->inodes_with_caps_lock); } spin_unlock(&realm->inodes_with_caps_lock); - iput(lastinode); + ceph_async_iput(lastinode); dout("queue_realm_cap_snaps %p %llx done\n", realm, realm->ino); } @@ -806,7 +808,9 @@ static void flush_snaps(struct ceph_mds_client *mdsc) ihold(inode); spin_unlock(&mdsc->snap_flush_lock); ceph_flush_snaps(ci, &session); - iput(inode); + /* avoid calling iput_final() while holding + * session->s_mutex or in mds dispatch threads */ + ceph_async_iput(inode); spin_lock(&mdsc->snap_flush_lock); } spin_unlock(&mdsc->snap_flush_lock); @@ -950,12 +954,14 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, ceph_get_snap_realm(mdsc, realm); ceph_put_snap_realm(mdsc, oldrealm); - iput(inode); + /* avoid calling iput_final() while holding + * mdsc->snap_rwsem or mds in dispatch threads */ + ceph_async_iput(inode); continue; skip_inode: spin_unlock(&ci->i_ceph_lock); - iput(inode); + ceph_async_iput(inode); } /* we may have taken some of the old realm's children. */ diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 285edda4fc3b..ed1b65a6c2c3 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only #include <linux/ceph/ceph_debug.h> @@ -671,18 +672,12 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, * The number of concurrent works can be high but they don't need * to be processed in parallel, limit concurrency. */ - fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1); - if (!fsc->wb_wq) + fsc->inode_wq = alloc_workqueue("ceph-inode", WQ_UNBOUND, 0); + if (!fsc->inode_wq) goto fail_client; - fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1); - if (!fsc->pg_inv_wq) - goto fail_wb_wq; - fsc->trunc_wq = alloc_workqueue("ceph-trunc", 0, 1); - if (!fsc->trunc_wq) - goto fail_pg_inv_wq; fsc->cap_wq = alloc_workqueue("ceph-cap", 0, 1); if (!fsc->cap_wq) - goto fail_trunc_wq; + goto fail_inode_wq; /* set up mempools */ err = -ENOMEM; @@ -696,12 +691,8 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, fail_cap_wq: destroy_workqueue(fsc->cap_wq); -fail_trunc_wq: - destroy_workqueue(fsc->trunc_wq); -fail_pg_inv_wq: - destroy_workqueue(fsc->pg_inv_wq); -fail_wb_wq: - destroy_workqueue(fsc->wb_wq); +fail_inode_wq: + destroy_workqueue(fsc->inode_wq); fail_client: ceph_destroy_client(fsc->client); fail: @@ -714,9 +705,7 @@ fail: static void flush_fs_workqueues(struct ceph_fs_client *fsc) { - flush_workqueue(fsc->wb_wq); - flush_workqueue(fsc->pg_inv_wq); - flush_workqueue(fsc->trunc_wq); + flush_workqueue(fsc->inode_wq); flush_workqueue(fsc->cap_wq); } @@ -724,9 +713,7 @@ static void destroy_fs_client(struct ceph_fs_client *fsc) { dout("destroy_fs_client %p\n", fsc); - destroy_workqueue(fsc->wb_wq); - destroy_workqueue(fsc->pg_inv_wq); - destroy_workqueue(fsc->trunc_wq); + destroy_workqueue(fsc->inode_wq); destroy_workqueue(fsc->cap_wq); mempool_destroy(fsc->wb_pagevec_pool); @@ -845,6 +832,12 @@ static void ceph_umount_begin(struct super_block *sb) return; } +static int ceph_remount(struct super_block *sb, int *flags, char *data) +{ + sync_filesystem(sb); + return 0; +} + static const struct super_operations ceph_super_ops = { .alloc_inode = ceph_alloc_inode, .destroy_inode = ceph_destroy_inode, @@ -853,6 +846,7 @@ static const struct super_operations ceph_super_ops = { .drop_inode = ceph_drop_inode, .sync_fs = ceph_sync_fs, .put_super = ceph_put_super, + .remount_fs = ceph_remount, .show_options = ceph_show_options, .statfs = ceph_statfs, .umount_begin = ceph_umount_begin, @@ -943,9 +937,7 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) dout("mount opening path %s\n", path); } - err = ceph_fs_debugfs_init(fsc); - if (err < 0) - goto out; + ceph_fs_debugfs_init(fsc); root = open_root_dentry(fsc, path, started); if (IS_ERR(root)) { diff --git a/fs/ceph/super.h b/fs/ceph/super.h index c5b4a05905c0..fbe6869a3f95 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -109,9 +109,7 @@ struct ceph_fs_client { mempool_t *wb_pagevec_pool; atomic_long_t writeback_count; - struct workqueue_struct *wb_wq; - struct workqueue_struct *pg_inv_wq; - struct workqueue_struct *trunc_wq; + struct workqueue_struct *inode_wq; struct workqueue_struct *cap_wq; #ifdef CONFIG_DEBUG_FS @@ -387,10 +385,8 @@ struct ceph_inode_info { struct list_head i_snap_realm_item; struct list_head i_snap_flush_item; - struct work_struct i_wb_work; /* writeback work */ - struct work_struct i_pg_inv_work; /* page invalidation work */ - - struct work_struct i_vmtruncate_work; + struct work_struct i_work; + unsigned long i_work_mask; #ifdef CONFIG_CEPH_FSCACHE struct fscache_cookie *fscache; @@ -513,6 +509,13 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, /* + * Masks of ceph inode work. + */ +#define CEPH_I_WORK_WRITEBACK 0 /* writeback */ +#define CEPH_I_WORK_INVALIDATE_PAGES 1 /* invalidate pages */ +#define CEPH_I_WORK_VMTRUNCATE 2 /* vmtruncate */ + +/* * We set the ERROR_WRITE bit when we start seeing write errors on an inode * and then clear it when they start succeeding. Note that we do a lockless * check first, and only take the lock if it looks like it needs to be changed. @@ -896,9 +899,9 @@ extern int ceph_inode_holds_cap(struct inode *inode, int mask); extern bool ceph_inode_set_size(struct inode *inode, loff_t size); extern void __ceph_do_pending_vmtruncate(struct inode *inode); extern void ceph_queue_vmtruncate(struct inode *inode); - extern void ceph_queue_invalidate(struct inode *inode); extern void ceph_queue_writeback(struct inode *inode); +extern void ceph_async_iput(struct inode *inode); extern int __ceph_do_getattr(struct inode *inode, struct page *locked_page, int mask, bool force); @@ -1083,6 +1086,7 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg); /* export.c */ extern const struct export_operations ceph_export_ops; +struct inode *ceph_lookup_inode(struct super_block *sb, u64 ino); /* locks.c */ extern __init void ceph_flock_init(void); @@ -1098,7 +1102,7 @@ extern int ceph_locks_to_pagelist(struct ceph_filelock *flocks, int num_fcntl_locks, int num_flock_locks); /* debugfs.c */ -extern int ceph_fs_debugfs_init(struct ceph_fs_client *client); +extern void ceph_fs_debugfs_init(struct ceph_fs_client *client); extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client); /* quota.c */ @@ -1133,5 +1137,6 @@ extern bool ceph_quota_is_max_bytes_approaching(struct inode *inode, loff_t newlen); extern bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf); +extern void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc); #endif /* _FS_CEPH_SUPER_H */ diff --git a/fs/char_dev.c b/fs/char_dev.c index d18cad28c1c3..00dfe17871ac 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -98,7 +98,7 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, int minorct, const char *name) { struct char_device_struct *cd, *curr, *prev = NULL; - int ret = -EBUSY; + int ret; int i; if (major >= CHRDEV_MAJOR_MAX) { @@ -129,6 +129,7 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, major = ret; } + ret = -EBUSY; i = major_to_index(major); for (curr = chrdevs[i]; curr; prev = curr, curr = curr->next) { if (curr->major < major) diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 76724efc831c..523e9ea78a28 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config CIFS tristate "SMB3 and CIFS support (advanced network filesystem)" depends on INET @@ -9,7 +10,7 @@ config CIFS select CRYPTO_SHA512 select CRYPTO_CMAC select CRYPTO_HMAC - select CRYPTO_ARC4 + select CRYPTO_LIB_ARC4 select CRYPTO_AEAD2 select CRYPTO_CCM select CRYPTO_ECB diff --git a/fs/cifs/asn1.c b/fs/cifs/asn1.c index 3d19595eb352..689162e2e175 100644 --- a/fs/cifs/asn1.c +++ b/fs/cifs/asn1.c @@ -1,20 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * The ASB.1/BER parsing code is derived from ip_nat_snmp_basic.c which was in * turn derived from the gxsnmp package by Gregory McLean & Jochen Friedrich * * Copyright (c) 2000 RP Internet (www.rpi.net.au). - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/module.h> diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 6a69f11aacf7..ec933fb0b36e 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * fs/cifs_debug.c * * Copyright (C) International Business Machines Corp., 2000,2005 * * Modified by Steve French (sfrench@us.ibm.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> #include <linux/string.h> @@ -380,6 +367,8 @@ skip_rdma: atomic_read(&server->in_send), atomic_read(&server->num_waiters)); #endif + /* dump session id helpful for use with network trace */ + seq_printf(m, " SessionId: 0x%llx", ses->Suid); if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) seq_puts(m, " encrypted"); if (ses->sign) diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index 631dc1bb21c1..3d392620a2f4 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * * Copyright (c) International Business Machines Corp., 2000,2002 * Modified by Steve French (sfrench@us.ibm.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * */ #ifndef _H_CIFS_DEBUG diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 5d83c924cc47..41957b82d796 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Contains the CIFS DFS referral mounting routines used for handling * traversal via DFS junction point @@ -6,10 +7,6 @@ * Copyright (C) International Business Machines Corp., 2008 * Author(s): Igor Mammedov (niallain@gmail.com) * Steve French (sfrench@us.ibm.com) - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/dcache.h> diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index a2b2355e7f01..498777d859eb 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * fs/cifs/cifs_unicode.c * * Copyright (c) International Business Machines Corp., 2000,2009 * Modified by Steve French (sfrench@us.ibm.com) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> #include <linux/slab.h> diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h index 8360b74530a9..80b3d845419f 100644 --- a/fs/cifs/cifs_unicode.h +++ b/fs/cifs/cifs_unicode.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * cifs_unicode: Unicode kernel case support * @@ -7,28 +8,12 @@ * * Copyright (c) International Business Machines Corp., 2000,2009 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * * Notes: * These APIs are based on the C library functions. The semantics * should match the C functions but with expanded size operands. * * The upper/lower functions are based on a table created by mkupr. * This is a compressed table of upper and lower case conversion. - * */ #ifndef _CIFS_UNICODE_H #define _CIFS_UNICODE_H diff --git a/fs/cifs/cifs_uniupr.h b/fs/cifs/cifs_uniupr.h index 0ac7c5a8633a..7b272fcdf0d3 100644 --- a/fs/cifs/cifs_uniupr.h +++ b/fs/cifs/cifs_uniupr.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) International Business Machines Corp., 2000,2002 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * uniupr.h - Unicode compressed case ranges - * */ #ifndef UNIUPR_NOUPPER diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index d2a05e46d6f5..97b7497c13ef 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -33,7 +33,8 @@ #include <linux/ctype.h> #include <linux/random.h> #include <linux/highmem.h> -#include <crypto/skcipher.h> +#include <linux/fips.h> +#include <crypto/arc4.h> #include <crypto/aead.h> int __cifs_calc_signature(struct smb_rqst *rqst, @@ -772,63 +773,32 @@ setup_ntlmv2_rsp_ret: int calc_seckey(struct cifs_ses *ses) { - int rc; - struct crypto_skcipher *tfm_arc4; - struct scatterlist sgin, sgout; - struct skcipher_request *req; - unsigned char *sec_key; + unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */ + struct arc4_ctx *ctx_arc4; - sec_key = kmalloc(CIFS_SESS_KEY_SIZE, GFP_KERNEL); - if (sec_key == NULL) - return -ENOMEM; + if (fips_enabled) + return -ENODEV; get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE); - tfm_arc4 = crypto_alloc_skcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm_arc4)) { - rc = PTR_ERR(tfm_arc4); - cifs_dbg(VFS, "could not allocate crypto API arc4\n"); - goto out; - } - - rc = crypto_skcipher_setkey(tfm_arc4, ses->auth_key.response, - CIFS_SESS_KEY_SIZE); - if (rc) { - cifs_dbg(VFS, "%s: Could not set response as a key\n", - __func__); - goto out_free_cipher; - } - - req = skcipher_request_alloc(tfm_arc4, GFP_KERNEL); - if (!req) { - rc = -ENOMEM; - cifs_dbg(VFS, "could not allocate crypto API arc4 request\n"); - goto out_free_cipher; + ctx_arc4 = kmalloc(sizeof(*ctx_arc4), GFP_KERNEL); + if (!ctx_arc4) { + cifs_dbg(VFS, "could not allocate arc4 context\n"); + return -ENOMEM; } - sg_init_one(&sgin, sec_key, CIFS_SESS_KEY_SIZE); - sg_init_one(&sgout, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE); - - skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sgin, &sgout, CIFS_CPHTXT_SIZE, NULL); - - rc = crypto_skcipher_encrypt(req); - skcipher_request_free(req); - if (rc) { - cifs_dbg(VFS, "could not encrypt session key rc: %d\n", rc); - goto out_free_cipher; - } + arc4_setkey(ctx_arc4, ses->auth_key.response, CIFS_SESS_KEY_SIZE); + arc4_crypt(ctx_arc4, ses->ntlmssp->ciphertext, sec_key, + CIFS_CPHTXT_SIZE); /* make secondary_key/nonce as session key */ memcpy(ses->auth_key.response, sec_key, CIFS_SESS_KEY_SIZE); /* and make len as that of session key only */ ses->auth_key.len = CIFS_SESS_KEY_SIZE; -out_free_cipher: - crypto_free_skcipher(tfm_arc4); -out: - kfree(sec_key); - return rc; + memzero_explicit(sec_key, CIFS_SESS_KEY_SIZE); + kzfree(ctx_arc4); + return 0; } void diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index b1a5fcfa3ce1..24635b65effa 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -303,6 +303,7 @@ cifs_alloc_inode(struct super_block *sb) cifs_inode->uniqueid = 0; cifs_inode->createtime = 0; cifs_inode->epoch = 0; + spin_lock_init(&cifs_inode->open_file_lock); generate_random_uuid(cifs_inode->lease_key); /* @@ -878,6 +879,9 @@ out: static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) { + struct cifsFileInfo *cfile = file->private_data; + struct cifs_tcon *tcon; + /* * whence == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate * the cached file length @@ -909,6 +913,12 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int whence) if (rc < 0) return (loff_t)rc; } + if (cfile && cfile->tlink) { + tcon = tlink_tcon(cfile->tlink); + if (tcon->ses->server->ops->llseek) + return tcon->ses->server->ops->llseek(file, tcon, + offset, whence); + } return generic_file_llseek(file, offset, whence); } @@ -1070,11 +1080,6 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, cifs_dbg(FYI, "copychunk range\n"); - if (src_inode == target_inode) { - rc = -EINVAL; - goto out; - } - if (!src_file->private_data || !dst_file->private_data) { rc = -EBADF; cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n"); @@ -1144,6 +1149,10 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff, len, flags); free_xid(xid); + + if (rc == -EOPNOTSUPP || rc == -EXDEV) + rc = generic_copy_file_range(src_file, off, dst_file, + destoff, len, flags); return rc; } @@ -1586,7 +1595,6 @@ MODULE_DESCRIPTION ("VFS to access SMB3 servers e.g. Samba, Macs, Azure and Windows (and " "also older servers complying with the SNIA CIFS Specification)"); MODULE_VERSION(CIFS_VERSION); -MODULE_SOFTDEP("pre: arc4"); MODULE_SOFTDEP("pre: des"); MODULE_SOFTDEP("pre: ecb"); MODULE_SOFTDEP("pre: hmac"); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 33c251b408aa..4777b3c4a92c 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -497,6 +497,8 @@ struct smb_version_operations { /* version specific fiemap implementation */ int (*fiemap)(struct cifs_tcon *tcon, struct cifsFileInfo *, struct fiemap_extent_info *, u64, u64); + /* version specific llseek implementation */ + loff_t (*llseek)(struct file *, struct cifs_tcon *, loff_t, int); }; struct smb_version_values { @@ -1375,6 +1377,7 @@ struct cifsInodeInfo { struct rw_semaphore lock_sem; /* protect the fields above */ /* BB add in lists for dirty pages i.e. write caching info for oplock */ struct list_head openFileList; + spinlock_t open_file_lock; /* protects openFileList */ __u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */ unsigned int oplock; /* oplock/lease level we have */ unsigned int epoch; /* used to track lease state changes */ @@ -1778,10 +1781,14 @@ require use of the stronger protocol */ * tcp_ses_lock protects: * list operations on tcp and SMB session lists * tcon->open_file_lock protects the list of open files hanging off the tcon + * inode->open_file_lock protects the openFileList hanging off the inode * cfile->file_info_lock protects counters and fields in cifs file struct * f_owner.lock protects certain per file struct operations * mapping->page_lock protects certain per page operations * + * Note that the cifs_tcon.open_file_lock should be taken before + * not after the cifsInodeInfo.open_file_lock + * * Semaphores * ---------- * sesSem operations on smb session diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 084756cfdaee..714a359c7c8d 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -476,6 +476,7 @@ cifs_reconnect(struct TCP_Server_Info *server) spin_lock(&GlobalMid_Lock); server->nr_targets = 1; #ifdef CONFIG_CIFS_DFS_UPCALL + spin_unlock(&GlobalMid_Lock); cifs_sb = find_super_by_tcp(server); if (IS_ERR(cifs_sb)) { rc = PTR_ERR(cifs_sb); @@ -493,6 +494,7 @@ cifs_reconnect(struct TCP_Server_Info *server) } cifs_dbg(FYI, "%s: will retry %d target(s)\n", __func__, server->nr_targets); + spin_lock(&GlobalMid_Lock); #endif if (server->tcpStatus == CifsExiting) { /* the demux thread will exit normally @@ -528,6 +530,21 @@ cifs_reconnect(struct TCP_Server_Info *server) /* do not want to be sending data on a socket we are freeing */ cifs_dbg(FYI, "%s: tearing down socket\n", __func__); mutex_lock(&server->srv_mutex); + if (server->ssocket) { + cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", + server->ssocket->state, server->ssocket->flags); + kernel_sock_shutdown(server->ssocket, SHUT_WR); + cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n", + server->ssocket->state, server->ssocket->flags); + sock_release(server->ssocket); + server->ssocket = NULL; + } + server->sequence_number = 0; + server->session_estab = false; + kfree(server->session_key.response); + server->session_key.response = NULL; + server->session_key.len = 0; + server->lstrp = jiffies; /* mark submitted MIDs for retry and issue callback */ INIT_LIST_HEAD(&retry_list); @@ -540,6 +557,7 @@ cifs_reconnect(struct TCP_Server_Info *server) list_move(&mid_entry->qhead, &retry_list); } spin_unlock(&GlobalMid_Lock); + mutex_unlock(&server->srv_mutex); cifs_dbg(FYI, "%s: issuing mid callbacks\n", __func__); list_for_each_safe(tmp, tmp2, &retry_list) { @@ -548,24 +566,11 @@ cifs_reconnect(struct TCP_Server_Info *server) mid_entry->callback(mid_entry); } - if (server->ssocket) { - cifs_dbg(FYI, "State: 0x%x Flags: 0x%lx\n", - server->ssocket->state, server->ssocket->flags); - kernel_sock_shutdown(server->ssocket, SHUT_WR); - cifs_dbg(FYI, "Post shutdown state: 0x%x Flags: 0x%lx\n", - server->ssocket->state, server->ssocket->flags); - sock_release(server->ssocket); - server->ssocket = NULL; - } else if (cifs_rdma_enabled(server)) + if (cifs_rdma_enabled(server)) { + mutex_lock(&server->srv_mutex); smbd_destroy(server); - server->sequence_number = 0; - server->session_estab = false; - kfree(server->session_key.response); - server->session_key.response = NULL; - server->session_key.len = 0; - server->lstrp = jiffies; - - mutex_unlock(&server->srv_mutex); + mutex_unlock(&server->srv_mutex); + } do { try_to_freeze(); @@ -2443,6 +2448,10 @@ match_port(struct TCP_Server_Info *server, struct sockaddr *addr) { __be16 port, *sport; + /* SMBDirect manages its own ports, don't match it here */ + if (server->rdma) + return true; + switch (addr->sa_family) { case AF_INET: sport = &((struct sockaddr_in *) &server->dstaddr)->sin_port; @@ -2622,7 +2631,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) task = xchg(&server->tsk, NULL); if (task) - force_sig(SIGKILL, task); + send_sig(SIGKILL, task, 1); } static struct TCP_Server_Info * diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 85dc89d3a203..e3e1c13df439 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -132,7 +132,7 @@ static inline void flush_cache_ent(struct dfs_cache_entry *ce) return; hlist_del_init_rcu(&ce->ce_hlist); - kfree(ce->ce_path); + kfree_const(ce->ce_path); free_tgts(ce); dfs_cache_count--; call_rcu(&ce->ce_rcu, free_cache_entry); @@ -422,7 +422,7 @@ alloc_cache_entry(const char *path, const struct dfs_info3_param *refs, rc = copy_ref_data(refs, numrefs, ce, NULL); if (rc) { - kfree(ce->ce_path); + kfree_const(ce->ce_path); kmem_cache_free(dfs_cache_slab, ce); ce = ERR_PTR(rc); } diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 7ede7306599f..534cbba72789 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -77,7 +77,8 @@ dns_resolve_server_name_to_ip(const char *unc, char **ip_addr) goto name_is_IP_address; /* Perform the upcall */ - rc = dns_query(NULL, hostname, len, NULL, ip_addr, NULL); + rc = dns_query(current->nsproxy->net_ns, NULL, hostname, len, + NULL, ip_addr, NULL, false); if (rc < 0) cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n", __func__, len, len, hostname); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index ce9a5be11df5..97090693d182 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -338,10 +338,12 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, atomic_inc(&tcon->num_local_opens); /* if readable file instance put first in list*/ + spin_lock(&cinode->open_file_lock); if (file->f_mode & FMODE_READ) list_add(&cfile->flist, &cinode->openFileList); else list_add_tail(&cfile->flist, &cinode->openFileList); + spin_unlock(&cinode->open_file_lock); spin_unlock(&tcon->open_file_lock); if (fid->purge_cache) @@ -413,7 +415,9 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler) cifs_add_pending_open_locked(&fid, cifs_file->tlink, &open); /* remove it from the lists */ + spin_lock(&cifsi->open_file_lock); list_del(&cifs_file->flist); + spin_unlock(&cifsi->open_file_lock); list_del(&cifs_file->tlist); atomic_dec(&tcon->num_local_opens); @@ -1950,9 +1954,9 @@ refind_writable: return 0; } - spin_lock(&tcon->open_file_lock); + spin_lock(&cifs_inode->open_file_lock); list_move_tail(&inv_file->flist, &cifs_inode->openFileList); - spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_inode->open_file_lock); cifsFileInfo_put(inv_file); ++refind; inv_file = NULL; @@ -3216,7 +3220,9 @@ cifs_read_allocate_pages(struct cifs_readdata *rdata, unsigned int nr_pages) } if (rc) { - for (i = 0; i < nr_pages; i++) { + unsigned int nr_page_failed = i; + + for (i = 0; i < nr_page_failed; i++) { put_page(rdata->pages[i]); rdata->pages[i] = NULL; } diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index fdd908e4a26b..ed92958e842d 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * fs/cifs/netmisc.c * @@ -6,20 +7,6 @@ * * Error mapping routines from Samba libsmb/errormap.c * Copyright (C) Andrew Tridgell 2001 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/net.h> diff --git a/fs/cifs/nterr.c b/fs/cifs/nterr.c index b6023c646123..358a766375b4 100644 --- a/fs/cifs/nterr.c +++ b/fs/cifs/nterr.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Unix SMB/Netbios implementation. * Version 1.9. * RPC Pipe client / server routines * Copyright (C) Luke Kenneth Casson Leighton 1997-2001. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ /* NT error codes - see nterr.h */ diff --git a/fs/cifs/nterr.h b/fs/cifs/nterr.h index 7a0eae5ae7c9..edd4741cab0a 100644 --- a/fs/cifs/nterr.h +++ b/fs/cifs/nterr.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* Unix SMB/Netbios implementation. Version 1.9. @@ -7,19 +8,6 @@ Copyright (C) Luke Kenneth Casson Leighton 1996-2000 Copyright (C) Paul Ashton 1998-2000 - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index c4e75afa3258..9e430ae9314f 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -1,20 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * SMB1 (CIFS) version specific operations * * Copyright (c) 2012, Jeff Layton <jlayton@redhat.com> - * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License v2 as published - * by the Free Software Foundation. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/pagemap.h> diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index e32c264e3adb..82ade16c9501 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -457,7 +457,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_FILE_INVALID, -EIO, "STATUS_FILE_INVALID"}, {STATUS_ALLOTTED_SPACE_EXCEEDED, -EIO, "STATUS_ALLOTTED_SPACE_EXCEEDED"}, - {STATUS_INSUFFICIENT_RESOURCES, -EREMOTEIO, + {STATUS_INSUFFICIENT_RESOURCES, -EAGAIN, "STATUS_INSUFFICIENT_RESOURCES"}, {STATUS_DFS_EXIT_PATH_FOUND, -EIO, "STATUS_DFS_EXIT_PATH_FOUND"}, {STATUS_DEVICE_DATA_ERROR, -EIO, "STATUS_DEVICE_DATA_ERROR"}, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index a930c8965e5c..9fd56b0acd7e 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1,20 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * SMB2 version specific operations * * Copyright (c) 2012, Jeff Layton <jlayton@redhat.com> - * - * This library is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License v2 as published - * by the Free Software Foundation. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this library; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/pagemap.h> @@ -282,7 +270,7 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) __u64 wire_mid = le64_to_cpu(shdr->MessageId); if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) { - cifs_dbg(VFS, "encrypted frame parsing not supported yet"); + cifs_dbg(VFS, "Encrypted frame parsing not supported yet\n"); return NULL; } @@ -324,6 +312,7 @@ static int smb2_negotiate(const unsigned int xid, struct cifs_ses *ses) { int rc; + ses->server->CurrentMid = 0; rc = SMB2_negotiate(xid, ses); /* BB we probably don't need to retry with modern servers */ @@ -789,8 +778,6 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); else close_shroot(&tcon->crfid); - - return; } static void @@ -818,7 +805,6 @@ smb2_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid, FS_DEVICE_INFORMATION); SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); - return; } static int @@ -906,9 +892,8 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, value = &src->ea_data[src->ea_name_length + 1]; value_len = (size_t)le16_to_cpu(src->ea_value_length); - if (name_len == 0) { + if (name_len == 0) break; - } if (src_size < 8 + name_len + 1 + value_len) { cifs_dbg(FYI, "EA entry goes beyond length of list\n"); @@ -1161,6 +1146,7 @@ static void smb2_clear_stats(struct cifs_tcon *tcon) { int i; + for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) { atomic_set(&tcon->stats.smb2_stats.smb2_com_sent[i], 0); atomic_set(&tcon->stats.smb2_stats.smb2_com_failed[i], 0); @@ -1529,7 +1515,7 @@ smb2_copychunk_range(const unsigned int xid, if (pcchunk == NULL) return -ENOMEM; - cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n"); + cifs_dbg(FYI, "%s: about to call request res key\n", __func__); /* Request a key from the server to identify the source of the copy */ rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink), srcfile->fid.persistent_fid, @@ -1649,6 +1635,7 @@ static unsigned int smb2_read_data_offset(char *buf) { struct smb2_read_rsp *rsp = (struct smb2_read_rsp *)buf; + return rsp->DataOffset; } @@ -1777,7 +1764,7 @@ smb2_duplicate_extents(const unsigned int xid, dup_ext_buf.SourceFileOffset = cpu_to_le64(src_off); dup_ext_buf.TargetFileOffset = cpu_to_le64(dest_off); dup_ext_buf.ByteCount = cpu_to_le64(len); - cifs_dbg(FYI, "duplicate extents: src off %lld dst off %lld len %lld", + cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n", src_off, dest_off, len); rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); @@ -1794,7 +1781,7 @@ smb2_duplicate_extents(const unsigned int xid, &ret_data_len); if (ret_data_len > 0) - cifs_dbg(FYI, "non-zero response length in duplicate extents"); + cifs_dbg(FYI, "Non-zero response length in duplicate extents\n"); duplicate_extents_out: return rc; @@ -1983,9 +1970,9 @@ smb2_close_dir(const unsigned int xid, struct cifs_tcon *tcon, } /* -* If we negotiate SMB2 protocol and get STATUS_PENDING - update -* the number of credits and return true. Otherwise - return false. -*/ + * If we negotiate SMB2 protocol and get STATUS_PENDING - update + * the number of credits and return true. Otherwise - return false. + */ static bool smb2_is_status_pending(char *buf, struct TCP_Server_Info *server) { @@ -2306,7 +2293,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, struct get_dfs_referral_rsp *dfs_rsp = NULL; u32 dfs_req_size = 0, dfs_rsp_size = 0; - cifs_dbg(FYI, "smb2_get_dfs_refer path <%s>\n", search_name); + cifs_dbg(FYI, "%s: path: %s\n", __func__, search_name); /* * Try to use the IPC tcon, otherwise just use any @@ -2360,7 +2347,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, if (rc) { if ((rc != -ENOENT) && (rc != -EOPNOTSUPP)) - cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); + cifs_dbg(VFS, "ioctl error in %s rc=%d\n", __func__, rc); goto out; } @@ -2369,7 +2356,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, nls_codepage, remap, search_name, true /* is_unicode */); if (rc) { - cifs_dbg(VFS, "parse error in smb2_get_dfs_refer rc=%d\n", rc); + cifs_dbg(VFS, "parse error in %s rc=%d\n", __func__, rc); goto out; } @@ -2385,6 +2372,41 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, kfree(dfs_rsp); return rc; } + +static int +parse_reparse_symlink(struct reparse_symlink_data_buffer *symlink_buf, + u32 plen, char **target_path, + struct cifs_sb_info *cifs_sb) +{ + unsigned int sub_len; + unsigned int sub_offset; + + /* We only handle Symbolic Link : MS-FSCC 2.1.2.4 */ + if (le32_to_cpu(symlink_buf->ReparseTag) != IO_REPARSE_TAG_SYMLINK) { + cifs_dbg(VFS, "srv returned invalid symlink buffer\n"); + return -EIO; + } + + sub_offset = le16_to_cpu(symlink_buf->SubstituteNameOffset); + sub_len = le16_to_cpu(symlink_buf->SubstituteNameLength); + if (sub_offset + 20 > plen || + sub_offset + sub_len + 20 > plen) { + cifs_dbg(VFS, "srv returned malformed symlink buffer\n"); + return -EIO; + } + + *target_path = cifs_strndup_from_utf16( + symlink_buf->PathBuffer + sub_offset, + sub_len, true, cifs_sb->local_nls); + if (!(*target_path)) + return -ENOMEM; + + convert_delimiter(*target_path, '/'); + cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + + return 0; +} + #define SMB2_SYMLINK_STRUCT_SIZE \ (sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp)) @@ -2414,11 +2436,13 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct kvec close_iov[1]; struct smb2_create_rsp *create_rsp; struct smb2_ioctl_rsp *ioctl_rsp; - char *ioctl_buf; + struct reparse_data_buffer *reparse_buf; u32 plen; cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path); + *target_path = NULL; + if (smb3_encryption_required(tcon)) flags |= CIFS_TRANSFORM_REQ; @@ -2496,17 +2520,36 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, if ((rc == 0) && (is_reparse_point)) { /* See MS-FSCC 2.3.23 */ - ioctl_buf = (char *)ioctl_rsp + le32_to_cpu(ioctl_rsp->OutputOffset); + reparse_buf = (struct reparse_data_buffer *) + ((char *)ioctl_rsp + + le32_to_cpu(ioctl_rsp->OutputOffset)); plen = le32_to_cpu(ioctl_rsp->OutputCount); if (plen + le32_to_cpu(ioctl_rsp->OutputOffset) > rsp_iov[1].iov_len) { - cifs_dbg(VFS, "srv returned invalid ioctl length: %d\n", plen); + cifs_dbg(VFS, "srv returned invalid ioctl len: %d\n", + plen); rc = -EIO; goto querty_exit; } - /* Do stuff with ioctl_buf/plen */ + if (plen < 8) { + cifs_dbg(VFS, "reparse buffer is too small. Must be " + "at least 8 bytes but was %d\n", plen); + rc = -EIO; + goto querty_exit; + } + + if (plen < le16_to_cpu(reparse_buf->ReparseDataLength) + 8) { + cifs_dbg(VFS, "srv returned invalid reparse buf " + "length: %d\n", plen); + rc = -EIO; + goto querty_exit; + } + + rc = parse_reparse_symlink( + (struct reparse_symlink_data_buffer *)reparse_buf, + plen, target_path, cifs_sb); goto querty_exit; } @@ -2745,7 +2788,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, inode = d_inode(cfile->dentry); cifsi = CIFS_I(inode); - trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, + trace_smb3_zero_enter(xid, cfile->fid.persistent_fid, tcon->tid, ses->Suid, offset, len); @@ -2759,7 +2802,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, return rc; } - cifs_dbg(FYI, "offset %lld len %lld", offset, len); + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); fsctl_buf.FileOffset = cpu_to_le64(offset); fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); @@ -2816,7 +2859,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, return rc; } - cifs_dbg(FYI, "offset %lld len %lld", offset, len); + cifs_dbg(FYI, "Offset %lld len %lld\n", offset, len); fsctl_buf.FileOffset = cpu_to_le64(offset); fsctl_buf.BeyondFinalZero = cpu_to_le64(offset + len); @@ -2922,6 +2965,90 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, return rc; } +static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offset, int whence) +{ + struct cifsFileInfo *wrcfile, *cfile = file->private_data; + struct cifsInodeInfo *cifsi; + struct inode *inode; + int rc = 0; + struct file_allocated_range_buffer in_data, *out_data = NULL; + u32 out_data_len; + unsigned int xid; + + if (whence != SEEK_HOLE && whence != SEEK_DATA) + return generic_file_llseek(file, offset, whence); + + inode = d_inode(cfile->dentry); + cifsi = CIFS_I(inode); + + if (offset < 0 || offset >= i_size_read(inode)) + return -ENXIO; + + xid = get_xid(); + /* + * We need to be sure that all dirty pages are written as they + * might fill holes on the server. + * Note that we also MUST flush any written pages since at least + * some servers (Windows2016) will not reflect recent writes in + * QUERY_ALLOCATED_RANGES until SMB2_flush is called. + */ + wrcfile = find_writable_file(cifsi, false); + if (wrcfile) { + filemap_write_and_wait(inode->i_mapping); + smb2_flush_file(xid, tcon, &wrcfile->fid); + cifsFileInfo_put(wrcfile); + } + + if (!(cifsi->cifsAttrs & FILE_ATTRIBUTE_SPARSE_FILE)) { + if (whence == SEEK_HOLE) + offset = i_size_read(inode); + goto lseek_exit; + } + + in_data.file_offset = cpu_to_le64(offset); + in_data.length = cpu_to_le64(i_size_read(inode)); + + rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + FSCTL_QUERY_ALLOCATED_RANGES, true, + (char *)&in_data, sizeof(in_data), + sizeof(struct file_allocated_range_buffer), + (char **)&out_data, &out_data_len); + if (rc == -E2BIG) + rc = 0; + if (rc) + goto lseek_exit; + + if (whence == SEEK_HOLE && out_data_len == 0) + goto lseek_exit; + + if (whence == SEEK_DATA && out_data_len == 0) { + rc = -ENXIO; + goto lseek_exit; + } + + if (out_data_len < sizeof(struct file_allocated_range_buffer)) { + rc = -EINVAL; + goto lseek_exit; + } + if (whence == SEEK_DATA) { + offset = le64_to_cpu(out_data->file_offset); + goto lseek_exit; + } + if (offset < le64_to_cpu(out_data->file_offset)) + goto lseek_exit; + + offset = le64_to_cpu(out_data->file_offset) + le64_to_cpu(out_data->length); + + lseek_exit: + free_xid(xid); + kfree(out_data); + if (!rc) + return vfs_setpos(file, offset, inode->i_sb->s_maxbytes); + else + return rc; +} + static int smb3_fiemap(struct cifs_tcon *tcon, struct cifsFileInfo *cfile, struct fiemap_extent_info *fei, u64 start, u64 len) @@ -3384,7 +3511,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, req = aead_request_alloc(tfm, GFP_KERNEL); if (!req) { - cifs_dbg(VFS, "%s: Failed to alloc aead request", __func__); + cifs_dbg(VFS, "%s: Failed to alloc aead request\n", __func__); return -ENOMEM; } @@ -3395,7 +3522,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, sg = init_sg(num_rqst, rqst, sign); if (!sg) { - cifs_dbg(VFS, "%s: Failed to init sg", __func__); + cifs_dbg(VFS, "%s: Failed to init sg\n", __func__); rc = -ENOMEM; goto free_req; } @@ -3403,7 +3530,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, iv_len = crypto_aead_ivsize(tfm); iv = kzalloc(iv_len, GFP_KERNEL); if (!iv) { - cifs_dbg(VFS, "%s: Failed to alloc IV", __func__); + cifs_dbg(VFS, "%s: Failed to alloc iv\n", __func__); rc = -ENOMEM; goto free_sg; } @@ -3511,7 +3638,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst, fill_transform_hdr(tr_hdr, orig_len, old_rq); rc = crypt_message(server, num_rqst, new_rq, 1); - cifs_dbg(FYI, "encrypt message returned %d", rc); + cifs_dbg(FYI, "Encrypt message returned %d\n", rc); if (rc) goto err_free; @@ -3552,7 +3679,7 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf, rqst.rq_tailsz = (page_data_size % PAGE_SIZE) ? : PAGE_SIZE; rc = crypt_message(server, 1, &rqst, 0); - cifs_dbg(FYI, "decrypt message returned %d\n", rc); + cifs_dbg(FYI, "Decrypt message returned %d\n", rc); if (rc) return rc; @@ -4166,6 +4293,7 @@ struct smb_version_operations smb20_operations = { .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_operations smb21_operations = { @@ -4266,6 +4394,7 @@ struct smb_version_operations smb21_operations = { .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_operations smb30_operations = { @@ -4375,6 +4504,7 @@ struct smb_version_operations smb30_operations = { .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_operations smb311_operations = { @@ -4485,6 +4615,7 @@ struct smb_version_operations smb311_operations = { .ioctl_query_info = smb2_ioctl_query_info, .make_node = smb2_make_node, .fiemap = smb3_fiemap, + .llseek = smb3_llseek, }; struct smb_version_values smb20_values = { diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 29f011d8d8e2..75311a8a68bf 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1054,7 +1054,8 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) * not supported error. Client should accept it. */ cifs_dbg(VFS, "Server does not support validate negotiate\n"); - return 0; + rc = 0; + goto out_free_inbuf; } else if (rc != 0) { cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc); rc = -EIO; @@ -2538,11 +2539,25 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, struct kvec *iov = rqst->rq_iov; unsigned int total_len; int rc; + char *in_data_buf; rc = smb2_plain_req_init(SMB2_IOCTL, tcon, (void **) &req, &total_len); if (rc) return rc; + if (indatalen) { + /* + * indatalen is usually small at a couple of bytes max, so + * just allocate through generic pool + */ + in_data_buf = kmalloc(indatalen, GFP_NOFS); + if (!in_data_buf) { + cifs_small_buf_release(req); + return -ENOMEM; + } + memcpy(in_data_buf, in_data, indatalen); + } + req->CtlCode = cpu_to_le32(opcode); req->PersistentFileId = persistent_fid; req->VolatileFileId = volatile_fid; @@ -2563,7 +2578,7 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, cpu_to_le32(offsetof(struct smb2_ioctl_req, Buffer)); rqst->rq_nvec = 2; iov[0].iov_len = total_len - 1; - iov[1].iov_base = in_data; + iov[1].iov_base = in_data_buf; iov[1].iov_len = indatalen; } else { rqst->rq_nvec = 1; @@ -2605,8 +2620,13 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, void SMB2_ioctl_free(struct smb_rqst *rqst) { - if (rqst && rqst->rq_iov) + int i; + if (rqst && rqst->rq_iov) { cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */ + for (i = 1; i < rqst->rq_nvec; i++) + if (rqst->rq_iov[i].iov_base != smb2_padding) + kfree(rqst->rq_iov[i].iov_base); + } } @@ -3094,9 +3114,14 @@ void smb2_reconnect_server(struct work_struct *work) tcon_exist = true; } } + /* + * IPC has the same lifetime as its session and uses its + * refcount. + */ if (ses->tcon_ipc && ses->tcon_ipc->need_reconnect) { list_add_tail(&ses->tcon_ipc->rlist, &tmp_list); tcon_exist = true; + ses->ses_count++; } } /* @@ -3115,7 +3140,10 @@ void smb2_reconnect_server(struct work_struct *work) else resched = true; list_del_init(&tcon->rlist); - cifs_put_tcon(tcon); + if (tcon->ipc) + cifs_put_smb_ses(tcon->ses); + else + cifs_put_tcon(tcon); } cifs_dbg(FYI, "Reconnecting tcons finished\n"); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index c7d5813bebd8..858353d20c39 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -914,7 +914,19 @@ struct reparse_mount_point_data_buffer { __u8 PathBuffer[0]; /* Variable Length */ } __packed; -/* See MS-FSCC 2.1.2.4 and cifspdu.h for struct reparse_symlink_data */ +#define SYMLINK_FLAG_RELATIVE 0x00000001 + +struct reparse_symlink_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le16 SubstituteNameOffset; + __le16 SubstituteNameLength; + __le16 PrintNameOffset; + __le16 PrintNameLength; + __le32 Flags; + __u8 PathBuffer[0]; /* Variable Length */ +} __packed; /* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */ diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 251ef1223206..cd07e5301d42 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -1,17 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2017, Microsoft Corporation. * * Author(s): Long Li <longli@microsoft.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. */ #include <linux/module.h> #include <linux/highmem.h> @@ -903,7 +894,7 @@ static int smbd_create_header(struct smbd_connection *info, request->sge[0].addr = ib_dma_map_single(info->id->device, (void *)packet, header_length, - DMA_BIDIRECTIONAL); + DMA_TO_DEVICE); if (ib_dma_mapping_error(info->id->device, request->sge[0].addr)) { mempool_free(request, info->request_mempool); rc = -EIO; @@ -1005,7 +996,7 @@ static int smbd_post_send_sgl(struct smbd_connection *info, for_each_sg(sgl, sg, num_sgs, i) { request->sge[i+1].addr = ib_dma_map_page(info->id->device, sg_page(sg), - sg->offset, sg->length, DMA_BIDIRECTIONAL); + sg->offset, sg->length, DMA_TO_DEVICE); if (ib_dma_mapping_error( info->id->device, request->sge[i+1].addr)) { rc = -EIO; @@ -2110,8 +2101,10 @@ int smbd_send(struct TCP_Server_Info *server, goto done; } - rqst_idx = 0; + log_write(INFO, "num_rqst=%d total length=%u\n", + num_rqst, remaining_data_length); + rqst_idx = 0; next_rqst: rqst = &rqst_array[rqst_idx]; iov = rqst->rq_iov; diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index f6241b8bce5f..6ff880a1e186 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -1,17 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) 2017, Microsoft Corporation. * * Author(s): Long Li <longli@microsoft.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. */ #ifndef _SMBDIRECT_H #define _SMBDIRECT_H diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c index a0b80ac651a6..2b6d87bfdf8e 100644 --- a/fs/cifs/smbencrypt.c +++ b/fs/cifs/smbencrypt.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Unix SMB/Netbios implementation. Version 1.9. @@ -8,19 +9,6 @@ Copyright (C) Andrew Bartlett <abartlet@samba.org> 2002-2003 Modified by Steve French (sfrench@us.ibm.com) 2002-2003 - This program is free software; you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation; either version 2 of the License, or - (at your option) any later version. - - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. - - You should have received a copy of the GNU General Public License - along with this program; if not, write to the Free Software - Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/crypto.h> diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 9a16ff4b9f5e..60661b3f983a 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -33,7 +33,7 @@ #include <linux/uaccess.h> #include <asm/processor.h> #include <linux/mempool.h> -#include <linux/signal.h> +#include <linux/sched/signal.h> #include "cifspdu.h" #include "cifsglob.h" #include "cifsproto.h" diff --git a/fs/cifs/winucase.c b/fs/cifs/winucase.c index 1506d4fddb2c..1a23a1d2ebf9 100644 --- a/fs/cifs/winucase.c +++ b/fs/cifs/winucase.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * fs/cifs/winucase.c * * Copyright (c) Jeffrey Layton <jlayton@redhat.com>, 2013 * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * * The const tables in this file were converted from the following info * provided by Microsoft: * diff --git a/fs/coda/Kconfig b/fs/coda/Kconfig index c0e5a7fad06d..ae6759f9594a 100644 --- a/fs/coda/Kconfig +++ b/fs/coda/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config CODA_FS tristate "Coda file system support (advanced network fs)" depends on INET diff --git a/fs/coda/Makefile b/fs/coda/Makefile index 1bab69a0d347..1ce66819da2a 100644 --- a/fs/coda/Makefile +++ b/fs/coda/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux Coda filesystem routines. # diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index c5234c21b539..0ceef32e6fae 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * An implementation of a loadable kernel mode driver providing * multiple kernel/user space bidirectional communications links. * * Author: Alan Cox <alan@lxorguk.ukuu.org.uk> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. * * Adapted to become the Linux 2.0 Coda pseudo device * Peter Braam <braam@maths.ox.ac.uk> @@ -39,7 +35,6 @@ #include <linux/device.h> #include <linux/pid_namespace.h> #include <asm/io.h> -#include <linux/poll.h> #include <linux/uaccess.h> #include <linux/coda.h> diff --git a/fs/compat.c b/fs/compat.c index 4a0aaaf53217..436d228cf71c 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/compat.c * @@ -9,10 +10,6 @@ * Copyright (C) 1998 Eddie C. Dost (ecd@skynet.be) * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs * Copyright (C) 2003 Pavel Machek (pavel@ucw.cz) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/compat.h> diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c index 15f6e96b3bd9..b7f9ffa1d5f1 100644 --- a/fs/compat_binfmt_elf.c +++ b/fs/compat_binfmt_elf.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * 32-bit compatibility support for ELF format executables and core dumps. * * Copyright (C) 2007 Red Hat, Inc. All rights reserved. * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License v.2. - * * Red Hat Author: Roland McGrath. * * This file is used in a 64-bit kernel that wants to support 32-bit ELF. diff --git a/fs/configfs/Kconfig b/fs/configfs/Kconfig index 9febcdefdfdc..272b64456999 100644 --- a/fs/configfs/Kconfig +++ b/fs/configfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config CONFIGFS_FS tristate "Userspace-driven configuration filesystem" select SYSFS diff --git a/fs/configfs/Makefile b/fs/configfs/Makefile index 00ffb278e98c..0200498ede27 100644 --- a/fs/configfs/Makefile +++ b/fs/configfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the configfs virtual filesystem # diff --git a/fs/configfs/configfs_internal.h b/fs/configfs/configfs_internal.h index ccc31fa6f1a7..f752d83a9c44 100644 --- a/fs/configfs/configfs_internal.h +++ b/fs/configfs/configfs_internal.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset:8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * configfs_internal.h - Internal stuff for configfs * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 591e82ba443c..92112915de8e 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * dir.c - Operations for configfs directories. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * @@ -27,6 +13,7 @@ #undef DEBUG #include <linux/fs.h> +#include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/module.h> #include <linux/slab.h> @@ -58,15 +45,13 @@ static void configfs_d_iput(struct dentry * dentry, if (sd) { /* Coordinate with configfs_readdir */ spin_lock(&configfs_dirent_lock); - /* Coordinate with configfs_attach_attr where will increase - * sd->s_count and update sd->s_dentry to new allocated one. - * Only set sd->dentry to null when this dentry is the only - * sd owner. - * If not do so, configfs_d_iput may run just after - * configfs_attach_attr and set sd->s_dentry to null - * even it's still in use. + /* + * Set sd->s_dentry to null only when this dentry is the one + * that is going to be killed. Otherwise configfs_d_iput may + * run just after configfs_attach_attr and set sd->s_dentry to + * NULL even it's still in use. */ - if (atomic_read(&sd->s_count) <= 2) + if (sd->s_dentry == dentry) sd->s_dentry = NULL; spin_unlock(&configfs_dirent_lock); @@ -1757,12 +1742,19 @@ int configfs_register_group(struct config_group *parent_group, inode_lock_nested(d_inode(parent), I_MUTEX_PARENT); ret = create_default_group(parent_group, group); - if (!ret) { - spin_lock(&configfs_dirent_lock); - configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); - spin_unlock(&configfs_dirent_lock); - } + if (ret) + goto err_out; + + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + inode_unlock(d_inode(parent)); + return 0; +err_out: inode_unlock(d_inode(parent)); + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); return ret; } EXPORT_SYMBOL(configfs_register_group); @@ -1797,6 +1789,7 @@ void configfs_unregister_group(struct config_group *group) configfs_detach_group(&group->cg_item); d_inode(dentry)->i_flags |= S_DEAD; dont_mount(dentry); + fsnotify_rmdir(d_inode(parent), dentry); d_delete(dentry); inode_unlock(d_inode(parent)); @@ -1925,6 +1918,7 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) configfs_detach_group(&group->cg_item); d_inode(dentry)->i_flags |= S_DEAD; dont_mount(dentry); + fsnotify_rmdir(d_inode(root), dentry); inode_unlock(d_inode(dentry)); d_delete(dentry); diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 62580dba3552..61e4db4390a1 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * file.c - operations for regular (text) files. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index 28ef9e528853..ab0284321912 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * inode.c - basic inode and dentry operations. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * diff --git a/fs/configfs/item.c b/fs/configfs/item.c index 99d491cd01f9..6e0f1fcb8a5b 100644 --- a/fs/configfs/item.c +++ b/fs/configfs/item.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * item.c - library routines for handling generic config items * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Based on kobject: * kobject is Copyright (c) 2002-2003 Patrick Mochel * diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index cfd91320e869..791304fdde9d 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * mount.c - operations for initializing and mounting configfs. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index a5c54af861f7..91eac6c55e07 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * symlink.c - operations for configfs symlinks. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Based on sysfs: * sysfs is Copyright (C) 2001, 2002, 2003 Patrick Mochel * diff --git a/fs/cramfs/Kconfig b/fs/cramfs/Kconfig index 5933f995309a..c8bebb70a971 100644 --- a/fs/cramfs/Kconfig +++ b/fs/cramfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config CRAMFS tristate "Compressed ROM file system support (cramfs)" select ZLIB_INFLATE diff --git a/fs/cramfs/Makefile b/fs/cramfs/Makefile index 92ebb464a725..8c3ed2982419 100644 --- a/fs/cramfs/Makefile +++ b/fs/cramfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux cramfs routines. # diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig index f0de238000c0..5fdf24877c17 100644 --- a/fs/crypto/Kconfig +++ b/fs/crypto/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config FS_ENCRYPTION bool "FS Encryption (Per-file encryption)" select CRYPTO @@ -6,7 +7,6 @@ config FS_ENCRYPTION select CRYPTO_ECB select CRYPTO_XTS select CRYPTO_CTS - select CRYPTO_SHA256 select KEYS help Enable encryption of files and directories. This diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile index cb496989a6b6..4f0df5e682e4 100644 --- a/fs/crypto/Makefile +++ b/fs/crypto/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_FS_ENCRYPTION) += fscrypto.o fscrypto-y := crypto.o fname.o hooks.o keyinfo.o policy.o diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index b46021ebde85..82da2510721f 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -33,9 +33,8 @@ static void __fscrypt_decrypt_bio(struct bio *bio, bool done) bio_for_each_segment_all(bv, bio, iter_all) { struct page *page = bv->bv_page; - int ret = fscrypt_decrypt_page(page->mapping->host, page, - PAGE_SIZE, 0, page->index); - + int ret = fscrypt_decrypt_pagecache_blocks(page, bv->bv_len, + bv->bv_offset); if (ret) SetPageError(page); else if (done) @@ -53,9 +52,8 @@ EXPORT_SYMBOL(fscrypt_decrypt_bio); static void completion_pages(struct work_struct *work) { - struct fscrypt_ctx *ctx = - container_of(work, struct fscrypt_ctx, r.work); - struct bio *bio = ctx->r.bio; + struct fscrypt_ctx *ctx = container_of(work, struct fscrypt_ctx, work); + struct bio *bio = ctx->bio; __fscrypt_decrypt_bio(bio, true); fscrypt_release_ctx(ctx); @@ -64,57 +62,29 @@ static void completion_pages(struct work_struct *work) void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, struct bio *bio) { - INIT_WORK(&ctx->r.work, completion_pages); - ctx->r.bio = bio; - fscrypt_enqueue_decrypt_work(&ctx->r.work); + INIT_WORK(&ctx->work, completion_pages); + ctx->bio = bio; + fscrypt_enqueue_decrypt_work(&ctx->work); } EXPORT_SYMBOL(fscrypt_enqueue_decrypt_bio); -void fscrypt_pullback_bio_page(struct page **page, bool restore) -{ - struct fscrypt_ctx *ctx; - struct page *bounce_page; - - /* The bounce data pages are unmapped. */ - if ((*page)->mapping) - return; - - /* The bounce data page is unmapped. */ - bounce_page = *page; - ctx = (struct fscrypt_ctx *)page_private(bounce_page); - - /* restore control page */ - *page = ctx->w.control_page; - - if (restore) - fscrypt_restore_control_page(bounce_page); -} -EXPORT_SYMBOL(fscrypt_pullback_bio_page); - int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { - struct fscrypt_ctx *ctx; - struct page *ciphertext_page = NULL; + const unsigned int blockbits = inode->i_blkbits; + const unsigned int blocksize = 1 << blockbits; + struct page *ciphertext_page; struct bio *bio; int ret, err = 0; - BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE); - - ctx = fscrypt_get_ctx(GFP_NOFS); - if (IS_ERR(ctx)) - return PTR_ERR(ctx); - - ciphertext_page = fscrypt_alloc_bounce_page(ctx, GFP_NOWAIT); - if (IS_ERR(ciphertext_page)) { - err = PTR_ERR(ciphertext_page); - goto errout; - } + ciphertext_page = fscrypt_alloc_bounce_page(GFP_NOWAIT); + if (!ciphertext_page) + return -ENOMEM; while (len--) { - err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk, - ZERO_PAGE(0), ciphertext_page, - PAGE_SIZE, 0, GFP_NOFS); + err = fscrypt_crypt_block(inode, FS_ENCRYPT, lblk, + ZERO_PAGE(0), ciphertext_page, + blocksize, 0, GFP_NOFS); if (err) goto errout; @@ -124,14 +94,11 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, goto errout; } bio_set_dev(bio, inode->i_sb->s_bdev); - bio->bi_iter.bi_sector = - pblk << (inode->i_sb->s_blocksize_bits - 9); + bio->bi_iter.bi_sector = pblk << (blockbits - 9); bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - ret = bio_add_page(bio, ciphertext_page, - inode->i_sb->s_blocksize, 0); - if (ret != inode->i_sb->s_blocksize) { + ret = bio_add_page(bio, ciphertext_page, blocksize, 0); + if (WARN_ON(ret != blocksize)) { /* should never happen! */ - WARN_ON(1); bio_put(bio); err = -EIO; goto errout; @@ -147,7 +114,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, } err = 0; errout: - fscrypt_release_ctx(ctx); + fscrypt_free_bounce_page(ciphertext_page); return err; } EXPORT_SYMBOL(fscrypt_zeroout_range); diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 68e2ca4c4af6..45c3d0427fb2 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This contains encryption functions for per-file encryption. * @@ -58,23 +59,16 @@ void fscrypt_enqueue_decrypt_work(struct work_struct *work) EXPORT_SYMBOL(fscrypt_enqueue_decrypt_work); /** - * fscrypt_release_ctx() - Releases an encryption context - * @ctx: The encryption context to release. + * fscrypt_release_ctx() - Release a decryption context + * @ctx: The decryption context to release. * - * If the encryption context was allocated from the pre-allocated pool, returns - * it to that pool. Else, frees it. - * - * If there's a bounce page in the context, this frees that. + * If the decryption context was allocated from the pre-allocated pool, return + * it to that pool. Else, free it. */ void fscrypt_release_ctx(struct fscrypt_ctx *ctx) { unsigned long flags; - if (ctx->flags & FS_CTX_HAS_BOUNCE_BUFFER_FL && ctx->w.bounce_page) { - mempool_free(ctx->w.bounce_page, fscrypt_bounce_page_pool); - ctx->w.bounce_page = NULL; - } - ctx->w.control_page = NULL; if (ctx->flags & FS_CTX_REQUIRES_FREE_ENCRYPT_FL) { kmem_cache_free(fscrypt_ctx_cachep, ctx); } else { @@ -86,12 +80,12 @@ void fscrypt_release_ctx(struct fscrypt_ctx *ctx) EXPORT_SYMBOL(fscrypt_release_ctx); /** - * fscrypt_get_ctx() - Gets an encryption context + * fscrypt_get_ctx() - Get a decryption context * @gfp_flags: The gfp flag for memory allocation * - * Allocates and initializes an encryption context. + * Allocate and initialize a decryption context. * - * Return: A new encryption context on success; an ERR_PTR() otherwise. + * Return: A new decryption context on success; an ERR_PTR() otherwise. */ struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) { @@ -99,14 +93,8 @@ struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) unsigned long flags; /* - * We first try getting the ctx from a free list because in - * the common case the ctx will have an allocated and - * initialized crypto tfm, so it's probably a worthwhile - * optimization. For the bounce page, we first try getting it - * from the kernel allocator because that's just about as fast - * as getting it from a list and because a cache of free pages - * should generally be a "last resort" option for a filesystem - * to be able to do its job. + * First try getting a ctx from the free list so that we don't have to + * call into the slab allocator. */ spin_lock_irqsave(&fscrypt_ctx_lock, flags); ctx = list_first_entry_or_null(&fscrypt_free_ctxs, @@ -122,11 +110,31 @@ struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) } else { ctx->flags &= ~FS_CTX_REQUIRES_FREE_ENCRYPT_FL; } - ctx->flags &= ~FS_CTX_HAS_BOUNCE_BUFFER_FL; return ctx; } EXPORT_SYMBOL(fscrypt_get_ctx); +struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags) +{ + return mempool_alloc(fscrypt_bounce_page_pool, gfp_flags); +} + +/** + * fscrypt_free_bounce_page() - free a ciphertext bounce page + * + * Free a bounce page that was allocated by fscrypt_encrypt_pagecache_blocks(), + * or by fscrypt_alloc_bounce_page() directly. + */ +void fscrypt_free_bounce_page(struct page *bounce_page) +{ + if (!bounce_page) + return; + set_page_private(bounce_page, (unsigned long)NULL); + ClearPagePrivate(bounce_page); + mempool_free(bounce_page, fscrypt_bounce_page_pool); +} +EXPORT_SYMBOL(fscrypt_free_bounce_page); + void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, const struct fscrypt_info *ci) { @@ -140,10 +148,11 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num, crypto_cipher_encrypt_one(ci->ci_essiv_tfm, iv->raw, iv->raw); } -int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, - u64 lblk_num, struct page *src_page, - struct page *dest_page, unsigned int len, - unsigned int offs, gfp_t gfp_flags) +/* Encrypt or decrypt a single filesystem block of file contents */ +int fscrypt_crypt_block(const struct inode *inode, fscrypt_direction_t rw, + u64 lblk_num, struct page *src_page, + struct page *dest_page, unsigned int len, + unsigned int offs, gfp_t gfp_flags) { union fscrypt_iv iv; struct skcipher_request *req = NULL; @@ -153,7 +162,10 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, struct crypto_skcipher *tfm = ci->ci_ctfm; int res = 0; - BUG_ON(len == 0); + if (WARN_ON_ONCE(len <= 0)) + return -EINVAL; + if (WARN_ON_ONCE(len % FS_CRYPTO_BLOCK_SIZE != 0)) + return -EINVAL; fscrypt_generate_iv(&iv, lblk_num, ci); @@ -185,126 +197,158 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw, return 0; } -struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx, - gfp_t gfp_flags) -{ - ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags); - if (ctx->w.bounce_page == NULL) - return ERR_PTR(-ENOMEM); - ctx->flags |= FS_CTX_HAS_BOUNCE_BUFFER_FL; - return ctx->w.bounce_page; -} - /** - * fscypt_encrypt_page() - Encrypts a page - * @inode: The inode for which the encryption should take place - * @page: The page to encrypt. Must be locked for bounce-page - * encryption. - * @len: Length of data to encrypt in @page and encrypted - * data in returned page. - * @offs: Offset of data within @page and returned - * page holding encrypted data. - * @lblk_num: Logical block number. This must be unique for multiple - * calls with same inode, except when overwriting - * previously written data. - * @gfp_flags: The gfp flag for memory allocation - * - * Encrypts @page using the ctx encryption context. Performs encryption - * either in-place or into a newly allocated bounce page. - * Called on the page write path. + * fscrypt_encrypt_pagecache_blocks() - Encrypt filesystem blocks from a pagecache page + * @page: The locked pagecache page containing the block(s) to encrypt + * @len: Total size of the block(s) to encrypt. Must be a nonzero + * multiple of the filesystem's block size. + * @offs: Byte offset within @page of the first block to encrypt. Must be + * a multiple of the filesystem's block size. + * @gfp_flags: Memory allocation flags * - * Bounce page allocation is the default. - * In this case, the contents of @page are encrypted and stored in an - * allocated bounce page. @page has to be locked and the caller must call - * fscrypt_restore_control_page() on the returned ciphertext page to - * release the bounce buffer and the encryption context. + * A new bounce page is allocated, and the specified block(s) are encrypted into + * it. In the bounce page, the ciphertext block(s) will be located at the same + * offsets at which the plaintext block(s) were located in the source page; any + * other parts of the bounce page will be left uninitialized. However, normally + * blocksize == PAGE_SIZE and the whole page is encrypted at once. * - * In-place encryption is used by setting the FS_CFLG_OWN_PAGES flag in - * fscrypt_operations. Here, the input-page is returned with its content - * encrypted. + * This is for use by the filesystem's ->writepages() method. * - * Return: A page with the encrypted content on success. Else, an - * error value or NULL. + * Return: the new encrypted bounce page on success; an ERR_PTR() on failure */ -struct page *fscrypt_encrypt_page(const struct inode *inode, - struct page *page, - unsigned int len, - unsigned int offs, - u64 lblk_num, gfp_t gfp_flags) +struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, + unsigned int len, + unsigned int offs, + gfp_t gfp_flags) { - struct fscrypt_ctx *ctx; - struct page *ciphertext_page = page; + const struct inode *inode = page->mapping->host; + const unsigned int blockbits = inode->i_blkbits; + const unsigned int blocksize = 1 << blockbits; + struct page *ciphertext_page; + u64 lblk_num = ((u64)page->index << (PAGE_SHIFT - blockbits)) + + (offs >> blockbits); + unsigned int i; int err; - BUG_ON(len % FS_CRYPTO_BLOCK_SIZE != 0); + if (WARN_ON_ONCE(!PageLocked(page))) + return ERR_PTR(-EINVAL); - if (inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES) { - /* with inplace-encryption we just encrypt the page */ - err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num, page, - ciphertext_page, len, offs, - gfp_flags); - if (err) - return ERR_PTR(err); + if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offs, blocksize))) + return ERR_PTR(-EINVAL); - return ciphertext_page; - } - - BUG_ON(!PageLocked(page)); - - ctx = fscrypt_get_ctx(gfp_flags); - if (IS_ERR(ctx)) - return ERR_CAST(ctx); - - /* The encryption operation will require a bounce page. */ - ciphertext_page = fscrypt_alloc_bounce_page(ctx, gfp_flags); - if (IS_ERR(ciphertext_page)) - goto errout; + ciphertext_page = fscrypt_alloc_bounce_page(gfp_flags); + if (!ciphertext_page) + return ERR_PTR(-ENOMEM); - ctx->w.control_page = page; - err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num, - page, ciphertext_page, len, offs, - gfp_flags); - if (err) { - ciphertext_page = ERR_PTR(err); - goto errout; + for (i = offs; i < offs + len; i += blocksize, lblk_num++) { + err = fscrypt_crypt_block(inode, FS_ENCRYPT, lblk_num, + page, ciphertext_page, + blocksize, i, gfp_flags); + if (err) { + fscrypt_free_bounce_page(ciphertext_page); + return ERR_PTR(err); + } } SetPagePrivate(ciphertext_page); - set_page_private(ciphertext_page, (unsigned long)ctx); - lock_page(ciphertext_page); + set_page_private(ciphertext_page, (unsigned long)page); return ciphertext_page; +} +EXPORT_SYMBOL(fscrypt_encrypt_pagecache_blocks); -errout: - fscrypt_release_ctx(ctx); - return ciphertext_page; +/** + * fscrypt_encrypt_block_inplace() - Encrypt a filesystem block in-place + * @inode: The inode to which this block belongs + * @page: The page containing the block to encrypt + * @len: Size of block to encrypt. Doesn't need to be a multiple of the + * fs block size, but must be a multiple of FS_CRYPTO_BLOCK_SIZE. + * @offs: Byte offset within @page at which the block to encrypt begins + * @lblk_num: Filesystem logical block number of the block, i.e. the 0-based + * number of the block within the file + * @gfp_flags: Memory allocation flags + * + * Encrypt a possibly-compressed filesystem block that is located in an + * arbitrary page, not necessarily in the original pagecache page. The @inode + * and @lblk_num must be specified, as they can't be determined from @page. + * + * Return: 0 on success; -errno on failure + */ +int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num, gfp_t gfp_flags) +{ + return fscrypt_crypt_block(inode, FS_ENCRYPT, lblk_num, page, page, + len, offs, gfp_flags); } -EXPORT_SYMBOL(fscrypt_encrypt_page); +EXPORT_SYMBOL(fscrypt_encrypt_block_inplace); /** - * fscrypt_decrypt_page() - Decrypts a page in-place - * @inode: The corresponding inode for the page to decrypt. - * @page: The page to decrypt. Must be locked in case - * it is a writeback page (FS_CFLG_OWN_PAGES unset). - * @len: Number of bytes in @page to be decrypted. - * @offs: Start of data in @page. - * @lblk_num: Logical block number. + * fscrypt_decrypt_pagecache_blocks() - Decrypt filesystem blocks in a pagecache page + * @page: The locked pagecache page containing the block(s) to decrypt + * @len: Total size of the block(s) to decrypt. Must be a nonzero + * multiple of the filesystem's block size. + * @offs: Byte offset within @page of the first block to decrypt. Must be + * a multiple of the filesystem's block size. * - * Decrypts page in-place using the ctx encryption context. + * The specified block(s) are decrypted in-place within the pagecache page, + * which must still be locked and not uptodate. Normally, blocksize == + * PAGE_SIZE and the whole page is decrypted at once. * - * Called from the read completion callback. + * This is for use by the filesystem's ->readpages() method. * - * Return: Zero on success, non-zero otherwise. + * Return: 0 on success; -errno on failure */ -int fscrypt_decrypt_page(const struct inode *inode, struct page *page, - unsigned int len, unsigned int offs, u64 lblk_num) +int fscrypt_decrypt_pagecache_blocks(struct page *page, unsigned int len, + unsigned int offs) { - if (!(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES)) - BUG_ON(!PageLocked(page)); + const struct inode *inode = page->mapping->host; + const unsigned int blockbits = inode->i_blkbits; + const unsigned int blocksize = 1 << blockbits; + u64 lblk_num = ((u64)page->index << (PAGE_SHIFT - blockbits)) + + (offs >> blockbits); + unsigned int i; + int err; + + if (WARN_ON_ONCE(!PageLocked(page))) + return -EINVAL; + + if (WARN_ON_ONCE(len <= 0 || !IS_ALIGNED(len | offs, blocksize))) + return -EINVAL; + + for (i = offs; i < offs + len; i += blocksize, lblk_num++) { + err = fscrypt_crypt_block(inode, FS_DECRYPT, lblk_num, page, + page, blocksize, i, GFP_NOFS); + if (err) + return err; + } + return 0; +} +EXPORT_SYMBOL(fscrypt_decrypt_pagecache_blocks); - return fscrypt_do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page, - len, offs, GFP_NOFS); +/** + * fscrypt_decrypt_block_inplace() - Decrypt a filesystem block in-place + * @inode: The inode to which this block belongs + * @page: The page containing the block to decrypt + * @len: Size of block to decrypt. Doesn't need to be a multiple of the + * fs block size, but must be a multiple of FS_CRYPTO_BLOCK_SIZE. + * @offs: Byte offset within @page at which the block to decrypt begins + * @lblk_num: Filesystem logical block number of the block, i.e. the 0-based + * number of the block within the file + * + * Decrypt a possibly-compressed filesystem block that is located in an + * arbitrary page, not necessarily in the original pagecache page. The @inode + * and @lblk_num must be specified, as they can't be determined from @page. + * + * Return: 0 on success; -errno on failure + */ +int fscrypt_decrypt_block_inplace(const struct inode *inode, struct page *page, + unsigned int len, unsigned int offs, + u64 lblk_num) +{ + return fscrypt_crypt_block(inode, FS_DECRYPT, lblk_num, page, page, + len, offs, GFP_NOFS); } -EXPORT_SYMBOL(fscrypt_decrypt_page); +EXPORT_SYMBOL(fscrypt_decrypt_block_inplace); /* * Validate dentries in encrypted directories to make sure we aren't potentially @@ -354,18 +398,6 @@ const struct dentry_operations fscrypt_d_ops = { .d_revalidate = fscrypt_d_revalidate, }; -void fscrypt_restore_control_page(struct page *page) -{ - struct fscrypt_ctx *ctx; - - ctx = (struct fscrypt_ctx *)page_private(page); - set_page_private(page, (unsigned long)NULL); - ClearPagePrivate(page); - unlock_page(page); - fscrypt_release_ctx(ctx); -} -EXPORT_SYMBOL(fscrypt_restore_control_page); - static void fscrypt_destroy(void) { struct fscrypt_ctx *pos, *n; diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index eccea3d8f923..00d150ff3033 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -12,7 +12,6 @@ */ #include <linux/scatterlist.h> -#include <linux/ratelimit.h> #include <crypto/skcipher.h> #include "fscrypt_private.h" diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 7da276159593..8978eec9d766 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -94,7 +94,6 @@ typedef enum { } fscrypt_direction_t; #define FS_CTX_REQUIRES_FREE_ENCRYPT_FL 0x00000001 -#define FS_CTX_HAS_BOUNCE_BUFFER_FL 0x00000002 static inline bool fscrypt_valid_enc_modes(u32 contents_mode, u32 filenames_mode) @@ -117,14 +116,12 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode, /* crypto.c */ extern struct kmem_cache *fscrypt_info_cachep; extern int fscrypt_initialize(unsigned int cop_flags); -extern int fscrypt_do_page_crypto(const struct inode *inode, - fscrypt_direction_t rw, u64 lblk_num, - struct page *src_page, - struct page *dest_page, - unsigned int len, unsigned int offs, - gfp_t gfp_flags); -extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx, - gfp_t gfp_flags); +extern int fscrypt_crypt_block(const struct inode *inode, + fscrypt_direction_t rw, u64 lblk_num, + struct page *src_page, struct page *dest_page, + unsigned int len, unsigned int offs, + gfp_t gfp_flags); +extern struct page *fscrypt_alloc_bounce_page(gfp_t gfp_flags); extern const struct dentry_operations fscrypt_d_ops; extern void __printf(3, 4) __cold diff --git a/fs/crypto/hooks.c b/fs/crypto/hooks.c index 2dc22549d724..c1d6715d88e9 100644 --- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -1,10 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/crypto/hooks.c * * Encryption hooks for higher-level filesystem operations. */ -#include <linux/ratelimit.h> #include "fscrypt_private.h" /** diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index dcd91a3fbe49..207ebed918c1 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -12,7 +12,6 @@ #include <keys/user-type.h> #include <linux/hashtable.h> #include <linux/scatterlist.h> -#include <linux/ratelimit.h> #include <crypto/aes.h> #include <crypto/algapi.h> #include <crypto/sha.h> diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index d536889ac31b..4941fe8471ce 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -81,6 +81,8 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg) if (ret == -ENODATA) { if (!S_ISDIR(inode->i_mode)) ret = -ENOTDIR; + else if (IS_DEADDIR(inode)) + ret = -ENOENT; else if (!inode->i_sb->s_cop->empty_dir(inode)) ret = -ENOTEMPTY; else @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/dax.c - Direct Access filesystem code * Copyright (c) 2013-2014 Intel Corporation * Author: Matthew Wilcox <matthew.r.wilcox@intel.com> * Author: Ross Zwisler <ross.zwisler@linux.intel.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <linux/atomic.h> @@ -728,12 +720,11 @@ static void *dax_insert_entry(struct xa_state *xas, xas_reset(xas); xas_lock_irq(xas); - if (dax_entry_size(entry) != dax_entry_size(new_entry)) { + if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + void *old; + dax_disassociate_entry(entry, mapping, false); dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address); - } - - if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { /* * Only swap our new entry into the page cache if the current * entry is a zero page or an empty entry. If a normal PTE or @@ -742,7 +733,7 @@ static void *dax_insert_entry(struct xa_state *xas, * existing entry is a PMD, we will just leave the PMD in the * tree and dirty it if necessary. */ - void *old = dax_lock_entry(xas, new_entry); + old = dax_lock_entry(xas, new_entry); WARN_ON_ONCE(old != xa_mk_value(xa_to_value(entry) | DAX_LOCKED)); entry = new_entry; @@ -1196,7 +1187,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, unsigned flags = 0; if (iov_iter_rw(iter) == WRITE) { - lockdep_assert_held_exclusive(&inode->i_rwsem); + lockdep_assert_held_write(&inode->i_rwsem); flags |= IOMAP_WRITE; } else { lockdep_assert_held(&inode->i_rwsem); diff --git a/fs/dcache.c b/fs/dcache.c index 8136bda27a1f..f41121e5d1ec 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/dcache.c * @@ -2371,7 +2372,6 @@ EXPORT_SYMBOL(d_hash_and_lookup); void d_delete(struct dentry * dentry) { struct inode *inode = dentry->d_inode; - int isdir = d_is_dir(dentry); spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); @@ -2386,7 +2386,6 @@ void d_delete(struct dentry * dentry) spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } - fsnotify_nameremove(dentry, isdir); } EXPORT_SYMBOL(d_delete); diff --git a/fs/dcookies.c b/fs/dcookies.c index 57bc96435feb..6eeb61100a09 100644 --- a/fs/dcookies.c +++ b/fs/dcookies.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * dcookies.c * diff --git a/fs/debugfs/Makefile b/fs/debugfs/Makefile index 840c45696668..9c0fe38cfb5e 100644 --- a/fs/debugfs/Makefile +++ b/fs/debugfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only debugfs-objs := inode.o file.o obj-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index ddd708b09fa1..93e4ca6b2ad7 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -997,25 +997,19 @@ static const struct file_operations u32_array_fops = { * @array as data. If the @mode variable is so set it can be read from. * Writing is not supported. Seek within the file is also not supported. * Once array is created its size can not be changed. - * - * The function returns a pointer to dentry on success. If an error occurs, - * %ERR_PTR(-ERROR) or NULL will be returned. If debugfs is not enabled in - * the kernel, the value %ERR_PTR(-ENODEV) will be returned. */ -struct dentry *debugfs_create_u32_array(const char *name, umode_t mode, - struct dentry *parent, - u32 *array, u32 elements) +void debugfs_create_u32_array(const char *name, umode_t mode, + struct dentry *parent, u32 *array, u32 elements) { struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL); if (data == NULL) - return NULL; + return; data->array = array; data->elements = elements; - return debugfs_create_file_unsafe(name, mode, parent, data, - &u32_array_fops); + debugfs_create_file_unsafe(name, mode, parent, data, &u32_array_fops); } EXPORT_SYMBOL_GPL(debugfs_create_u32_array); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index acef14ad53db..042b688ed124 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -2,13 +2,16 @@ /* * inode.c - part of debugfs, a tiny little debug file system * - * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> + * Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. + * Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org> * * debugfs is for people to use instead of /proc or /sys. * See ./Documentation/core-api/kernel-api.rst for more details. */ +#define pr_fmt(fmt) "debugfs: " fmt + #include <linux/module.h> #include <linux/fs.h> #include <linux/mount.h> @@ -285,15 +288,17 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) struct dentry *dentry; int error; - pr_debug("debugfs: creating file '%s'\n",name); + pr_debug("creating file '%s'\n", name); if (IS_ERR(parent)) return parent; error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); - if (error) + if (error) { + pr_err("Unable to pin filesystem for file '%s'\n", name); return ERR_PTR(error); + } /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super @@ -306,6 +311,12 @@ static struct dentry *start_creating(const char *name, struct dentry *parent) inode_lock(d_inode(parent)); dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(dentry) && d_really_is_positive(dentry)) { + if (d_is_dir(dentry)) + pr_err("Directory '%s' with parent '%s' already present!\n", + name, parent->d_name.name); + else + pr_err("File '%s' in directory '%s' already present!\n", + name, parent->d_name.name); dput(dentry); dentry = ERR_PTR(-EEXIST); } @@ -349,8 +360,11 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, return dentry; inode = debugfs_get_inode(dentry->d_sb); - if (unlikely(!inode)) + if (unlikely(!inode)) { + pr_err("out of free dentries, can not create file '%s'\n", + name); return failed_creating(dentry); + } inode->i_mode = mode; inode->i_private = data; @@ -511,8 +525,11 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) return dentry; inode = debugfs_get_inode(dentry->d_sb); - if (unlikely(!inode)) + if (unlikely(!inode)) { + pr_err("out of free dentries, can not create directory '%s'\n", + name); return failed_creating(dentry); + } inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; inode->i_op = &simple_dir_inode_operations; @@ -550,8 +567,11 @@ struct dentry *debugfs_create_automount(const char *name, return dentry; inode = debugfs_get_inode(dentry->d_sb); - if (unlikely(!inode)) + if (unlikely(!inode)) { + pr_err("out of free dentries, can not create automount '%s'\n", + name); return failed_creating(dentry); + } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; @@ -606,6 +626,8 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { + pr_err("out of free dentries, can not create symlink '%s'\n", + name); kfree(link); return failed_creating(dentry); } @@ -617,13 +639,10 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, } EXPORT_SYMBOL_GPL(debugfs_create_symlink); -static void __debugfs_remove_file(struct dentry *dentry, struct dentry *parent) +static void __debugfs_file_removed(struct dentry *dentry) { struct debugfs_fsdata *fsd; - simple_unlink(d_inode(parent), dentry); - d_delete(dentry); - /* * Paired with the closing smp_mb() implied by a successful * cmpxchg() in debugfs_file_get(): either @@ -644,16 +663,18 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent) if (simple_positive(dentry)) { dget(dentry); - if (!d_is_reg(dentry)) { - if (d_is_dir(dentry)) - ret = simple_rmdir(d_inode(parent), dentry); - else - simple_unlink(d_inode(parent), dentry); + if (d_is_dir(dentry)) { + ret = simple_rmdir(d_inode(parent), dentry); if (!ret) - d_delete(dentry); + fsnotify_rmdir(d_inode(parent), dentry); } else { - __debugfs_remove_file(dentry, parent); + simple_unlink(d_inode(parent), dentry); + fsnotify_unlink(d_inode(parent), dentry); } + if (!ret) + d_delete(dentry); + if (d_is_reg(dentry)) + __debugfs_file_removed(dentry); dput(dentry); } return ret; diff --git a/fs/devpts/Makefile b/fs/devpts/Makefile index 236696efcbac..66064c8fcb3e 100644 --- a/fs/devpts/Makefile +++ b/fs/devpts/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux /dev/pts virtual filesystem. # diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 553a3f3300ae..beeadca23b05 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- linux-c -*- --------------------------------------------------------- * * * linux/fs/devpts/inode.c * * Copyright 1998-2004 H. Peter Anvin -- All Rights Reserved * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. - * * ------------------------------------------------------------------------- */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -624,6 +621,7 @@ void devpts_pty_kill(struct dentry *dentry) dentry->d_fsdata = NULL; drop_nlink(dentry->d_inode); + fsnotify_unlink(d_inode(dentry->d_parent), dentry); d_delete(dentry); dput(dentry); /* d_alloc_name() in devpts_pty_new() */ } diff --git a/fs/direct-io.c b/fs/direct-io.c index fbe885d68035..ae196784f487 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/direct-io.c * @@ -537,8 +538,8 @@ static struct bio *dio_await_one(struct dio *dio) */ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) { - struct bio_vec *bvec; blk_status_t err = bio->bi_status; + bool should_dirty = dio->op == REQ_OP_READ && dio->should_dirty; if (err) { if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT)) @@ -547,19 +548,10 @@ static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio) dio->io_error = -EIO; } - if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) { + if (dio->is_async && should_dirty) { bio_check_pages_dirty(bio); /* transfers ownership */ } else { - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, iter_all) { - struct page *page = bvec->bv_page; - - if (dio->op == REQ_OP_READ && !PageCompound(page) && - dio->should_dirty) - set_page_dirty_lock(page); - put_page(page); - } + bio_release_pages(bio, should_dirty); bio_put(bio); } return err; diff --git a/fs/dlm/Kconfig b/fs/dlm/Kconfig index e4242c3f8486..f82a4952769d 100644 --- a/fs/dlm/Kconfig +++ b/fs/dlm/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only menuconfig DLM tristate "Distributed Lock Manager (DLM)" depends on INET diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index 47ee66d70109..283c7b94edda 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2010 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/ast.h b/fs/dlm/ast.h index 757b551c6820..181ad7d20c4d 100644 --- a/fs/dlm/ast.h +++ b/fs/dlm/ast.h @@ -1,11 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2010 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/config.c b/fs/dlm/config.c index 1270551d24e3..3b21082e1b55 100644 --- a/fs/dlm/config.c +++ b/fs/dlm/config.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/config.h b/fs/dlm/config.h index 6041eec886ab..2b471aae4e61 100644 --- a/fs/dlm/config.h +++ b/fs/dlm/config.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index fa08448e35dd..0e941d42e3e9 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2009 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c index d975851a7e1e..10c36ae1a8f9 100644 --- a/fs/dlm/dir.c +++ b/fs/dlm/dir.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/dir.h b/fs/dlm/dir.h index 417506344456..03844d086be2 100644 --- a/fs/dlm/dir.h +++ b/fs/dlm/dir.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 748e8d59e611..da1173a0b274 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index a928ba008d7d..18d81599522f 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2010 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h index ed8ebd3a8593..456c6ec3ef6f 100644 --- a/fs/dlm/lock.h +++ b/fs/dlm/lock.h @@ -1,11 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index db43b98c4d64..afb8340918b8 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ @@ -160,6 +158,7 @@ static struct attribute *dlm_attrs[] = { &dlm_attr_recover_nodeid.attr, NULL, }; +ATTRIBUTE_GROUPS(dlm); static ssize_t dlm_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) @@ -189,7 +188,7 @@ static const struct sysfs_ops dlm_attr_ops = { }; static struct kobj_type dlm_ktype = { - .default_attrs = dlm_attrs, + .default_groups = dlm_groups, .sysfs_ops = &dlm_attr_ops, .release = lockspace_kobj_release, }; diff --git a/fs/dlm/lockspace.h b/fs/dlm/lockspace.h index f879f87901f8..a78d853b9342 100644 --- a/fs/dlm/lockspace.h +++ b/fs/dlm/lockspace.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index c98ad9777ad9..114ebfe30929 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2009 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/lowcomms.h b/fs/dlm/lowcomms.h index 67462e54fc2f..687b2894e469 100644 --- a/fs/dlm/lowcomms.h +++ b/fs/dlm/lowcomms.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2009 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/lvb_table.h b/fs/dlm/lvb_table.h index cc3e92f3feef..09052d967174 100644 --- a/fs/dlm/lvb_table.h +++ b/fs/dlm/lvb_table.h @@ -1,11 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/main.c b/fs/dlm/main.c index 8e1b618891be..39579927ed84 100644 --- a/fs/dlm/main.c +++ b/fs/dlm/main.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/member.c b/fs/dlm/member.c index 0bc43b35d2c5..7ad83deb4505 100644 --- a/fs/dlm/member.c +++ b/fs/dlm/member.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2011 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/member.h b/fs/dlm/member.h index 3deb70661c69..433b2fac9f4a 100644 --- a/fs/dlm/member.h +++ b/fs/dlm/member.h @@ -1,11 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2011 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c index 37be29f21d04..5918f4d39586 100644 --- a/fs/dlm/memory.c +++ b/fs/dlm/memory.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/memory.h b/fs/dlm/memory.h index 177c11cbb0a6..4f218ea4b187 100644 --- a/fs/dlm/memory.h +++ b/fs/dlm/memory.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c index f3396c622aec..921322d133e3 100644 --- a/fs/dlm/midcomms.c +++ b/fs/dlm/midcomms.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/midcomms.h b/fs/dlm/midcomms.h index 95852a5f111d..2e122e81c8d0 100644 --- a/fs/dlm/midcomms.h +++ b/fs/dlm/midcomms.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index d8e27defa89f..e7f550327d5d 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2007 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License v.2. */ #include <net/genetlink.h> diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index c7d5a2ea3d03..c38b2b8ffd1d 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/fs.h> diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index 70c625999d36..e3d9f72c640d 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/rcom.h b/fs/dlm/rcom.h index 206723ab744d..454d3c4814ab 100644 --- a/fs/dlm/rcom.h +++ b/fs/dlm/rcom.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index ce2aa54ca2e2..8928e99dfd47 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/recover.h b/fs/dlm/recover.h index d8c8738c70eb..235e0d25cd48 100644 --- a/fs/dlm/recover.h +++ b/fs/dlm/recover.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index 6f4e1d42d733..85e245392715 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/recoverd.h b/fs/dlm/recoverd.h index 8856079733fa..d1944dc5f9e6 100644 --- a/fs/dlm/recoverd.h +++ b/fs/dlm/recoverd.h @@ -1,12 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/requestqueue.c b/fs/dlm/requestqueue.c index 1695f1b0dd45..e89e0ff8bfa3 100644 --- a/fs/dlm/requestqueue.c +++ b/fs/dlm/requestqueue.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/requestqueue.h b/fs/dlm/requestqueue.h index 10ce449b77da..4e403469a845 100644 --- a/fs/dlm/requestqueue.h +++ b/fs/dlm/requestqueue.h @@ -1,11 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 3c84c62dadb7..5264bac75115 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2006-2010 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License v.2. */ #include <linux/miscdevice.h> diff --git a/fs/dlm/user.h b/fs/dlm/user.h index 00499ab8835f..6b9bce6b96e0 100644 --- a/fs/dlm/user.h +++ b/fs/dlm/user.h @@ -1,9 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2006-2010 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License v.2. */ #ifndef __USER_DOT_H__ diff --git a/fs/dlm/util.c b/fs/dlm/util.c index e36520af7cc0..cfd0d00b19ae 100644 --- a/fs/dlm/util.c +++ b/fs/dlm/util.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/dlm/util.h b/fs/dlm/util.h index 2b25915161c0..cc719ca9397e 100644 --- a/fs/dlm/util.h +++ b/fs/dlm/util.h @@ -1,11 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /****************************************************************************** ******************************************************************************* ** ** Copyright (C) 2005 Red Hat, Inc. All rights reserved. ** -** This copyrighted material is made available to anyone wishing to use, -** modify, copy, or redistribute it subject to the terms and conditions -** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ diff --git a/fs/ecryptfs/Kconfig b/fs/ecryptfs/Kconfig index 434aa313f077..522c35d5292b 100644 --- a/fs/ecryptfs/Kconfig +++ b/fs/ecryptfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config ECRYPT_FS tristate "eCrypt filesystem layer support" depends on KEYS && CRYPTO && (ENCRYPTED_KEYS || ENCRYPTED_KEYS=n) diff --git a/fs/ecryptfs/Makefile b/fs/ecryptfs/Makefile index 49678a69947d..4f2cc5b2542d 100644 --- a/fs/ecryptfs/Makefile +++ b/fs/ecryptfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux eCryptfs # diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 491cf5baa8c2..91d65f337d87 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * @@ -6,21 +7,6 @@ * Copyright (C) 2004-2007 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Michael C. Thompson <mcthomps@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <crypto/hash.h> diff --git a/fs/ecryptfs/debug.c b/fs/ecryptfs/debug.c index 3d2bdf546ec6..d131d070826f 100644 --- a/fs/ecryptfs/debug.c +++ b/fs/ecryptfs/debug.c @@ -1,24 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * Functions only useful for debugging. * * Copyright (C) 2006 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include "ecryptfs_kernel.h" diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index 63cd2c147221..44606f079efb 100644 --- a/fs/ecryptfs/dentry.c +++ b/fs/ecryptfs/dentry.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * @@ -5,21 +6,6 @@ * Copyright (C) 2001-2003 Stony Brook University * Copyright (C) 2004-2006 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/dcache.h> diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index e74cb2a0b299..1c1a56be7ea2 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /** * eCryptfs: Linux filesystem encryption layer * Kernel declarations. @@ -8,21 +9,6 @@ * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Trevor S. Highland <trevor.highland@gmail.com> * Tyler Hicks <tyhicks@ou.edu> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #ifndef ECRYPTFS_KERNEL_H diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index b76a9853325e..feecb57defa7 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * @@ -6,21 +7,6 @@ * Copyright (C) 2004-2007 International Business Machines Corp. * Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com> * Michael C. Thompson <mcthomps@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/file.h> diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 5c36ceecb5c1..1e994d780f37 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * @@ -6,21 +7,6 @@ * Copyright (C) 2004-2007 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Michael C. Thompsion <mcthomps@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/file.h> diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 90fbac5d485b..9536e592e25a 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * In-kernel key management code. Includes functions to parse and @@ -8,21 +9,6 @@ * Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com> * Michael C. Thompson <mcthomps@us.ibm.com> * Trevor S. Highland <trevor.highland@gmail.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <crypto/hash.h> diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index e00d45af84ea..a7c903cb01a0 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * * Copyright (C) 2008 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/kthread.h> diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 025d66a705db..b8a7ce379ffe 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * @@ -7,21 +8,6 @@ * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Michael C. Thompson <mcthomps@us.ibm.com> * Tyler Hicks <tyhicks@ou.edu> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/dcache.h> diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index 9fdd5bcf4564..d668e60b85b5 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /** * eCryptfs: Linux filesystem encryption layer * * Copyright (C) 2004-2008 International Business Machines Corp. * Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com> * Tyler Hicks <tyhicks@ou.edu> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/sched.h> #include <linux/slab.h> diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 2d1158e5f950..742ece22c1d4 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -1,22 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /** * eCryptfs: Linux filesystem encryption layer * * Copyright (C) 2008 International Business Machines Corp. * Author(s): Michael A. Halcrow <mhalcrow@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index cdf358b209d9..cffa0c1ec829 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * This is where eCryptfs coordinates the symmetric encryption and @@ -8,21 +9,6 @@ * Copyright (C) 2001-2003 Stony Brook University * Copyright (C) 2004-2007 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/pagemap.h> diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c index c596e7c03424..0438997ac9d8 100644 --- a/fs/ecryptfs/read_write.c +++ b/fs/ecryptfs/read_write.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * * Copyright (C) 2007 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index c3e511f2b6c0..6b1853f1c06a 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * eCryptfs: Linux filesystem encryption layer * @@ -6,21 +7,6 @@ * Copyright (C) 2004-2006 International Business Machines Corp. * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com> * Michael C. Thompson <mcthomps@us.ibm.com> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of the - * License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA - * 02111-1307, USA. */ #include <linux/fs.h> diff --git a/fs/efivarfs/Kconfig b/fs/efivarfs/Kconfig index c2499ef174a2..edec8a19c894 100644 --- a/fs/efivarfs/Kconfig +++ b/fs/efivarfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config EFIVAR_FS tristate "EFI Variable filesystem" depends on EFI diff --git a/fs/efivarfs/Makefile b/fs/efivarfs/Makefile index 955d478177d5..0b1c5e63eb71 100644 --- a/fs/efivarfs/Makefile +++ b/fs/efivarfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the efivarfs filesystem # diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index 8e568428c88b..e9e27a271af0 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/efi.h> @@ -110,16 +107,22 @@ out_free: return size; } -static int -efivarfs_ioc_getxflags(struct file *file, void __user *arg) +static inline unsigned int efivarfs_getflags(struct inode *inode) { - struct inode *inode = file->f_mapping->host; unsigned int i_flags; unsigned int flags = 0; i_flags = inode->i_flags; if (i_flags & S_IMMUTABLE) flags |= FS_IMMUTABLE_FL; + return flags; +} + +static int +efivarfs_ioc_getxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int flags = efivarfs_getflags(inode); if (copy_to_user(arg, &flags, sizeof(flags))) return -EFAULT; @@ -132,6 +135,7 @@ efivarfs_ioc_setxflags(struct file *file, void __user *arg) struct inode *inode = file->f_mapping->host; unsigned int flags; unsigned int i_flags = 0; + unsigned int oldflags = efivarfs_getflags(inode); int error; if (!inode_owner_or_capable(inode)) @@ -143,9 +147,6 @@ efivarfs_ioc_setxflags(struct file *file, void __user *arg) if (flags & ~FS_IMMUTABLE_FL) return -EOPNOTSUPP; - if (!capable(CAP_LINUX_IMMUTABLE)) - return -EPERM; - if (flags & FS_IMMUTABLE_FL) i_flags |= S_IMMUTABLE; @@ -155,12 +156,16 @@ efivarfs_ioc_setxflags(struct file *file, void __user *arg) return error; inode_lock(inode); + + error = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (error) + goto out; + inode_set_flags(inode, i_flags, S_IMMUTABLE); +out: inode_unlock(inode); - mnt_drop_write_file(file); - - return 0; + return error; } static long diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 8c6ab6c95727..96c0c86f3fff 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/efi.h> diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index b4505188e799..30ae44cb7453 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 Red Hat, Inc. * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef EFIVAR_FS_INTERNAL_H #define EFIVAR_FS_INTERNAL_H diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 5b68e4294faa..5bc3c4a4c563 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Red Hat, Inc. * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/ctype.h> diff --git a/fs/efs/Kconfig b/fs/efs/Kconfig index d020e3c30fea..2df1bac8b375 100644 --- a/fs/efs/Kconfig +++ b/fs/efs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config EFS_FS tristate "EFS file system support (read only)" depends on BLOCK diff --git a/fs/efs/Makefile b/fs/efs/Makefile index 963543d46f0d..85e5b88f9471 100644 --- a/fs/efs/Makefile +++ b/fs/efs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux efs-filesystem routines. # diff --git a/fs/efs/inode.c b/fs/efs/inode.c index cdf0872382af..89e73a6f0d36 100644 --- a/fs/efs/inode.c +++ b/fs/efs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * inode.c * diff --git a/fs/eventfd.c b/fs/eventfd.c index 08d3bd602f73..8aa0ea8c55e8 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/eventfd.c * @@ -21,6 +22,9 @@ #include <linux/eventfd.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/idr.h> + +static DEFINE_IDA(eventfd_ida); struct eventfd_ctx { struct kref kref; @@ -35,6 +39,7 @@ struct eventfd_ctx { */ __u64 count; unsigned int flags; + int id; }; /** @@ -69,6 +74,8 @@ EXPORT_SYMBOL_GPL(eventfd_signal); static void eventfd_free_ctx(struct eventfd_ctx *ctx) { + if (ctx->id >= 0) + ida_simple_remove(&eventfd_ida, ctx->id); kfree(ctx); } @@ -297,6 +304,7 @@ static void eventfd_show_fdinfo(struct seq_file *m, struct file *f) seq_printf(m, "eventfd-count: %16llx\n", (unsigned long long)ctx->count); spin_unlock_irq(&ctx->wqh.lock); + seq_printf(m, "eventfd-id: %d\n", ctx->id); } #endif @@ -400,6 +408,7 @@ static int do_eventfd(unsigned int count, int flags) init_waitqueue_head(&ctx->wqh); ctx->count = count; ctx->flags = flags; + ctx->id = ida_simple_get(&eventfd_ida, 0, 0, GFP_KERNEL); fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx, O_RDWR | (flags & EFD_SHARED_FCNTL_FLAGS)); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 4a0e98d87fcc..4c74c768ae43 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1,14 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * * Davide Libenzi <davidel@xmailserver.org> - * */ #include <linux/init.h> @@ -2330,7 +2325,7 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, error = do_epoll_wait(epfd, events, maxevents, timeout); - restore_user_sigmask(sigmask, &sigsaved); + restore_user_sigmask(sigmask, &sigsaved, error == -EINTR); return error; } @@ -2355,7 +2350,7 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, err = do_epoll_wait(epfd, events, maxevents, timeout); - restore_user_sigmask(sigmask, &sigsaved); + restore_user_sigmask(sigmask, &sigsaved, err == -EINTR); return err; } diff --git a/fs/exec.c b/fs/exec.c index 2e0033348d8e..c71cbfe6826a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/exec.c * @@ -1652,15 +1653,17 @@ int search_binary_handler(struct linux_binprm *bprm) if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); + bprm->recursion_depth++; retval = fmt->load_binary(bprm); + bprm->recursion_depth--; + read_lock(&binfmt_lock); put_binfmt(fmt); - bprm->recursion_depth--; if (retval < 0 && !bprm->mm) { /* we got to flush_old_exec() and failed after it */ read_unlock(&binfmt_lock); - force_sigsegv(SIGSEGV, current); + force_sigsegv(SIGSEGV); return retval; } if (retval != -ENOEXEC || !bprm->file) { diff --git a/fs/exportfs/Makefile b/fs/exportfs/Makefile index d7c5d4ddb34b..a04a8af83efd 100644 --- a/fs/exportfs/Makefile +++ b/fs/exportfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the filesystem export support routines. diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index c69927bed4ef..f0e549783caf 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Neil Brown 2002 * Copyright (C) Christoph Hellwig 2007 diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig index 894e4c53d1d2..54eec9185627 100644 --- a/fs/ext2/Kconfig +++ b/fs/ext2/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config EXT2_FS tristate "Second extended fs support" help diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 33db13365c5e..547c165299c0 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -1197,7 +1197,7 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi) /* * Returns 1 if the passed-in block region is valid; 0 if some part overlaps - * with filesystem metadata blocksi. + * with filesystem metadata blocks. */ int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk, unsigned int count) @@ -1212,7 +1212,6 @@ int ext2_data_block_valid(struct ext2_sb_info *sbi, ext2_fsblk_t start_blk, (start_blk + count >= sbi->s_sb_block)) return 0; - return 1; } diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index a0c5ea91fcd4..fda7d3f5b4be 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -172,9 +172,7 @@ static void ext2_preread_inode(struct inode *inode) struct backing_dev_info *bdi; bdi = inode_to_bdi(inode); - if (bdi_read_congested(bdi)) - return; - if (bdi_write_congested(bdi)) + if (bdi_rw_congested(bdi)) return; block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb); @@ -511,6 +509,7 @@ repeat_in_this_group: /* * Scanned all blockgroups. */ + brelse(bitmap_bh); err = -ENOSPC; goto fail; got: diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index e474127dd255..7004ce581a32 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1400,7 +1400,7 @@ void ext2_set_file_ops(struct inode *inode) struct inode *ext2_iget (struct super_block *sb, unsigned long ino) { struct ext2_inode_info *ei; - struct buffer_head * bh; + struct buffer_head * bh = NULL; struct ext2_inode *raw_inode; struct inode *inode; long ret = -EIO; @@ -1446,7 +1446,6 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) */ if (inode->i_nlink == 0 && (inode->i_mode == 0 || ei->i_dtime)) { /* this inode is deleted */ - brelse (bh); ret = -ESTALE; goto bad_inode; } @@ -1463,7 +1462,6 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) !ext2_data_block_valid(EXT2_SB(sb), ei->i_file_acl, 1)) { ext2_error(sb, "ext2_iget", "bad extended attribute block %u", ei->i_file_acl); - brelse(bh); ret = -EFSCORRUPTED; goto bad_inode; } @@ -1526,6 +1524,7 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) return inode; bad_inode: + brelse(bh); iget_failed(inode); return ERR_PTR(ret); } @@ -1640,7 +1639,7 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc) } int ext2_getattr(const struct path *path, struct kstat *stat, - u32 request_mask, unsigned int query_falgs) + u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct ext2_inode_info *ei = EXT2_I(inode); diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index 0367c0039e68..1b853fb0b163 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -60,18 +60,10 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) } oldflags = ei->i_flags; - /* - * The IMMUTABLE and APPEND_ONLY flags can only be changed by - * the relevant capability. - * - * This test looks nicer. Thanks to Pauline Middelink - */ - if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - inode_unlock(inode); - ret = -EPERM; - goto setflags_out; - } + ret = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (ret) { + inode_unlock(inode); + goto setflags_out; } flags = flags & EXT2_FL_USER_MODIFIABLE; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 3988633789cb..44eb6e7eb492 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/ext2/super.c * @@ -302,16 +303,16 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root) if (test_opt(sb, NOBH)) seq_puts(seq, ",nobh"); - if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA) + if (test_opt(sb, USRQUOTA)) seq_puts(seq, ",usrquota"); - if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA) + if (test_opt(sb, GRPQUOTA)) seq_puts(seq, ",grpquota"); - if (sbi->s_mount_opt & EXT2_MOUNT_XIP) + if (test_opt(sb, XIP)) seq_puts(seq, ",xip"); - if (sbi->s_mount_opt & EXT2_MOUNT_DAX) + if (test_opt(sb, DAX)) seq_puts(seq, ",dax"); if (!test_opt(sb, RESERVATION)) @@ -934,8 +935,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) sbi->s_resgid = opts.s_resgid; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | - ((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? - SB_POSIXACL : 0); + (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); sb->s_iflags |= SB_I_CGROUPWB; if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV && @@ -966,11 +966,11 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); - if (sbi->s_mount_opt & EXT2_MOUNT_DAX) { + if (test_opt(sb, DAX)) { if (!bdev_dax_supported(sb->s_bdev, blocksize)) { ext2_msg(sb, KERN_ERR, "DAX unsupported by block device. Turning off DAX."); - sbi->s_mount_opt &= ~EXT2_MOUNT_DAX; + clear_opt(sbi->s_mount_opt, DAX); } } @@ -1403,7 +1403,7 @@ out_set: sbi->s_resuid = new_opts.s_resuid; sbi->s_resgid = new_opts.s_resgid; sb->s_flags = (sb->s_flags & ~SB_POSIXACL) | - ((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? SB_POSIXACL : 0); + (test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0); spin_unlock(&sbi->s_lock); return 0; diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 1e33e0ac8cf1..79369c13cc55 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -134,6 +134,53 @@ ext2_xattr_handler(int name_index) return handler; } +static bool +ext2_xattr_header_valid(struct ext2_xattr_header *header) +{ + if (header->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || + header->h_blocks != cpu_to_le32(1)) + return false; + + return true; +} + +static bool +ext2_xattr_entry_valid(struct ext2_xattr_entry *entry, + char *end, size_t end_offs) +{ + struct ext2_xattr_entry *next; + size_t size; + + next = EXT2_XATTR_NEXT(entry); + if ((char *)next >= end) + return false; + + if (entry->e_value_block != 0) + return false; + + size = le32_to_cpu(entry->e_value_size); + if (size > end_offs || + le16_to_cpu(entry->e_value_offs) + size > end_offs) + return false; + + return true; +} + +static int +ext2_xattr_cmp_entry(int name_index, size_t name_len, const char *name, + struct ext2_xattr_entry *entry) +{ + int cmp; + + cmp = name_index - entry->e_name_index; + if (!cmp) + cmp = name_len - entry->e_name_len; + if (!cmp) + cmp = memcmp(name, entry->e_name, name_len); + + return cmp; +} + /* * ext2_xattr_get() * @@ -152,7 +199,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name, struct ext2_xattr_entry *entry; size_t name_len, size; char *end; - int error; + int error, not_found; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", @@ -176,9 +223,9 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name, ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(HDR(bh)->h_refcount)); end = bh->b_data + bh->b_size; - if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || - HDR(bh)->h_blocks != cpu_to_le32(1)) { -bad_block: ext2_error(inode->i_sb, "ext2_xattr_get", + if (!ext2_xattr_header_valid(HDR(bh))) { +bad_block: + ext2_error(inode->i_sb, "ext2_xattr_get", "inode %ld: bad block %d", inode->i_ino, EXT2_I(inode)->i_file_acl); error = -EIO; @@ -188,29 +235,25 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_get", /* find named attribute */ entry = FIRST_ENTRY(bh); while (!IS_LAST_ENTRY(entry)) { - struct ext2_xattr_entry *next = - EXT2_XATTR_NEXT(entry); - if ((char *)next >= end) + if (!ext2_xattr_entry_valid(entry, end, + inode->i_sb->s_blocksize)) goto bad_block; - if (name_index == entry->e_name_index && - name_len == entry->e_name_len && - memcmp(name, entry->e_name, name_len) == 0) + + not_found = ext2_xattr_cmp_entry(name_index, name_len, name, + entry); + if (!not_found) goto found; - entry = next; + if (not_found < 0) + break; + + entry = EXT2_XATTR_NEXT(entry); } if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); error = -ENODATA; goto cleanup; found: - /* check the buffer size */ - if (entry->e_value_block != 0) - goto bad_block; size = le32_to_cpu(entry->e_value_size); - if (size > inode->i_sb->s_blocksize || - le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize) - goto bad_block; - if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); if (buffer) { @@ -266,9 +309,9 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size) ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(HDR(bh)->h_refcount)); end = bh->b_data + bh->b_size; - if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || - HDR(bh)->h_blocks != cpu_to_le32(1)) { -bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", + if (!ext2_xattr_header_valid(HDR(bh))) { +bad_block: + ext2_error(inode->i_sb, "ext2_xattr_list", "inode %ld: bad block %d", inode->i_ino, EXT2_I(inode)->i_file_acl); error = -EIO; @@ -278,11 +321,10 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list", /* check the on-disk data structure */ entry = FIRST_ENTRY(bh); while (!IS_LAST_ENTRY(entry)) { - struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(entry); - - if ((char *)next >= end) + if (!ext2_xattr_entry_valid(entry, end, + inode->i_sb->s_blocksize)) goto bad_block; - entry = next; + entry = EXT2_XATTR_NEXT(entry); } if (ext2_xattr_cache_insert(ea_block_cache, bh)) ea_idebug(inode, "cache insert failed"); @@ -367,7 +409,7 @@ ext2_xattr_set(struct inode *inode, int name_index, const char *name, struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; struct ext2_xattr_header *header = NULL; - struct ext2_xattr_entry *here, *last; + struct ext2_xattr_entry *here = NULL, *last = NULL; size_t name_len, free, min_offs = sb->s_blocksize; int not_found = 1, error; char *end; @@ -406,47 +448,39 @@ ext2_xattr_set(struct inode *inode, int name_index, const char *name, le32_to_cpu(HDR(bh)->h_refcount)); header = HDR(bh); end = bh->b_data + bh->b_size; - if (header->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || - header->h_blocks != cpu_to_le32(1)) { -bad_block: ext2_error(sb, "ext2_xattr_set", + if (!ext2_xattr_header_valid(header)) { +bad_block: + ext2_error(sb, "ext2_xattr_set", "inode %ld: bad block %d", inode->i_ino, EXT2_I(inode)->i_file_acl); error = -EIO; goto cleanup; } - /* Find the named attribute. */ - here = FIRST_ENTRY(bh); - while (!IS_LAST_ENTRY(here)) { - struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(here); - if ((char *)next >= end) - goto bad_block; - if (!here->e_value_block && here->e_value_size) { - size_t offs = le16_to_cpu(here->e_value_offs); - if (offs < min_offs) - min_offs = offs; - } - not_found = name_index - here->e_name_index; - if (!not_found) - not_found = name_len - here->e_name_len; - if (!not_found) - not_found = memcmp(name, here->e_name,name_len); - if (not_found <= 0) - break; - here = next; - } - last = here; - /* We still need to compute min_offs and last. */ + /* + * Find the named attribute. If not found, 'here' will point + * to entry where the new attribute should be inserted to + * maintain sorting. + */ + last = FIRST_ENTRY(bh); while (!IS_LAST_ENTRY(last)) { - struct ext2_xattr_entry *next = EXT2_XATTR_NEXT(last); - if ((char *)next >= end) + if (!ext2_xattr_entry_valid(last, end, sb->s_blocksize)) goto bad_block; - if (!last->e_value_block && last->e_value_size) { + if (last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) min_offs = offs; } - last = next; + if (not_found > 0) { + not_found = ext2_xattr_cmp_entry(name_index, + name_len, + name, last); + if (not_found <= 0) + here = last; + } + last = EXT2_XATTR_NEXT(last); } + if (not_found > 0) + here = last; /* Check whether we have enough space left. */ free = min_offs - ((char*)last - (char*)header) - sizeof(__u32); @@ -454,7 +488,6 @@ bad_block: ext2_error(sb, "ext2_xattr_set", /* We will use a new extended attribute block. */ free = sb->s_blocksize - sizeof(struct ext2_xattr_header) - sizeof(__u32); - here = last = NULL; /* avoid gcc uninitialized warning. */ } if (not_found) { @@ -470,14 +503,7 @@ bad_block: ext2_error(sb, "ext2_xattr_set", error = -EEXIST; if (flags & XATTR_CREATE) goto cleanup; - if (!here->e_value_block && here->e_value_size) { - size_t size = le32_to_cpu(here->e_value_size); - - if (le16_to_cpu(here->e_value_offs) + size > - sb->s_blocksize || size > sb->s_blocksize) - goto bad_block; - free += EXT2_XATTR_SIZE(size); - } + free += EXT2_XATTR_SIZE(le32_to_cpu(here->e_value_size)); free += EXT2_XATTR_LEN(name_len); } error = -ENOSPC; @@ -506,11 +532,10 @@ bad_block: ext2_error(sb, "ext2_xattr_set", unlock_buffer(bh); ea_bdebug(bh, "cloning"); - header = kmalloc(bh->b_size, GFP_KERNEL); + header = kmemdup(HDR(bh), bh->b_size, GFP_KERNEL); error = -ENOMEM; if (header == NULL) goto cleanup; - memcpy(header, HDR(bh), bh->b_size); header->h_refcount = cpu_to_le32(1); offset = (char *)here - bh->b_data; @@ -542,7 +567,7 @@ bad_block: ext2_error(sb, "ext2_xattr_set", here->e_name_len = name_len; memcpy(here->e_name, name, name_len); } else { - if (!here->e_value_block && here->e_value_size) { + if (here->e_value_size) { char *first_val = (char *)header + min_offs; size_t offs = le16_to_cpu(here->e_value_offs); char *val = (char *)header + offs; @@ -569,7 +594,7 @@ bad_block: ext2_error(sb, "ext2_xattr_set", last = ENTRY(header+1); while (!IS_LAST_ENTRY(last)) { size_t o = le16_to_cpu(last->e_value_offs); - if (!last->e_value_block && o < offs) + if (o < offs) last->e_value_offs = cpu_to_le16(o + size); last = EXT2_XATTR_NEXT(last); @@ -784,8 +809,7 @@ ext2_xattr_delete_inode(struct inode *inode) goto cleanup; } ea_bdebug(bh, "b_count=%d", atomic_read(&(bh->b_count))); - if (HDR(bh)->h_magic != cpu_to_le32(EXT2_XATTR_MAGIC) || - HDR(bh)->h_blocks != cpu_to_le32(1)) { + if (!ext2_xattr_header_valid(HDR(bh))) { ext2_error(inode->i_sb, "ext2_xattr_delete_inode", "inode %ld: bad block %d", inode->i_ino, EXT2_I(inode)->i_file_acl); diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 06f77ca7f36e..cbb5ca830e57 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # Ext3 configs are here for backward compatibility with old configs which may # have EXT3_FS set but not EXT4_FS set and thus would result in non-bootable # kernels after the removal of ext3 driver. diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e5d6ee61ff48..0b202e00d93f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -603,9 +603,9 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi, } /** - * ext4_should_retry_alloc() + * ext4_should_retry_alloc() - check if a block allocation should be retried * @sb: super block - * @retries number of attemps has been made + * @retries: number of attemps has been made * * ext4_should_retry_alloc() is called when ENOSPC is returned, and if * it is profitable to retry the operation, this function will wait diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 968f163b5feb..8e83741b02e0 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -142,7 +142,8 @@ static int ext4_protect_reserved_inode(struct super_block *sb, u32 ino) struct inode *inode; struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_map_blocks map; - u32 i = 0, err = 0, num, n; + u32 i = 0, num; + int err = 0, n; if ((ino < EXT4_ROOT_INO) || (ino > le32_to_cpu(sbi->s_es->s_inodes_count))) @@ -276,6 +277,11 @@ int ext4_check_blockref(const char *function, unsigned int line, __le32 *bref = p; unsigned int blk; + if (ext4_has_feature_journal(inode->i_sb) && + (inode->i_ino == + le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) + return 0; + while (bref < p+max) { blk = le32_to_cpu(*bref++); if (blk && diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 884a6e776809..86054f31fe4d 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -33,6 +33,9 @@ static int ext4_dx_readdir(struct file *, struct dir_context *); /** + * is_dx_dir() - check if a directory is using htree indexing + * @inode: directory inode + * * Check if the given dir-inode refers to an htree-indexed directory * (or a directory which could potentially get converted to use htree * indexing). @@ -109,7 +112,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct buffer_head *bh = NULL; - int dir_has_error = 0; struct fscrypt_str fstr = FSTR_INIT(NULL, 0); if (IS_ENCRYPTED(inode)) { @@ -145,8 +147,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) return err; } - offset = ctx->pos & (sb->s_blocksize - 1); - while (ctx->pos < inode->i_size) { struct ext4_map_blocks map; @@ -155,9 +155,18 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) goto errout; } cond_resched(); + offset = ctx->pos & (sb->s_blocksize - 1); map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb); map.m_len = 1; err = ext4_map_blocks(NULL, inode, &map, 0); + if (err == 0) { + /* m_len should never be zero but let's avoid + * an infinite loop if it somehow is */ + if (map.m_len == 0) + map.m_len = 1; + ctx->pos += map.m_len * sb->s_blocksize; + continue; + } if (err > 0) { pgoff_t index = map.m_pblk >> (PAGE_SHIFT - inode->i_blkbits); @@ -176,13 +185,6 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) } if (!bh) { - if (!dir_has_error) { - EXT4_ERROR_FILE(file, 0, - "directory contains a " - "hole at offset %llu", - (unsigned long long) ctx->pos); - dir_has_error = 1; - } /* corrupt size? Maybe no more blocks to read */ if (ctx->pos > inode->i_blocks << 9) break; @@ -192,8 +194,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) /* Check the checksum */ if (!buffer_verified(bh) && - !ext4_dirent_csum_verify(inode, - (struct ext4_dir_entry *)bh->b_data)) { + !ext4_dirblock_csum_verify(inode, bh)) { EXT4_ERROR_FILE(file, 0, "directory fails checksum " "at offset %llu", (unsigned long long)ctx->pos); @@ -671,10 +672,10 @@ static int ext4_d_compare(const struct dentry *dentry, unsigned int len, if (!IS_CASEFOLDED(dentry->d_parent->d_inode)) { if (len != name->len) return -1; - return !memcmp(str, name, len); + return memcmp(str, name->name, len); } - return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr); + return ext4_ci_compare(dentry->d_parent->d_inode, name, &qstr, false); } static int ext4_d_hash(const struct dentry *dentry, struct qstr *str) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1cb67859e051..bf660aa7a9e0 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -421,7 +421,8 @@ struct flex_groups { EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL) /* Flags that are appropriate for regular files (all but dir-specific ones). */ -#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL)) +#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\ + EXT4_PROJINHERIT_FL)) /* Flags that are appropriate for non-directories/regular files. */ #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL) @@ -2077,6 +2078,9 @@ struct ext4_filename { #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif +#ifdef CONFIG_UNICODE + struct fscrypt_str cf_name; +#endif }; #define fname_name(p) ((p)->disk_name.name) @@ -2302,6 +2306,12 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); +#ifdef CONFIG_UNICODE +extern void ext4_fname_setup_ci_filename(struct inode *dir, + const struct qstr *iname, + struct fscrypt_str *fname); +#endif + #ifdef CONFIG_FS_ENCRYPTION static inline void ext4_fname_from_fscrypt_name(struct ext4_filename *dst, const struct fscrypt_name *src) @@ -2328,6 +2338,10 @@ static inline int ext4_fname_setup_filename(struct inode *dir, return err; ext4_fname_from_fscrypt_name(fname, &name); + +#ifdef CONFIG_UNICODE + ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); +#endif return 0; } @@ -2343,6 +2357,10 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, return err; ext4_fname_from_fscrypt_name(fname, &name); + +#ifdef CONFIG_UNICODE + ext4_fname_setup_ci_filename(dir, &dentry->d_name, &fname->cf_name); +#endif return 0; } @@ -2356,6 +2374,11 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->crypto_buf.name = NULL; fname->usr_fname = NULL; fname->disk_name.name = NULL; + +#ifdef CONFIG_UNICODE + kfree(fname->cf_name.name); + fname->cf_name.name = NULL; +#endif } #else /* !CONFIG_FS_ENCRYPTION */ static inline int ext4_fname_setup_filename(struct inode *dir, @@ -2366,6 +2389,11 @@ static inline int ext4_fname_setup_filename(struct inode *dir, fname->usr_fname = iname; fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; + +#ifdef CONFIG_UNICODE + ext4_fname_setup_ci_filename(dir, iname, &fname->cf_name); +#endif + return 0; } @@ -2376,7 +2404,13 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, return ext4_fname_setup_filename(dir, &dentry->d_name, 1, fname); } -static inline void ext4_fname_free_filename(struct ext4_filename *fname) { } +static inline void ext4_fname_free_filename(struct ext4_filename *fname) +{ +#ifdef CONFIG_UNICODE + kfree(fname->cf_name.name); + fname->cf_name.name = NULL; +#endif +} #endif /* !CONFIG_FS_ENCRYPTION */ /* dir.c */ @@ -2568,8 +2602,8 @@ extern int ext4_ext_migrate(struct inode *); extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ -extern int ext4_dirent_csum_verify(struct inode *inode, - struct ext4_dir_entry *dirent); +extern int ext4_dirblock_csum_verify(struct inode *inode, + struct buffer_head *bh); extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, @@ -3070,11 +3104,11 @@ extern int ext4_try_create_inline_dir(handle_t *handle, extern int ext4_read_inline_dir(struct file *filp, struct dir_context *ctx, int *has_inline_data); -extern int htree_inlinedir_to_tree(struct file *dir_file, - struct inode *dir, ext4_lblk_t block, - struct dx_hash_info *hinfo, - __u32 start_hash, __u32 start_minor_hash, - int *has_inline_data); +extern int ext4_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data); extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, struct ext4_dir_entry_2 **res_dir, @@ -3113,14 +3147,13 @@ extern struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, struct ext4_dir_entry_2 *de, int blocksize, int csum_size, unsigned int parent_ino, int dotdot_real_len); -extern void initialize_dirent_tail(struct ext4_dir_entry_tail *t, - unsigned int blocksize); -extern int ext4_handle_dirty_dirent_node(handle_t *handle, - struct inode *inode, - struct buffer_head *bh); +extern void ext4_initialize_dirent_tail(struct buffer_head *bh, + unsigned int blocksize); +extern int ext4_handle_dirty_dirblock(handle_t *handle, struct inode *inode, + struct buffer_head *bh); extern int ext4_ci_compare(const struct inode *parent, - const struct qstr *name, - const struct qstr *entry); + const struct qstr *fname, + const struct qstr *entry, bool quick); #define S_SHIFT 12 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 75a5309f2231..ef8fcf7d0d3b 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -361,20 +361,20 @@ static inline int ext4_journal_force_commit(journal_t *journal) } static inline int ext4_jbd2_inode_add_write(handle_t *handle, - struct inode *inode) + struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) - return jbd2_journal_inode_add_write(handle, - EXT4_I(inode)->jinode); + return jbd2_journal_inode_ranged_write(handle, + EXT4_I(inode)->jinode, start_byte, length); return 0; } static inline int ext4_jbd2_inode_add_wait(handle_t *handle, - struct inode *inode) + struct inode *inode, loff_t start_byte, loff_t length) { if (ext4_handle_valid(handle)) - return jbd2_journal_inode_add_wait(handle, - EXT4_I(inode)->jinode); + return jbd2_journal_inode_ranged_wait(handle, + EXT4_I(inode)->jinode, start_byte, length); return 0; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0f89f5190cd7..92266a2da7d6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -518,10 +518,14 @@ __read_extent_tree_block(const char *function, unsigned int line, } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); - if (err) - goto errout; + if (!ext4_has_feature_journal(inode->i_sb) || + (inode->i_ino != + le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) { + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; + } set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries @@ -1035,6 +1039,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ int err = 0; + size_t ext_size = 0; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ @@ -1126,6 +1131,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1205,6 +1214,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } + /* zero out unused area in the extent block */ + ext_size = sizeof(struct ext4_extent_header) + + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); + memset(bh->b_data + ext_size, 0, + inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1270,6 +1284,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; + size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) @@ -1295,9 +1310,11 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, goto out; } + ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ - memmove(bh->b_data, EXT4_I(inode)->i_data, - sizeof(EXT4_I(inode)->i_data)); + memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); + /* zero out unused area in the extent block */ + memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); @@ -5659,8 +5676,8 @@ out_mutex: } /** - * ext4_swap_extents - Swap extents between two inodes - * + * ext4_swap_extents() - Swap extents between two inodes + * @handle: handle for this transaction * @inode1: First inode * @inode2: Second inode * @lblk1: Start block for first inode diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 023a3eb3afa3..7521de2dcf3a 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -1317,7 +1317,6 @@ static int es_do_reclaim_extents(struct ext4_inode_info *ei, ext4_lblk_t end, es = __es_tree_search(&tree->root, ei->i_es_shrink_lblk); if (!es) goto out_wrap; - node = &es->rb_node; while (*nr_to_scan > 0) { if (es->es_lblk > end) { ei->i_es_shrink_lblk = end + 1; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 98ec11f69cd4..f4a24a46245e 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -165,6 +165,10 @@ static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from) ret = generic_write_checks(iocb, from); if (ret <= 0) return ret; + + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + /* * If we have encountered a bitmap-format file, the size limit * is smaller than s_maxbytes, which is for extent-mapped files. @@ -264,6 +268,13 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) } ret = __generic_file_write_iter(iocb, from); + /* + * Unaligned direct AIO must be the only IO in flight. Otherwise + * overlapping aligned IO after unaligned might result in data + * corruption. + */ + if (ret == -EIOCBQUEUED && unaligned_aio) + ext4_unwritten_wait(inode); inode_unlock(inode); if (ret > 0) diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 4b99e2db95b8..dbccf46f1770 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -626,7 +626,7 @@ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, { struct ext4_fsmap dkeys[2]; /* per-dev keys */ struct ext4_getfsmap_dev handlers[EXT4_GETFSMAP_DEVS]; - struct ext4_getfsmap_info info = {0}; + struct ext4_getfsmap_info info = { NULL }; int i; int error = 0; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 2024d3fa5504..36699a131168 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -294,14 +294,12 @@ static int ext4_blks_to_allocate(Indirect *branch, int k, unsigned int blks, } /** - * ext4_alloc_branch - allocate and set up a chain of blocks. - * @handle: handle for this transaction - * @inode: owner - * @indirect_blks: number of allocated indirect blocks - * @blks: number of allocated direct blocks - * @goal: preferred place for allocation - * @offsets: offsets (in the blocks) to store the pointers to next. - * @branch: place to store the chain in. + * ext4_alloc_branch() - allocate and set up a chain of blocks + * @handle: handle for this transaction + * @ar: structure describing the allocation request + * @indirect_blks: number of allocated indirect blocks + * @offsets: offsets (in the blocks) to store the pointers to next. + * @branch: place to store the chain in. * * This function allocates blocks, zeroes out all but the last one, * links them into chain and (if we are synchronous) writes them to disk. @@ -396,15 +394,11 @@ failed: } /** - * ext4_splice_branch - splice the allocated branch onto inode. + * ext4_splice_branch() - splice the allocated branch onto inode. * @handle: handle for this transaction - * @inode: owner - * @block: (logical) number of block we are adding - * @chain: chain of indirect blocks (with a missing link - see - * ext4_alloc_branch) + * @ar: structure describing the allocation request * @where: location of missing link * @num: number of indirect blocks we are adding - * @blks: number of direct blocks we are adding * * This function fills the missing link and does all housekeeping needed in * inode (->i_blocks, etc.). In case of success we end up with the full diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index f73bc3925282..88cdf3c90bd1 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1132,7 +1132,6 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, { int err, csum_size = 0, header_size = 0; struct ext4_dir_entry_2 *de; - struct ext4_dir_entry_tail *t; void *target = dir_block->b_data; /* @@ -1158,13 +1157,11 @@ static int ext4_finish_convert_inline_dir(handle_t *handle, inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size, inode->i_sb->s_blocksize - csum_size); - if (csum_size) { - t = EXT4_DIRENT_TAIL(dir_block->b_data, - inode->i_sb->s_blocksize); - initialize_dirent_tail(t, inode->i_sb->s_blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(dir_block, + inode->i_sb->s_blocksize); set_buffer_uptodate(dir_block); - err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); + err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) return err; set_buffer_verified(dir_block); @@ -1327,11 +1324,11 @@ out: * inlined dir. It returns the number directory entries loaded * into the tree. If there is an error it is returned in err. */ -int htree_inlinedir_to_tree(struct file *dir_file, - struct inode *dir, ext4_lblk_t block, - struct dx_hash_info *hinfo, - __u32 start_hash, __u32 start_minor_hash, - int *has_inline_data) +int ext4_inlinedir_to_tree(struct file *dir_file, + struct inode *dir, ext4_lblk_t block, + struct dx_hash_info *hinfo, + __u32 start_hash, __u32 start_minor_hash, + int *has_inline_data) { int err = 0, count = 0; unsigned int parent_ino; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 82298c63ea6d..420fe3deed39 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -731,10 +731,16 @@ out_sem: !(flags & EXT4_GET_BLOCKS_ZERO) && !ext4_is_quota_file(inode) && ext4_should_order_data(inode)) { + loff_t start_byte = + (loff_t)map->m_lblk << inode->i_blkbits; + loff_t length = (loff_t)map->m_len << inode->i_blkbits; + if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) - ret = ext4_jbd2_inode_add_wait(handle, inode); + ret = ext4_jbd2_inode_add_wait(handle, inode, + start_byte, length); else - ret = ext4_jbd2_inode_add_write(handle, inode); + ret = ext4_jbd2_inode_add_write(handle, inode, + start_byte, length); if (ret) return ret; } @@ -1164,8 +1170,9 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, int err = 0; unsigned blocksize = inode->i_sb->s_blocksize; unsigned bbits; - struct buffer_head *bh, *head, *wait[2], **wait_bh = wait; - bool decrypt = false; + struct buffer_head *bh, *head, *wait[2]; + int nr_wait = 0; + int i; BUG_ON(!PageLocked(page)); BUG_ON(from > PAGE_SIZE); @@ -1217,23 +1224,32 @@ static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, !buffer_unwritten(bh) && (block_start < from || block_end > to)) { ll_rw_block(REQ_OP_READ, 0, 1, &bh); - *wait_bh++ = bh; - decrypt = IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode); + wait[nr_wait++] = bh; } } /* * If we issued read requests, let them complete. */ - while (wait_bh > wait) { - wait_on_buffer(*--wait_bh); - if (!buffer_uptodate(*wait_bh)) + for (i = 0; i < nr_wait; i++) { + wait_on_buffer(wait[i]); + if (!buffer_uptodate(wait[i])) err = -EIO; } - if (unlikely(err)) + if (unlikely(err)) { page_zero_new_buffers(page, from, to); - else if (decrypt) - err = fscrypt_decrypt_page(page->mapping->host, page, - PAGE_SIZE, 0, page->index); + } else if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) { + for (i = 0; i < nr_wait; i++) { + int err2; + + err2 = fscrypt_decrypt_pagecache_blocks(page, blocksize, + bh_offset(wait[i])); + if (err2) { + clear_buffer_uptodate(wait[i]); + err = err2; + } + } + } + return err; } #endif @@ -4065,9 +4081,8 @@ static int __ext4_block_zero_page_range(handle_t *handle, if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) { /* We expect the key to be set. */ BUG_ON(!fscrypt_has_encryption_key(inode)); - BUG_ON(blocksize != PAGE_SIZE); - WARN_ON_ONCE(fscrypt_decrypt_page(page->mapping->host, - page, PAGE_SIZE, 0, page->index)); + WARN_ON_ONCE(fscrypt_decrypt_pagecache_blocks( + page, blocksize, bh_offset(bh))); } } if (ext4_should_journal_data(inode)) { @@ -4085,7 +4100,8 @@ static int __ext4_block_zero_page_range(handle_t *handle, err = 0; mark_buffer_dirty(bh); if (ext4_should_order_data(inode)) - err = ext4_jbd2_inode_add_write(handle, inode); + err = ext4_jbd2_inode_add_write(handle, inode, from, + length); } unlock: @@ -4570,6 +4586,7 @@ static int __ext4_get_inode_loc(struct inode *inode, struct buffer_head *bh; struct super_block *sb = inode->i_sb; ext4_fsblk_t block; + struct blk_plug plug; int inodes_per_block, inode_offset; iloc->bh = NULL; @@ -4658,6 +4675,7 @@ make_io: * If we need to do any I/O, try to pre-readahead extra * blocks from the inode table. */ + blk_start_plug(&plug); if (EXT4_SB(sb)->s_inode_readahead_blks) { ext4_fsblk_t b, end, table; unsigned num; @@ -4688,6 +4706,7 @@ make_io: get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh); + blk_finish_plug(&plug); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { EXT4_ERROR_INODE_BLOCK(inode, block, @@ -5520,6 +5539,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) return -EIO; + if (unlikely(IS_IMMUTABLE(inode))) + return -EPERM; + + if (unlikely(IS_APPEND(inode) && + (ia_valid & (ATTR_MODE | ATTR_UID | + ATTR_GID | ATTR_TIMES_SET)))) + return -EPERM; + error = setattr_prepare(dentry, attr); if (error) return error; @@ -5571,7 +5598,7 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid & ATTR_SIZE) { handle_t *handle; loff_t oldsize = inode->i_size; - int shrink = (attr->ia_size <= inode->i_size); + int shrink = (attr->ia_size < inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -5585,18 +5612,33 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size) inode_inc_iversion(inode); - if (ext4_should_order_data(inode) && - (attr->ia_size < inode->i_size)) { - error = ext4_begin_ordered_truncate(inode, + if (shrink) { + if (ext4_should_order_data(inode)) { + error = ext4_begin_ordered_truncate(inode, attr->ia_size); - if (error) - goto err_out; + if (error) + goto err_out; + } + /* + * Blocks are going to be removed from the inode. Wait + * for dio in flight. + */ + inode_dio_wait(inode); + } + + down_write(&EXT4_I(inode)->i_mmap_sem); + + rc = ext4_break_layouts(inode); + if (rc) { + up_write(&EXT4_I(inode)->i_mmap_sem); + return rc; } + if (attr->ia_size != inode->i_size) { handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); if (IS_ERR(handle)) { error = PTR_ERR(handle); - goto err_out; + goto out_mmap_sem; } if (ext4_handle_valid(handle) && shrink) { error = ext4_orphan_add(handle, inode); @@ -5624,33 +5666,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) i_size_write(inode, attr->ia_size); up_write(&EXT4_I(inode)->i_data_sem); ext4_journal_stop(handle); - if (error) { - if (orphan) - ext4_orphan_del(NULL, inode); - goto err_out; - } - } - if (!shrink) - pagecache_isize_extended(inode, oldsize, inode->i_size); - - /* - * Blocks are going to be removed from the inode. Wait - * for dio in flight. Temporarily disable - * dioread_nolock to prevent livelock. - */ - if (orphan) { - if (!ext4_should_journal_data(inode)) { - inode_dio_wait(inode); - } else + if (error) + goto out_mmap_sem; + if (!shrink) { + pagecache_isize_extended(inode, oldsize, + inode->i_size); + } else if (ext4_should_journal_data(inode)) { ext4_wait_for_tail_page_commit(inode); - } - down_write(&EXT4_I(inode)->i_mmap_sem); - - rc = ext4_break_layouts(inode); - if (rc) { - up_write(&EXT4_I(inode)->i_mmap_sem); - error = rc; - goto err_out; + } } /* @@ -5658,11 +5681,16 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) * in data=journal mode to make pages freeable. */ truncate_pagecache(inode, inode->i_size); - if (shrink) { + /* + * Call ext4_truncate() even if i_size didn't change to + * truncate possible preallocated blocks. + */ + if (attr->ia_size <= oldsize) { rc = ext4_truncate(inode); if (rc) error = rc; } +out_mmap_sem: up_write(&EXT4_I(inode)->i_mmap_sem); } @@ -6193,6 +6221,9 @@ vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf) get_block_t *get_block; int retries = 0; + if (unlikely(IS_IMMUTABLE(inode))) + return VM_FAULT_SIGBUS; + sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 7e85ecf0b849..442f7ef873fc 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -269,6 +269,29 @@ static int uuid_is_zero(__u8 u[16]) } #endif +/* + * If immutable is set and we are not clearing it, we're not allowed to change + * anything else in the inode. Don't error out if we're only trying to set + * immutable on an immutable file. + */ +static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid, + unsigned int flags) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + unsigned int oldflags = ei->i_flags; + + if (!(oldflags & EXT4_IMMUTABLE_FL) || !(flags & EXT4_IMMUTABLE_FL)) + return 0; + + if ((oldflags & ~EXT4_IMMUTABLE_FL) != (flags & ~EXT4_IMMUTABLE_FL)) + return -EPERM; + if (ext4_has_feature_project(inode->i_sb) && + __kprojid_val(ei->i_projid) != new_projid) + return -EPERM; + + return 0; +} + static int ext4_ioctl_setflags(struct inode *inode, unsigned int flags) { @@ -289,16 +312,9 @@ static int ext4_ioctl_setflags(struct inode *inode, /* The JOURNAL_DATA flag is modifiable only by root */ jflag = flags & EXT4_JOURNAL_DATA_FL; - /* - * The IMMUTABLE and APPEND_ONLY flags can only be changed by - * the relevant capability. - * - * This test looks nicer. Thanks to Pauline Middelink - */ - if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) - goto flags_out; - } + err = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (err) + goto flags_out; /* * The JOURNAL_DATA flag can only be changed by @@ -340,6 +356,20 @@ static int ext4_ioctl_setflags(struct inode *inode, } } + /* + * Wait for all pending directio and then flush all the dirty pages + * for this file. The flush marks all the pages readonly, so any + * subsequent attempt to write to the file (particularly mmap pages) + * will come through the filesystem and fail. + */ + if (S_ISREG(inode->i_mode) && !IS_IMMUTABLE(inode) && + (flags & EXT4_IMMUTABLE_FL)) { + inode_dio_wait(inode); + err = filemap_write_and_wait(inode->i_mapping); + if (err) + goto flags_out; + } + handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); @@ -608,7 +638,7 @@ static int ext4_getfsmap_format(struct ext4_fsmap *xfm, void *priv) static int ext4_ioc_getfsmap(struct super_block *sb, struct fsmap_head __user *arg) { - struct getfsmap_info info = {0}; + struct getfsmap_info info = { NULL }; struct ext4_fsmap_head xhead = {0}; struct fsmap_head head; bool aborted = false; @@ -704,28 +734,15 @@ group_add_out: return err; } -static int ext4_ioctl_check_project(struct inode *inode, struct fsxattr *fa) +static void ext4_fill_fsxattr(struct inode *inode, struct fsxattr *fa) { - /* - * Project Quota ID state is only allowed to change from within the init - * namespace. Enforce that restriction only if we are trying to change - * the quota ID state. Everything else is allowed in user namespaces. - */ - if (current_user_ns() == &init_user_ns) - return 0; - - if (__kprojid_val(EXT4_I(inode)->i_projid) != fa->fsx_projid) - return -EINVAL; + struct ext4_inode_info *ei = EXT4_I(inode); - if (ext4_test_inode_flag(inode, EXT4_INODE_PROJINHERIT)) { - if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT)) - return -EINVAL; - } else { - if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) - return -EINVAL; - } + simple_fill_fsxattr(fa, ext4_iflags_to_xflags(ei->i_flags & + EXT4_FL_USER_VISIBLE)); - return 0; + if (ext4_has_feature_project(inode->i_sb)) + fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid); } long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) @@ -742,6 +759,8 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return ext4_ioc_getfsmap(sb, (void __user *)arg); case EXT4_IOC_GETFLAGS: flags = ei->i_flags & EXT4_FL_USER_VISIBLE; + if (S_ISREG(inode->i_mode)) + flags &= ~EXT4_PROJINHERIT_FL; return put_user(flags, (int __user *) arg); case EXT4_IOC_SETFLAGS: { int err; @@ -769,7 +788,11 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return err; inode_lock(inode); - err = ext4_ioctl_setflags(inode, flags); + err = ext4_ioctl_check_immutable(inode, + from_kprojid(&init_user_ns, ei->i_projid), + flags); + if (!err) + err = ext4_ioctl_setflags(inode, flags); inode_unlock(inode); mnt_drop_write_file(filp); return err; @@ -1096,13 +1119,7 @@ resizefs_out: { struct fsxattr fa; - memset(&fa, 0, sizeof(struct fsxattr)); - fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE); - - if (ext4_has_feature_project(inode->i_sb)) { - fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, - EXT4_I(inode)->i_projid); - } + ext4_fill_fsxattr(inode, &fa); if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) @@ -1111,7 +1128,7 @@ resizefs_out: } case EXT4_IOC_FSSETXATTR: { - struct fsxattr fa; + struct fsxattr fa, old_fa; int err; if (copy_from_user(&fa, (struct fsxattr __user *)arg, @@ -1134,11 +1151,15 @@ resizefs_out: return err; inode_lock(inode); - err = ext4_ioctl_check_project(inode, &fa); + ext4_fill_fsxattr(inode, &old_fa); + err = vfs_ioc_fssetxattr_check(inode, &old_fa, &fa); if (err) goto out; flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) | (flags & EXT4_FL_XFLAG_VISIBLE); + err = ext4_ioctl_check_immutable(inode, fa.fsx_projid, flags); + if (err) + goto out; err = ext4_ioctl_setflags(inode, flags); if (err) goto out; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 99ba720dbb7a..a3e2767bdf2f 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -4696,8 +4696,9 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b, * ext4_free_blocks() -- Free given blocks and update quota * @handle: handle for this transaction * @inode: inode - * @block: start physical block to free - * @count: number of blocks to count + * @bh: optional buffer of the block to be freed + * @block: starting physical block to be freed + * @count: number of blocks to be freed * @flags: flags used by ext4_free_blocks */ void ext4_free_blocks(handle_t *handle, struct inode *inode, diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 1083a9f3f16a..30ce3dc69378 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -13,11 +13,10 @@ #include "ext4_extents.h" /** - * get_ext_path - Find an extent path for designated logical block number. - * - * @inode: an inode which is searched + * get_ext_path() - Find an extent path for designated logical block number. + * @inode: inode to be searched * @lblock: logical block number to find an extent path - * @path: pointer to an extent path pointer (for output) + * @ppath: pointer to an extent path pointer (for output) * * ext4_find_extent wrapper. Return 0 on success, or a negative error value * on failure. @@ -42,8 +41,9 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock, } /** - * ext4_double_down_write_data_sem - Acquire two inodes' write lock - * of i_data_sem + * ext4_double_down_write_data_sem() - write lock two inodes's i_data_sem + * @first: inode to be locked + * @second: inode to be locked * * Acquire write lock of i_data_sem of the two inodes */ @@ -390,7 +390,8 @@ data_copy: /* Even in case of data=writeback it is reasonable to pin * inode to transaction, to prevent unexpected data loss */ - *err = ext4_jbd2_inode_add_write(handle, orig_inode); + *err = ext4_jbd2_inode_add_write(handle, orig_inode, + (loff_t)orig_page_offset << PAGE_SHIFT, replaced_size); unlock_pages: unlock_page(pagep[0]); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 6d50f53b7a15..129029534075 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -82,8 +82,18 @@ static struct buffer_head *ext4_append(handle_t *handle, static int ext4_dx_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent); +/* + * Hints to ext4_read_dirblock regarding whether we expect a directory + * block being read to be an index block, or a block containing + * directory entries (and if the latter, whether it was found via a + * logical block in an htree index block). This is used to control + * what sort of sanity checkinig ext4_read_dirblock() will do on the + * directory block read from the storage device. EITHER will means + * the caller doesn't know what kind of directory block will be read, + * so no specific verification will be done. + */ typedef enum { - EITHER, INDEX, DIRENT + EITHER, INDEX, DIRENT, DIRENT_HTREE } dirblock_type_t; #define ext4_read_dirblock(inode, block, type) \ @@ -109,11 +119,14 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, return bh; } - if (!bh) { + if (!bh && (type == INDEX || type == DIRENT_HTREE)) { ext4_error_inode(inode, func, line, block, - "Directory hole found"); + "Directory hole found for htree %s block", + (type == INDEX) ? "index" : "leaf"); return ERR_PTR(-EFSCORRUPTED); } + if (!bh) + return NULL; dirent = (struct ext4_dir_entry *) bh->b_data; /* Determine whether or not we have an index block */ if (is_dx(inode)) { @@ -150,7 +163,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, } } if (!is_dx_block) { - if (ext4_dirent_csum_verify(inode, dirent)) + if (ext4_dirblock_csum_verify(inode, bh)) set_buffer_verified(bh); else { ext4_error_inode(inode, func, line, block, @@ -280,9 +293,11 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, struct inode *dir, struct inode *inode); /* checksumming functions */ -void initialize_dirent_tail(struct ext4_dir_entry_tail *t, - unsigned int blocksize) +void ext4_initialize_dirent_tail(struct buffer_head *bh, + unsigned int blocksize) { + struct ext4_dir_entry_tail *t = EXT4_DIRENT_TAIL(bh->b_data, blocksize); + memset(t, 0, sizeof(struct ext4_dir_entry_tail)); t->det_rec_len = ext4_rec_len_to_disk( sizeof(struct ext4_dir_entry_tail), blocksize); @@ -291,17 +306,17 @@ void initialize_dirent_tail(struct ext4_dir_entry_tail *t, /* Walk through a dirent block to find a checksum "dirent" at the tail */ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, - struct ext4_dir_entry *de) + struct buffer_head *bh) { struct ext4_dir_entry_tail *t; #ifdef PARANOID struct ext4_dir_entry *d, *top; - d = de; - top = (struct ext4_dir_entry *)(((void *)de) + + d = (struct ext4_dir_entry *)bh->b_data; + top = (struct ext4_dir_entry *)(bh->b_data + (EXT4_BLOCK_SIZE(inode->i_sb) - - sizeof(struct ext4_dir_entry_tail))); + sizeof(struct ext4_dir_entry_tail))); while (d < top && d->rec_len) d = (struct ext4_dir_entry *)(((void *)d) + le16_to_cpu(d->rec_len)); @@ -311,7 +326,7 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, t = (struct ext4_dir_entry_tail *)d; #else - t = EXT4_DIRENT_TAIL(de, EXT4_BLOCK_SIZE(inode->i_sb)); + t = EXT4_DIRENT_TAIL(bh->b_data, EXT4_BLOCK_SIZE(inode->i_sb)); #endif if (t->det_reserved_zero1 || @@ -323,8 +338,7 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, return t; } -static __le32 ext4_dirent_csum(struct inode *inode, - struct ext4_dir_entry *dirent, int size) +static __le32 ext4_dirblock_csum(struct inode *inode, void *dirent, int size) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); @@ -344,49 +358,49 @@ static void __warn_no_space_for_csum(struct inode *inode, const char *func, "No space for directory leaf checksum. Please run e2fsck -D."); } -int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) +int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh) { struct ext4_dir_entry_tail *t; if (!ext4_has_metadata_csum(inode->i_sb)) return 1; - t = get_dirent_tail(inode, dirent); + t = get_dirent_tail(inode, bh); if (!t) { warn_no_space_for_csum(inode); return 0; } - if (t->det_checksum != ext4_dirent_csum(inode, dirent, - (void *)t - (void *)dirent)) + if (t->det_checksum != ext4_dirblock_csum(inode, bh->b_data, + (char *)t - bh->b_data)) return 0; return 1; } -static void ext4_dirent_csum_set(struct inode *inode, - struct ext4_dir_entry *dirent) +static void ext4_dirblock_csum_set(struct inode *inode, + struct buffer_head *bh) { struct ext4_dir_entry_tail *t; if (!ext4_has_metadata_csum(inode->i_sb)) return; - t = get_dirent_tail(inode, dirent); + t = get_dirent_tail(inode, bh); if (!t) { warn_no_space_for_csum(inode); return; } - t->det_checksum = ext4_dirent_csum(inode, dirent, - (void *)t - (void *)dirent); + t->det_checksum = ext4_dirblock_csum(inode, bh->b_data, + (char *)t - bh->b_data); } -int ext4_handle_dirty_dirent_node(handle_t *handle, - struct inode *inode, - struct buffer_head *bh) +int ext4_handle_dirty_dirblock(handle_t *handle, + struct inode *inode, + struct buffer_head *bh) { - ext4_dirent_csum_set(inode, (struct ext4_dir_entry *)bh->b_data); + ext4_dirblock_csum_set(inode, bh); return ext4_handle_dirty_metadata(handle, inode, bh); } @@ -872,12 +886,15 @@ static void dx_release(struct dx_frame *frames) { struct dx_root_info *info; int i; + unsigned int indirect_levels; if (frames[0].bh == NULL) return; info = &((struct dx_root *)frames[0].bh->b_data)->info; - for (i = 0; i <= info->indirect_levels; i++) { + /* save local copy, "info" may be freed after brelse() */ + indirect_levels = info->indirect_levels; + for (i = 0; i <= indirect_levels; i++) { if (frames[i].bh == NULL) break; brelse(frames[i].bh); @@ -977,7 +994,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) return PTR_ERR(bh); @@ -1087,10 +1104,10 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; if (ext4_has_inline_data(dir)) { int has_inline_data = 1; - count = htree_inlinedir_to_tree(dir_file, dir, 0, - &hinfo, start_hash, - start_minor_hash, - &has_inline_data); + count = ext4_inlinedir_to_tree(dir_file, dir, 0, + &hinfo, start_hash, + start_minor_hash, + &has_inline_data); if (has_inline_data) { *next_hash = ~0; return count; @@ -1256,19 +1273,24 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) #ifdef CONFIG_UNICODE /* * Test whether a case-insensitive directory entry matches the filename - * being searched for. + * being searched for. If quick is set, assume the name being looked up + * is already in the casefolded form. * * Returns: 0 if the directory entry matches, more than 0 if it * doesn't match or less than zero on error. */ int ext4_ci_compare(const struct inode *parent, const struct qstr *name, - const struct qstr *entry) + const struct qstr *entry, bool quick) { const struct ext4_sb_info *sbi = EXT4_SB(parent->i_sb); const struct unicode_map *um = sbi->s_encoding; int ret; - ret = utf8_strncasecmp(um, name, entry); + if (quick) + ret = utf8_strncasecmp_folded(um, name, entry); + else + ret = utf8_strncasecmp(um, name, entry); + if (ret < 0) { /* Handle invalid character sequence as either an error * or as an opaque byte sequence. @@ -1284,6 +1306,32 @@ int ext4_ci_compare(const struct inode *parent, const struct qstr *name, return ret; } + +void ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, + struct fscrypt_str *cf_name) +{ + int len; + + if (!IS_CASEFOLDED(dir)) { + cf_name->name = NULL; + return; + } + + cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS); + if (!cf_name->name) + return; + + len = utf8_casefold(EXT4_SB(dir->i_sb)->s_encoding, + iname, cf_name->name, + EXT4_NAME_LEN); + if (len <= 0) { + kfree(cf_name->name); + cf_name->name = NULL; + return; + } + cf_name->len = (unsigned) len; + +} #endif /* @@ -1310,8 +1358,15 @@ static inline bool ext4_match(const struct inode *parent, #endif #ifdef CONFIG_UNICODE - if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) - return (ext4_ci_compare(parent, fname->usr_fname, &entry) == 0); + if (EXT4_SB(parent->i_sb)->s_encoding && IS_CASEFOLDED(parent)) { + if (fname->cf_name.name) { + struct qstr cf = {.name = fname->cf_name.name, + .len = fname->cf_name.len}; + return !ext4_ci_compare(parent, &cf, &entry, true); + } + return !ext4_ci_compare(parent, fname->usr_fname, &entry, + false); + } #endif return fscrypt_match_name(&f, de->name, de->name_len); @@ -1481,8 +1536,7 @@ restart: if (!buffer_verified(bh) && !is_dx_internal_node(dir, block, (struct ext4_dir_entry *)bh->b_data) && - !ext4_dirent_csum_verify(dir, - (struct ext4_dir_entry *)bh->b_data)) { + !ext4_dirblock_csum_verify(dir, bh)) { EXT4_ERROR_INODE(dir, "checksumming directory " "block %lu", (unsigned long)block); brelse(bh); @@ -1583,7 +1637,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, return (struct buffer_head *) frame; do { block = dx_get_block(frame->at); - bh = ext4_read_dirblock(dir, block, DIRENT); + bh = ext4_read_dirblock(dir, block, DIRENT_HTREE); if (IS_ERR(bh)) goto errout; @@ -1766,7 +1820,6 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, char *data1 = (*bh)->b_data, *data2; unsigned split, move, size; struct ext4_dir_entry_2 *de = NULL, *de2; - struct ext4_dir_entry_tail *t; int csum_size = 0; int err = 0, i; @@ -1827,11 +1880,8 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, (char *) de2, blocksize); if (csum_size) { - t = EXT4_DIRENT_TAIL(data2, blocksize); - initialize_dirent_tail(t, blocksize); - - t = EXT4_DIRENT_TAIL(data1, blocksize); - initialize_dirent_tail(t, blocksize); + ext4_initialize_dirent_tail(*bh, blocksize); + ext4_initialize_dirent_tail(bh2, blocksize); } dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data1, @@ -1845,7 +1895,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, de = de2; } dx_insert_block(frame, hash2 + continued, newblock); - err = ext4_handle_dirty_dirent_node(handle, dir, bh2); + err = ext4_handle_dirty_dirblock(handle, dir, bh2); if (err) goto journal_error; err = ext4_handle_dirty_dx_node(handle, dir, frame->bh); @@ -1973,7 +2023,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, inode_inc_iversion(dir); ext4_mark_inode_dirty(handle, dir); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, dir, bh); + err = ext4_handle_dirty_dirblock(handle, dir, bh); if (err) ext4_std_error(dir->i_sb, err); return 0; @@ -1992,8 +2042,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct dx_entry *entries; struct ext4_dir_entry_2 *de, *de2; - struct ext4_dir_entry_tail *t; - char *data1, *top; + char *data2, *top; unsigned len; int retval; unsigned blocksize; @@ -2033,21 +2082,18 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, return PTR_ERR(bh2); } ext4_set_inode_flag(dir, EXT4_INODE_INDEX); - data1 = bh2->b_data; + data2 = bh2->b_data; - memcpy (data1, de, len); - de = (struct ext4_dir_entry_2 *) data1; - top = data1 + len; + memcpy(data2, de, len); + de = (struct ext4_dir_entry_2 *) data2; + top = data2 + len; while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) de = de2; - de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - - (char *) de, - blocksize); + de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - + (char *) de, blocksize); - if (csum_size) { - t = EXT4_DIRENT_TAIL(data1, blocksize); - initialize_dirent_tail(t, blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(bh2, blocksize); /* Initialize the root; the dot dirents already exist */ de = (struct ext4_dir_entry_2 *) (&root->dotdot); @@ -2077,7 +2123,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (retval) goto out_frames; - retval = ext4_handle_dirty_dirent_node(handle, dir, bh2); + retval = ext4_handle_dirty_dirblock(handle, dir, bh2); if (retval) goto out_frames; @@ -2117,7 +2163,6 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct inode *dir = d_inode(dentry->d_parent); struct buffer_head *bh = NULL; struct ext4_dir_entry_2 *de; - struct ext4_dir_entry_tail *t; struct super_block *sb; struct ext4_sb_info *sbi; struct ext4_filename fname; @@ -2167,6 +2212,11 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0; block < blocks; block++) { bh = ext4_read_dirblock(dir, block, DIRENT); + if (bh == NULL) { + bh = ext4_bread(handle, dir, block, + EXT4_GET_BLOCKS_CREATE); + goto add_to_new_block; + } if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2187,6 +2237,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, brelse(bh); } bh = ext4_append(handle, dir, &block); +add_to_new_block: if (IS_ERR(bh)) { retval = PTR_ERR(bh); bh = NULL; @@ -2196,10 +2247,8 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, de->inode = 0; de->rec_len = ext4_rec_len_to_disk(blocksize - csum_size, blocksize); - if (csum_size) { - t = EXT4_DIRENT_TAIL(bh->b_data, blocksize); - initialize_dirent_tail(t, blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(bh, blocksize); retval = add_dirent_to_buf(handle, &fname, dir, inode, de, bh); out: @@ -2231,7 +2280,7 @@ again: return PTR_ERR(frame); entries = frame->entries; at = frame->at; - bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT); + bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT_HTREE); if (IS_ERR(bh)) { err = PTR_ERR(bh); bh = NULL; @@ -2457,7 +2506,7 @@ static int ext4_delete_entry(handle_t *handle, goto out; BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, dir, bh); + err = ext4_handle_dirty_dirblock(handle, dir, bh); if (unlikely(err)) goto out; @@ -2659,7 +2708,6 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, { struct buffer_head *dir_block = NULL; struct ext4_dir_entry_2 *de; - struct ext4_dir_entry_tail *t; ext4_lblk_t block = 0; unsigned int blocksize = dir->i_sb->s_blocksize; int csum_size = 0; @@ -2683,13 +2731,11 @@ static int ext4_init_new_dir(handle_t *handle, struct inode *dir, de = (struct ext4_dir_entry_2 *)dir_block->b_data; ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0); set_nlink(inode, 2); - if (csum_size) { - t = EXT4_DIRENT_TAIL(dir_block->b_data, blocksize); - initialize_dirent_tail(t, blocksize); - } + if (csum_size) + ext4_initialize_dirent_tail(dir_block, blocksize); BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); + err = ext4_handle_dirty_dirblock(handle, inode, dir_block); if (err) goto out; set_buffer_verified(dir_block); @@ -2779,7 +2825,10 @@ bool ext4_empty_dir(struct inode *inode) EXT4_ERROR_INODE(inode, "invalid size"); return true; } - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, + * so treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) return true; @@ -2801,6 +2850,10 @@ bool ext4_empty_dir(struct inode *inode) brelse(bh); lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb); bh = ext4_read_dirblock(inode, lblock, EITHER); + if (bh == NULL) { + offset += sb->s_blocksize; + continue; + } if (IS_ERR(bh)) return true; de = (struct ext4_dir_entry_2 *) bh->b_data; @@ -3366,7 +3419,10 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle, struct buffer_head *bh; if (!ext4_has_inline_data(inode)) { - bh = ext4_read_dirblock(inode, 0, EITHER); + /* The first directory block must not be a hole, so + * treat it as DIRENT_HTREE + */ + bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE); if (IS_ERR(bh)) { *retval = PTR_ERR(bh); return NULL; @@ -3427,9 +3483,8 @@ static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent, ent->inode, ent->dir_bh); } else { - retval = ext4_handle_dirty_dirent_node(handle, - ent->inode, - ent->dir_bh); + retval = ext4_handle_dirty_dirblock(handle, ent->inode, + ent->dir_bh); } } else { retval = ext4_mark_inode_dirty(handle, ent->inode); @@ -3459,8 +3514,7 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, ext4_mark_inode_dirty(handle, ent->dir); BUFFER_TRACE(ent->bh, "call ext4_handle_dirty_metadata"); if (!ent->inlined) { - retval = ext4_handle_dirty_dirent_node(handle, - ent->dir, ent->bh); + retval = ext4_handle_dirty_dirblock(handle, ent->dir, ent->bh); if (unlikely(retval)) { ext4_std_error(ent->dir->i_sb, retval); return retval; diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 4690618a92e9..a18a47a2a1d1 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -66,9 +66,7 @@ static void ext4_finish_bio(struct bio *bio) bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; -#ifdef CONFIG_FS_ENCRYPTION - struct page *data_page = NULL; -#endif + struct page *bounce_page = NULL; struct buffer_head *bh, *head; unsigned bio_start = bvec->bv_offset; unsigned bio_end = bio_start + bvec->bv_len; @@ -78,13 +76,10 @@ static void ext4_finish_bio(struct bio *bio) if (!page) continue; -#ifdef CONFIG_FS_ENCRYPTION - if (!page->mapping) { - /* The bounce data pages are unmapped. */ - data_page = page; - fscrypt_pullback_bio_page(&page, false); + if (fscrypt_is_bounce_page(page)) { + bounce_page = page; + page = fscrypt_pagecache_page(bounce_page); } -#endif if (bio->bi_status) { SetPageError(page); @@ -111,10 +106,7 @@ static void ext4_finish_bio(struct bio *bio) bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); local_irq_restore(flags); if (!under_io) { -#ifdef CONFIG_FS_ENCRYPTION - if (data_page) - fscrypt_restore_control_page(data_page); -#endif + fscrypt_free_bounce_page(bounce_page); end_page_writeback(page); } } @@ -415,7 +407,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, struct writeback_control *wbc, bool keep_towrite) { - struct page *data_page = NULL; + struct page *bounce_page = NULL; struct inode *inode = page->mapping->host; unsigned block_start; struct buffer_head *bh, *head; @@ -475,14 +467,22 @@ int ext4_bio_write_page(struct ext4_io_submit *io, bh = head = page_buffers(page); + /* + * If any blocks are being written to an encrypted file, encrypt them + * into a bounce page. For simplicity, just encrypt until the last + * block which might be needed. This may cause some unneeded blocks + * (e.g. holes) to be unnecessarily encrypted, but this is rare and + * can't happen in the common case of blocksize == PAGE_SIZE. + */ if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode) && nr_to_submit) { gfp_t gfp_flags = GFP_NOFS; + unsigned int enc_bytes = round_up(len, i_blocksize(inode)); retry_encrypt: - data_page = fscrypt_encrypt_page(inode, page, PAGE_SIZE, 0, - page->index, gfp_flags); - if (IS_ERR(data_page)) { - ret = PTR_ERR(data_page); + bounce_page = fscrypt_encrypt_pagecache_blocks(page, enc_bytes, + 0, gfp_flags); + if (IS_ERR(bounce_page)) { + ret = PTR_ERR(bounce_page); if (ret == -ENOMEM && wbc->sync_mode == WB_SYNC_ALL) { if (io->io_bio) { ext4_io_submit(io); @@ -491,7 +491,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, gfp_flags |= __GFP_NOFAIL; goto retry_encrypt; } - data_page = NULL; + bounce_page = NULL; goto out; } } @@ -500,8 +500,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, do { if (!buffer_async_write(bh)) continue; - ret = io_submit_add_bh(io, inode, - data_page ? data_page : page, bh); + ret = io_submit_add_bh(io, inode, bounce_page ?: page, bh); if (ret) { /* * We only get here on ENOMEM. Not much else @@ -517,8 +516,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io, /* Error stopped previous loop? Clean up buffers... */ if (ret) { out: - if (data_page) - fscrypt_restore_control_page(data_page); + fscrypt_free_bounce_page(bounce_page); printk_ratelimited(KERN_ERR "%s: ret = %d\n", __func__, ret); redirty_page_for_writepage(wbc, page); do { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f71b5254a990..4079605d437a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -699,7 +699,7 @@ void __ext4_abort(struct super_block *sb, const char *function, jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); } - if (test_opt(sb, ERRORS_PANIC)) { + if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) { if (EXT4_SB(sb)->s_journal && !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR)) return; @@ -4661,7 +4661,7 @@ failed_mount: #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) - kfree(sbi->s_qf_names[i]); + kfree(get_qf_name(sb, sbi, i)); #endif ext4_blkdev_remove(sbi); brelse(bh); diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 04b4f53f0659..b3cd7655a6ff 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -230,6 +230,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(journal_task), NULL, }; +ATTRIBUTE_GROUPS(ext4); /* Features this copy of ext4 supports */ EXT4_ATTR_FEATURE(lazy_itable_init); @@ -256,6 +257,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(metadata_csum_seed), NULL, }; +ATTRIBUTE_GROUPS(ext4_feat); static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi) { @@ -374,13 +376,13 @@ static const struct sysfs_ops ext4_attr_ops = { }; static struct kobj_type ext4_sb_ktype = { - .default_attrs = ext4_attrs, + .default_groups = ext4_groups, .sysfs_ops = &ext4_attr_ops, .release = ext4_sb_release, }; static struct kobj_type ext4_feat_ktype = { - .default_attrs = ext4_feat_attrs, + .default_groups = ext4_feat_groups, .sysfs_ops = &ext4_attr_ops, .release = (void (*)(struct kobject *))kfree, }; diff --git a/fs/f2fs/Kconfig b/fs/f2fs/Kconfig index e57cc754d543..110a38ca5d53 100644 --- a/fs/f2fs/Kconfig +++ b/fs/f2fs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config F2FS_FS tristate "F2FS filesystem support" depends on BLOCK diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 6a8db4abdf5f..0ca530afc684 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -186,7 +186,7 @@ static void f2fs_write_end_io(struct bio *bio) continue; } - fscrypt_pullback_bio_page(&page, true); + fscrypt_finalize_bounce_page(&page); if (unlikely(bio->bi_status)) { mapping_set_error(page->mapping, -EIO); @@ -363,10 +363,9 @@ static bool __has_merged_page(struct bio *bio, struct inode *inode, bio_for_each_segment_all(bvec, bio, iter_all) { - if (bvec->bv_page->mapping) - target = bvec->bv_page; - else - target = fscrypt_control_page(bvec->bv_page); + target = bvec->bv_page; + if (fscrypt_is_bounce_page(target)) + target = fscrypt_pagecache_page(target); if (inode && inode == target->mapping->host) return true; @@ -1785,8 +1784,9 @@ static int encrypt_one_page(struct f2fs_io_info *fio) f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); retry_encrypt: - fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page, - PAGE_SIZE, 0, fio->page->index, gfp_flags); + fio->encrypted_page = fscrypt_encrypt_pagecache_blocks(fio->page, + PAGE_SIZE, 0, + gfp_flags); if (IS_ERR(fio->encrypted_page)) { /* flush pending IOs and wait for a while in the ENOMEM case */ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { @@ -1958,8 +1958,7 @@ got_it: err = f2fs_inplace_write_data(fio); if (err) { if (f2fs_encrypted_file(inode)) - fscrypt_pullback_bio_page(&fio->encrypted_page, - true); + fscrypt_finalize_bounce_page(&fio->encrypted_page); if (PageWriteback(page)) end_page_writeback(page); } else { diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig index 3ff1772f612e..718163d0c621 100644 --- a/fs/fat/Kconfig +++ b/fs/fat/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config FAT_FS tristate select NLS diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 9d01db37183f..1bda2ab6745b 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/dir.c * diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 495edeafd60a..265983635f2b 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -1,6 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, OGAWA Hirofumi - * Released under GPL v2. */ #include <linux/blkdev.h> diff --git a/fs/fat/file.c b/fs/fat/file.c index b3bed32946b1..4614c0ba5f1c 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/file.c * @@ -193,12 +194,17 @@ static int fat_file_release(struct inode *inode, struct file *filp) int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { struct inode *inode = filp->f_mapping->host; - int res, err; + int err; + + err = __generic_file_fsync(filp, start, end, datasync); + if (err) + return err; - res = generic_file_fsync(filp, start, end, datasync); err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); + if (err) + return err; - return res ? res : err; + return blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); } diff --git a/fs/fat/inode.c b/fs/fat/inode.c index ba93d1373306..05689198f5af 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/inode.c * diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 4fc950bb6433..1e08bd54c5fb 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/misc.c * diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index f2cd365a4e86..9d062886fbc1 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/msdos/namei.c * diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 996c8c25e9c6..0cdd0fb9f742 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/vfat/namei.c * diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index eb192656fba2..af191371c352 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -1,14 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only /* fs/fat/nfs.c - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #include <linux/exportfs.h> diff --git a/fs/file_table.c b/fs/file_table.c index 3f9c1b452c1d..b07b53f24ff5 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/file_table.c * diff --git a/fs/freevxfs/Kconfig b/fs/freevxfs/Kconfig index ce49df1020dd..c05c71d57291 100644 --- a/fs/freevxfs/Kconfig +++ b/fs/freevxfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config VXFS_FS tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)" depends on BLOCK diff --git a/fs/freevxfs/Makefile b/fs/freevxfs/Makefile index 87ad097440d6..e6ee59291521 100644 --- a/fs/freevxfs/Makefile +++ b/fs/freevxfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # VxFS Makefile # diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 36855c1f8daf..9ebfb1b28430 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * @@ -523,8 +524,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) isw->inode = inode; - atomic_inc(&isw_nr_in_flight); - /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page @@ -532,6 +531,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); + + atomic_inc(&isw_nr_in_flight); + goto out_unlock; out_free: @@ -713,6 +715,7 @@ void wbc_detach_inode(struct writeback_control *wbc) void wbc_account_io(struct writeback_control *wbc, struct page *page, size_t bytes) { + struct cgroup_subsys_state *css; int id; /* @@ -724,7 +727,12 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page, if (!wbc->wb) return; - id = mem_cgroup_css_from_page(page)->id; + css = mem_cgroup_css_from_page(page); + /* dead cgroups shouldn't contribute to inode ownership arbitration */ + if (!(css->flags & CSS_ONLINE)) + return; + + id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; @@ -901,7 +909,11 @@ restart: void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { - synchronize_rcu(); + /* + * Use rcu_barrier() to wait for all pending callbacks to + * ensure that all in-flight wb switches are in the workqueue. + */ + rcu_barrier(); flush_workqueue(isw_wq); } } diff --git a/fs/fs_context.c b/fs/fs_context.c index a47ccd5a4a78..103643c68e3f 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Provide a way to create a superblock configuration context within the kernel * that allows a superblock to be set up prior to mounting. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 570d71043acf..0d388faa25d1 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Filesystem parameter parser. * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/export.h> diff --git a/fs/fs_struct.c b/fs/fs_struct.c index be0250788b73..ca639ed967b7 100644 --- a/fs/fs_struct.c +++ b/fs/fs_struct.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 3f6dfa989881..506c5e643f0d 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config FSCACHE tristate "General filesystem local caching manager" diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index cdcb376ef8df..f78793f3d21e 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache cache handling * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL CACHE diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index c550512ce335..0ce39658a620 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* netfs cookie management * * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * See Documentation/filesystems/caching/netfs-api.txt for more information on * the netfs API. */ diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c index aa46e48d8c75..09ed8795ad86 100644 --- a/fs/fscache/fsdef.c +++ b/fs/fscache/fsdef.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Filesystem index definition * * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL CACHE diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c index 9a13e9e15b69..4e5beeaaf454 100644 --- a/fs/fscache/histogram.c +++ b/fs/fscache/histogram.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache latency histogram * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL THREAD diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index d6209022e965..9616af3768e1 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* Internal definitions for FS-Cache * * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ /* diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 30ad89db1efc..59c2494efda3 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* General filesystem local caching manager * * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL CACHE diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c index c2f605483cc5..cce92216fa28 100644 --- a/fs/fscache/netfs.c +++ b/fs/fscache/netfs.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache netfs (client) registration * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL COOKIE diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 43e6e28c164f..72ebfe578f40 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Global fscache object list maintainer and viewer * * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL COOKIE diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 6d9cb1719de5..cfeba839a0f2 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache object state machine handler * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * See Documentation/filesystems/caching/object.txt for a description of the * object state machine and the in-kernel representations. */ diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index 8d265790374c..1a22a55f75a0 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache worker operation management routines * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * See Documentation/filesystems/caching/operations.txt */ diff --git a/fs/fscache/page.c b/fs/fscache/page.c index 111349f67d98..26af6fdf1538 100644 --- a/fs/fscache/page.c +++ b/fs/fscache/page.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Cache page management and data I/O routines * * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL PAGE diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 49a8c90414bc..5523446e2952 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache statistics viewing interface * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL OPERATION diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 00564a1dfd76..a5aa93ece8c5 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* FS-Cache statistics * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #define FSCACHE_DEBUG_LEVEL THREAD diff --git a/fs/fsopen.c b/fs/fsopen.c index 3bb9c0c8cbcc..a8bf83ce8d4e 100644 --- a/fs/fsopen.c +++ b/fs/fsopen.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* Filesystem access-by-fd. * * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/fs_context.h> @@ -92,7 +88,7 @@ static int fscontext_create_fd(struct fs_context *fc, unsigned int o_flags) { int fd; - fd = anon_inode_getfd("fscontext", &fscontext_fops, fc, + fd = anon_inode_getfd("[fscontext]", &fscontext_fops, fc, O_RDWR | o_flags); if (fd < 0) put_fs_context(fc); diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 76f09ce7e5b2..24fc5a5c1b97 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config FUSE_FS tristate "FUSE (Filesystem in Userspace) support" select FS_POSIX_ACL diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index f7b807bc1027..9485019c2a14 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the FUSE filesystem. # diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 4b41df1d4642..bab7a0db81dd 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * CUSE: Character device in Userspace * * Copyright (C) 2008-2009 SUSE Linux Products GmbH * Copyright (C) 2008-2009 Tejun Heo <tj@kernel.org> * - * This file is released under the GPLv2. - * * CUSE enables character devices to be implemented from userland much * like FUSE allows filesystems. On initialization /dev/cuse is * created. By opening the file and replying to the CUSE_INIT request diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 24ea19cfe07e..ea8237513dfa 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1317,16 +1317,6 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, unsigned reqsize; unsigned int hash; - /* - * Require sane minimum read buffer - that has capacity for fixed part - * of any request header + negotated max_write room for data. If the - * requirement is not satisfied return EINVAL to the filesystem server - * to indicate that it is not following FUSE server/client contract. - * Don't dequeue / abort any request. - */ - if (nbytes < max_t(size_t, FUSE_MIN_READ_BUFFER, 4096 + fc->max_write)) - return -EINVAL; - restart: spin_lock(&fiq->waitq.lock); err = -EAGAIN; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 3959f08279e6..5ae2828beb00 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1377,10 +1377,17 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, if (err && !nbytes) break; - if (write) + if (write) { + if (!capable(CAP_FSETID)) { + struct fuse_write_in *inarg; + + inarg = &req->misc.write.in; + inarg->write_flags |= FUSE_WRITE_KILL_PRIV; + } nres = fuse_send_write(req, io, pos, nbytes, owner); - else + } else { nres = fuse_send_read(req, io, pos, nbytes, owner); + } if (!io->async) fuse_release_user_pages(req, io->should_dirty); @@ -3014,6 +3021,16 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return ret; } +static int fuse_writeback_range(struct inode *inode, loff_t start, loff_t end) +{ + int err = filemap_write_and_wait_range(inode->i_mapping, start, end); + + if (!err) + fuse_sync_writes(inode); + + return err; +} + static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, loff_t length) { @@ -3042,12 +3059,10 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, inode_lock(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { loff_t endbyte = offset + length - 1; - err = filemap_write_and_wait_range(inode->i_mapping, - offset, endbyte); + + err = fuse_writeback_range(inode, offset, endbyte); if (err) goto out; - - fuse_sync_writes(inode); } } @@ -3055,7 +3070,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, offset + length > i_size_read(inode)) { err = inode_newsize_ok(inode, offset + length); if (err) - return err; + goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE)) @@ -3097,12 +3112,13 @@ out: return err; } -static ssize_t fuse_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t len, unsigned int flags) +static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags) { struct fuse_file *ff_in = file_in->private_data; struct fuse_file *ff_out = file_out->private_data; + struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); struct fuse_inode *fi_out = get_fuse_inode(inode_out); struct fuse_conn *fc = ff_in->fc; @@ -3126,15 +3142,27 @@ static ssize_t fuse_copy_file_range(struct file *file_in, loff_t pos_in, if (fc->no_copy_file_range) return -EOPNOTSUPP; + if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) + return -EXDEV; + + if (fc->writeback_cache) { + inode_lock(inode_in); + err = fuse_writeback_range(inode_in, pos_in, pos_in + len); + inode_unlock(inode_in); + if (err) + return err; + } + inode_lock(inode_out); + err = file_modified(file_out); + if (err) + goto out; + if (fc->writeback_cache) { - err = filemap_write_and_wait_range(inode_out->i_mapping, - pos_out, pos_out + len); + err = fuse_writeback_range(inode_out, pos_out, pos_out + len); if (err) goto out; - - fuse_sync_writes(inode_out); } if (is_unstable) @@ -3169,10 +3197,26 @@ out: clear_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state); inode_unlock(inode_out); + file_accessed(file_in); return err; } +static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, + size_t len, unsigned int flags) +{ + ssize_t ret; + + ret = __fuse_copy_file_range(src_file, src_off, dst_file, dst_off, + len, flags); + + if (ret == -EOPNOTSUPP || ret == -EXDEV) + ret = generic_copy_file_range(src_file, src_off, dst_file, + dst_off, len, flags); + return ret; +} + static const struct file_operations fuse_file_operations = { .llseek = fuse_file_llseek, .read_iter = fuse_file_read_iter, diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig index 6a1e499543f5..03c966840422 100644 --- a/fs/gfs2/Kconfig +++ b/fs/gfs2/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config GFS2_FS tristate "GFS2 file system support" select FS_POSIX_ACL diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index af5f87a493d9..09e6be8aa036 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/sched.h> diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h index f674fdd22337..61353a1501c5 100644 --- a/fs/gfs2/acl.h +++ b/fs/gfs2/acl.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __ACL_DOT_H__ diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 6210d4429d84..f42048cc5454 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/sched.h> @@ -85,15 +82,11 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, } /** - * gfs2_writepage_common - Common bits of writepage - * @page: The page to be written + * gfs2_writepage - Write page for writeback mappings + * @page: The page * @wbc: The writeback control - * - * Returns: 1 if writepage is ok, otherwise an error code or zero if no error. */ - -static int gfs2_writepage_common(struct page *page, - struct writeback_control *wbc) +static int gfs2_writepage(struct page *page, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; struct gfs2_inode *ip = GFS2_I(inode); @@ -112,7 +105,9 @@ static int gfs2_writepage_common(struct page *page, page->mapping->a_ops->invalidatepage(page, 0, PAGE_SIZE); goto out; } - return 1; + + return nobh_writepage(page, gfs2_get_block_noalloc, wbc); + redirty: redirty_page_for_writepage(wbc, page); out: @@ -120,24 +115,6 @@ out: return 0; } -/** - * gfs2_writepage - Write page for writeback mappings - * @page: The page - * @wbc: The writeback control - * - */ - -static int gfs2_writepage(struct page *page, struct writeback_control *wbc) -{ - int ret; - - ret = gfs2_writepage_common(page, wbc); - if (ret <= 0) - return ret; - - return nobh_writepage(page, gfs2_get_block_noalloc, wbc); -} - /* This is the same as calling block_write_full_page, but it also * writes pages outside of i_size */ @@ -457,8 +434,7 @@ static int gfs2_jdata_writepages(struct address_space *mapping, * * Returns: errno */ - -int stuffed_readpage(struct gfs2_inode *ip, struct page *page) +static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) { struct buffer_head *dibh; u64 dsize = i_size_read(&ip->i_inode); @@ -521,7 +497,7 @@ static int __gfs2_readpage(void *file, struct page *page) error = mpage_readpage(page, gfs2_block_map); } - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) return -EIO; return error; @@ -638,7 +614,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping, gfs2_glock_dq(&gh); out_uninit: gfs2_holder_uninit(&gh); - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) ret = -EIO; return ret; } @@ -689,47 +665,6 @@ out: } /** - * gfs2_stuffed_write_end - Write end for stuffed files - * @inode: The inode - * @dibh: The buffer_head containing the on-disk inode - * @pos: The file position - * @copied: How much was actually copied by the VFS - * @page: The page - * - * This copies the data from the page into the inode block after - * the inode data structure itself. - * - * Returns: copied bytes or errno - */ -int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh, - loff_t pos, unsigned copied, - struct page *page) -{ - struct gfs2_inode *ip = GFS2_I(inode); - u64 to = pos + copied; - void *kaddr; - unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode); - - BUG_ON(pos + copied > gfs2_max_stuffed_size(ip)); - - kaddr = kmap_atomic(page); - memcpy(buf + pos, kaddr + pos, copied); - flush_dcache_page(page); - kunmap_atomic(kaddr); - - WARN_ON(!PageUptodate(page)); - unlock_page(page); - put_page(page); - - if (copied) { - if (inode->i_size < to) - i_size_write(inode, to); - mark_inode_dirty(inode); - } - return copied; -} - -/** * jdata_set_page_dirty - Page dirtying function * @page: The page to dirty * @@ -762,7 +697,7 @@ static sector_t gfs2_bmap(struct address_space *mapping, sector_t lblock) return 0; if (!gfs2_is_stuffed(ip)) - dblock = generic_block_bmap(mapping, lblock, gfs2_block_map); + dblock = iomap_bmap(mapping, lblock, &gfs2_iomap_ops); gfs2_glock_dq_uninit(&i_gh); @@ -891,7 +826,7 @@ cannot_release: return 0; } -static const struct address_space_operations gfs2_writeback_aops = { +static const struct address_space_operations gfs2_aops = { .writepage = gfs2_writepage, .writepages = gfs2_writepages, .readpage = gfs2_readpage, @@ -905,21 +840,6 @@ static const struct address_space_operations gfs2_writeback_aops = { .error_remove_page = generic_error_remove_page, }; -static const struct address_space_operations gfs2_ordered_aops = { - .writepage = gfs2_writepage, - .writepages = gfs2_writepages, - .readpage = gfs2_readpage, - .readpages = gfs2_readpages, - .set_page_dirty = __set_page_dirty_buffers, - .bmap = gfs2_bmap, - .invalidatepage = gfs2_invalidatepage, - .releasepage = gfs2_releasepage, - .direct_IO = noop_direct_IO, - .migratepage = buffer_migrate_page, - .is_partially_uptodate = block_is_partially_uptodate, - .error_remove_page = generic_error_remove_page, -}; - static const struct address_space_operations gfs2_jdata_aops = { .writepage = gfs2_jdata_writepage, .writepages = gfs2_jdata_writepages, @@ -935,15 +855,8 @@ static const struct address_space_operations gfs2_jdata_aops = { void gfs2_set_aops(struct inode *inode) { - struct gfs2_inode *ip = GFS2_I(inode); - struct gfs2_sbd *sdp = GFS2_SB(inode); - - if (gfs2_is_jdata(ip)) + if (gfs2_is_jdata(GFS2_I(inode))) inode->i_mapping->a_ops = &gfs2_jdata_aops; - else if (gfs2_is_writeback(sdp)) - inode->i_mapping->a_ops = &gfs2_writeback_aops; - else if (gfs2_is_ordered(sdp)) - inode->i_mapping->a_ops = &gfs2_ordered_aops; else - BUG(); + inode->i_mapping->a_ops = &gfs2_aops; } diff --git a/fs/gfs2/aops.h b/fs/gfs2/aops.h index fa8e5d0144dd..ff9877a68780 100644 --- a/fs/gfs2/aops.h +++ b/fs/gfs2/aops.h @@ -8,10 +8,6 @@ #include "incore.h" -extern int stuffed_readpage(struct gfs2_inode *ip, struct page *page); -extern int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh, - loff_t pos, unsigned copied, - struct page *page); extern void adjust_fs_space(struct inode *inode); extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, unsigned int from, unsigned int len); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index f42718dd292f..79581b9bdebb 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/spinlock.h> @@ -598,7 +595,6 @@ enum alloc_state { * gfs2_iomap_alloc - Build a metadata tree of the requested height * @inode: The GFS2 inode * @iomap: The iomap structure - * @flags: iomap flags * @mp: The metapath, with proper height information calculated * * In this routine we may have to alloc: @@ -625,7 +621,7 @@ enum alloc_state { */ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap, - unsigned flags, struct metapath *mp) + struct metapath *mp) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); @@ -994,9 +990,12 @@ static void gfs2_write_unlock(struct inode *inode) static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos, unsigned len, struct iomap *iomap) { + unsigned int blockmask = i_blocksize(inode) - 1; struct gfs2_sbd *sdp = GFS2_SB(inode); + unsigned int blocks; - return gfs2_trans_begin(sdp, RES_DINODE + (len >> inode->i_blkbits), 0); + blocks = ((pos & blockmask) + len + blockmask) >> inode->i_blkbits; + return gfs2_trans_begin(sdp, RES_DINODE + blocks, 0); } static void gfs2_iomap_page_done(struct inode *inode, loff_t pos, @@ -1088,7 +1087,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, } if (iomap->type == IOMAP_HOLE) { - ret = gfs2_iomap_alloc(inode, iomap, flags, mp); + ret = gfs2_iomap_alloc(inode, iomap, mp); if (ret) { gfs2_trans_end(sdp); gfs2_inplace_release(ip); @@ -1182,6 +1181,8 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, if (ip->i_qadata && ip->i_qadata->qa_qd_num) gfs2_quota_unlock(ip); + if (iomap->flags & IOMAP_F_SIZE_CHANGED) + mark_inode_dirty(inode); gfs2_write_unlock(inode); out: @@ -1232,7 +1233,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, if (create) { ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, &iomap, &mp); if (!ret && iomap.type == IOMAP_HOLE) - ret = gfs2_iomap_alloc(inode, &iomap, IOMAP_WRITE, &mp); + ret = gfs2_iomap_alloc(inode, &iomap, &mp); release_metapath(&mp); } else { ret = gfs2_iomap_get(inode, pos, length, 0, &iomap, &mp); @@ -1462,7 +1463,7 @@ int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length, ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, iomap, &mp); if (!ret && iomap->type == IOMAP_HOLE) - ret = gfs2_iomap_alloc(inode, iomap, IOMAP_WRITE, &mp); + ret = gfs2_iomap_alloc(inode, iomap, &mp); release_metapath(&mp); return ret; } @@ -1862,9 +1863,8 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) gfs2_assert_withdraw(sdp, bh); if (gfs2_assert_withdraw(sdp, prev_bnr != bh->b_blocknr)) { - printk(KERN_EMERG "GFS2: fsid=%s:inode %llu, " - "block:%llu, i_h:%u, s_h:%u, mp_h:%u\n", - sdp->sd_fsname, + fs_emerg(sdp, "inode %llu, block:%llu, i_h:%u," + "s_h:%u, mp_h:%u\n", (unsigned long long)ip->i_no_addr, prev_bnr, ip->i_height, strip_h, mp_h); } diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h index 19a1fd772c61..b88fd45ab79f 100644 --- a/fs/gfs2/bmap.h +++ b/fs/gfs2/bmap.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __BMAP_DOT_H__ diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 5173b98ca036..a7bb76e9a82b 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/spinlock.h> diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index db9a05244a35..6f35d19eec25 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ /* @@ -753,7 +750,7 @@ static struct gfs2_dirent *gfs2_dirent_split_alloc(struct inode *inode, struct gfs2_dirent *dent; dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, gfs2_dirent_find_offset, name, ptr); - if (!dent || IS_ERR(dent)) + if (IS_ERR_OR_NULL(dent)) return dent; return do_init_dirent(inode, dent, name, bh, (unsigned)(ptr - (void *)dent)); @@ -857,7 +854,7 @@ static struct gfs2_dirent *gfs2_dirent_search(struct inode *inode, return ERR_PTR(error); dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size, scan, name, NULL); got_dent: - if (unlikely(dent == NULL || IS_ERR(dent))) { + if (IS_ERR_OR_NULL(dent)) { brelse(bh); bh = NULL; } diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h index e1b309c24dab..0ac2dc8564df 100644 --- a/fs/gfs2/dir.h +++ b/fs/gfs2/dir.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __DIR_DOT_H__ diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index a332f3cd925e..3f717285ee48 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/spinlock.h> diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 58a768e59712..52fa1ef8400b 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/slab.h> @@ -139,27 +136,36 @@ static struct { {FS_JOURNAL_DATA_FL, GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA}, }; +static inline u32 gfs2_gfsflags_to_fsflags(struct inode *inode, u32 gfsflags) +{ + int i; + u32 fsflags = 0; + + if (S_ISDIR(inode->i_mode)) + gfsflags &= ~GFS2_DIF_JDATA; + else + gfsflags &= ~GFS2_DIF_INHERIT_JDATA; + + for (i = 0; i < ARRAY_SIZE(fsflag_gfs2flag); i++) + if (gfsflags & fsflag_gfs2flag[i].gfsflag) + fsflags |= fsflag_gfs2flag[i].fsflag; + return fsflags; +} + static int gfs2_get_flags(struct file *filp, u32 __user *ptr) { struct inode *inode = file_inode(filp); struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_holder gh; - int i, error; - u32 gfsflags, fsflags = 0; + int error; + u32 fsflags; gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh); error = gfs2_glock_nq(&gh); if (error) goto out_uninit; - gfsflags = ip->i_diskflags; - if (S_ISDIR(inode->i_mode)) - gfsflags &= ~GFS2_DIF_JDATA; - else - gfsflags &= ~GFS2_DIF_INHERIT_JDATA; - for (i = 0; i < ARRAY_SIZE(fsflag_gfs2flag); i++) - if (gfsflags & fsflag_gfs2flag[i].gfsflag) - fsflags |= fsflag_gfs2flag[i].fsflag; + fsflags = gfs2_gfsflags_to_fsflags(inode, ip->i_diskflags); if (put_user(fsflags, ptr)) error = -EFAULT; @@ -203,9 +209,11 @@ void gfs2_set_inode_flags(struct inode *inode) * @filp: file pointer * @reqflags: The flags to set * @mask: Indicates which flags are valid + * @fsflags: The FS_* inode flags passed in * */ -static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) +static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask, + const u32 fsflags) { struct inode *inode = file_inode(filp); struct gfs2_inode *ip = GFS2_I(inode); @@ -213,7 +221,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) struct buffer_head *bh; struct gfs2_holder gh; int error; - u32 new_flags, flags; + u32 new_flags, flags, oldflags; error = mnt_want_write_file(filp); if (error) @@ -223,6 +231,11 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) if (error) goto out_drop_write; + oldflags = gfs2_gfsflags_to_fsflags(inode, ip->i_diskflags); + error = vfs_ioc_setflags_prepare(inode, oldflags, fsflags); + if (error) + goto out; + error = -EACCES; if (!inode_owner_or_capable(inode)) goto out; @@ -311,7 +324,7 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr) mask &= ~(GFS2_DIF_TOPDIR | GFS2_DIF_INHERIT_JDATA); } - return do_gfs2_set_flags(filp, gfsflags, mask); + return do_gfs2_set_flags(filp, gfsflags, mask, fsflags); } static int gfs2_getlabel(struct file *filp, char __user *label) @@ -366,31 +379,30 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size) } /** - * gfs2_allocate_page_backing - Use bmap to allocate blocks + * gfs2_allocate_page_backing - Allocate blocks for a write fault * @page: The (locked) page to allocate backing for * - * We try to allocate all the blocks required for the page in - * one go. This might fail for various reasons, so we keep - * trying until all the blocks to back this page are allocated. - * If some of the blocks are already allocated, thats ok too. + * We try to allocate all the blocks required for the page in one go. This + * might fail for various reasons, so we keep trying until all the blocks to + * back this page are allocated. If some of the blocks are already allocated, + * that is ok too. */ - static int gfs2_allocate_page_backing(struct page *page) { - struct inode *inode = page->mapping->host; - struct buffer_head bh; - unsigned long size = PAGE_SIZE; - u64 lblock = page->index << (PAGE_SHIFT - inode->i_blkbits); + u64 pos = page_offset(page); + u64 size = PAGE_SIZE; do { - bh.b_state = 0; - bh.b_size = size; - gfs2_block_map(inode, lblock, &bh, 1); - if (!buffer_mapped(&bh)) + struct iomap iomap = { }; + + if (gfs2_iomap_get_alloc(page->mapping->host, pos, 1, &iomap)) return -EIO; - size -= bh.b_size; - lblock += (bh.b_size >> inode->i_blkbits); - } while(size > 0); + + iomap.length = min(iomap.length, size); + size -= iomap.length; + pos += iomap.length; + } while (size > 0); + return 0; } @@ -411,7 +423,7 @@ static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf) struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_alloc_parms ap = { .aflags = 0, }; unsigned long last_index; - u64 pos = page->index << PAGE_SHIFT; + u64 pos = page_offset(page); unsigned int data_blocks, ind_blocks, rblocks; struct gfs2_holder gh; loff_t size; @@ -1169,7 +1181,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl) cmd = F_SETLK; fl->fl_type = F_UNLCK; } - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) { + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) { if (fl->fl_type == F_UNLCK) locks_lock_file_wait(file, fl); return -EIO; diff --git a/fs/gfs2/gfs2.h b/fs/gfs2/gfs2.h index ef606e3a5cf4..ed78e5f20f41 100644 --- a/fs/gfs2/gfs2.h +++ b/fs/gfs2/gfs2.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __GFS2_DOT_H__ diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 15c605cfcfc8..e23fb8b7b020 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -140,7 +137,7 @@ void gfs2_glock_free(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - BUG_ON(test_bit(GLF_REVOKES, &gl->gl_flags)); + BUG_ON(atomic_read(&gl->gl_revokes)); rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms); smp_mb(); wake_up_glock(gl); @@ -547,7 +544,7 @@ __acquires(&gl->gl_lockref.lock) unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0); int ret; - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) && + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) && target != LM_ST_UNLOCKED) return; lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP | @@ -584,7 +581,7 @@ __acquires(&gl->gl_lockref.lock) } else if (ret) { fs_err(sdp, "lm_lock ret %d\n", ret); - GLOCK_BUG_ON(gl, !test_bit(SDF_SHUTDOWN, + GLOCK_BUG_ON(gl, !test_bit(SDF_WITHDRAWN, &sdp->sd_flags)); } } else { /* lock_nolock */ @@ -684,7 +681,7 @@ static void delete_work_func(struct work_struct *work) goto out; inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED); - if (inode && !IS_ERR(inode)) { + if (!IS_ERR_OR_NULL(inode)) { d_prune_aliases(inode); iput(inode); } @@ -1078,7 +1075,7 @@ trap_recursive: fs_err(sdp, "pid: %d\n", pid_nr(gh->gh_owner_pid)); fs_err(sdp, "lock type: %d req lock state : %d\n", gh->gh_gl->gl_name.ln_type, gh->gh_state); - gfs2_dump_glock(NULL, gl); + gfs2_dump_glock(NULL, gl, true); BUG(); } @@ -1097,7 +1094,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh) struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; int error = 0; - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) return -EIO; if (test_bit(GLF_LRU, &gl->gl_flags)) @@ -1613,16 +1610,16 @@ void gfs2_glock_thaw(struct gfs2_sbd *sdp) glock_hash_walk(thaw_glock, sdp); } -static void dump_glock(struct seq_file *seq, struct gfs2_glock *gl) +static void dump_glock(struct seq_file *seq, struct gfs2_glock *gl, bool fsid) { spin_lock(&gl->gl_lockref.lock); - gfs2_dump_glock(seq, gl); + gfs2_dump_glock(seq, gl, fsid); spin_unlock(&gl->gl_lockref.lock); } static void dump_glock_func(struct gfs2_glock *gl) { - dump_glock(NULL, gl); + dump_glock(NULL, gl, true); } /** @@ -1707,10 +1704,12 @@ static const char *hflags2str(char *buf, u16 flags, unsigned long iflags) * dump_holder - print information about a glock holder * @seq: the seq_file struct * @gh: the glock holder + * @fs_id_buf: pointer to file system id (if requested) * */ -static void dump_holder(struct seq_file *seq, const struct gfs2_holder *gh) +static void dump_holder(struct seq_file *seq, const struct gfs2_holder *gh, + const char *fs_id_buf) { struct task_struct *gh_owner = NULL; char flags_buf[32]; @@ -1718,8 +1717,8 @@ static void dump_holder(struct seq_file *seq, const struct gfs2_holder *gh) rcu_read_lock(); if (gh->gh_owner_pid) gh_owner = pid_task(gh->gh_owner_pid, PIDTYPE_PID); - gfs2_print_dbg(seq, " H: s:%s f:%s e:%d p:%ld [%s] %pS\n", - state2str(gh->gh_state), + gfs2_print_dbg(seq, "%s H: s:%s f:%s e:%d p:%ld [%s] %pS\n", + fs_id_buf, state2str(gh->gh_state), hflags2str(flags_buf, gh->gh_flags, gh->gh_iflags), gh->gh_error, gh->gh_owner_pid ? (long)pid_nr(gh->gh_owner_pid) : -1, @@ -1769,6 +1768,7 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl) * gfs2_dump_glock - print information about a glock * @seq: The seq_file struct * @gl: the glock + * @fsid: If true, also dump the file system id * * The file format is as follows: * One line per object, capital letters are used to indicate objects @@ -1782,33 +1782,38 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl) * */ -void gfs2_dump_glock(struct seq_file *seq, struct gfs2_glock *gl) +void gfs2_dump_glock(struct seq_file *seq, struct gfs2_glock *gl, bool fsid) { const struct gfs2_glock_operations *glops = gl->gl_ops; unsigned long long dtime; const struct gfs2_holder *gh; char gflags_buf[32]; + char fs_id_buf[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + memset(fs_id_buf, 0, sizeof(fs_id_buf)); + if (fsid && sdp) /* safety precaution */ + sprintf(fs_id_buf, "fsid=%s: ", sdp->sd_fsname); dtime = jiffies - gl->gl_demote_time; dtime *= 1000000/HZ; /* demote time in uSec */ if (!test_bit(GLF_DEMOTE, &gl->gl_flags)) dtime = 0; - gfs2_print_dbg(seq, "G: s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d v:%d r:%d m:%ld\n", - state2str(gl->gl_state), + gfs2_print_dbg(seq, "%sG: s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d " + "v:%d r:%d m:%ld\n", fs_id_buf, state2str(gl->gl_state), gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number, gflags2str(gflags_buf, gl), state2str(gl->gl_target), state2str(gl->gl_demote_state), dtime, atomic_read(&gl->gl_ail_count), - test_bit(GLF_REVOKES, &gl->gl_flags) ? 1 : 0, + atomic_read(&gl->gl_revokes), (int)gl->gl_lockref.count, gl->gl_hold_time); list_for_each_entry(gh, &gl->gl_holders, gh_list) - dump_holder(seq, gh); + dump_holder(seq, gh, fs_id_buf); if (gl->gl_state != LM_ST_UNLOCKED && glops->go_dump) - glops->go_dump(seq, gl); + glops->go_dump(seq, gl, fs_id_buf); } static int gfs2_glstats_seq_show(struct seq_file *seq, void *iter_ptr) @@ -2009,7 +2014,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) { - dump_glock(seq, iter_ptr); + dump_glock(seq, iter_ptr, false); return 0; } diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h index 936b3295839c..e4e0bed5257c 100644 --- a/fs/gfs2/glock.h +++ b/fs/gfs2/glock.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __GLOCK_DOT_H__ @@ -202,8 +199,11 @@ extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, struct gfs2_holder *gh); extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs); -extern void gfs2_dump_glock(struct seq_file *seq, struct gfs2_glock *gl); -#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { gfs2_dump_glock(NULL, gl); BUG(); } } while(0) +extern void gfs2_dump_glock(struct seq_file *seq, struct gfs2_glock *gl, + bool fsid); +#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { \ + gfs2_dump_glock(NULL, gl, true); \ + BUG(); } } while(0) extern __printf(2, 3) void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...); @@ -269,7 +269,7 @@ static inline void glock_set_object(struct gfs2_glock *gl, void *object) { spin_lock(&gl->gl_lockref.lock); if (gfs2_assert_warn(gl->gl_name.ln_sbd, gl->gl_object == NULL)) - gfs2_dump_glock(NULL, gl); + gfs2_dump_glock(NULL, gl, true); gl->gl_object = object; spin_unlock(&gl->gl_lockref.lock); } @@ -281,7 +281,7 @@ static inline void glock_set_object(struct gfs2_glock *gl, void *object) * * I'd love to similarly add this: * else if (gfs2_assert_warn(gl->gl_sbd, gl->gl_object == object)) - * gfs2_dump_glock(NULL, gl); + * gfs2_dump_glock(NULL, gl, true); * Unfortunately, that's not possible because as soon as gfs2_delete_inode * frees the block in the rgrp, another process can reassign it for an I_NEW * inode in gfs2_create_inode because that calls new_inode, not gfs2_iget. diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 24ada3ccc525..ff213690e364 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/spinlock.h> @@ -464,10 +461,12 @@ static int inode_go_lock(struct gfs2_holder *gh) * inode_go_dump - print information about an inode * @seq: The iterator * @ip: the inode + * @fs_id_buf: file system id (may be empty) * */ -static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl) +static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl, + const char *fs_id_buf) { struct gfs2_inode *ip = gl->gl_object; struct inode *inode = &ip->i_inode; @@ -480,7 +479,8 @@ static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl) nrpages = inode->i_data.nrpages; xa_unlock_irq(&inode->i_data.i_pages); - gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu p:%lu\n", + gfs2_print_dbg(seq, "%s I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu " + "p:%lu\n", fs_id_buf, (unsigned long long)ip->i_no_formal_ino, (unsigned long long)ip->i_no_addr, IF2DT(ip->i_inode.i_mode), ip->i_flags, @@ -506,7 +506,8 @@ static void freeze_go_sync(struct gfs2_glock *gl) atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { - printk(KERN_INFO "GFS2: couldn't freeze filesystem: %d\n", error); + fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", + error); gfs2_assert_withdraw(sdp, 0); } queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work); @@ -539,7 +540,7 @@ static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh) gfs2_consist(sdp); /* Initialize some head of the log stuff */ - if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) { + if (!test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) { sdp->sd_log_sequence = head.lh_sequence + 1; gfs2_log_pointers_init(sdp, head.lh_blkno); } diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h index 8ed1857c1a8d..2dd192e85618 100644 --- a/fs/gfs2/glops.h +++ b/fs/gfs2/glops.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __GLOPS_DOT_H__ diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index b15755068593..7a993d7c022e 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __INCORE_DOT_H__ @@ -243,7 +240,8 @@ struct gfs2_glock_operations { int (*go_demote_ok) (const struct gfs2_glock *gl); int (*go_lock) (struct gfs2_holder *gh); void (*go_unlock) (struct gfs2_holder *gh); - void (*go_dump)(struct seq_file *seq, struct gfs2_glock *gl); + void (*go_dump)(struct seq_file *seq, struct gfs2_glock *gl, + const char *fs_id_buf); void (*go_callback)(struct gfs2_glock *gl, bool remote); const int go_type; const unsigned long go_flags; @@ -345,7 +343,6 @@ enum { GLF_OBJECT = 14, /* Used only for tracing */ GLF_BLOCKING = 15, GLF_INODE_CREATING = 16, /* Inode creation occurring */ - GLF_REVOKES = 17, /* Glock has revokes in queue */ }; struct gfs2_glock { @@ -375,6 +372,7 @@ struct gfs2_glock { struct list_head gl_lru; struct list_head gl_ail_list; atomic_t gl_ail_count; + atomic_t gl_revokes; struct delayed_work gl_work; union { /* For inode and iopen glocks only */ @@ -507,7 +505,6 @@ struct gfs2_trans { unsigned int tr_num_buf_rm; unsigned int tr_num_databuf_rm; unsigned int tr_num_revoke; - unsigned int tr_num_revoke_rm; struct list_head tr_list; struct list_head tr_databuf; @@ -612,7 +609,7 @@ struct gfs2_tune { enum { SDF_JOURNAL_CHECKED = 0, SDF_JOURNAL_LIVE = 1, - SDF_SHUTDOWN = 2, + SDF_WITHDRAWN = 2, SDF_NOBARRIERS = 3, SDF_NORECOVERY = 4, SDF_DEMOTE = 5, diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 998051c4aea7..2e2a8a2fb51d 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/slab.h> @@ -796,7 +793,7 @@ fail_free_acls: fail_gunlock: gfs2_dir_no_add(&da); gfs2_glock_dq_uninit(ghs); - if (inode && !IS_ERR(inode)) { + if (!IS_ERR_OR_NULL(inode)) { clear_nlink(inode); if (!free_vfs_inode) mark_inode_dirty(inode); diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 18d4af7417fa..580adbf0b5e1 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __INODE_DOT_H__ diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 31df26ed7854..4361804646d8 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright 2004-2011 Red Hat, Inc. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -31,9 +28,10 @@ * @delta is the difference between the current rtt sample and the * running average srtt. We add 1/8 of that to the srtt in order to * update the current srtt estimate. The variance estimate is a bit - * more complicated. We subtract the abs value of the @delta from - * the current variance estimate and add 1/4 of that to the running - * total. + * more complicated. We subtract the current variance estimate from + * the abs value of the @delta and add 1/4 of that to the running + * total. That's equivalent to 3/4 of the current variance + * estimate plus 1/4 of the abs of @delta. * * Note that the index points at the array entry containing the smoothed * mean value, and the variance is always in the following entry @@ -49,7 +47,7 @@ static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index, s64 delta = sample - s->stats[index]; s->stats[index] += (delta >> 3); index++; - s->stats[index] += ((abs(delta) - s->stats[index]) >> 2); + s->stats[index] += (s64)(abs(delta) - s->stats[index]) >> 2; } /** diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index a2e1df488df0..58e237fba565 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/sched.h> @@ -606,10 +603,8 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) gfs2_remove_from_ail(bd); /* drops ref on bh */ bd->bd_bh = NULL; sdp->sd_log_num_revoke++; - if (!test_bit(GLF_REVOKES, &gl->gl_flags)) { - set_bit(GLF_REVOKES, &gl->gl_flags); + if (atomic_inc_return(&gl->gl_revokes) == 1) gfs2_glock_hold(gl); - } set_bit(GLF_LFLUSH, &gl->gl_flags); list_add(&bd->bd_list, &sdp->sd_log_revokes); } @@ -887,7 +882,6 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new) old->tr_num_buf_rm += new->tr_num_buf_rm; old->tr_num_databuf_rm += new->tr_num_databuf_rm; old->tr_num_revoke += new->tr_num_revoke; - old->tr_num_revoke_rm += new->tr_num_revoke_rm; list_splice_tail_init(&new->tr_databuf, &old->tr_databuf); list_splice_tail_init(&new->tr_buf, &old->tr_buf); @@ -909,7 +903,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) set_bit(TR_ATTACHED, &tr->tr_flags); } - sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm; + sdp->sd_log_commited_revoke += tr->tr_num_revoke; reserved = calc_reserved(sdp); maxres = sdp->sd_log_blks_reserved + tr->tr_reserved; gfs2_assert_withdraw(sdp, maxres >= reserved); diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index 7a34a3234266..2315fca47a2b 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __LOG_DOT_H__ diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 33ab662c9aac..5b17979af539 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/sched.h> @@ -762,9 +759,27 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start, if (gfs2_meta_check(sdp, bh_ip)) error = -EIO; - else + else { + struct gfs2_meta_header *mh = + (struct gfs2_meta_header *)bh_ip->b_data; + + if (mh->mh_type == cpu_to_be32(GFS2_METATYPE_RG)) { + struct gfs2_rgrpd *rgd; + + rgd = gfs2_blk2rgrpd(sdp, blkno, false); + if (rgd && rgd->rd_addr == blkno && + rgd->rd_bits && rgd->rd_bits->bi_bh) { + fs_info(sdp, "Replaying 0x%llx but we " + "already have a bh!\n", + (unsigned long long)blkno); + fs_info(sdp, "busy:%d, pinned:%d\n", + buffer_busy(rgd->rd_bits->bi_bh) ? 1 : 0, + buffer_pinned(rgd->rd_bits->bi_bh)); + gfs2_dump_glock(NULL, rgd->rd_gl, true); + } + } mark_buffer_dirty(bh_ip); - + } brelse(bh_log); brelse(bh_ip); @@ -860,34 +875,19 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { struct list_head *head = &sdp->sd_log_revokes; - struct gfs2_bufdata *bd, *tmp; - - /* - * Glocks can be referenced repeatedly on the revoke list, but the list - * only holds one reference. All glocks on the list will have the - * GLF_REVOKES flag set initially. - */ - - list_for_each_entry_safe(bd, tmp, head, bd_list) { - struct gfs2_glock *gl = bd->bd_gl; + struct gfs2_bufdata *bd; + struct gfs2_glock *gl; - if (test_bit(GLF_REVOKES, &gl->gl_flags)) { - /* Keep each glock on the list exactly once. */ - clear_bit(GLF_REVOKES, &gl->gl_flags); - continue; + while (!list_empty(head)) { + bd = list_entry(head->next, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); + gl = bd->bd_gl; + if (atomic_dec_return(&gl->gl_revokes) == 0) { + clear_bit(GLF_LFLUSH, &gl->gl_flags); + gfs2_glock_queue_put(gl); } - list_del(&bd->bd_list); - kmem_cache_free(gfs2_bufdata_cachep, bd); - } - list_for_each_entry_safe(bd, tmp, head, bd_list) { - struct gfs2_glock *gl = bd->bd_gl; - - list_del(&bd->bd_list); kmem_cache_free(gfs2_bufdata_cachep, bd); - clear_bit(GLF_LFLUSH, &gl->gl_flags); - gfs2_glock_queue_put(gl); } - /* the list is empty now */ } static void revoke_lo_before_scan(struct gfs2_jdesc *jd, diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index f195ffb435ac..9c059957a733 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __LOPS_DOT_H__ diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index c700738de1f7..a1a295b739fb 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -59,6 +56,7 @@ static void gfs2_init_glock_once(void *foo) INIT_LIST_HEAD(&gl->gl_lru); INIT_LIST_HEAD(&gl->gl_ail_list); atomic_set(&gl->gl_ail_count, 0); + atomic_set(&gl->gl_revokes, 0); } static void gfs2_init_gl_aspace_once(void *foo) diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index ff86e1d4f8ff..662ef36c1874 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/sched.h> @@ -254,7 +251,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, struct buffer_head *bh, *bhs[2]; int num = 0; - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) { + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) { *bhp = NULL; return -EIO; } @@ -312,7 +309,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh) { - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) return -EIO; wait_on_buffer(bh); @@ -323,7 +320,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh) gfs2_io_error_bh_wd(sdp, bh); return -EIO; } - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) return -EIO; return 0; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index ffdf6aa3509d..eafb74e861c6 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __DIO_DOT_H__ diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 46f6615eaf12..4a8e5a7310f0 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -64,6 +61,13 @@ static void gfs2_tune_init(struct gfs2_tune *gt) gt->gt_complain_secs = 10; } +void free_sbd(struct gfs2_sbd *sdp) +{ + if (sdp->sd_lkstats) + free_percpu(sdp->sd_lkstats); + kfree(sdp); +} + static struct gfs2_sbd *init_sbd(struct super_block *sb) { struct gfs2_sbd *sdp; @@ -75,10 +79,8 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) sdp->sd_vfs = sb; sdp->sd_lkstats = alloc_percpu(struct gfs2_pcpu_lkstats); - if (!sdp->sd_lkstats) { - kfree(sdp); - return NULL; - } + if (!sdp->sd_lkstats) + goto fail; sb->s_fs_info = sdp; set_bit(SDF_NOJOURNALID, &sdp->sd_flags); @@ -137,8 +139,11 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) mutex_init(&sdp->sd_freeze_mutex); return sdp; -} +fail: + free_sbd(sdp); + return NULL; +} /** * gfs2_check_sb - Check superblock @@ -571,7 +576,7 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh) INIT_WORK(&jd->jd_work, gfs2_recover_func); jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1); - if (!jd->jd_inode || IS_ERR(jd->jd_inode)) { + if (IS_ERR_OR_NULL(jd->jd_inode)) { if (!jd->jd_inode) error = -ENOENT; else @@ -999,7 +1004,7 @@ hostdata_error: void gfs2_lm_unmount(struct gfs2_sbd *sdp) { const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops; - if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) && + if (likely(!test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) && lm->lm_unmount) lm->lm_unmount(sdp); } @@ -1089,8 +1094,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent if (error) { /* In this case, we haven't initialized sysfs, so we have to manually free the sdp. */ - free_percpu(sdp->sd_lkstats); - kfree(sdp); + free_sbd(sdp); sb->s_fs_info = NULL; return error; } @@ -1193,7 +1197,6 @@ fail_lm: gfs2_lm_unmount(sdp); fail_debug: gfs2_delete_debugfs_file(sdp); - free_percpu(sdp->sd_lkstats); /* gfs2_sys_fs_del must be the last thing we do, since it causes * sysfs to call function gfs2_sbd_release, which frees sdp. */ gfs2_sys_fs_del(sdp); @@ -1373,7 +1376,6 @@ static void gfs2_kill_sb(struct super_block *sb) sdp->sd_root_dir = NULL; sdp->sd_master_dir = NULL; shrink_dcache_sb(sb); - free_percpu(sdp->sd_lkstats); kill_block_super(sb); } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 2ae5a109eea7..69c4b77f127b 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ /* @@ -1478,7 +1475,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error) { if (error == 0 || error == -EROFS) return; - if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) { + if (!test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) { fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error); sdp->sd_log_error = error; wake_up(&sdp->sd_logd_waitq); diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 836f29480be6..765627d9a91e 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __QUOTA_DOT_H__ diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 389b3ef77e20..c529f8749a89 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/module.h> @@ -391,7 +388,8 @@ void gfs2_recover_func(struct work_struct *work) } t_tlck = ktime_get(); - fs_info(sdp, "jid=%u: Replaying journal...\n", jd->jd_jid); + fs_info(sdp, "jid=%u: Replaying journal...0x%x to 0x%x\n", + jd->jd_jid, head.lh_tail, head.lh_blkno); for (pass = 0; pass < 2; pass++) { lops_before_scan(jd, &head, pass); diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 1831a1974c8c..0d30f8e804f4 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __RECOVERY_DOT_H__ diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 15d6e32de55f..49ac0a5e74ea 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -613,11 +610,12 @@ int gfs2_rsqa_alloc(struct gfs2_inode *ip) return gfs2_qa_alloc(ip); } -static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) +static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs, + const char *fs_id_buf) { struct gfs2_inode *ip = container_of(rs, struct gfs2_inode, i_res); - gfs2_print_dbg(seq, " B: n:%llu s:%llu b:%u f:%u\n", + gfs2_print_dbg(seq, "%s B: n:%llu s:%llu b:%u f:%u\n", fs_id_buf, (unsigned long long)ip->i_no_addr, (unsigned long long)gfs2_rbm_to_block(&rs->rs_rbm), rs->rs_rbm.offset, rs->rs_free); @@ -1114,32 +1112,33 @@ static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd) { struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl; struct gfs2_rgrp *str = (struct gfs2_rgrp *)rgd->rd_bits[0].bi_bh->b_data; + struct gfs2_sbd *sdp = rgd->rd_sbd; int valid = 1; if (rgl->rl_flags != str->rg_flags) { - printk(KERN_WARNING "GFS2: rgd: %llu lvb flag mismatch %u/%u", - (unsigned long long)rgd->rd_addr, + fs_warn(sdp, "GFS2: rgd: %llu lvb flag mismatch %u/%u", + (unsigned long long)rgd->rd_addr, be32_to_cpu(rgl->rl_flags), be32_to_cpu(str->rg_flags)); valid = 0; } if (rgl->rl_free != str->rg_free) { - printk(KERN_WARNING "GFS2: rgd: %llu lvb free mismatch %u/%u", - (unsigned long long)rgd->rd_addr, - be32_to_cpu(rgl->rl_free), be32_to_cpu(str->rg_free)); + fs_warn(sdp, "GFS2: rgd: %llu lvb free mismatch %u/%u", + (unsigned long long)rgd->rd_addr, + be32_to_cpu(rgl->rl_free), be32_to_cpu(str->rg_free)); valid = 0; } if (rgl->rl_dinodes != str->rg_dinodes) { - printk(KERN_WARNING "GFS2: rgd: %llu lvb dinode mismatch %u/%u", - (unsigned long long)rgd->rd_addr, - be32_to_cpu(rgl->rl_dinodes), - be32_to_cpu(str->rg_dinodes)); + fs_warn(sdp, "GFS2: rgd: %llu lvb dinode mismatch %u/%u", + (unsigned long long)rgd->rd_addr, + be32_to_cpu(rgl->rl_dinodes), + be32_to_cpu(str->rg_dinodes)); valid = 0; } if (rgl->rl_igeneration != str->rg_igeneration) { - printk(KERN_WARNING "GFS2: rgd: %llu lvb igen mismatch " - "%llu/%llu", (unsigned long long)rgd->rd_addr, - (unsigned long long)be64_to_cpu(rgl->rl_igeneration), - (unsigned long long)be64_to_cpu(str->rg_igeneration)); + fs_warn(sdp, "GFS2: rgd: %llu lvb igen mismatch %llu/%llu", + (unsigned long long)rgd->rd_addr, + (unsigned long long)be64_to_cpu(rgl->rl_igeneration), + (unsigned long long)be64_to_cpu(str->rg_igeneration)); valid = 0; } return valid; @@ -2249,10 +2248,12 @@ static void rgblk_free(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd, * gfs2_rgrp_dump - print out an rgrp * @seq: The iterator * @gl: The glock in question + * @fs_id_buf: pointer to file system id (if requested) * */ -void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl) +void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl, + const char *fs_id_buf) { struct gfs2_rgrpd *rgd = gl->gl_object; struct gfs2_blkreserv *trs; @@ -2260,14 +2261,15 @@ void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl) if (rgd == NULL) return; - gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u r:%u e:%u\n", + gfs2_print_dbg(seq, "%s R: n:%llu f:%02x b:%u/%u i:%u r:%u e:%u\n", + fs_id_buf, (unsigned long long)rgd->rd_addr, rgd->rd_flags, rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes, rgd->rd_reserved, rgd->rd_extfail_pt); if (rgd->rd_sbd->sd_args.ar_rgrplvb) { struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl; - gfs2_print_dbg(seq, " L: f:%02x b:%u i:%u\n", + gfs2_print_dbg(seq, "%s L: f:%02x b:%u i:%u\n", fs_id_buf, be32_to_cpu(rgl->rl_flags), be32_to_cpu(rgl->rl_free), be32_to_cpu(rgl->rl_dinodes)); @@ -2275,7 +2277,7 @@ void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl) spin_lock(&rgd->rd_rsspin); for (n = rb_first(&rgd->rd_rstree); n; n = rb_next(&trs->rs_node)) { trs = rb_entry(n, struct gfs2_blkreserv, rs_node); - dump_rs(seq, trs); + dump_rs(seq, trs, fs_id_buf); } spin_unlock(&rgd->rd_rsspin); } @@ -2283,10 +2285,13 @@ void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl) static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd) { struct gfs2_sbd *sdp = rgd->rd_sbd; + char fs_id_buf[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; + fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n", (unsigned long long)rgd->rd_addr); fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n"); - gfs2_rgrp_dump(NULL, rgd->rd_gl); + sprintf(fs_id_buf, "fsid=%s: ", sdp->sd_fsname); + gfs2_rgrp_dump(NULL, rgd->rd_gl, fs_id_buf); rgd->rd_flags |= GFS2_RDF_ERROR; } diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h index 499079a9dbbe..c14a673ae36f 100644 --- a/fs/gfs2/rgrp.h +++ b/fs/gfs2/rgrp.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __RGRP_DOT_H__ @@ -72,7 +69,8 @@ extern void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist); extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist); extern u64 gfs2_ri_total(struct gfs2_sbd *sdp); -extern void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl); +extern void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl, + const char *fs_id_buf); extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset, struct buffer_head *bh, const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index fbf6b1fd330b..0acc5834f653 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -397,6 +394,7 @@ static int init_threads(struct gfs2_sbd *sdp) fail: kthread_stop(sdp->sd_logd_process); + sdp->sd_logd_process = NULL; return error; } @@ -454,8 +452,12 @@ fail: freeze_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq_uninit(&freeze_gh); fail_threads: - kthread_stop(sdp->sd_quotad_process); - kthread_stop(sdp->sd_logd_process); + if (sdp->sd_quotad_process) + kthread_stop(sdp->sd_quotad_process); + sdp->sd_quotad_process = NULL; + if (sdp->sd_logd_process) + kthread_stop(sdp->sd_logd_process); + sdp->sd_logd_process = NULL; return error; } @@ -803,7 +805,7 @@ static void gfs2_dirty_inode(struct inode *inode, int flags) if (!(flags & I_DIRTY_INODE)) return; - if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) + if (unlikely(test_bit(SDF_WITHDRAWN, &sdp->sd_flags))) return; if (!gfs2_glock_is_locked_by_me(ip->i_gl)) { ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh); @@ -852,12 +854,16 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp) error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE, &freeze_gh); - if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + if (error && !test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) return error; flush_workqueue(gfs2_delete_workqueue); - kthread_stop(sdp->sd_quotad_process); - kthread_stop(sdp->sd_logd_process); + if (sdp->sd_quotad_process) + kthread_stop(sdp->sd_quotad_process); + sdp->sd_quotad_process = NULL; + if (sdp->sd_logd_process) + kthread_stop(sdp->sd_logd_process); + sdp->sd_logd_process = NULL; gfs2_quota_sync(sdp->sd_vfs, 0); gfs2_statfs_sync(sdp->sd_vfs, 0); @@ -972,14 +978,14 @@ void gfs2_freeze_func(struct work_struct *work) error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, 0, &freeze_gh); if (error) { - printk(KERN_INFO "GFS2: couldn't get freeze lock : %d\n", error); + fs_info(sdp, "GFS2: couldn't get freeze lock : %d\n", error); gfs2_assert_withdraw(sdp, 0); } else { atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); error = thaw_super(sb); if (error) { - printk(KERN_INFO "GFS2: couldn't thaw filesystem: %d\n", - error); + fs_info(sdp, "GFS2: couldn't thaw filesystem: %d\n", + error); gfs2_assert_withdraw(sdp, 0); } if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) @@ -1007,7 +1013,7 @@ static int gfs2_freeze(struct super_block *sb) if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) goto out; - if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) { + if (test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) { error = -EINVAL; goto out; } @@ -1017,20 +1023,14 @@ static int gfs2_freeze(struct super_block *sb) if (!error) break; - switch (error) { - case -EBUSY: + if (error == -EBUSY) fs_err(sdp, "waiting for recovery before freeze\n"); - break; - - default: + else fs_err(sdp, "error freezing FS: %d\n", error); - break; - } fs_err(sdp, "retrying...\n"); msleep(1000); } - error = 0; set_bit(SDF_FS_FROZEN, &sdp->sd_flags); out: mutex_unlock(&sdp->sd_freeze_mutex); @@ -1276,8 +1276,6 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) error = gfs2_make_fs_ro(sdp); else error = gfs2_make_fs_rw(sdp); - if (error) - return error; } sdp->sd_args = args; @@ -1303,7 +1301,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data) spin_unlock(>->gt_spin); gfs2_online_uevent(sdp); - return 0; + return error; } /** @@ -1477,7 +1475,7 @@ static void gfs2_final_release_pages(struct gfs2_inode *ip) truncate_inode_pages(gfs2_glock2aspace(ip->i_gl), 0); truncate_inode_pages(&inode->i_data, 0); - if (!test_bit(GLF_REVOKES, &gl->gl_flags)) { + if (atomic_read(&gl->gl_revokes) == 0) { clear_bit(GLF_LFLUSH, &gl->gl_flags); clear_bit(GLF_DIRTY, &gl->gl_flags); } diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index 73c97dccae21..9d49eaadb9d9 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __SUPER_DOT_H__ @@ -47,6 +44,8 @@ extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh, extern int gfs2_statfs_sync(struct super_block *sb, int type); extern void gfs2_freeze_func(struct work_struct *work); +extern void free_sbd(struct gfs2_sbd *sdp); + extern struct file_system_type gfs2_fs_type; extern struct file_system_type gfs2meta_fs_type; extern const struct export_operations gfs2_export_ops; diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 08e4996adc23..dd15b8e4af2c 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -121,7 +118,7 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len) static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf) { - unsigned int b = test_bit(SDF_SHUTDOWN, &sdp->sd_flags); + unsigned int b = test_bit(SDF_WITHDRAWN, &sdp->sd_flags); return snprintf(buf, PAGE_SIZE, "%u\n", b); } @@ -299,17 +296,18 @@ static struct attribute *gfs2_attrs[] = { &gfs2_attr_demote_rq.attr, NULL, }; +ATTRIBUTE_GROUPS(gfs2); static void gfs2_sbd_release(struct kobject *kobj) { struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); - kfree(sdp); + free_sbd(sdp); } static struct kobj_type gfs2_ktype = { .release = gfs2_sbd_release, - .default_attrs = gfs2_attrs, + .default_groups = gfs2_groups, .sysfs_ops = &gfs2_attr_ops, }; @@ -682,7 +680,6 @@ fail_lock_module: fail_tune: sysfs_remove_group(&sdp->sd_kobj, &tune_group); fail_reg: - free_percpu(sdp->sd_lkstats); fs_err(sdp, "error %d adding sysfs files\n", error); kobject_put(&sdp->sd_kobj); sb->s_fs_info = NULL; diff --git a/fs/gfs2/sys.h b/fs/gfs2/sys.h index 79182d6ad6ac..f8dacf20e1a4 100644 --- a/fs/gfs2/sys.h +++ b/fs/gfs2/sys.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __SYS_DOT_H__ diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index d328da7cde36..35e3059255fe 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -80,10 +77,10 @@ static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr) fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n", tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, test_bit(TR_TOUCHED, &tr->tr_flags)); - fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n", + fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u\n", tr->tr_num_buf_new, tr->tr_num_buf_rm, tr->tr_num_databuf_new, tr->tr_num_databuf_rm, - tr->tr_num_revoke, tr->tr_num_revoke_rm); + tr->tr_num_revoke); } void gfs2_trans_end(struct gfs2_sbd *sdp) @@ -266,7 +263,7 @@ void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke); sdp->sd_log_num_revoke--; kmem_cache_free(gfs2_bufdata_cachep, bd); - tr->tr_num_revoke_rm++; + tr->tr_num_revoke--; if (--n == 0) break; } diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h index 1e39f056ccb7..6071334de035 100644 --- a/fs/gfs2/trans.h +++ b/fs/gfs2/trans.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __TRANS_DOT_H__ diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 0a814ccac41d..83f6c582773a 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -44,7 +41,7 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...) struct va_format vaf; if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW && - test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + test_and_set_bit(SDF_WITHDRAWN, &sdp->sd_flags)) return 0; if (fmt) { @@ -181,9 +178,11 @@ int gfs2_consist_rgrpd_i(struct gfs2_rgrpd *rgd, int cluster_wide, const char *function, char *file, unsigned int line) { struct gfs2_sbd *sdp = rgd->rd_sbd; + char fs_id_buf[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; int rv; - gfs2_rgrp_dump(NULL, rgd->rd_gl); + sprintf(fs_id_buf, "fsid=%s: ", sdp->sd_fsname); + gfs2_rgrp_dump(NULL, rgd->rd_gl, fs_id_buf); rv = gfs2_lm_withdraw(sdp, "fatal: filesystem consistency error\n" " RG = %llu\n" @@ -259,7 +258,7 @@ void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh, const char *function, char *file, unsigned int line, bool withdraw) { - if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) + if (!test_bit(SDF_WITHDRAWN, &sdp->sd_flags)) fs_err(sdp, "fatal: I/O error\n" " block = %llu\n" diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index 9278fecba632..4b68b2c1fe56 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __UTIL_DOT_H__ diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index 675e704830df..bbe593d16bea 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #include <linux/slab.h> diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h index 2d887c88eb49..2aed9d7d483d 100644 --- a/fs/gfs2/xattr.h +++ b/fs/gfs2/xattr.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. - * - * This copyrighted material is made available to anyone wishing to use, - * modify, copy, or redistribute it subject to the terms and conditions - * of the GNU General Public License version 2. */ #ifndef __EATTR_DOT_H__ diff --git a/fs/hfs/Kconfig b/fs/hfs/Kconfig index 998e3a6decf3..44f6e89bcb75 100644 --- a/fs/hfs/Kconfig +++ b/fs/hfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config HFS_FS tristate "Apple Macintosh file system support" depends on BLOCK diff --git a/fs/hfs/Makefile b/fs/hfs/Makefile index c41f5a85f42d..b65459bf3dc4 100644 --- a/fs/hfs/Makefile +++ b/fs/hfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux hfs filesystem routines. # diff --git a/fs/hfsplus/Kconfig b/fs/hfsplus/Kconfig index a63371815aab..7d4229aecec0 100644 --- a/fs/hfsplus/Kconfig +++ b/fs/hfsplus/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config HFSPLUS_FS tristate "Apple Extended HFS file system support" depends on BLOCK diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 5e6502ef7415..ce15b9496b77 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -57,9 +57,8 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags) return 0; } -static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags) +static inline unsigned int hfsplus_getflags(struct inode *inode) { - struct inode *inode = file_inode(file); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); unsigned int flags = 0; @@ -69,6 +68,13 @@ static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags) flags |= FS_APPEND_FL; if (hip->userflags & HFSPLUS_FLG_NODUMP) flags |= FS_NODUMP_FL; + return flags; +} + +static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags) +{ + struct inode *inode = file_inode(file); + unsigned int flags = hfsplus_getflags(inode); return put_user(flags, user_flags); } @@ -78,6 +84,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) struct inode *inode = file_inode(file); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); unsigned int flags, new_fl = 0; + unsigned int oldflags = hfsplus_getflags(inode); int err = 0; err = mnt_want_write_file(file); @@ -96,13 +103,9 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) inode_lock(inode); - if ((flags & (FS_IMMUTABLE_FL|FS_APPEND_FL)) || - inode->i_flags & (S_IMMUTABLE|S_APPEND)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - err = -EPERM; - goto out_unlock_inode; - } - } + err = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (err) + goto out_unlock_inode; /* don't silently ignore unsupported ext2 flags */ if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) { diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 0cc5feff76cd..2b9e5743105e 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/hfsplus/super.c * diff --git a/fs/hpfs/Kconfig b/fs/hpfs/Kconfig index 56bd15c5bf6c..56aa0336254a 100644 --- a/fs/hpfs/Kconfig +++ b/fs/hpfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config HPFS_FS tristate "OS/2 HPFS file system support" depends on BLOCK diff --git a/fs/hpfs/Makefile b/fs/hpfs/Makefile index 57b786fb9827..153c17382c19 100644 --- a/fs/hpfs/Makefile +++ b/fs/hpfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux hpfs filesystem routines. # diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index ed4264bca790..9db6d84f0d62 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/hpfs/super.c * diff --git a/fs/hugetlbfs/Makefile b/fs/hugetlbfs/Makefile index 6adf870c63c6..d876ecfbe6bb 100644 --- a/fs/hugetlbfs/Makefile +++ b/fs/hugetlbfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux ramfs routines. # diff --git a/fs/inode.c b/fs/inode.c index e9d18b2c3f91..0f1e3b563c47 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) @@ -361,7 +362,7 @@ EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { - xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ); + xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); @@ -1898,6 +1899,26 @@ int file_update_time(struct file *file) } EXPORT_SYMBOL(file_update_time); +/* Caller must hold the file's inode lock */ +int file_modified(struct file *file) +{ + int err; + + /* + * Clear the security bits if the process is not being run by root. + * This keeps people from modifying setuid and setgid binaries. + */ + err = file_remove_privs(file); + if (err) + return err; + + if (unlikely(file->f_mode & FMODE_NOCMTIME)) + return 0; + + return file_update_time(file); +} +EXPORT_SYMBOL(file_modified); + int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) @@ -2169,3 +2190,89 @@ struct timespec64 current_time(struct inode *inode) return timespec64_trunc(now, inode->i_sb->s_time_gran); } EXPORT_SYMBOL(current_time); + +/* + * Generic function to check FS_IOC_SETFLAGS values and reject any invalid + * configurations. + * + * Note: the caller should be holding i_mutex, or else be sure that they have + * exclusive access to the inode structure. + */ +int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, + unsigned int flags) +{ + /* + * The IMMUTABLE and APPEND_ONLY flags can only be changed by + * the relevant capability. + * + * This test looks nicer. Thanks to Pauline Middelink + */ + if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && + !capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + return 0; +} +EXPORT_SYMBOL(vfs_ioc_setflags_prepare); + +/* + * Generic function to check FS_IOC_FSSETXATTR values and reject any invalid + * configurations. + * + * Note: the caller should be holding i_mutex, or else be sure that they have + * exclusive access to the inode structure. + */ +int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, + struct fsxattr *fa) +{ + /* + * Can't modify an immutable/append-only file unless we have + * appropriate permission. + */ + if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & + (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND) && + !capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + /* + * Project Quota ID state is only allowed to change from within the init + * namespace. Enforce that restriction only if we are trying to change + * the quota ID state. Everything else is allowed in user namespaces. + */ + if (current_user_ns() != &init_user_ns) { + if (old_fa->fsx_projid != fa->fsx_projid) + return -EINVAL; + if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & + FS_XFLAG_PROJINHERIT) + return -EINVAL; + } + + /* Check extent size hints. */ + if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) + return -EINVAL; + + if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && + !S_ISDIR(inode->i_mode)) + return -EINVAL; + + if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && + !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) + return -EINVAL; + + /* + * It is only valid to set the DAX flag on regular files and + * directories on filesystems. + */ + if ((fa->fsx_xflags & FS_XFLAG_DAX) && + !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) + return -EINVAL; + + /* Extent size hints of zero turn off the flags. */ + if (fa->fsx_extsize == 0) + fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); + if (fa->fsx_cowextsize == 0) + fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; + + return 0; +} +EXPORT_SYMBOL(vfs_ioc_fssetxattr_check); diff --git a/fs/internal.h b/fs/internal.h index 0010889f2e85..2f3c3de51fad 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* fs/ internal definitions * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ struct super_block; @@ -44,8 +40,6 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait) extern void guard_bio_eod(int rw, struct bio *bio); extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len, get_block_t *get_block, struct iomap *iomap); -void __generic_write_end(struct inode *inode, loff_t pos, unsigned copied, - struct page *page); /* * char_dev.c diff --git a/fs/io_uring.c b/fs/io_uring.c index fdc18321d70c..4ed4b110a154 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -231,7 +231,6 @@ struct io_ring_ctx { struct task_struct *sqo_thread; /* if using sq thread polling */ struct mm_struct *sqo_mm; wait_queue_head_t sqo_wait; - unsigned sqo_stop; struct { /* CQ ring */ @@ -329,9 +328,8 @@ struct io_kiocb { #define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */ #define REQ_F_FIXED_FILE 4 /* ctx owns file */ #define REQ_F_SEQ_PREV 8 /* sequential with previous */ -#define REQ_F_PREPPED 16 /* prep already done */ -#define REQ_F_IO_DRAIN 32 /* drain existing IO first */ -#define REQ_F_IO_DRAINED 64 /* drain done */ +#define REQ_F_IO_DRAIN 16 /* drain existing IO first */ +#define REQ_F_IO_DRAINED 32 /* drain done */ u64 user_data; u32 error; /* iopoll result from callback */ u32 sequence; @@ -490,7 +488,7 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx) } static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, - long res, unsigned ev_flags) + long res) { struct io_uring_cqe *cqe; @@ -503,7 +501,7 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data, if (cqe) { WRITE_ONCE(cqe->user_data, ki_user_data); WRITE_ONCE(cqe->res, res); - WRITE_ONCE(cqe->flags, ev_flags); + WRITE_ONCE(cqe->flags, 0); } else { unsigned overflow = READ_ONCE(ctx->cq_ring->overflow); @@ -522,12 +520,12 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) } static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 user_data, - long res, unsigned ev_flags) + long res) { unsigned long flags; spin_lock_irqsave(&ctx->completion_lock, flags); - io_cqring_fill_event(ctx, user_data, res, ev_flags); + io_cqring_fill_event(ctx, user_data, res); io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); @@ -581,6 +579,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, state->cur_req++; } + req->file = NULL; req->ctx = ctx; req->flags = 0; /* one is dropped after submission, the other at completion */ @@ -629,7 +628,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, req = list_first_entry(done, struct io_kiocb, list); list_del(&req->list); - io_cqring_fill_event(ctx, req->user_data, req->error, 0); + io_cqring_fill_event(ctx, req->user_data, req->error); (*nr_events)++; if (refcount_dec_and_test(&req->refs)) { @@ -777,7 +776,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) kiocb_end_write(kiocb); - io_cqring_add_event(req->ctx, req->user_data, res, 0); + io_cqring_add_event(req->ctx, req->user_data, res); io_put_req(req); } @@ -896,9 +895,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, if (!req->file) return -EBADF; - /* For -EAGAIN retry, everything is already prepped */ - if (req->flags & REQ_F_PREPPED) - return 0; if (force_nonblock && !io_file_supports_async(req->file)) force_nonblock = false; @@ -941,7 +937,6 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s, return -EINVAL; kiocb->ki_complete = io_complete_rw; } - req->flags |= REQ_F_PREPPED; return 0; } @@ -1003,9 +998,6 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); if (offset) iov_iter_advance(iter, offset); - - /* don't drop a reference to these pages */ - iter->type |= ITER_BVEC_FLAG_NO_REF; return 0; } @@ -1216,7 +1208,7 @@ static int io_nop(struct io_kiocb *req, u64 user_data) if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; - io_cqring_add_event(ctx, user_data, err, 0); + io_cqring_add_event(ctx, user_data, err); io_put_req(req); return 0; } @@ -1227,16 +1219,12 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (!req->file) return -EBADF; - /* Prep already done (EAGAIN retry) */ - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; - req->flags |= REQ_F_PREPPED; return 0; } @@ -1265,7 +1253,7 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe, end > 0 ? end : LLONG_MAX, fsync_flags & IORING_FSYNC_DATASYNC); - io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); + io_cqring_add_event(req->ctx, sqe->user_data, ret); io_put_req(req); return 0; } @@ -1277,16 +1265,12 @@ static int io_prep_sfr(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (!req->file) return -EBADF; - /* Prep already done (EAGAIN retry) */ - if (req->flags & REQ_F_PREPPED) - return 0; if (unlikely(ctx->flags & IORING_SETUP_IOPOLL)) return -EINVAL; if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index)) return -EINVAL; - req->flags |= REQ_F_PREPPED; return ret; } @@ -1313,7 +1297,7 @@ static int io_sync_file_range(struct io_kiocb *req, ret = sync_file_range(req->rw.ki_filp, sqe_off, sqe_len, flags); - io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); + io_cqring_add_event(req->ctx, sqe->user_data, ret); io_put_req(req); return 0; } @@ -1371,7 +1355,7 @@ static int io_poll_remove(struct io_kiocb *req, const struct io_uring_sqe *sqe) } spin_unlock_irq(&ctx->completion_lock); - io_cqring_add_event(req->ctx, sqe->user_data, ret, 0); + io_cqring_add_event(req->ctx, sqe->user_data, ret); io_put_req(req); return 0; } @@ -1380,7 +1364,7 @@ static void io_poll_complete(struct io_ring_ctx *ctx, struct io_kiocb *req, __poll_t mask) { req->poll.done = true; - io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask), 0); + io_cqring_fill_event(ctx, req->user_data, mangle_poll(mask)); io_commit_cqring(ctx); } @@ -1700,7 +1684,7 @@ restart: io_put_req(req); if (ret) { - io_cqring_add_event(ctx, sqe->user_data, ret, 0); + io_cqring_add_event(ctx, sqe->user_data, ret); io_put_req(req); } @@ -1815,10 +1799,8 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, req->sequence = ctx->cached_sq_head - 1; } - if (!io_op_needs_file(s->sqe)) { - req->file = NULL; + if (!io_op_needs_file(s->sqe)) return 0; - } if (flags & IOSQE_FIXED_FILE) { if (unlikely(!ctx->user_files || @@ -2005,7 +1987,7 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes, continue; } - io_cqring_add_event(ctx, sqes[i].sqe->user_data, ret, 0); + io_cqring_add_event(ctx, sqes[i].sqe->user_data, ret); } if (statep) @@ -2028,7 +2010,7 @@ static int io_sq_thread(void *data) set_fs(USER_DS); timeout = inflight = 0; - while (!kthread_should_stop() && !ctx->sqo_stop) { + while (!kthread_should_park()) { bool all_fixed, mm_fault = false; int i; @@ -2090,7 +2072,7 @@ static int io_sq_thread(void *data) smp_mb(); if (!io_get_sqring(ctx, &sqes[0])) { - if (kthread_should_stop()) { + if (kthread_should_park()) { finish_wait(&ctx->sqo_wait, &wait); break; } @@ -2140,8 +2122,7 @@ static int io_sq_thread(void *data) mmput(cur_mm); } - if (kthread_should_park()) - kthread_parkme(); + kthread_parkme(); return 0; } @@ -2170,7 +2151,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) ret = io_submit_sqe(ctx, &s, statep); if (ret) - io_cqring_add_event(ctx, s.sqe->user_data, ret, 0); + io_cqring_add_event(ctx, s.sqe->user_data, ret); } io_commit_sqring(ctx); @@ -2182,6 +2163,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit) static unsigned io_cqring_events(struct io_cq_ring *ring) { + /* See comment at the top of this file */ + smp_rmb(); return READ_ONCE(ring->r.tail) - READ_ONCE(ring->r.head); } @@ -2194,11 +2177,8 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, { struct io_cq_ring *ring = ctx->cq_ring; sigset_t ksigmask, sigsaved; - DEFINE_WAIT(wait); int ret; - /* See comment at the top of this file */ - smp_rmb(); if (io_cqring_events(ring) >= min_events) return 0; @@ -2216,26 +2196,13 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, return ret; } - do { - prepare_to_wait(&ctx->wait, &wait, TASK_INTERRUPTIBLE); - - ret = 0; - /* See comment at the top of this file */ - smp_rmb(); - if (io_cqring_events(ring) >= min_events) - break; + ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events); - schedule(); + if (sig) + restore_user_sigmask(sig, &sigsaved, ret == -ERESTARTSYS); + if (ret == -ERESTARTSYS) ret = -EINTR; - if (signal_pending(current)) - break; - } while (1); - - finish_wait(&ctx->wait, &wait); - - if (sig) - restore_user_sigmask(sig, &sigsaved); return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0; } @@ -2273,8 +2240,11 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) static void io_sq_thread_stop(struct io_ring_ctx *ctx) { if (ctx->sqo_thread) { - ctx->sqo_stop = 1; - mb(); + /* + * The park is a bit of a work-around, without it we get + * warning spews on shutdown with SQPOLL set and affinity + * set to a single CPU. + */ kthread_park(ctx->sqo_thread); kthread_stop(ctx->sqo_thread); ctx->sqo_thread = NULL; @@ -2467,10 +2437,11 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx, ctx->sq_thread_idle = HZ; if (p->flags & IORING_SETUP_SQ_AFF) { - int cpu = array_index_nospec(p->sq_thread_cpu, - nr_cpu_ids); + int cpu = p->sq_thread_cpu; ret = -EINVAL; + if (cpu >= nr_cpu_ids) + goto err; if (!cpu_online(cpu)) goto err; @@ -2642,7 +2613,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg, ret = io_copy_iov(ctx, &iov, arg, i); if (ret) - break; + goto err; /* * Don't impose further limits on the size and buffer @@ -2803,8 +2774,10 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) io_eventfd_unregister(ctx); #if defined(CONFIG_UNIX) - if (ctx->ring_sock) + if (ctx->ring_sock) { + ctx->ring_sock->file = NULL; /* so that iput() is called */ sock_release(ctx->ring_sock); + } #endif io_mem_free(ctx->sq_ring); diff --git a/fs/iomap.c b/fs/iomap.c index 23ef63fd1669..217c3e5a13d6 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -287,7 +287,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap_readpage_ctx *ctx = data; struct page *page = ctx->cur_page; struct iomap_page *iop = iomap_page_create(inode, page); - bool is_contig = false; + bool same_page = false, is_contig = false; loff_t orig_pos = pos; unsigned poff, plen; sector_t sector; @@ -315,10 +315,14 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, * Try to merge into a previous segment if we can. */ sector = iomap_sector(iomap, pos); - if (ctx->bio && bio_end_sector(ctx->bio) == sector) { - if (__bio_try_merge_page(ctx->bio, page, plen, poff, true)) - goto done; + if (ctx->bio && bio_end_sector(ctx->bio) == sector) is_contig = true; + + if (is_contig && + __bio_try_merge_page(ctx->bio, page, plen, poff, &same_page)) { + if (!same_page && iop) + atomic_inc(&iop->read_count); + goto done; } /* @@ -329,7 +333,7 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data, if (iop) atomic_inc(&iop->read_count); - if (!ctx->bio || !is_contig || bio_full(ctx->bio)) { + if (!ctx->bio || !is_contig || bio_full(ctx->bio, plen)) { gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL); int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -773,6 +777,7 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page, struct iomap *iomap) { const struct iomap_page_ops *page_ops = iomap->page_ops; + loff_t old_size = inode->i_size; int ret; if (iomap->type == IOMAP_INLINE) { @@ -784,9 +789,21 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len, ret = __iomap_write_end(inode, pos, len, copied, page, iomap); } - __generic_write_end(inode, pos, ret, page); + /* + * Update the in-memory inode size after copying the data into the page + * cache. It's up to the file system to write the updated size to disk, + * preferably after I/O completion so that no stale data is exposed. + */ + if (pos + ret > old_size) { + i_size_write(inode, pos + ret); + iomap->flags |= IOMAP_F_SIZE_CHANGED; + } + unlock_page(page); + + if (old_size < pos) + pagecache_isize_extended(inode, old_size, pos); if (page_ops && page_ops->page_done) - page_ops->page_done(inode, pos, copied, page, iomap); + page_ops->page_done(inode, pos, ret, page, iomap); put_page(page); if (ret < len) @@ -1595,13 +1612,7 @@ static void iomap_dio_bio_end_io(struct bio *bio) if (should_dirty) { bio_check_pages_dirty(bio); } else { - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) { - struct bvec_iter_all iter_all; - struct bio_vec *bvec; - - bio_for_each_segment_all(bvec, bio, iter_all) - put_page(bvec->bv_page); - } + bio_release_pages(bio, false); bio_put(bio); } } diff --git a/fs/isofs/Kconfig b/fs/isofs/Kconfig index 8ab9878e3671..5e7419599f50 100644 --- a/fs/isofs/Kconfig +++ b/fs/isofs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config ISO9660_FS tristate "ISO 9660 CDROM file system support" help diff --git a/fs/isofs/compress.c b/fs/isofs/compress.c index 10205ececc27..bc12ac7e2312 100644 --- a/fs/isofs/compress.c +++ b/fs/isofs/compress.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- linux-c -*- ------------------------------------------------------- * * * Copyright 2001 H. Peter Anvin - All Rights Reserved * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 675 Mass Ave, Cambridge MA 02139, - * USA; either version 2 of the License, or (at your option) any later - * version; incorporated herein by reference. - * * ----------------------------------------------------------------------- */ /* diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index 603b052a3c94..9e30d8703735 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/isofs/inode.c * diff --git a/fs/isofs/zisofs.h b/fs/isofs/zisofs.h index 273795709155..70f1a218fc92 100644 --- a/fs/isofs/zisofs.h +++ b/fs/isofs/zisofs.h @@ -1,13 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* ----------------------------------------------------------------------- * * * Copyright 2001 H. Peter Anvin - All Rights Reserved * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, Inc., 675 Mass Ave, Cambridge MA 02139, - * USA; either version 2 of the License, or (at your option) any later - * version; incorporated herein by reference. - * * ----------------------------------------------------------------------- */ /* diff --git a/fs/jbd2/Kconfig b/fs/jbd2/Kconfig index 5a9f5534d57b..4ad2c67f93f1 100644 --- a/fs/jbd2/Kconfig +++ b/fs/jbd2/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config JBD2 tristate select CRC32 diff --git a/fs/jbd2/Makefile b/fs/jbd2/Makefile index 802a3413872a..126b4da6c7de 100644 --- a/fs/jbd2/Makefile +++ b/fs/jbd2/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux journaling routines. # diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index efd0ce9489ae..132fb92098c7 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -184,17 +184,18 @@ static int journal_wait_on_commit_record(journal_t *journal, /* * write the filemap data using writepage() address_space_operations. * We don't do block allocation here even for delalloc. We don't - * use writepages() because with dealyed allocation we may be doing + * use writepages() because with delayed allocation we may be doing * block allocation in writepages(). */ -static int journal_submit_inode_data_buffers(struct address_space *mapping) +static int journal_submit_inode_data_buffers(struct address_space *mapping, + loff_t dirty_start, loff_t dirty_end) { int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = mapping->nrpages * 2, - .range_start = 0, - .range_end = i_size_read(mapping->host), + .range_start = dirty_start, + .range_end = dirty_end, }; ret = generic_writepages(mapping, &wbc); @@ -218,6 +219,9 @@ static int journal_submit_data_buffers(journal_t *journal, spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + loff_t dirty_start = jinode->i_dirty_start; + loff_t dirty_end = jinode->i_dirty_end; + if (!(jinode->i_flags & JI_WRITE_DATA)) continue; mapping = jinode->i_vfs_inode->i_mapping; @@ -230,7 +234,8 @@ static int journal_submit_data_buffers(journal_t *journal, * only allocated blocks here. */ trace_jbd2_submit_inode_data(jinode->i_vfs_inode); - err = journal_submit_inode_data_buffers(mapping); + err = journal_submit_inode_data_buffers(mapping, dirty_start, + dirty_end); if (!ret) ret = err; spin_lock(&journal->j_list_lock); @@ -257,12 +262,16 @@ static int journal_finish_inode_data_buffers(journal_t *journal, /* For locking, see the comment in journal_submit_data_buffers() */ spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { + loff_t dirty_start = jinode->i_dirty_start; + loff_t dirty_end = jinode->i_dirty_end; + if (!(jinode->i_flags & JI_WAIT_DATA)) continue; jinode->i_flags |= JI_COMMIT_RUNNING; spin_unlock(&journal->j_list_lock); - err = filemap_fdatawait_keep_errors( - jinode->i_vfs_inode->i_mapping); + err = filemap_fdatawait_range_keep_errors( + jinode->i_vfs_inode->i_mapping, dirty_start, + dirty_end); if (!ret) ret = err; spin_lock(&journal->j_list_lock); @@ -282,6 +291,8 @@ static int journal_finish_inode_data_buffers(journal_t *journal, &jinode->i_transaction->t_inode_list); } else { jinode->i_transaction = NULL; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; } } spin_unlock(&journal->j_list_lock); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 37e16d969925..953990eb70a9 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -66,9 +66,6 @@ EXPORT_SYMBOL(jbd2_journal_get_undo_access); EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); EXPORT_SYMBOL(jbd2_journal_forget); -#if 0 -EXPORT_SYMBOL(journal_sync_buffer); -#endif EXPORT_SYMBOL(jbd2_journal_flush); EXPORT_SYMBOL(jbd2_journal_revoke); @@ -94,6 +91,8 @@ EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); EXPORT_SYMBOL(jbd2_journal_inode_add_write); EXPORT_SYMBOL(jbd2_journal_inode_add_wait); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); @@ -203,7 +202,7 @@ loop: if (journal->j_flags & JBD2_UNMOUNT) goto end_loop; - jbd_debug(1, "commit_sequence=%d, commit_request=%d\n", + jbd_debug(1, "commit_sequence=%u, commit_request=%u\n", journal->j_commit_sequence, journal->j_commit_request); if (journal->j_commit_sequence != journal->j_commit_request) { @@ -324,7 +323,7 @@ static void journal_kill_thread(journal_t *journal) * IO is in progress. do_get_write_access() handles this. * * The function returns a pointer to the buffer_head to be used for IO. - * + * * * Return value: * <0: Error @@ -500,7 +499,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) */ journal->j_commit_request = target; - jbd_debug(1, "JBD2: requesting commit %d/%d\n", + jbd_debug(1, "JBD2: requesting commit %u/%u\n", journal->j_commit_request, journal->j_commit_sequence); journal->j_running_transaction->t_requested = jiffies; @@ -513,7 +512,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n", journal->j_commit_request, journal->j_commit_sequence, - target, journal->j_running_transaction ? + target, journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0); return 0; } @@ -698,12 +697,12 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) #ifdef CONFIG_JBD2_DEBUG if (!tid_geq(journal->j_commit_request, tid)) { printk(KERN_ERR - "%s: error: j_commit_request=%d, tid=%d\n", + "%s: error: j_commit_request=%u, tid=%u\n", __func__, journal->j_commit_request, tid); } #endif while (tid_gt(tid, journal->j_commit_sequence)) { - jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n", + jbd_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", tid, journal->j_commit_sequence); read_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); @@ -944,7 +943,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) trace_jbd2_update_log_tail(journal, tid, block, freed); jbd_debug(1, - "Cleaning journal tail from %d to %d (offset %lu), " + "Cleaning journal tail from %u to %u (offset %lu), " "freeing %lu\n", journal->j_tail_sequence, tid, block, freed); @@ -1318,7 +1317,7 @@ static int journal_reset(journal_t *journal) */ if (sb->s_start == 0) { jbd_debug(1, "JBD2: Skipping superblock update on recovered sb " - "(start %ld, seq %d, errno %d)\n", + "(start %ld, seq %u, errno %d)\n", journal->j_tail, journal->j_tail_sequence, journal->j_errno); journal->j_flags |= JBD2_FLUSHED; @@ -1453,7 +1452,7 @@ static void jbd2_mark_journal_empty(journal_t *journal, int write_op) return; } - jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n", + jbd_debug(1, "JBD2: Marking journal as empty (seq %u)\n", journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); @@ -2375,22 +2374,19 @@ static struct kmem_cache *jbd2_journal_head_cache; static atomic_t nr_journal_heads = ATOMIC_INIT(0); #endif -static int jbd2_journal_init_journal_head_cache(void) +static int __init jbd2_journal_init_journal_head_cache(void) { - int retval; - - J_ASSERT(jbd2_journal_head_cache == NULL); + J_ASSERT(!jbd2_journal_head_cache); jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head", sizeof(struct journal_head), 0, /* offset */ SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU, NULL); /* ctor */ - retval = 0; if (!jbd2_journal_head_cache) { - retval = -ENOMEM; printk(KERN_EMERG "JBD2: no memory for journal_head cache\n"); + return -ENOMEM; } - return retval; + return 0; } static void jbd2_journal_destroy_journal_head_cache(void) @@ -2577,6 +2573,8 @@ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) jinode->i_next_transaction = NULL; jinode->i_vfs_inode = inode; jinode->i_flags = 0; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; INIT_LIST_HEAD(&jinode->i_list); } @@ -2636,28 +2634,38 @@ static void __exit jbd2_remove_jbd_stats_proc_entry(void) struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; +static int __init jbd2_journal_init_inode_cache(void) +{ + J_ASSERT(!jbd2_inode_cache); + jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); + if (!jbd2_inode_cache) { + pr_emerg("JBD2: failed to create inode cache\n"); + return -ENOMEM; + } + return 0; +} + static int __init jbd2_journal_init_handle_cache(void) { + J_ASSERT(!jbd2_handle_cache); jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY); - if (jbd2_handle_cache == NULL) { + if (!jbd2_handle_cache) { printk(KERN_EMERG "JBD2: failed to create handle cache\n"); return -ENOMEM; } - jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); - if (jbd2_inode_cache == NULL) { - printk(KERN_EMERG "JBD2: failed to create inode cache\n"); - kmem_cache_destroy(jbd2_handle_cache); - return -ENOMEM; - } return 0; } +static void jbd2_journal_destroy_inode_cache(void) +{ + kmem_cache_destroy(jbd2_inode_cache); + jbd2_inode_cache = NULL; +} + static void jbd2_journal_destroy_handle_cache(void) { kmem_cache_destroy(jbd2_handle_cache); jbd2_handle_cache = NULL; - kmem_cache_destroy(jbd2_inode_cache); - jbd2_inode_cache = NULL; } /* @@ -2668,21 +2676,27 @@ static int __init journal_init_caches(void) { int ret; - ret = jbd2_journal_init_revoke_caches(); + ret = jbd2_journal_init_revoke_record_cache(); + if (ret == 0) + ret = jbd2_journal_init_revoke_table_cache(); if (ret == 0) ret = jbd2_journal_init_journal_head_cache(); if (ret == 0) ret = jbd2_journal_init_handle_cache(); if (ret == 0) + ret = jbd2_journal_init_inode_cache(); + if (ret == 0) ret = jbd2_journal_init_transaction_cache(); return ret; } static void jbd2_journal_destroy_caches(void) { - jbd2_journal_destroy_revoke_caches(); + jbd2_journal_destroy_revoke_record_cache(); + jbd2_journal_destroy_revoke_table_cache(); jbd2_journal_destroy_journal_head_cache(); jbd2_journal_destroy_handle_cache(); + jbd2_journal_destroy_inode_cache(); jbd2_journal_destroy_transaction_cache(); jbd2_journal_destroy_slabs(); } diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index a1143e57a718..69b9bc329964 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -178,33 +178,41 @@ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal, return NULL; } -void jbd2_journal_destroy_revoke_caches(void) +void jbd2_journal_destroy_revoke_record_cache(void) { kmem_cache_destroy(jbd2_revoke_record_cache); jbd2_revoke_record_cache = NULL; +} + +void jbd2_journal_destroy_revoke_table_cache(void) +{ kmem_cache_destroy(jbd2_revoke_table_cache); jbd2_revoke_table_cache = NULL; } -int __init jbd2_journal_init_revoke_caches(void) +int __init jbd2_journal_init_revoke_record_cache(void) { J_ASSERT(!jbd2_revoke_record_cache); - J_ASSERT(!jbd2_revoke_table_cache); - jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s, SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY); - if (!jbd2_revoke_record_cache) - goto record_cache_failure; + if (!jbd2_revoke_record_cache) { + pr_emerg("JBD2: failed to create revoke_record cache\n"); + return -ENOMEM; + } + return 0; +} + +int __init jbd2_journal_init_revoke_table_cache(void) +{ + J_ASSERT(!jbd2_revoke_table_cache); jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s, SLAB_TEMPORARY); - if (!jbd2_revoke_table_cache) - goto table_cache_failure; - return 0; -table_cache_failure: - jbd2_journal_destroy_revoke_caches(); -record_cache_failure: + if (!jbd2_revoke_table_cache) { + pr_emerg("JBD2: failed to create revoke_table cache\n"); return -ENOMEM; + } + return 0; } static struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index f940d31c2adc..990e7b5062e7 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -42,9 +42,11 @@ int __init jbd2_journal_init_transaction_cache(void) 0, SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY, NULL); - if (transaction_cache) - return 0; - return -ENOMEM; + if (!transaction_cache) { + pr_emerg("JBD2: failed to create transaction cache\n"); + return -ENOMEM; + } + return 0; } void jbd2_journal_destroy_transaction_cache(void) @@ -2563,7 +2565,7 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh) * File inode in the inode list of the handle's transaction */ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, - unsigned long flags) + unsigned long flags, loff_t start_byte, loff_t end_byte) { transaction_t *transaction = handle->h_transaction; journal_t *journal; @@ -2575,26 +2577,17 @@ static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode, jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino, transaction->t_tid); - /* - * First check whether inode isn't already on the transaction's - * lists without taking the lock. Note that this check is safe - * without the lock as we cannot race with somebody removing inode - * from the transaction. The reason is that we remove inode from the - * transaction only in journal_release_jbd_inode() and when we commit - * the transaction. We are guarded from the first case by holding - * a reference to the inode. We are safe against the second case - * because if jinode->i_transaction == transaction, commit code - * cannot touch the transaction because we hold reference to it, - * and if jinode->i_next_transaction == transaction, commit code - * will only file the inode where we want it. - */ - if ((jinode->i_transaction == transaction || - jinode->i_next_transaction == transaction) && - (jinode->i_flags & flags) == flags) - return 0; - spin_lock(&journal->j_list_lock); jinode->i_flags |= flags; + + if (jinode->i_dirty_end) { + jinode->i_dirty_start = min(jinode->i_dirty_start, start_byte); + jinode->i_dirty_end = max(jinode->i_dirty_end, end_byte); + } else { + jinode->i_dirty_start = start_byte; + jinode->i_dirty_end = end_byte; + } + /* Is inode already attached where we need it? */ if (jinode->i_transaction == transaction || jinode->i_next_transaction == transaction) @@ -2629,12 +2622,28 @@ done: int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode) { return jbd2_journal_file_inode(handle, jinode, - JI_WRITE_DATA | JI_WAIT_DATA); + JI_WRITE_DATA | JI_WAIT_DATA, 0, LLONG_MAX); } int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode) { - return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA); + return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, 0, + LLONG_MAX); +} + +int jbd2_journal_inode_ranged_write(handle_t *handle, + struct jbd2_inode *jinode, loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, + JI_WRITE_DATA | JI_WAIT_DATA, start_byte, + start_byte + length - 1); +} + +int jbd2_journal_inode_ranged_wait(handle_t *handle, struct jbd2_inode *jinode, + loff_t start_byte, loff_t length) +{ + return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA, + start_byte, start_byte + length - 1); } /* diff --git a/fs/jffs2/Kconfig b/fs/jffs2/Kconfig index ad850c5bf2ca..7c96bc107218 100644 --- a/fs/jffs2/Kconfig +++ b/fs/jffs2/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config JFFS2_FS tristate "Journalling Flash File System v2 (JFFS2) support" select CRC32 diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 7d8654a1472e..f8fb89b10227 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -109,9 +109,9 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg) return ret; } -int jffs2_do_readpage_unlock(struct inode *inode, struct page *pg) +int jffs2_do_readpage_unlock(void *data, struct page *pg) { - int ret = jffs2_do_readpage_nolock(inode, pg); + int ret = jffs2_do_readpage_nolock(data, pg); unlock_page(pg); return ret; } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 112d85849db1..8a20ddd25f2d 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -687,7 +687,7 @@ unsigned char *jffs2_gc_fetch_page(struct jffs2_sb_info *c, struct page *pg; pg = read_cache_page(inode->i_mapping, offset >> PAGE_SHIFT, - (void *)jffs2_do_readpage_unlock, inode); + jffs2_do_readpage_unlock, inode); if (IS_ERR(pg)) return (void *)pg; diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index a2dbbb3f4c74..bd3d5f0ddc34 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -155,7 +155,7 @@ extern const struct file_operations jffs2_file_operations; extern const struct inode_operations jffs2_file_inode_operations; extern const struct address_space_operations jffs2_file_address_operations; int jffs2_fsync(struct file *, loff_t, loff_t, int); -int jffs2_do_readpage_unlock (struct inode *inode, struct page *pg); +int jffs2_do_readpage_unlock(void *data, struct page *pg); /* ioctl.c */ long jffs2_ioctl(struct file *, unsigned int, unsigned long); diff --git a/fs/jfs/Kconfig b/fs/jfs/Kconfig index 851de78fdabb..22a273bd4648 100644 --- a/fs/jfs/Kconfig +++ b/fs/jfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config JFS_FS tristate "JFS filesystem support" select NLS diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index ebb299003a5b..92cc0ac2d1fc 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -1,21 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2002-2004 * Copyright (C) Andreas Gruenbacher, 2001 * Copyright (C) Linus Torvalds, 1991, 1992 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/sched.h> diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 36665fd37095..930d2701f206 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2002 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/mm.h> diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index f2b92b292abe..9486afcdac76 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index ba34dae8bd9f..10ee0ecca1a8 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -98,24 +98,16 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) /* Lock against other parallel changes of flags */ inode_lock(inode); - oldflags = jfs_inode->mode2; - - /* - * The IMMUTABLE and APPEND_ONLY flags can only be changed by - * the relevant capability. - */ - if ((oldflags & JFS_IMMUTABLE_FL) || - ((flags ^ oldflags) & - (JFS_APPEND_FL | JFS_IMMUTABLE_FL))) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - inode_unlock(inode); - err = -EPERM; - goto setflags_out; - } + oldflags = jfs_map_ext2(jfs_inode->mode2 & JFS_FL_USER_VISIBLE, + 0); + err = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (err) { + inode_unlock(inode); + goto setflags_out; } flags = flags & JFS_FL_USER_MODIFIABLE; - flags |= oldflags & ~JFS_FL_USER_MODIFIABLE; + flags |= jfs_inode->mode2 & ~JFS_FL_USER_MODIFIABLE; jfs_inode->mode2 = flags; jfs_set_inode_flags(inode); diff --git a/fs/jfs/jfs_acl.h b/fs/jfs/jfs_acl.h index 489f993b7b13..9f8f92dd6f84 100644 --- a/fs/jfs/jfs_acl.h +++ b/fs/jfs/jfs_acl.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_ACL #define _H_JFS_ACL diff --git a/fs/jfs/jfs_btree.h b/fs/jfs/jfs_btree.h index 79c61805bd33..ce055ef50cd3 100644 --- a/fs/jfs/jfs_btree.h +++ b/fs/jfs/jfs_btree.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_BTREE #define _H_JFS_BTREE diff --git a/fs/jfs/jfs_debug.c b/fs/jfs/jfs_debug.c index 35a5b2a81ae0..888cdd685a1e 100644 --- a/fs/jfs/jfs_debug.c +++ b/fs/jfs/jfs_debug.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_debug.h b/fs/jfs/jfs_debug.h index 0d9e35da8462..48e2150c092e 100644 --- a/fs/jfs/jfs_debug.h +++ b/fs/jfs/jfs_debug.h @@ -1,20 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DEBUG #define _H_JFS_DEBUG diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 1682a87c00b2..5fa9fd594115 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2001 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DINODE #define _H_JFS_DINODE diff --git a/fs/jfs/jfs_discard.c b/fs/jfs/jfs_discard.c index f76ff0a46444..575cb2ba74fc 100644 --- a/fs/jfs/jfs_discard.c +++ b/fs/jfs/jfs_discard.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) Tino Reichardt, 2012 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_discard.h b/fs/jfs/jfs_discard.h index 40d1ee6081a0..05215fa27ebb 100644 --- a/fs/jfs/jfs_discard.h +++ b/fs/jfs/jfs_discard.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) Tino Reichardt, 2012 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DISCARD #define _H_JFS_DISCARD diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 49263e220dbc..caade185e568 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Tino Reichardt, 2012 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_dmap.h b/fs/jfs/jfs_dmap.h index 562b9a7e4311..29891fad3f09 100644 --- a/fs/jfs/jfs_dmap.h +++ b/fs/jfs/jfs_dmap.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DMAP #define _H_JFS_DMAP diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 52bae3f5c914..3acc954f7c04 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/jfs/jfs_dtree.h b/fs/jfs/jfs_dtree.h index fd4169e6e698..1758289647a0 100644 --- a/fs/jfs/jfs_dtree.h +++ b/fs/jfs/jfs_dtree.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_DTREE #define _H_JFS_DTREE diff --git a/fs/jfs/jfs_extent.c b/fs/jfs/jfs_extent.c index 2ae7d59ab10a..f65bd6b35412 100644 --- a/fs/jfs/jfs_extent.c +++ b/fs/jfs/jfs_extent.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_extent.h b/fs/jfs/jfs_extent.h index b567e12c52d3..dd635a8a0f8c 100644 --- a/fs/jfs/jfs_extent.h +++ b/fs/jfs/jfs_extent.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2001 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_EXTENT #define _H_JFS_EXTENT diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index b67d64671bb4..1e899298f7f0 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2003 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_FILSYS #define _H_JFS_FILSYS diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 93e8c590ff5c..937ca07b58b1 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/jfs/jfs_imap.h b/fs/jfs/jfs_imap.h index 610a0e9d8941..dd7409febe28 100644 --- a/fs/jfs/jfs_imap.h +++ b/fs/jfs/jfs_imap.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_IMAP #define _H_JFS_IMAP diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 340eb8e4f716..a466ec41cfbb 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -1,20 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_INCORE #define _H_JFS_INCORE diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index 4572b7cf183d..4cef170630db 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index 7b0b3a40788f..70a0d12e427e 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2001 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_INODE #define _H_JFS_INODE diff --git a/fs/jfs/jfs_lock.h b/fs/jfs/jfs_lock.h index ecf04882265e..feb37dd9debf 100644 --- a/fs/jfs/jfs_lock.h +++ b/fs/jfs/jfs_lock.h @@ -1,20 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2001 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_LOCK #define _H_JFS_LOCK diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index 4c77b808020b..9330eff210e0 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/jfs/jfs_logmgr.h b/fs/jfs/jfs_logmgr.h index 870fc22360e7..7fd125c8dd19 100644 --- a/fs/jfs/jfs_logmgr.h +++ b/fs/jfs/jfs_logmgr.h @@ -1,20 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_LOGMGR #define _H_JFS_LOGMGR diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index fa2c6824c7f2..a2f5338a5ea1 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2005 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h index 8b0ee514eb84..4179f9df4deb 100644 --- a/fs/jfs/jfs_metapage.h +++ b/fs/jfs/jfs_metapage.h @@ -1,20 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_METAPAGE #define _H_JFS_METAPAGE diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index c9c1f16b93df..eb8b9e233d73 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/jfs/jfs_superblock.h b/fs/jfs/jfs_superblock.h index eb03de7fa925..93402c42070f 100644 --- a/fs/jfs/jfs_superblock.h +++ b/fs/jfs/jfs_superblock.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2003 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_SUPERBLOCK #define _H_JFS_SUPERBLOCK diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c index 78789c5ed36b..c8ce7f1bc594 100644 --- a/fs/jfs/jfs_txnmgr.c +++ b/fs/jfs/jfs_txnmgr.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2005 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/jfs/jfs_txnmgr.h b/fs/jfs/jfs_txnmgr.h index ab7288937019..ba71eb5ced56 100644 --- a/fs/jfs/jfs_txnmgr.h +++ b/fs/jfs/jfs_txnmgr.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_TXNMGR #define _H_JFS_TXNMGR diff --git a/fs/jfs/jfs_types.h b/fs/jfs/jfs_types.h index 8f602dcb51fa..3ff9f26bc3e6 100644 --- a/fs/jfs/jfs_types.h +++ b/fs/jfs/jfs_types.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_TYPES #define _H_JFS_TYPES diff --git a/fs/jfs/jfs_umount.c b/fs/jfs/jfs_umount.c index 7971f37534a3..3e8b13e6aa01 100644 --- a/fs/jfs/jfs_umount.c +++ b/fs/jfs/jfs_umount.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* diff --git a/fs/jfs/jfs_unicode.c b/fs/jfs/jfs_unicode.c index 0148e2e4d97a..0c1e9027245a 100644 --- a/fs/jfs/jfs_unicode.c +++ b/fs/jfs/jfs_unicode.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_unicode.h b/fs/jfs/jfs_unicode.h index 8f0f02cb6ca6..9db62d047daa 100644 --- a/fs/jfs/jfs_unicode.h +++ b/fs/jfs/jfs_unicode.h @@ -1,20 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_UNICODE #define _H_JFS_UNICODE diff --git a/fs/jfs/jfs_uniupr.c b/fs/jfs/jfs_uniupr.c index cfe50666d312..d0b18c7befb8 100644 --- a/fs/jfs/jfs_uniupr.c +++ b/fs/jfs/jfs_uniupr.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/jfs_xattr.h b/fs/jfs/jfs_xattr.h index 561f6af46288..f0558b3348da 100644 --- a/fs/jfs/jfs_xattr.h +++ b/fs/jfs/jfs_xattr.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef H_JFS_XATTR diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c index 2c200b5256a6..16ad920f6fb1 100644 --- a/fs/jfs/jfs_xtree.c +++ b/fs/jfs/jfs_xtree.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2005 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ /* * jfs_xtree.c: extent allocation descriptor B+-tree manager diff --git a/fs/jfs/jfs_xtree.h b/fs/jfs/jfs_xtree.h index 1e0987986d5f..5f51be8596b3 100644 --- a/fs/jfs/jfs_xtree.h +++ b/fs/jfs/jfs_xtree.h @@ -1,19 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _H_JFS_XTREE #define _H_JFS_XTREE diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index fa719a1553b6..7a55d14cc1af 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 7ddcb445a3d9..66acea9d878b 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8f78fa374242..f4e10cb9f734 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/symlink.c b/fs/jfs/symlink.c index 38320607993e..a040719aafc4 100644 --- a/fs/jfs/symlink.c +++ b/fs/jfs/symlink.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) Christoph Hellwig, 2001-2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index a6797986b625..db41e7803163 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -1,20 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Copyright (C) Christoph Hellwig, 2002 - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See - * the GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/capability.h> diff --git a/fs/kernfs/Kconfig b/fs/kernfs/Kconfig index 397b5f7a7a16..e7f09105f6e9 100644 --- a/fs/kernfs/Kconfig +++ b/fs/kernfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # KERNFS should be selected by its users # diff --git a/fs/kernfs/Makefile b/fs/kernfs/Makefile index 674337c76673..4ca54ff54c98 100644 --- a/fs/kernfs/Makefile +++ b/fs/kernfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the kernfs pseudo filesystem # diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 016ba88f7335..a387534c9577 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/dir.c - kernfs directory implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> - * - * This file is released under the GPLv2. */ #include <linux/sched.h> diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 553ce0a92b05..e8c792b49616 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/file.c - kernfs file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> - * - * This file is released under the GPLv2. */ #include <linux/fs.h> diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index f89a0f13840e..f3f3984cce80 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/inode.c - kernfs inode implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> - * - * This file is released under the GPLv2. */ #include <linux/pagemap.h> diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index 3c437990f39a..02ce570a9a3c 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -1,11 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * fs/kernfs/kernfs-internal.h - kernfs internal header file * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <teheo@suse.de> - * - * This file is released under the GPLv2. */ #ifndef __KERNFS_INTERNAL_H diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index 9a4646eecb71..6c12fac2c287 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/mount.c - kernfs mount implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> - * - * This file is released under the GPLv2. */ #include <linux/fs.h> diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index eb46c3a16e2f..5432883d819f 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -1,11 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/symlink.c - kernfs symlink implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> - * - * This file is released under the GPLv2. */ #include <linux/fs.h> diff --git a/fs/libfs.c b/fs/libfs.c index 4b59b1816efb..7e52e77692ec 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/libfs.c * Library for filesystems writers. diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 70f520b41a19..a5bb3f721a9d 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/lockd/clntlock.c * @@ -56,7 +57,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init) u32 nlm_version = (nlm_init->nfs_version == 2) ? 1 : 4; int status; - status = lockd_up(nlm_init->net); + status = lockd_up(nlm_init->net, nlm_init->cred); if (status < 0) return ERR_PTR(status); @@ -241,7 +242,7 @@ reclaimer(void *ptr) allow_signal(SIGKILL); down_write(&host->h_rwsem); - lockd_up(net); /* note: this cannot fail as lockd is already running */ + lockd_up(net, NULL); /* note: this cannot fail as lockd is already running */ dprintk("lockd: reclaiming locks for host %s\n", host->h_name); diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index d9c32d1a20c0..b11f2afa84f1 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/lockd/clntproc.c * @@ -46,13 +47,14 @@ void nlmclnt_next_cookie(struct nlm_cookie *c) c->len=4; } -static struct nlm_lockowner *nlm_get_lockowner(struct nlm_lockowner *lockowner) +static struct nlm_lockowner * +nlmclnt_get_lockowner(struct nlm_lockowner *lockowner) { refcount_inc(&lockowner->count); return lockowner; } -static void nlm_put_lockowner(struct nlm_lockowner *lockowner) +static void nlmclnt_put_lockowner(struct nlm_lockowner *lockowner) { if (!refcount_dec_and_lock(&lockowner->count, &lockowner->host->h_lock)) return; @@ -81,28 +83,28 @@ static inline uint32_t __nlm_alloc_pid(struct nlm_host *host) return res; } -static struct nlm_lockowner *__nlm_find_lockowner(struct nlm_host *host, fl_owner_t owner) +static struct nlm_lockowner *__nlmclnt_find_lockowner(struct nlm_host *host, fl_owner_t owner) { struct nlm_lockowner *lockowner; list_for_each_entry(lockowner, &host->h_lockowners, list) { if (lockowner->owner != owner) continue; - return nlm_get_lockowner(lockowner); + return nlmclnt_get_lockowner(lockowner); } return NULL; } -static struct nlm_lockowner *nlm_find_lockowner(struct nlm_host *host, fl_owner_t owner) +static struct nlm_lockowner *nlmclnt_find_lockowner(struct nlm_host *host, fl_owner_t owner) { struct nlm_lockowner *res, *new = NULL; spin_lock(&host->h_lock); - res = __nlm_find_lockowner(host, owner); + res = __nlmclnt_find_lockowner(host, owner); if (res == NULL) { spin_unlock(&host->h_lock); new = kmalloc(sizeof(*new), GFP_KERNEL); spin_lock(&host->h_lock); - res = __nlm_find_lockowner(host, owner); + res = __nlmclnt_find_lockowner(host, owner); if (res == NULL && new != NULL) { res = new; refcount_set(&new->count, 1); @@ -456,7 +458,7 @@ static void nlmclnt_locks_copy_lock(struct file_lock *new, struct file_lock *fl) { spin_lock(&fl->fl_u.nfs_fl.owner->host->h_lock); new->fl_u.nfs_fl.state = fl->fl_u.nfs_fl.state; - new->fl_u.nfs_fl.owner = nlm_get_lockowner(fl->fl_u.nfs_fl.owner); + new->fl_u.nfs_fl.owner = nlmclnt_get_lockowner(fl->fl_u.nfs_fl.owner); list_add_tail(&new->fl_u.nfs_fl.list, &fl->fl_u.nfs_fl.owner->host->h_granted); spin_unlock(&fl->fl_u.nfs_fl.owner->host->h_lock); } @@ -466,7 +468,7 @@ static void nlmclnt_locks_release_private(struct file_lock *fl) spin_lock(&fl->fl_u.nfs_fl.owner->host->h_lock); list_del(&fl->fl_u.nfs_fl.list); spin_unlock(&fl->fl_u.nfs_fl.owner->host->h_lock); - nlm_put_lockowner(fl->fl_u.nfs_fl.owner); + nlmclnt_put_lockowner(fl->fl_u.nfs_fl.owner); } static const struct file_lock_operations nlmclnt_lock_ops = { @@ -477,7 +479,7 @@ static const struct file_lock_operations nlmclnt_lock_ops = { static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host) { fl->fl_u.nfs_fl.state = 0; - fl->fl_u.nfs_fl.owner = nlm_find_lockowner(host, fl->fl_owner); + fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host, fl->fl_owner); INIT_LIST_HEAD(&fl->fl_u.nfs_fl.list); fl->fl_ops = &nlmclnt_lock_ops; } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 346ed161756d..1a639e34847d 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/lockd/svc.c * @@ -188,28 +189,31 @@ lockd(void *vrqstp) static int create_lockd_listener(struct svc_serv *serv, const char *name, struct net *net, const int family, - const unsigned short port) + const unsigned short port, + const struct cred *cred) { struct svc_xprt *xprt; xprt = svc_find_xprt(serv, name, net, family, 0); if (xprt == NULL) return svc_create_xprt(serv, name, net, family, port, - SVC_SOCK_DEFAULTS); + SVC_SOCK_DEFAULTS, cred); svc_xprt_put(xprt); return 0; } static int create_lockd_family(struct svc_serv *serv, struct net *net, - const int family) + const int family, const struct cred *cred) { int err; - err = create_lockd_listener(serv, "udp", net, family, nlm_udpport); + err = create_lockd_listener(serv, "udp", net, family, nlm_udpport, + cred); if (err < 0) return err; - return create_lockd_listener(serv, "tcp", net, family, nlm_tcpport); + return create_lockd_listener(serv, "tcp", net, family, nlm_tcpport, + cred); } /* @@ -222,16 +226,17 @@ static int create_lockd_family(struct svc_serv *serv, struct net *net, * Returns zero if all listeners are available; otherwise a * negative errno value is returned. */ -static int make_socks(struct svc_serv *serv, struct net *net) +static int make_socks(struct svc_serv *serv, struct net *net, + const struct cred *cred) { static int warned; int err; - err = create_lockd_family(serv, net, PF_INET); + err = create_lockd_family(serv, net, PF_INET, cred); if (err < 0) goto out_err; - err = create_lockd_family(serv, net, PF_INET6); + err = create_lockd_family(serv, net, PF_INET6, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_err; @@ -246,7 +251,8 @@ out_err: return err; } -static int lockd_up_net(struct svc_serv *serv, struct net *net) +static int lockd_up_net(struct svc_serv *serv, struct net *net, + const struct cred *cred) { struct lockd_net *ln = net_generic(net, lockd_net_id); int error; @@ -258,7 +264,7 @@ static int lockd_up_net(struct svc_serv *serv, struct net *net) if (error) goto err_bind; - error = make_socks(serv, net); + error = make_socks(serv, net, cred); if (error < 0) goto err_bind; set_grace_period(net); @@ -461,7 +467,7 @@ static struct svc_serv *lockd_create_svc(void) /* * Bring up the lockd process if it's not already up. */ -int lockd_up(struct net *net) +int lockd_up(struct net *net, const struct cred *cred) { struct svc_serv *serv; int error; @@ -474,7 +480,7 @@ int lockd_up(struct net *net) goto err_create; } - error = lockd_up_net(serv, net); + error = lockd_up_net(serv, net, cred); if (error < 0) { lockd_unregister_notifiers(); goto err_put; @@ -807,5 +813,7 @@ static struct svc_program nlmsvc_program = { .pg_name = "lockd", /* service name */ .pg_class = "nfsd", /* share authentication with nfsd */ .pg_stats = &nlmsvc_stats, /* stats table */ - .pg_authenticate = &lockd_authenticate /* export authentication */ + .pg_authenticate = &lockd_authenticate, /* export authentication */ + .pg_init_request = svc_generic_init_request, + .pg_rpcbind_set = svc_generic_rpcbind_set, }; diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 1bddf70d9656..e4d3f783e06a 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -46,8 +46,14 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Set up the missing parts of the file_lock structure */ lock->fl.fl_file = file->f_file; - lock->fl.fl_owner = (fl_owner_t) host; + lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; + nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid); + if (!lock->fl.fl_owner) { + /* lockowner allocation has failed */ + nlmsvc_release_host(host); + return nlm_lck_denied_nolocks; + } } return 0; @@ -94,6 +100,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; @@ -142,6 +149,7 @@ __nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; @@ -178,6 +186,7 @@ __nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) resp->status = nlmsvc_cancel_blocked(SVC_NET(rqstp), file, &argp->lock); dprintk("lockd: CANCEL status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; @@ -217,6 +226,7 @@ __nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) resp->status = nlmsvc_unlock(SVC_NET(rqstp), file, &argp->lock); dprintk("lockd: UNLOCK status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; @@ -365,6 +375,7 @@ nlm4svc_proc_share(struct svc_rqst *rqstp) resp->status = nlmsvc_share_file(host, file, argp); dprintk("lockd: SHARE status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; @@ -399,6 +410,7 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp) resp->status = nlmsvc_unshare_file(host, file, argp); dprintk("lockd: UNSHARE status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index ea719cdd6a36..61d3cc2283dc 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -332,6 +332,93 @@ restart: mutex_unlock(&file->f_mutex); } +static struct nlm_lockowner * +nlmsvc_get_lockowner(struct nlm_lockowner *lockowner) +{ + refcount_inc(&lockowner->count); + return lockowner; +} + +static void nlmsvc_put_lockowner(struct nlm_lockowner *lockowner) +{ + if (!refcount_dec_and_lock(&lockowner->count, &lockowner->host->h_lock)) + return; + list_del(&lockowner->list); + spin_unlock(&lockowner->host->h_lock); + nlmsvc_release_host(lockowner->host); + kfree(lockowner); +} + +static struct nlm_lockowner *__nlmsvc_find_lockowner(struct nlm_host *host, pid_t pid) +{ + struct nlm_lockowner *lockowner; + list_for_each_entry(lockowner, &host->h_lockowners, list) { + if (lockowner->pid != pid) + continue; + return nlmsvc_get_lockowner(lockowner); + } + return NULL; +} + +static struct nlm_lockowner *nlmsvc_find_lockowner(struct nlm_host *host, pid_t pid) +{ + struct nlm_lockowner *res, *new = NULL; + + spin_lock(&host->h_lock); + res = __nlmsvc_find_lockowner(host, pid); + + if (res == NULL) { + spin_unlock(&host->h_lock); + new = kmalloc(sizeof(*res), GFP_KERNEL); + spin_lock(&host->h_lock); + res = __nlmsvc_find_lockowner(host, pid); + if (res == NULL && new != NULL) { + res = new; + /* fs/locks.c will manage the refcount through lock_ops */ + refcount_set(&new->count, 1); + new->pid = pid; + new->host = nlm_get_host(host); + list_add(&new->list, &host->h_lockowners); + new = NULL; + } + } + + spin_unlock(&host->h_lock); + kfree(new); + return res; +} + +void +nlmsvc_release_lockowner(struct nlm_lock *lock) +{ + if (lock->fl.fl_owner) + nlmsvc_put_lockowner(lock->fl.fl_owner); +} + +static void nlmsvc_locks_copy_lock(struct file_lock *new, struct file_lock *fl) +{ + struct nlm_lockowner *nlm_lo = (struct nlm_lockowner *)fl->fl_owner; + new->fl_owner = nlmsvc_get_lockowner(nlm_lo); +} + +static void nlmsvc_locks_release_private(struct file_lock *fl) +{ + nlmsvc_put_lockowner((struct nlm_lockowner *)fl->fl_owner); +} + +static const struct file_lock_operations nlmsvc_lock_ops = { + .fl_copy_lock = nlmsvc_locks_copy_lock, + .fl_release_private = nlmsvc_locks_release_private, +}; + +void nlmsvc_locks_init_private(struct file_lock *fl, struct nlm_host *host, + pid_t pid) +{ + fl->fl_owner = nlmsvc_find_lockowner(host, pid); + if (fl->fl_owner != NULL) + fl->fl_ops = &nlmsvc_lock_ops; +} + /* * Initialize arguments for GRANTED call. The nlm_rqst structure * has been cleared already. @@ -345,7 +432,7 @@ static int nlmsvc_setgrantargs(struct nlm_rqst *call, struct nlm_lock *lock) /* set default data area */ call->a_args.lock.oh.data = call->a_owner; - call->a_args.lock.svid = lock->fl.fl_pid; + call->a_args.lock.svid = ((struct nlm_lockowner *)lock->fl.fl_owner)->pid; if (lock->oh.len > NLMCLNT_OHSIZE) { void *data = kmalloc(lock->oh.len, GFP_KERNEL); @@ -509,6 +596,7 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, { int error; __be32 ret; + struct nlm_lockowner *test_owner; dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n", locks_inode(file->f_file)->i_sb->s_id, @@ -522,6 +610,9 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } + /* If there's a conflicting lock, remember to clean up the test lock */ + test_owner = (struct nlm_lockowner *)lock->fl.fl_owner; + error = vfs_test_lock(file->f_file, &lock->fl); if (error) { /* We can't currently deal with deferred test requests */ @@ -543,11 +634,16 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, conflock->caller = "somehost"; /* FIXME */ conflock->len = strlen(conflock->caller); conflock->oh.len = 0; /* don't return OH info */ - conflock->svid = lock->fl.fl_pid; + conflock->svid = ((struct nlm_lockowner *)lock->fl.fl_owner)->pid; conflock->fl.fl_type = lock->fl.fl_type; conflock->fl.fl_start = lock->fl.fl_start; conflock->fl.fl_end = lock->fl.fl_end; locks_release_private(&lock->fl); + + /* Clean up the test lock */ + lock->fl.fl_owner = NULL; + nlmsvc_put_lockowner(test_owner); + ret = nlm_lck_denied; out: return ret; @@ -692,25 +788,7 @@ nlmsvc_notify_blocked(struct file_lock *fl) printk(KERN_WARNING "lockd: notification for unknown block!\n"); } -static int nlmsvc_same_owner(struct file_lock *fl1, struct file_lock *fl2) -{ - return fl1->fl_owner == fl2->fl_owner && fl1->fl_pid == fl2->fl_pid; -} - -/* - * Since NLM uses two "keys" for tracking locks, we need to hash them down - * to one for the blocked_hash. Here, we're just xor'ing the host address - * with the pid in order to create a key value for picking a hash bucket. - */ -static unsigned long -nlmsvc_owner_key(struct file_lock *fl) -{ - return (unsigned long)fl->fl_owner ^ (unsigned long)fl->fl_pid; -} - const struct lock_manager_operations nlmsvc_lock_operations = { - .lm_compare_owner = nlmsvc_same_owner, - .lm_owner_key = nlmsvc_owner_key, .lm_notify = nlmsvc_notify_blocked, .lm_grant = nlmsvc_grant_deferred, }; diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index ea77c66d3cc3..d0bb7a6bf005 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -76,8 +76,14 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Set up the missing parts of the file_lock structure */ lock->fl.fl_file = file->f_file; - lock->fl.fl_owner = (fl_owner_t) host; + lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; + nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid); + if (!lock->fl.fl_owner) { + /* lockowner allocation has failed */ + nlmsvc_release_host(host); + return nlm_lck_denied_nolocks; + } } return 0; @@ -125,6 +131,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) dprintk("lockd: TEST status %d vers %d\n", ntohl(resp->status), rqstp->rq_vers); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; @@ -173,6 +180,7 @@ __nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: LOCK status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; @@ -210,6 +218,7 @@ __nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp) resp->status = cast_status(nlmsvc_cancel_blocked(net, file, &argp->lock)); dprintk("lockd: CANCEL status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; @@ -250,6 +259,7 @@ __nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp) resp->status = cast_status(nlmsvc_unlock(net, file, &argp->lock)); dprintk("lockd: UNLOCK status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; @@ -408,6 +418,7 @@ nlmsvc_proc_share(struct svc_rqst *rqstp) resp->status = cast_status(nlmsvc_share_file(host, file, argp)); dprintk("lockd: SHARE status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; @@ -442,6 +453,7 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp) resp->status = cast_status(nlmsvc_unshare_file(host, file, argp)); dprintk("lockd: UNSHARE status %d\n", ntohl(resp->status)); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rpc_success; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 899360ba3b84..028fc152da22 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/lockd/svcsubs.c * @@ -179,7 +180,7 @@ again: /* update current lock count */ file->f_locks++; - lockhost = (struct nlm_host *) fl->fl_owner; + lockhost = ((struct nlm_lockowner *)fl->fl_owner)->host; if (match(lockhost, host)) { struct file_lock lock = *fl; diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 9846f7e95282..982629f7b120 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -126,8 +126,6 @@ nlm_decode_lock(__be32 *p, struct nlm_lock *lock) lock->svid = ntohl(*p++); locks_init_lock(fl); - fl->fl_owner = current->files; - fl->fl_pid = current->tgid; fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; /* as good as anything else */ start = ntohl(*p++); @@ -269,7 +267,6 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) memset(lock, 0, sizeof(*lock)); locks_init_lock(&lock->fl); lock->svid = ~(u32) 0; - lock->fl.fl_pid = current->tgid; if (!(p = nlm_decode_cookie(p, &argp->cookie)) || !(p = xdr_decode_string_inplace(p, &lock->caller, diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 70154f376695..5fa9f48a9dba 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -118,8 +118,6 @@ nlm4_decode_lock(__be32 *p, struct nlm_lock *lock) lock->svid = ntohl(*p++); locks_init_lock(fl); - fl->fl_owner = current->files; - fl->fl_pid = current->tgid; fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; /* as good as anything else */ p = xdr_decode_hyper(p, &start); @@ -266,7 +264,6 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) memset(lock, 0, sizeof(*lock)); locks_init_lock(&lock->fl); lock->svid = ~(u32) 0; - lock->fl.fl_pid = current->tgid; if (!(p = nlm4_decode_cookie(p, &argp->cookie)) || !(p = xdr_decode_string_inplace(p, &lock->caller, diff --git a/fs/locks.c b/fs/locks.c index d7c05dde4ed8..686eae21daf6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/locks.c * @@ -352,6 +353,12 @@ EXPORT_SYMBOL_GPL(locks_alloc_lock); void locks_release_private(struct file_lock *fl) { + BUG_ON(waitqueue_active(&fl->fl_wait)); + BUG_ON(!list_empty(&fl->fl_list)); + BUG_ON(!list_empty(&fl->fl_blocked_requests)); + BUG_ON(!list_empty(&fl->fl_blocked_member)); + BUG_ON(!hlist_unhashed(&fl->fl_link)); + if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); @@ -371,12 +378,6 @@ EXPORT_SYMBOL_GPL(locks_release_private); /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { - BUG_ON(waitqueue_active(&fl->fl_wait)); - BUG_ON(!list_empty(&fl->fl_list)); - BUG_ON(!list_empty(&fl->fl_blocked_requests)); - BUG_ON(!list_empty(&fl->fl_blocked_member)); - BUG_ON(!hlist_unhashed(&fl->fl_link)); - locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } @@ -657,9 +658,6 @@ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) */ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) { - if (fl1->fl_lmops && fl1->fl_lmops->lm_compare_owner) - return fl2->fl_lmops == fl1->fl_lmops && - fl1->fl_lmops->lm_compare_owner(fl1, fl2); return fl1->fl_owner == fl2->fl_owner; } @@ -700,8 +698,6 @@ static void locks_delete_global_locks(struct file_lock *fl) static unsigned long posix_owner_key(struct file_lock *fl) { - if (fl->fl_lmops && fl->fl_lmops->lm_owner_key) - return fl->fl_lmops->lm_owner_key(fl); return (unsigned long)fl->fl_owner; } @@ -1533,11 +1529,21 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) { - if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) - return false; - if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) - return false; - return locks_conflict(breaker, lease); + bool rc; + + if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) { + rc = false; + goto trace; + } + if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) { + rc = false; + goto trace; + } + + rc = locks_conflict(breaker, lease); +trace: + trace_leases_conflict(rc, lease, breaker); + return rc; } static bool @@ -1752,10 +1758,10 @@ int fcntl_getlease(struct file *filp) } /** - * check_conflicting_open - see if the given dentry points to a file that has + * check_conflicting_open - see if the given file points to an inode that has * an existing open that would conflict with the * desired lease. - * @dentry: dentry to check + * @filp: file to check * @arg: type of lease that we're trying to acquire * @flags: current lock flags * @@ -1763,30 +1769,42 @@ int fcntl_getlease(struct file *filp) * conflict with the lease we're trying to set. */ static int -check_conflicting_open(const struct dentry *dentry, const long arg, int flags) +check_conflicting_open(struct file *filp, const long arg, int flags) { - int ret = 0; - struct inode *inode = dentry->d_inode; + struct inode *inode = locks_inode(filp); + int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) return 0; - if ((arg == F_RDLCK) && inode_is_open_for_write(inode)) - return -EAGAIN; + if (arg == F_RDLCK) + return inode_is_open_for_write(inode) ? -EAGAIN : 0; + else if (arg != F_WRLCK) + return 0; - if ((arg == F_WRLCK) && ((d_count(dentry) > 1) || - (atomic_read(&inode->i_count) > 1))) - ret = -EAGAIN; + /* + * Make sure that only read/write count is from lease requestor. + * Note that this will result in denying write leases when i_writecount + * is negative, which is what we want. (We shouldn't grant write leases + * on files open for execution.) + */ + if (filp->f_mode & FMODE_WRITE) + self_wcount = 1; + else if (filp->f_mode & FMODE_READ) + self_rcount = 1; - return ret; + if (atomic_read(&inode->i_writecount) != self_wcount || + atomic_read(&inode->i_readcount) != self_rcount) + return -EAGAIN; + + return 0; } static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct file_lock *fl, *my_fl = NULL, *lease; - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; @@ -1821,7 +1839,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - error = check_conflicting_open(dentry, arg, lease->fl_flags); + error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) goto out; @@ -1878,7 +1896,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * precedes these checks. */ smp_mb(); - error = check_conflicting_open(dentry, arg, lease->fl_flags); + error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) { locks_unlink_lock_ctx(lease); goto out; diff --git a/fs/mbcache.c b/fs/mbcache.c index 081ccf0caee3..97c54d3a2227 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/list.h> diff --git a/fs/minix/Kconfig b/fs/minix/Kconfig index bcd53a79156f..de2003974ff0 100644 --- a/fs/minix/Kconfig +++ b/fs/minix/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config MINIX_FS tristate "Minix file system support" depends on BLOCK diff --git a/fs/minix/Makefile b/fs/minix/Makefile index 3063015abfd0..a2d3ab58d187 100644 --- a/fs/minix/Makefile +++ b/fs/minix/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux minix filesystem routines. # diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 101200761f61..f96073f25432 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/minix/inode.c * diff --git a/fs/namei.c b/fs/namei.c index 20831c2fbb34..209c51a5226c 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3883,6 +3883,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); + fsnotify_rmdir(dir, dentry); out: inode_unlock(dentry->d_inode); @@ -3999,6 +4000,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate if (!error) { dont_mount(dentry); detach_mounts(dentry); + fsnotify_unlink(dir, dentry); } } } diff --git a/fs/namespace.c b/fs/namespace.c index ffb13f0562b0..6fbc9126367a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1,8 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/namespace.c * * (C) Copyright Al Viro 2000, 2001 - * Released under GPL v2. * * Based on code from fs/super.c, copyright Linus Torvalds and others. * Heavily rewritten. @@ -2105,6 +2105,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, /* Notice when we are propagating across user namespaces */ if (child->mnt_parent->mnt_ns->user_ns != user_ns) lock_mnt_tree(child); + child->mnt.mnt_flags &= ~MNT_LOCKED; commit_tree(child); } put_mountpoint(smp); @@ -2595,11 +2596,12 @@ static int do_move_mount(struct path *old_path, struct path *new_path) if (!check_mnt(p)) goto out; - /* The thing moved should be either ours or completely unattached. */ - if (attached && !check_mnt(old)) + /* The thing moved must be mounted... */ + if (!is_mounted(&old->mnt)) goto out; - if (!attached && !(ns && is_anon_ns(ns))) + /* ... and either ours or the root of anon namespace */ + if (!(attached ? check_mnt(old) : is_anon_ns(ns))) goto out; if (old->mnt.mnt_flags & MNT_LOCKED) @@ -3445,6 +3447,7 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags, ns->root = mnt; ns->mounts = 1; list_add(&mnt->mnt_list, &ns->list); + mntget(newmount.mnt); /* Attach to an apparent O_PATH fd with a note that we need to unmount * it, not just simply put it. diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 69d02cf8cf37..295a7a21b774 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config NFS_FS tristate "NFS client support" depends on INET && FILE_LOCKING && MULTIUSER diff --git a/fs/nfs/blocklayout/Makefile b/fs/nfs/blocklayout/Makefile index 3ca14c36d08b..7668a1bfb5fa 100644 --- a/fs/nfs/blocklayout/Makefile +++ b/fs/nfs/blocklayout/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the pNFS block layout driver kernel module # diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 0b602a39dd71..7817ad94a6ba 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -41,11 +41,13 @@ static struct svc_program nfs4_callback_program; static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) { + const struct cred *cred = current_cred(); int ret; struct nfs_net *nn = net_generic(net, nfs_net_id); ret = svc_create_xprt(serv, "tcp", net, PF_INET, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret <= 0) goto out_err; nn->nfs_callback_tcpport = ret; @@ -53,7 +55,8 @@ static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) nn->nfs_callback_tcpport, PF_INET, net->ns.inum); ret = svc_create_xprt(serv, "tcp", net, PF_INET6, - nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); + nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS, + cred); if (ret > 0) { nn->nfs_callback_tcpport6 = ret; dprintk("NFS: Callback listener port = %u (af %u, net %x)\n", @@ -457,4 +460,6 @@ static struct svc_program nfs4_callback_program = { .pg_class = "nfs", /* authentication class */ .pg_stats = &nfs4_callback_stats, .pg_authenticate = nfs_callback_authenticate, + .pg_init_request = svc_generic_init_request, + .pg_rpcbind_set = svc_generic_rpcbind_set, }; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 06233bfa6d73..73a5a5ea2976 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -983,7 +983,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp) out_invalidcred: pr_warn_ratelimited("NFS: NFSv4 callback contains invalid cred\n"); - return rpc_autherr_badcred; + return svc_return_autherr(rqstp, rpc_autherr_badcred); } /* diff --git a/fs/nfs/client.c b/fs/nfs/client.c index da74c4c4a244..d7e4f0848e28 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* client.c: NFS client sharing and management code * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ @@ -558,6 +554,7 @@ static int nfs_start_lockd(struct nfs_server *server) 1 : 0, .net = clp->cl_net, .nlmclnt_ops = clp->cl_nfs_mod->rpc_ops->nlmclnt_ops, + .cred = current_cred(), }; if (nlm_init.nfs_version > 3) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 8b78274e3e56..0ff3facf81da 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/delegation.c * diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 47d445bec8c9..57b6a45576ad 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/dir.c * diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 2436bd92bc00..0cb442406168 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/direct.c * diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index a7d3df85736d..aec769a500a1 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -22,7 +22,8 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, char *ip_addr = NULL; int ip_len; - ip_len = dns_query(NULL, name, namelen, NULL, &ip_addr, NULL); + ip_len = dns_query(net, NULL, name, namelen, NULL, &ip_addr, NULL, + false); if (ip_len > 0) ret = rpc_pton(net, ip_addr, ip_len, sa, salen); else diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 144e183250c3..95dc90570786 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/file.c * diff --git a/fs/nfs/filelayout/Makefile b/fs/nfs/filelayout/Makefile index 8516cdffb9e9..de056312d374 100644 --- a/fs/nfs/filelayout/Makefile +++ b/fs/nfs/filelayout/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the pNFS Files Layout Driver kernel module # diff --git a/fs/nfs/flexfilelayout/Makefile b/fs/nfs/flexfilelayout/Makefile index 1d2c9f6bbcd4..49f03422b6ad 100644 --- a/fs/nfs/flexfilelayout/Makefile +++ b/fs/nfs/flexfilelayout/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the pNFS Flexfile Layout Driver kernel module # diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 9920c52bd0cd..bcff3bf5ae09 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Module for pnfs flexfile layout driver. * diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index a809989807d6..19f856f45689 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -18,7 +18,7 @@ #define NFSDBG_FACILITY NFSDBG_PNFS_LD -static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS; +static unsigned int dataserver_timeo = NFS_DEF_TCP_TIMEO; static unsigned int dataserver_retrans; static bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg); diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c index 666415d13d52..15f271401dcc 100644 --- a/fs/nfs/fscache-index.c +++ b/fs/nfs/fscache-index.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* NFS FS-Cache index structure definition * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/init.h> diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 4dc887813c71..53507aa96b0b 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* NFS filesystem cache interface * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #include <linux/init.h> diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 161ba2edb9d0..25a75e40d91d 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* NFS filesystem cache interface definitions * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. */ #ifndef _NFS_FSCACHE_H diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 391dafaf9182..878c4c5982d9 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* getroot.c: get the root dentry for an NFS mount * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 3bc2550cfe4e..0b4a1a974411 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/inode.c * diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 15f099a24c29..9287eb666322 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/namespace.c * diff --git a/fs/nfs/nfs2super.c b/fs/nfs/nfs2super.c index 0a9782c9171a..467f21ee6a35 100644 --- a/fs/nfs/nfs2super.c +++ b/fs/nfs/nfs2super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2012 Netapp, Inc. All rights reserved. */ diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index 1afdb0f7473f..fb0c425b5d45 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> #include <linux/sunrpc/addr.h> diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c index 5c4394e4656b..7c5809431e61 100644 --- a/fs/nfs/nfs3super.c +++ b/fs/nfs/nfs3super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2012 Netapp, Inc. All rights reserved. */ diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 3ce246346f02..81b9b6d7927a 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index cf42a8b939e3..f4157eb1f69d 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -129,10 +129,13 @@ nfs4_file_flush(struct file *file, fl_owner_t id) } #ifdef CONFIG_NFS_V4_2 -static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - size_t count, unsigned int flags) +static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t count, unsigned int flags) { + /* Only offload copy if superblock is the same */ + if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) + return -EXDEV; if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY)) return -EOPNOTSUPP; if (file_inode(file_in) == file_inode(file_out)) @@ -140,6 +143,20 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count); } +static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t count, unsigned int flags) +{ + ssize_t ret; + + ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count, + flags); + if (ret == -EOPNOTSUPP || ret == -EXDEV) + ret = generic_copy_file_range(file_in, pos_in, file_out, + pos_out, count, flags); + return ret; +} + static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) { loff_t ret; diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 4884fdae28fb..1e7296395d71 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -291,7 +291,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen, if (IS_ERR(rkey)) { mutex_lock(&idmap->idmap_mutex); rkey = request_key_with_auxdata(&key_type_id_resolver_legacy, - desc, "", 0, idmap); + desc, NULL, "", 0, idmap); mutex_unlock(&idmap->idmap_mutex); } if (!IS_ERR(rkey)) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c29cbef6b53f..6418cb6c079b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1256,10 +1256,20 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, atomic_inc(&sp->so_count); p->o_arg.open_flags = flags; p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE); - p->o_arg.umask = current_umask(); p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim); p->o_arg.share_access = nfs4_map_atomic_open_share(server, fmode, flags); + if (flags & O_CREAT) { + p->o_arg.umask = current_umask(); + p->o_arg.label = nfs4_label_copy(p->a_label, label); + if (c->sattr != NULL && c->sattr->ia_valid != 0) { + p->o_arg.u.attrs = &p->attrs; + memcpy(&p->attrs, c->sattr, sizeof(p->attrs)); + + memcpy(p->o_arg.u.verifier.data, c->verf, + sizeof(p->o_arg.u.verifier.data)); + } + } /* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS * will return permission denied for all bits until close */ if (!(flags & O_EXCL)) { @@ -1283,7 +1293,6 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.server = server; p->o_arg.bitmask = nfs4_bitmask(server, label); p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0]; - p->o_arg.label = nfs4_label_copy(p->a_label, label); switch (p->o_arg.claim) { case NFS4_OPEN_CLAIM_NULL: case NFS4_OPEN_CLAIM_DELEGATE_CUR: @@ -1296,13 +1305,6 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, case NFS4_OPEN_CLAIM_DELEG_PREV_FH: p->o_arg.fh = NFS_FH(d_inode(dentry)); } - if (c != NULL && c->sattr != NULL && c->sattr->ia_valid != 0) { - p->o_arg.u.attrs = &p->attrs; - memcpy(&p->attrs, c->sattr, sizeof(p->attrs)); - - memcpy(p->o_arg.u.verifier.data, c->verf, - sizeof(p->o_arg.u.verifier.data)); - } p->c_arg.fh = &p->o_res.fh; p->c_arg.stateid = &p->o_res.stateid; p->c_arg.seqid = p->o_arg.seqid; @@ -6932,7 +6934,6 @@ struct nfs4_lock_waiter { struct task_struct *task; struct inode *inode; struct nfs_lowner *owner; - bool notified; }; static int @@ -6954,13 +6955,13 @@ nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, vo /* Make sure it's for the right inode */ if (nfs_compare_fh(NFS_FH(waiter->inode), &cbnl->cbnl_fh)) return 0; - - waiter->notified = true; } /* override "private" so we can use default_wake_function */ wait->private = waiter->task; - ret = autoremove_wake_function(wait, mode, flags, key); + ret = woken_wake_function(wait, mode, flags, key); + if (ret) + list_del_init(&wait->entry); wait->private = waiter; return ret; } @@ -6969,7 +6970,6 @@ static int nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) { int status = -ERESTARTSYS; - unsigned long flags; struct nfs4_lock_state *lsp = request->fl_u.nfs4_fl.owner; struct nfs_server *server = NFS_SERVER(state->inode); struct nfs_client *clp = server->nfs_client; @@ -6979,8 +6979,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) .s_dev = server->s_dev }; struct nfs4_lock_waiter waiter = { .task = current, .inode = state->inode, - .owner = &owner, - .notified = false }; + .owner = &owner}; wait_queue_entry_t wait; /* Don't bother with waitqueue if we don't expect a callback */ @@ -6990,27 +6989,22 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) init_wait(&wait); wait.private = &waiter; wait.func = nfs4_wake_lock_waiter; - add_wait_queue(q, &wait); while(!signalled()) { - waiter.notified = false; + add_wait_queue(q, &wait); status = nfs4_proc_setlk(state, cmd, request); - if ((status != -EAGAIN) || IS_SETLK(cmd)) + if ((status != -EAGAIN) || IS_SETLK(cmd)) { + finish_wait(q, &wait); break; - - status = -ERESTARTSYS; - spin_lock_irqsave(&q->lock, flags); - if (waiter.notified) { - spin_unlock_irqrestore(&q->lock, flags); - continue; } - set_current_state(TASK_INTERRUPTIBLE); - spin_unlock_irqrestore(&q->lock, flags); - freezable_schedule_timeout(NFS4_LOCK_MAXTIMEOUT); + status = -ERESTARTSYS; + freezer_do_not_count(); + wait_woken(&wait, TASK_INTERRUPTIBLE, NFS4_LOCK_MAXTIMEOUT); + freezer_count(); + finish_wait(q, &wait); } - finish_wait(q, &wait); return status; } #else /* !CONFIG_NFS_V4_1 */ diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index bcb532def9e2..4145a0138907 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/nfs/nfs4session.c * diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 689977e148cb..04c57066a11a 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2012 Bryan Schumaker <bjschuma@netapp.com> */ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 6ec30014a439..6ef5278326b6 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/pagelist.c * diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index f5ad75fafc3c..c0046c348910 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Common NFS I/O operations for the pnfs file based * layout drivers. diff --git a/fs/nfs/read.c b/fs/nfs/read.c index c799e540ed1e..c19841c82b6a 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/read.c * diff --git a/fs/nfs/super.c b/fs/nfs/super.c index d6c687419a81..f88ddac2dcdf 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/super.c * diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 52d533967485..0effeee28352 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -396,12 +396,6 @@ nfs_complete_sillyrename(struct rpc_task *task, struct nfs_renamedata *data) nfs_cancel_async_unlink(dentry); return; } - - /* - * vfs_unlink and the like do not issue this when a file is - * sillyrenamed, so do it here. - */ - fsnotify_nameremove(dentry, 0); } #define SILLYNAME_PREFIX ".nfs" diff --git a/fs/nfs/write.c b/fs/nfs/write.c index bc5bb9323412..059a7c38bc4f 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/write.c * diff --git a/fs/nfs_common/Makefile b/fs/nfs_common/Makefile index d153ca3ea577..4bebe834c009 100644 --- a/fs/nfs_common/Makefile +++ b/fs/nfs_common/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for Linux filesystem routines that are shared by client and server. # diff --git a/fs/nfs_common/grace.c b/fs/nfs_common/grace.c index 5be08f02a76b..b73d9dd37f73 100644 --- a/fs/nfs_common/grace.c +++ b/fs/nfs_common/grace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Common code for control of lockd and nfsv4 grace periods. * diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c index 538f142935ea..8ceb6425e01a 100644 --- a/fs/nfs_common/nfsacl.c +++ b/fs/nfs_common/nfsacl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/nfs_common/nfsacl.c * diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 20b1c17320d5..d25f6bbe7006 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config NFSD tristate "NFS server support" depends on INET diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 4fb1f72a25fb..66d4c55eb48e 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -121,15 +121,13 @@ nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp, { loff_t new_size = lcp->lc_last_wr + 1; struct iattr iattr = { .ia_valid = 0 }; - struct timespec ts; int error; - ts = timespec64_to_timespec(inode->i_mtime); if (lcp->lc_mtime.tv_nsec == UTIME_NOW || - timespec_compare(&lcp->lc_mtime, &ts) < 0) - lcp->lc_mtime = timespec64_to_timespec(current_time(inode)); + timespec64_compare(&lcp->lc_mtime, &inode->i_mtime) < 0) + lcp->lc_mtime = current_time(inode); iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME; - iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = timespec_to_timespec64(lcp->lc_mtime); + iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime; if (new_size > i_size_read(inode)) { iattr.ia_valid |= ATTR_SIZE; diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 4a98537efb0f..10ec5ecdf117 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -10,6 +10,7 @@ #define NFSCACHE_H #include <linux/sunrpc/svc.h> +#include "netns.h" /* * Representation of a reply cache entry. @@ -77,8 +78,8 @@ enum { /* Checksum this amount of the request */ #define RC_CSUMLEN (256U) -int nfsd_reply_cache_init(void); -void nfsd_reply_cache_shutdown(void); +int nfsd_reply_cache_init(struct nfsd_net *); +void nfsd_reply_cache_shutdown(struct nfsd_net *); int nfsd_cache_lookup(struct svc_rqst *); void nfsd_cache_update(struct svc_rqst *, int, __be32 *); int nfsd_reply_cache_stats_open(struct inode *, struct file *); diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 802993d8912f..baa01956a5b3 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -570,13 +570,13 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) err = get_int(&mesg, &an_int); if (err) goto out3; - exp.ex_anon_uid= make_kuid(&init_user_ns, an_int); + exp.ex_anon_uid= make_kuid(current_user_ns(), an_int); /* anon gid */ err = get_int(&mesg, &an_int); if (err) goto out3; - exp.ex_anon_gid= make_kgid(&init_user_ns, an_int); + exp.ex_anon_gid= make_kgid(current_user_ns(), an_int); /* fsid */ err = get_int(&mesg, &an_int); @@ -1170,15 +1170,17 @@ static void show_secinfo(struct seq_file *m, struct svc_export *exp) static void exp_flags(struct seq_file *m, int flag, int fsid, kuid_t anonu, kgid_t anong, struct nfsd4_fs_locations *fsloc) { + struct user_namespace *userns = m->file->f_cred->user_ns; + show_expflags(m, flag, NFSEXP_ALLFLAGS); if (flag & NFSEXP_FSID) seq_printf(m, ",fsid=%d", fsid); - if (!uid_eq(anonu, make_kuid(&init_user_ns, (uid_t)-2)) && - !uid_eq(anonu, make_kuid(&init_user_ns, 0x10000-2))) - seq_printf(m, ",anonuid=%u", from_kuid(&init_user_ns, anonu)); - if (!gid_eq(anong, make_kgid(&init_user_ns, (gid_t)-2)) && - !gid_eq(anong, make_kgid(&init_user_ns, 0x10000-2))) - seq_printf(m, ",anongid=%u", from_kgid(&init_user_ns, anong)); + if (!uid_eq(anonu, make_kuid(userns, (uid_t)-2)) && + !uid_eq(anonu, make_kuid(userns, 0x10000-2))) + seq_printf(m, ",anonuid=%u", from_kuid_munged(userns, anonu)); + if (!gid_eq(anong, make_kgid(userns, (gid_t)-2)) && + !gid_eq(anong, make_kgid(userns, 0x10000-2))) + seq_printf(m, ",anongid=%u", from_kgid_munged(userns, anong)); if (fsloc && fsloc->locations_count > 0) { char *loctype = (fsloc->migrated) ? "refer" : "replicas"; int i; diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c index 84831253203d..76bee0a0d308 100644 --- a/fs/nfsd/fault_inject.c +++ b/fs/nfsd/fault_inject.c @@ -127,24 +127,16 @@ static struct nfsd_fault_inject_op inject_ops[] = { }, }; -int nfsd_fault_inject_init(void) +void nfsd_fault_inject_init(void) { unsigned int i; struct nfsd_fault_inject_op *op; umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; debug_dir = debugfs_create_dir("nfsd", NULL); - if (!debug_dir) - goto fail; for (i = 0; i < ARRAY_SIZE(inject_ops); i++) { op = &inject_ops[i]; - if (!debugfs_create_file(op->file, mode, debug_dir, op, &fops_nfsd)) - goto fail; + debugfs_create_file(op->file, mode, debug_dir, op, &fops_nfsd); } - return 0; - -fail: - nfsd_fault_inject_cleanup(); - return -ENOMEM; } diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 32cb8c027483..bdfe5bcb3dcd 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -1,21 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * per net namespace data structures for nfsd * * Copyright (C) 2012, Jeff Layton <jlayton@redhat.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ #ifndef __NFSD_NETNS_H__ @@ -55,6 +42,11 @@ struct nfsd_net { bool grace_ended; time_t boot_time; + /* internal mount of the "nfsd" pseudofilesystem: */ + struct vfsmount *nfsd_mnt; + + struct dentry *nfsd_client_dir; + /* * reclaim_str_hashtbl[] holds known client info from previous reset/reboot * used in reboot/reset lease grace period processing @@ -104,6 +96,9 @@ struct nfsd_net { time_t nfsd4_grace; bool somebody_reclaimed; + bool track_reclaim_completes; + atomic_t nr_reclaim_complete; + bool nfsd_net_up; bool lockd_up; @@ -116,6 +111,7 @@ struct nfsd_net { */ unsigned int max_connections; + u32 clientid_base; u32 clientid_counter; u32 clverifier_counter; @@ -131,10 +127,56 @@ struct nfsd_net { u32 s2s_cp_cl_id; struct idr s2s_cp_stateids; spinlock_t s2s_cp_lock; + + /* + * Version information + */ + bool *nfsd_versions; + bool *nfsd4_minorversions; + + /* + * Duplicate reply cache + */ + struct nfsd_drc_bucket *drc_hashtbl; + struct kmem_cache *drc_slab; + + /* max number of entries allowed in the cache */ + unsigned int max_drc_entries; + + /* number of significant bits in the hash value */ + unsigned int maskbits; + unsigned int drc_hashsize; + + /* + * 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. + */ + + /* 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; + + /* longest hash chain seen */ + unsigned int longest_chain; + + /* size of cache when we saw the longest hash chain */ + unsigned int longest_chain_cachesize; + + struct shrinker nfsd_reply_cache_shrinker; }; /* Simple check to find out if a given net was properly initialized */ #define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl) +extern void nfsd_netns_free_versions(struct nfsd_net *nn); + extern unsigned int nfsd_net_id; #endif /* __NFSD_NETNS_H__ */ diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 8d789124ed3c..fcf31822c74c 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -96,7 +96,7 @@ decode_filename(__be32 *p, char **namp, unsigned int *lenp) } static __be32 * -decode_sattr3(__be32 *p, struct iattr *iap) +decode_sattr3(__be32 *p, struct iattr *iap, struct user_namespace *userns) { u32 tmp; @@ -107,12 +107,12 @@ decode_sattr3(__be32 *p, struct iattr *iap) iap->ia_mode = ntohl(*p++); } if (*p++) { - iap->ia_uid = make_kuid(&init_user_ns, ntohl(*p++)); + iap->ia_uid = make_kuid(userns, ntohl(*p++)); if (uid_valid(iap->ia_uid)) iap->ia_valid |= ATTR_UID; } if (*p++) { - iap->ia_gid = make_kgid(&init_user_ns, ntohl(*p++)); + iap->ia_gid = make_kgid(userns, ntohl(*p++)); if (gid_valid(iap->ia_gid)) iap->ia_valid |= ATTR_GID; } @@ -165,12 +165,13 @@ static __be32 * encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat) { + struct user_namespace *userns = nfsd_user_namespace(rqstp); struct timespec ts; *p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]); *p++ = htonl((u32) (stat->mode & S_IALLUGO)); *p++ = htonl((u32) stat->nlink); - *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid)); - *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid)); + *p++ = htonl((u32) from_kuid_munged(userns, stat->uid)); + *p++ = htonl((u32) from_kgid_munged(userns, stat->gid)); if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN) { p = xdr_encode_hyper(p, (u64) NFS3_MAXPATHLEN); } else { @@ -325,7 +326,7 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) p = decode_fh(p, &args->fh); if (!p) return 0; - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); if ((args->check_guard = ntohl(*p++)) != 0) { struct timespec time; @@ -455,7 +456,7 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) switch (args->createmode = ntohl(*p++)) { case NFS3_CREATE_UNCHECKED: case NFS3_CREATE_GUARDED: - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); break; case NFS3_CREATE_EXCLUSIVE: args->verf = p; @@ -476,7 +477,7 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) if (!(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); return xdr_argsize_check(rqstp, p); } @@ -491,7 +492,7 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) if (!(p = decode_fh(p, &args->ffh)) || !(p = decode_filename(p, &args->fname, &args->flen))) return 0; - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); args->tlen = ntohl(*p++); @@ -519,7 +520,7 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) if (args->ftype == NF3BLK || args->ftype == NF3CHR || args->ftype == NF3SOCK || args->ftype == NF3FIFO) - p = decode_sattr3(p, &args->attrs); + p = decode_sattr3(p, &args->attrs, nfsd_user_namespace(rqstp)); if (args->ftype == NF3BLK || args->ftype == NF3CHR) { args->major = ntohl(*p++); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 9b93e7a9a26d..397eb7820929 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1123,10 +1123,11 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) rpc_restart_call_prepare(task); return; case 1: - break; - case -1: - /* Network partition? */ - nfsd4_mark_cb_down(clp, task->tk_status); + switch (task->tk_status) { + case -EIO: + case -ETIMEDOUT: + nfsd4_mark_cb_down(clp, task->tk_status); + } break; default: BUG(); diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index bf137fec33ff..d1f285245af8 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -83,7 +83,7 @@ ent_init(struct cache_head *cnew, struct cache_head *citm) new->type = itm->type; strlcpy(new->name, itm->name, sizeof(new->name)); - strlcpy(new->authname, itm->authname, sizeof(new->name)); + strlcpy(new->authname, itm->authname, sizeof(new->authname)); } static void @@ -634,7 +634,7 @@ nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen, return nfserr_inval; status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id); - *uid = make_kuid(&init_user_ns, id); + *uid = make_kuid(nfsd_user_namespace(rqstp), id); if (!uid_valid(*uid)) status = nfserr_badowner; return status; @@ -651,7 +651,7 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, return nfserr_inval; status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id); - *gid = make_kgid(&init_user_ns, id); + *gid = make_kgid(nfsd_user_namespace(rqstp), id); if (!gid_valid(*gid)) status = nfserr_badowner; return status; @@ -660,13 +660,13 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, __be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp, kuid_t uid) { - u32 id = from_kuid(&init_user_ns, uid); + u32 id = from_kuid_munged(nfsd_user_namespace(rqstp), uid); return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id); } __be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp, kgid_t gid) { - u32 id = from_kgid(&init_user_ns, gid); + u32 id = from_kgid_munged(nfsd_user_namespace(rqstp), gid); return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id); } diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 44517fb5c0de..a79e24b79095 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -693,7 +693,7 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) ops->fence_client(ls); else nfsd4_cb_layout_fail(ls); - return -1; + return 1; case -NFS4ERR_NOMATCHING_LAYOUT: trace_nfsd_layout_recall_done(&ls->ls_stid.sc_stateid); task->tk_status = 0; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 4680ad3bf55b..8beda999e134 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1927,6 +1927,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) struct nfsd4_compound_state *cstate = &resp->cstate; struct svc_fh *current_fh = &cstate->current_fh; struct svc_fh *save_fh = &cstate->save_fh; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); __be32 status; svcxdr_init_encode(rqstp, resp); @@ -1949,7 +1950,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) * According to RFC3010, this takes precedence over all other errors. */ status = nfserr_minor_vers_mismatch; - if (nfsd_minorversion(args->minorversion, NFSD_TEST) <= 0) + if (nfsd_minorversion(nn, args->minorversion, NFSD_TEST) <= 0) goto out; status = nfserr_resource; if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND) diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 8c8563441208..87679557d0d6 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -169,12 +169,33 @@ legacy_recdir_name_error(struct nfs4_client *clp, int error) } static void +__nfsd4_create_reclaim_record_grace(struct nfs4_client *clp, + const char *dname, int len, struct nfsd_net *nn) +{ + struct xdr_netobj name; + struct nfs4_client_reclaim *crp; + + name.data = kmemdup(dname, len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return; + } + name.len = len; + crp = nfs4_client_to_reclaim(name, nn); + if (!crp) { + kfree(name.data); + return; + } + crp->cr_clp = clp; +} + +static void nfsd4_create_clid_dir(struct nfs4_client *clp) { const struct cred *original_cred; char dname[HEXDIR_LEN]; struct dentry *dir, *dentry; - struct nfs4_client_reclaim *crp; int status; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -220,11 +241,9 @@ out_put: out_unlock: inode_unlock(d_inode(dir)); if (status == 0) { - if (nn->in_grace) { - crp = nfs4_client_to_reclaim(dname, nn); - if (crp) - crp->cr_clp = clp; - } + if (nn->in_grace) + __nfsd4_create_reclaim_record_grace(clp, dname, + HEXDIR_LEN, nn); vfs_fsync(nn->rec_file, 0); } else { printk(KERN_ERR "NFSD: failed to write recovery record" @@ -345,10 +364,29 @@ out_unlock: } static void +__nfsd4_remove_reclaim_record_grace(const char *dname, int len, + struct nfsd_net *nn) +{ + struct xdr_netobj name; + struct nfs4_client_reclaim *crp; + + name.data = kmemdup(dname, len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return; + } + name.len = len; + crp = nfsd4_find_reclaim_client(name, nn); + kfree(name.data); + if (crp) + nfs4_remove_reclaim_record(crp, nn); +} + +static void nfsd4_remove_clid_dir(struct nfs4_client *clp) { const struct cred *original_cred; - struct nfs4_client_reclaim *crp; char dname[HEXDIR_LEN]; int status; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -373,12 +411,9 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) nfs4_reset_creds(original_cred); if (status == 0) { vfs_fsync(nn->rec_file, 0); - if (nn->in_grace) { - /* remove reclaim record */ - crp = nfsd4_find_reclaim_client(dname, nn); - if (crp) - nfs4_remove_reclaim_record(crp, nn); - } + if (nn->in_grace) + __nfsd4_remove_reclaim_record_grace(dname, + HEXDIR_LEN, nn); } out_drop_write: mnt_drop_write_file(nn->rec_file); @@ -392,14 +427,31 @@ static int purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) { int status; + struct xdr_netobj name; - if (nfs4_has_reclaimed_state(child->d_name.name, nn)) + if (child->d_name.len != HEXDIR_LEN - 1) { + printk("%s: illegal name %pd in recovery directory\n", + __func__, child); + /* Keep trying; maybe the others are OK: */ return 0; + } + name.data = kmemdup_nul(child->d_name.name, child->d_name.len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + goto out; + } + name.len = HEXDIR_LEN; + if (nfs4_has_reclaimed_state(name, nn)) + goto out_free; status = vfs_rmdir(d_inode(parent), child); if (status) printk("failed to remove client recovery directory %pd\n", child); +out_free: + kfree(name.data); +out: /* Keep trying, success or failure: */ return 0; } @@ -429,13 +481,24 @@ out: static int load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) { + struct xdr_netobj name; + if (child->d_name.len != HEXDIR_LEN - 1) { - printk("nfsd4: illegal name %pd in recovery directory\n", - child); + printk("%s: illegal name %pd in recovery directory\n", + __func__, child); /* Keep trying; maybe the others are OK: */ return 0; } - nfs4_client_to_reclaim(child->d_name.name, nn); + name.data = kmemdup_nul(child->d_name.name, child->d_name.len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + goto out; + } + name.len = HEXDIR_LEN; + if (!nfs4_client_to_reclaim(name, nn)) + kfree(name.data); +out: return 0; } @@ -564,6 +627,7 @@ nfsd4_legacy_tracking_init(struct net *net) status = nfsd4_load_reboot_recovery_data(net); if (status) goto err; + printk("NFSD: Using legacy client tracking operations.\n"); return 0; err: @@ -615,6 +679,7 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) char dname[HEXDIR_LEN]; struct nfs4_client_reclaim *crp; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + struct xdr_netobj name; /* did we already find that this client is stable? */ if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) @@ -627,13 +692,22 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) } /* look for it in the reclaim hashtable otherwise */ - crp = nfsd4_find_reclaim_client(dname, nn); + name.data = kmemdup(dname, HEXDIR_LEN, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + goto out_enoent; + } + name.len = HEXDIR_LEN; + crp = nfsd4_find_reclaim_client(name, nn); + kfree(name.data); if (crp) { set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); crp->cr_clp = clp; return 0; } +out_enoent: return -ENOENT; } @@ -656,6 +730,7 @@ struct cld_net { spinlock_t cn_lock; struct list_head cn_list; unsigned int cn_xid; + bool cn_has_legacy; }; struct cld_upcall { @@ -706,6 +781,40 @@ cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg) } static ssize_t +__cld_pipe_inprogress_downcall(const struct cld_msg __user *cmsg, + struct nfsd_net *nn) +{ + uint8_t cmd; + struct xdr_netobj name; + uint16_t namelen; + struct cld_net *cn = nn->cld_net; + + if (get_user(cmd, &cmsg->cm_cmd)) { + dprintk("%s: error when copying cmd from userspace", __func__); + return -EFAULT; + } + if (cmd == Cld_GraceStart) { + if (get_user(namelen, &cmsg->cm_u.cm_name.cn_len)) + return -EFAULT; + name.data = memdup_user(&cmsg->cm_u.cm_name.cn_id, namelen); + if (IS_ERR_OR_NULL(name.data)) + return -EFAULT; + name.len = namelen; + if (name.len > 5 && memcmp(name.data, "hash:", 5) == 0) { + name.len = name.len - 5; + memmove(name.data, name.data + 5, name.len); + cn->cn_has_legacy = true; + } + if (!nfs4_client_to_reclaim(name, nn)) { + kfree(name.data); + return -EFAULT; + } + return sizeof(*cmsg); + } + return -EFAULT; +} + +static ssize_t cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct cld_upcall *tmp, *cup; @@ -714,6 +823,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) struct nfsd_net *nn = net_generic(file_inode(filp)->i_sb->s_fs_info, nfsd_net_id); struct cld_net *cn = nn->cld_net; + int16_t status; if (mlen != sizeof(*cmsg)) { dprintk("%s: got %zu bytes, expected %zu\n", __func__, mlen, @@ -727,13 +837,24 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) return -EFAULT; } + /* + * copy the status so we know whether to remove the upcall from the + * list (for -EINPROGRESS, we just want to make sure the xid is + * valid, not remove the upcall from the list) + */ + if (get_user(status, &cmsg->cm_status)) { + dprintk("%s: error when copying status from userspace", __func__); + return -EFAULT; + } + /* walk the list and find corresponding xid */ cup = NULL; spin_lock(&cn->cn_lock); list_for_each_entry(tmp, &cn->cn_list, cu_list) { if (get_unaligned(&tmp->cu_msg.cm_xid) == xid) { cup = tmp; - list_del_init(&cup->cu_list); + if (status != -EINPROGRESS) + list_del_init(&cup->cu_list); break; } } @@ -745,6 +866,9 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) return -EINVAL; } + if (status == -EINPROGRESS) + return __cld_pipe_inprogress_downcall(cmsg, nn); + if (copy_from_user(&cup->cu_msg, src, mlen) != 0) return -EFAULT; @@ -820,7 +944,7 @@ nfsd4_cld_unregister_net(struct net *net, struct rpc_pipe *pipe) /* Initialize rpc_pipefs pipe for communication with client tracking daemon */ static int -nfsd4_init_cld_pipe(struct net *net) +__nfsd4_init_cld_pipe(struct net *net) { int ret; struct dentry *dentry; @@ -851,6 +975,7 @@ nfsd4_init_cld_pipe(struct net *net) } cn->cn_pipe->dentry = dentry; + cn->cn_has_legacy = false; nn->cld_net = cn; return 0; @@ -863,6 +988,17 @@ err: return ret; } +static int +nfsd4_init_cld_pipe(struct net *net) +{ + int status; + + status = __nfsd4_init_cld_pipe(net); + if (!status) + printk("NFSD: Using old nfsdcld client tracking operations.\n"); + return status; +} + static void nfsd4_remove_cld_pipe(struct net *net) { @@ -991,9 +1127,14 @@ out_err: "record from stable storage: %d\n", ret); } -/* Check for presence of a record, and update its timestamp */ +/* + * For older nfsdcld's that do not allow us to "slurp" the clients + * from the tracking database during startup. + * + * Check for presence of a record, and update its timestamp + */ static int -nfsd4_cld_check(struct nfs4_client *clp) +nfsd4_cld_check_v0(struct nfs4_client *clp) { int ret; struct cld_upcall *cup; @@ -1026,8 +1167,84 @@ nfsd4_cld_check(struct nfs4_client *clp) return ret; } +/* + * For newer nfsdcld's that allow us to "slurp" the clients + * from the tracking database during startup. + * + * Check for presence of a record in the reclaim_str_hashtbl + */ +static int +nfsd4_cld_check(struct nfs4_client *clp) +{ + struct nfs4_client_reclaim *crp; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + struct cld_net *cn = nn->cld_net; + int status; + char dname[HEXDIR_LEN]; + struct xdr_netobj name; + + /* did we already find that this client is stable? */ + if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags)) + return 0; + + /* look for it in the reclaim hashtable otherwise */ + crp = nfsd4_find_reclaim_client(clp->cl_name, nn); + if (crp) + goto found; + + if (cn->cn_has_legacy) { + status = nfs4_make_rec_clidname(dname, &clp->cl_name); + if (status) + return -ENOENT; + + name.data = kmemdup(dname, HEXDIR_LEN, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return -ENOENT; + } + name.len = HEXDIR_LEN; + crp = nfsd4_find_reclaim_client(name, nn); + kfree(name.data); + if (crp) + goto found; + + } + return -ENOENT; +found: + crp->cr_clp = clp; + return 0; +} + +static int +nfsd4_cld_grace_start(struct nfsd_net *nn) +{ + int ret; + struct cld_upcall *cup; + struct cld_net *cn = nn->cld_net; + + cup = alloc_cld_upcall(cn); + if (!cup) { + ret = -ENOMEM; + goto out_err; + } + + cup->cu_msg.cm_cmd = Cld_GraceStart; + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg); + if (!ret) + ret = cup->cu_msg.cm_status; + + free_cld_upcall(cup); +out_err: + if (ret) + dprintk("%s: Unable to get clients from userspace: %d\n", + __func__, ret); + return ret; +} + +/* For older nfsdcld's that need cm_gracetime */ static void -nfsd4_cld_grace_done(struct nfsd_net *nn) +nfsd4_cld_grace_done_v0(struct nfsd_net *nn) { int ret; struct cld_upcall *cup; @@ -1051,11 +1268,149 @@ out_err: printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret); } -static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = { +/* + * For newer nfsdcld's that do not need cm_gracetime. We also need to call + * nfs4_release_reclaim() to clear out the reclaim_str_hashtbl. + */ +static void +nfsd4_cld_grace_done(struct nfsd_net *nn) +{ + int ret; + struct cld_upcall *cup; + struct cld_net *cn = nn->cld_net; + + cup = alloc_cld_upcall(cn); + if (!cup) { + ret = -ENOMEM; + goto out_err; + } + + cup->cu_msg.cm_cmd = Cld_GraceDone; + ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg); + if (!ret) + ret = cup->cu_msg.cm_status; + + free_cld_upcall(cup); +out_err: + nfs4_release_reclaim(nn); + if (ret) + printk(KERN_ERR "NFSD: Unable to end grace period: %d\n", ret); +} + +static int +nfs4_cld_state_init(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + int i; + + nn->reclaim_str_hashtbl = kmalloc_array(CLIENT_HASH_SIZE, + sizeof(struct list_head), + GFP_KERNEL); + if (!nn->reclaim_str_hashtbl) + return -ENOMEM; + + for (i = 0; i < CLIENT_HASH_SIZE; i++) + INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]); + nn->reclaim_str_hashtbl_size = 0; + nn->track_reclaim_completes = true; + atomic_set(&nn->nr_reclaim_complete, 0); + + return 0; +} + +static void +nfs4_cld_state_shutdown(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nn->track_reclaim_completes = false; + kfree(nn->reclaim_str_hashtbl); +} + +static bool +cld_running(struct nfsd_net *nn) +{ + struct cld_net *cn = nn->cld_net; + struct rpc_pipe *pipe = cn->cn_pipe; + + return pipe->nreaders || pipe->nwriters; +} + +static int +nfsd4_cld_tracking_init(struct net *net) +{ + int status; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + bool running; + int retries = 10; + + status = nfs4_cld_state_init(net); + if (status) + return status; + + status = __nfsd4_init_cld_pipe(net); + if (status) + goto err_shutdown; + + /* + * rpc pipe upcalls take 30 seconds to time out, so we don't want to + * queue an upcall unless we know that nfsdcld is running (because we + * want this to fail fast so that nfsd4_client_tracking_init() can try + * the next client tracking method). nfsdcld should already be running + * before nfsd is started, so the wait here is for nfsdcld to open the + * pipefs file we just created. + */ + while (!(running = cld_running(nn)) && retries--) + msleep(100); + + if (!running) { + status = -ETIMEDOUT; + goto err_remove; + } + + status = nfsd4_cld_grace_start(nn); + if (status) { + if (status == -EOPNOTSUPP) + printk(KERN_WARNING "NFSD: Please upgrade nfsdcld.\n"); + nfs4_release_reclaim(nn); + goto err_remove; + } else + printk("NFSD: Using nfsdcld client tracking operations.\n"); + return 0; + +err_remove: + nfsd4_remove_cld_pipe(net); +err_shutdown: + nfs4_cld_state_shutdown(net); + return status; +} + +static void +nfsd4_cld_tracking_exit(struct net *net) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + nfs4_release_reclaim(nn); + nfsd4_remove_cld_pipe(net); + nfs4_cld_state_shutdown(net); +} + +/* For older nfsdcld's */ +static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops_v0 = { .init = nfsd4_init_cld_pipe, .exit = nfsd4_remove_cld_pipe, .create = nfsd4_cld_create, .remove = nfsd4_cld_remove, + .check = nfsd4_cld_check_v0, + .grace_done = nfsd4_cld_grace_done_v0, +}; + +/* For newer nfsdcld's */ +static const struct nfsd4_client_tracking_ops nfsd4_cld_tracking_ops = { + .init = nfsd4_cld_tracking_init, + .exit = nfsd4_cld_tracking_exit, + .create = nfsd4_cld_create, + .remove = nfsd4_cld_remove, .check = nfsd4_cld_check, .grace_done = nfsd4_cld_grace_done, }; @@ -1267,6 +1622,8 @@ nfsd4_umh_cltrack_init(struct net *net) ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL); kfree(grace_start); + if (!ret) + printk("NFSD: Using UMH upcall client tracking operations.\n"); return ret; } @@ -1416,9 +1773,20 @@ nfsd4_client_tracking_init(struct net *net) if (nn->client_tracking_ops) goto do_init; + /* First, try to use nfsdcld */ + nn->client_tracking_ops = &nfsd4_cld_tracking_ops; + status = nn->client_tracking_ops->init(net); + if (!status) + return status; + if (status != -ETIMEDOUT) { + nn->client_tracking_ops = &nfsd4_cld_tracking_ops_v0; + status = nn->client_tracking_ops->init(net); + if (!status) + return status; + } + /* - * First, try a UMH upcall. It should succeed or fail quickly, so - * there's little harm in trying that first. + * Next, try the UMH upcall. */ nn->client_tracking_ops = &nfsd4_umh_tracking_ops; status = nn->client_tracking_ops->init(net); @@ -1426,25 +1794,23 @@ nfsd4_client_tracking_init(struct net *net) return status; /* - * See if the recoverydir exists and is a directory. If it is, - * then use the legacy ops. + * Finally, See if the recoverydir exists and is a directory. + * If it is, then use the legacy ops. */ nn->client_tracking_ops = &nfsd4_legacy_tracking_ops; status = kern_path(nfs4_recoverydir(), LOOKUP_FOLLOW, &path); if (!status) { status = d_is_dir(path.dentry); path_put(&path); - if (status) - goto do_init; + if (!status) { + status = -EINVAL; + goto out; + } } - /* Finally, try to use nfsdcld */ - nn->client_tracking_ops = &nfsd4_cld_tracking_ops; - printk(KERN_WARNING "NFSD: the nfsdcld client tracking upcall will be " - "removed in 3.10. Please transition to using " - "nfsdcltrack.\n"); do_init: status = nn->client_tracking_ops->init(net); +out: if (status) { printk(KERN_WARNING "NFSD: Unable to initialize client " "recovery tracking! (%d)\n", status); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index eca4a23f93c8..7857942c5ca6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -42,6 +42,7 @@ #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> #include <linux/jhash.h> +#include <linux/string_helpers.h> #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" @@ -77,6 +78,7 @@ static u64 current_sessionid = 1; /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); +void nfsd4_end_grace(struct nfsd_net *nn); /* Locking: */ @@ -98,6 +100,13 @@ enum nfsd4_st_mutex_lock_subclass { */ static DECLARE_WAIT_QUEUE_HEAD(close_wq); +/* + * A waitqueue where a writer to clients/#/ctl destroying a client can + * wait for cl_rpc_users to drop to 0 and then for the client to be + * unhashed. + */ +static DECLARE_WAIT_QUEUE_HEAD(expiry_wq); + static struct kmem_cache *client_slab; static struct kmem_cache *openowner_slab; static struct kmem_cache *lockowner_slab; @@ -137,7 +146,7 @@ static __be32 get_client_locked(struct nfs4_client *clp) if (is_client_expired(clp)) return nfserr_expired; - atomic_inc(&clp->cl_refcount); + atomic_inc(&clp->cl_rpc_users); return nfs_ok; } @@ -169,20 +178,24 @@ static void put_client_renew_locked(struct nfs4_client *clp) lockdep_assert_held(&nn->client_lock); - if (!atomic_dec_and_test(&clp->cl_refcount)) + if (!atomic_dec_and_test(&clp->cl_rpc_users)) return; if (!is_client_expired(clp)) renew_client_locked(clp); + else + wake_up_all(&expiry_wq); } static void put_client_renew(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - if (!atomic_dec_and_lock(&clp->cl_refcount, &nn->client_lock)) + if (!atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) return; if (!is_client_expired(clp)) renew_client_locked(clp); + else + wake_up_all(&expiry_wq); spin_unlock(&nn->client_lock); } @@ -693,7 +706,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla idr_preload(GFP_KERNEL); spin_lock(&cl->cl_lock); - new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 0, 0, GFP_NOWAIT); + /* Reserving 0 for start of file in nfsdfs "states" file: */ + new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 1, 0, GFP_NOWAIT); spin_unlock(&cl->cl_lock); idr_preload_end(); if (new_id < 0) @@ -1067,9 +1081,9 @@ static unsigned int clientid_hashval(u32 id) return id & CLIENT_HASH_MASK; } -static unsigned int clientstr_hashval(const char *name) +static unsigned int clientstr_hashval(struct xdr_netobj name) { - return opaque_hashval(name, 8) & CLIENT_HASH_MASK; + return opaque_hashval(name.data, 8) & CLIENT_HASH_MASK; } /* @@ -1562,7 +1576,7 @@ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca) * Never use more than a third of the remaining memory, * unless it's the only way to give this client a slot: */ - avail = clamp_t(int, avail, slotsize, total_avail/3); + avail = clamp_t(unsigned long, avail, slotsize, total_avail/3); num = min_t(int, num, avail / slotsize); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock); @@ -1843,7 +1857,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; - clp->cl_name.data = kmemdup(name.data, name.len, GFP_KERNEL); + xdr_netobj_dup(&clp->cl_name, &name, GFP_KERNEL); if (clp->cl_name.data == NULL) goto err_no_name; clp->cl_ownerstr_hashtbl = kmalloc_array(OWNER_HASH_SIZE, @@ -1853,10 +1867,9 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) goto err_no_hashtbl; for (i = 0; i < OWNER_HASH_SIZE; i++) INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]); - clp->cl_name.len = name.len; INIT_LIST_HEAD(&clp->cl_sessions); idr_init(&clp->cl_stateids); - atomic_set(&clp->cl_refcount, 0); + atomic_set(&clp->cl_rpc_users, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_openowners); @@ -1878,6 +1891,25 @@ err_no_name: return NULL; } +static void __free_client(struct kref *k) +{ + struct nfsdfs_client *c = container_of(k, struct nfsdfs_client, cl_ref); + struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs); + + free_svc_cred(&clp->cl_cred); + kfree(clp->cl_ownerstr_hashtbl); + kfree(clp->cl_name.data); + kfree(clp->cl_nii_domain.data); + kfree(clp->cl_nii_name.data); + idr_destroy(&clp->cl_stateids); + kmem_cache_free(client_slab, clp); +} + +static void drop_client(struct nfs4_client *clp) +{ + kref_put(&clp->cl_nfsdfs.cl_ref, __free_client); +} + static void free_client(struct nfs4_client *clp) { @@ -1890,11 +1922,12 @@ free_client(struct nfs4_client *clp) free_session(ses); } rpc_destroy_wait_queue(&clp->cl_cb_waitq); - free_svc_cred(&clp->cl_cred); - kfree(clp->cl_ownerstr_hashtbl); - kfree(clp->cl_name.data); - idr_destroy(&clp->cl_stateids); - kmem_cache_free(client_slab, clp); + if (clp->cl_nfsd_dentry) { + nfsd_client_rmdir(clp->cl_nfsd_dentry); + clp->cl_nfsd_dentry = NULL; + wake_up_all(&expiry_wq); + } + drop_client(clp); } /* must be called under the client_lock */ @@ -1935,7 +1968,7 @@ unhash_client(struct nfs4_client *clp) static __be32 mark_client_expired_locked(struct nfs4_client *clp) { - if (atomic_read(&clp->cl_refcount)) + if (atomic_read(&clp->cl_rpc_users)) return nfserr_jukebox; unhash_client_locked(clp); return nfs_ok; @@ -1988,6 +2021,7 @@ __destroy_client(struct nfs4_client *clp) if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); free_client(clp); + wake_up_all(&expiry_wq); } static void @@ -1997,6 +2031,22 @@ destroy_client(struct nfs4_client *clp) __destroy_client(clp); } +static void inc_reclaim_complete(struct nfs4_client *clp) +{ + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + if (!nn->track_reclaim_completes) + return; + if (!nfsd4_find_reclaim_client(clp->cl_name, nn)) + return; + if (atomic_inc_return(&nn->nr_reclaim_complete) == + nn->reclaim_str_hashtbl_size) { + printk(KERN_INFO "NFSD: all clients done reclaiming, ending NFSv4 grace period (net %x)\n", + clp->net->ns.inum); + nfsd4_end_grace(nn); + } +} + static void expire_client(struct nfs4_client *clp) { unhash_client(clp); @@ -2048,11 +2098,6 @@ compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) return memcmp(o1->data, o2->data, o1->len); } -static int same_name(const char *n1, const char *n2) -{ - return 0 == memcmp(n1, n2, HEXDIR_LEN); -} - static int same_verf(nfs4_verifier *v1, nfs4_verifier *v2) { @@ -2187,6 +2232,342 @@ find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask) return s; } +static struct nfs4_client *get_nfsdfs_clp(struct inode *inode) +{ + struct nfsdfs_client *nc; + nc = get_nfsdfs_client(inode); + if (!nc) + return NULL; + return container_of(nc, struct nfs4_client, cl_nfsdfs); +} + +static void seq_quote_mem(struct seq_file *m, char *data, int len) +{ + seq_printf(m, "\""); + seq_escape_mem_ascii(m, data, len); + seq_printf(m, "\""); +} + +static int client_info_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct nfs4_client *clp; + u64 clid; + + clp = get_nfsdfs_clp(inode); + if (!clp) + return -ENXIO; + memcpy(&clid, &clp->cl_clientid, sizeof(clid)); + seq_printf(m, "clientid: 0x%llx\n", clid); + seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr); + seq_printf(m, "name: "); + seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len); + seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); + if (clp->cl_nii_domain.data) { + seq_printf(m, "Implementation domain: "); + seq_quote_mem(m, clp->cl_nii_domain.data, + clp->cl_nii_domain.len); + seq_printf(m, "\nImplementation name: "); + seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len); + seq_printf(m, "\nImplementation time: [%ld, %ld]\n", + clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec); + } + drop_client(clp); + + return 0; +} + +static int client_info_open(struct inode *inode, struct file *file) +{ + return single_open(file, client_info_show, inode); +} + +static const struct file_operations client_info_fops = { + .open = client_info_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void *states_start(struct seq_file *s, loff_t *pos) + __acquires(&clp->cl_lock) +{ + struct nfs4_client *clp = s->private; + unsigned long id = *pos; + void *ret; + + spin_lock(&clp->cl_lock); + ret = idr_get_next_ul(&clp->cl_stateids, &id); + *pos = id; + return ret; +} + +static void *states_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct nfs4_client *clp = s->private; + unsigned long id = *pos; + void *ret; + + id = *pos; + id++; + ret = idr_get_next_ul(&clp->cl_stateids, &id); + *pos = id; + return ret; +} + +static void states_stop(struct seq_file *s, void *v) + __releases(&clp->cl_lock) +{ + struct nfs4_client *clp = s->private; + + spin_unlock(&clp->cl_lock); +} + +static void nfs4_show_superblock(struct seq_file *s, struct file *f) +{ + struct inode *inode = file_inode(f); + + seq_printf(s, "superblock: \"%02x:%02x:%ld\"", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), + inode->i_ino); +} + +static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo) +{ + seq_printf(s, "owner: "); + seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len); +} + +static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_ol_stateid *ols; + struct nfs4_file *nf; + struct file *file; + struct nfs4_stateowner *oo; + unsigned int access, deny; + + if (st->sc_type != NFS4_OPEN_STID && st->sc_type != NFS4_LOCK_STID) + return 0; /* XXX: or SEQ_SKIP? */ + ols = openlockstateid(st); + oo = ols->st_stateowner; + nf = st->sc_file; + file = find_any_file(nf); + + seq_printf(s, "- 0x%16phN: { type: open, ", &st->sc_stateid); + + access = bmap_to_share_mode(ols->st_access_bmap); + deny = bmap_to_share_mode(ols->st_deny_bmap); + + seq_printf(s, "access: \%s\%s, ", + access & NFS4_SHARE_ACCESS_READ ? "r" : "-", + access & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); + seq_printf(s, "deny: \%s\%s, ", + deny & NFS4_SHARE_ACCESS_READ ? "r" : "-", + deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); + + nfs4_show_superblock(s, file); + seq_printf(s, ", "); + nfs4_show_owner(s, oo); + seq_printf(s, " }\n"); + fput(file); + + return 0; +} + +static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_ol_stateid *ols; + struct nfs4_file *nf; + struct file *file; + struct nfs4_stateowner *oo; + + ols = openlockstateid(st); + oo = ols->st_stateowner; + nf = st->sc_file; + file = find_any_file(nf); + + seq_printf(s, "- 0x%16phN: { type: lock, ", &st->sc_stateid); + + /* + * Note: a lock stateid isn't really the same thing as a lock, + * it's the locking state held by one owner on a file, and there + * may be multiple (or no) lock ranges associated with it. + * (Same for the matter is true of open stateids.) + */ + + nfs4_show_superblock(s, file); + /* XXX: open stateid? */ + seq_printf(s, ", "); + nfs4_show_owner(s, oo); + seq_printf(s, " }\n"); + fput(file); + + return 0; +} + +static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_delegation *ds; + struct nfs4_file *nf; + struct file *file; + + ds = delegstateid(st); + nf = st->sc_file; + file = nf->fi_deleg_file; + + seq_printf(s, "- 0x%16phN: { type: deleg, ", &st->sc_stateid); + + /* Kinda dead code as long as we only support read delegs: */ + seq_printf(s, "access: %s, ", + ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w"); + + /* XXX: lease time, whether it's being recalled. */ + + nfs4_show_superblock(s, file); + seq_printf(s, " }\n"); + + return 0; +} + +static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_layout_stateid *ls; + struct file *file; + + ls = container_of(st, struct nfs4_layout_stateid, ls_stid); + file = ls->ls_file; + + seq_printf(s, "- 0x%16phN: { type: layout, ", &st->sc_stateid); + + /* XXX: What else would be useful? */ + + nfs4_show_superblock(s, file); + seq_printf(s, " }\n"); + + return 0; +} + +static int states_show(struct seq_file *s, void *v) +{ + struct nfs4_stid *st = v; + + switch (st->sc_type) { + case NFS4_OPEN_STID: + return nfs4_show_open(s, st); + case NFS4_LOCK_STID: + return nfs4_show_lock(s, st); + case NFS4_DELEG_STID: + return nfs4_show_deleg(s, st); + case NFS4_LAYOUT_STID: + return nfs4_show_layout(s, st); + default: + return 0; /* XXX: or SEQ_SKIP? */ + } + /* XXX: copy stateids? */ +} + +static struct seq_operations states_seq_ops = { + .start = states_start, + .next = states_next, + .stop = states_stop, + .show = states_show +}; + +static int client_states_open(struct inode *inode, struct file *file) +{ + struct seq_file *s; + struct nfs4_client *clp; + int ret; + + clp = get_nfsdfs_clp(inode); + if (!clp) + return -ENXIO; + + ret = seq_open(file, &states_seq_ops); + if (ret) + return ret; + s = file->private_data; + s->private = clp; + return 0; +} + +static int client_opens_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct nfs4_client *clp = m->private; + + /* XXX: alternatively, we could get/drop in seq start/stop */ + drop_client(clp); + return 0; +} + +static const struct file_operations client_states_fops = { + .open = client_states_open, + .read = seq_read, + .llseek = seq_lseek, + .release = client_opens_release, +}; + +/* + * Normally we refuse to destroy clients that are in use, but here the + * administrator is telling us to just do it. We also want to wait + * so the caller has a guarantee that the client's locks are gone by + * the time the write returns: + */ +static void force_expire_client(struct nfs4_client *clp) +{ + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + bool already_expired; + + spin_lock(&clp->cl_lock); + clp->cl_time = 0; + spin_unlock(&clp->cl_lock); + + wait_event(expiry_wq, atomic_read(&clp->cl_rpc_users) == 0); + spin_lock(&nn->client_lock); + already_expired = list_empty(&clp->cl_lru); + if (!already_expired) + unhash_client_locked(clp); + spin_unlock(&nn->client_lock); + + if (!already_expired) + expire_client(clp); + else + wait_event(expiry_wq, clp->cl_nfsd_dentry == NULL); +} + +static ssize_t client_ctl_write(struct file *file, const char __user *buf, + size_t size, loff_t *pos) +{ + char *data; + struct nfs4_client *clp; + + data = simple_transaction_get(file, buf, size); + if (IS_ERR(data)) + return PTR_ERR(data); + if (size != 7 || 0 != memcmp(data, "expire\n", 7)) + return -EINVAL; + clp = get_nfsdfs_clp(file_inode(file)); + if (!clp) + return -ENXIO; + force_expire_client(clp); + drop_client(clp); + return 7; +} + +static const struct file_operations client_ctl_fops = { + .write = client_ctl_write, + .release = simple_transaction_release, +}; + +static const struct tree_descr client_files[] = { + [0] = {"info", &client_info_fops, S_IRUSR}, + [1] = {"states", &client_states_fops, S_IRUSR}, + [2] = {"ctl", &client_ctl_fops, S_IRUSR|S_IWUSR}, + [3] = {""}, +}; + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2194,6 +2575,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, struct sockaddr *sa = svc_addr(rqstp); int ret; struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); clp = alloc_client(name); if (clp == NULL) @@ -2204,13 +2586,22 @@ static struct nfs4_client *create_client(struct xdr_netobj name, free_client(clp); return NULL; } + gen_clid(clp, nn); + kref_init(&clp->cl_nfsdfs.cl_ref); nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL); clp->cl_time = get_seconds(); clear_bit(0, &clp->cl_cb_slot_busy); copy_verf(clp, verf); - rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa); + memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); clp->cl_cb_session = NULL; clp->net = net; + clp->cl_nfsd_dentry = nfsd_client_mkdir(nn, &clp->cl_nfsdfs, + clp->cl_clientid.cl_id - nn->clientid_base, + client_files); + if (!clp->cl_nfsd_dentry) { + free_client(clp); + return NULL; + } return clp; } @@ -2521,6 +2912,22 @@ static bool client_has_state(struct nfs4_client *clp) || !list_empty(&clp->async_copies); } +static __be32 copy_impl_id(struct nfs4_client *clp, + struct nfsd4_exchange_id *exid) +{ + if (!exid->nii_domain.data) + return 0; + xdr_netobj_dup(&clp->cl_nii_domain, &exid->nii_domain, GFP_KERNEL); + if (!clp->cl_nii_domain.data) + return nfserr_jukebox; + xdr_netobj_dup(&clp->cl_nii_name, &exid->nii_name, GFP_KERNEL); + if (!clp->cl_nii_name.data) + return nfserr_jukebox; + clp->cl_nii_time.tv_sec = exid->nii_time.tv_sec; + clp->cl_nii_time.tv_nsec = exid->nii_time.tv_nsec; + return 0; +} + __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -2547,6 +2954,9 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, new = create_client(exid->clname, rqstp, &verf); if (new == NULL) return nfserr_jukebox; + status = copy_impl_id(new, exid); + if (status) + goto out_nolock; switch (exid->spa_how) { case SP4_MACH_CRED: @@ -2655,7 +3065,6 @@ out_new: new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0]; new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1]; - gen_clid(new, nn); add_to_unconfirmed(new); swap(new, conf); out_copy: @@ -3354,6 +3763,7 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, status = nfs_ok; nfsd4_client_record_create(cstate->session->se_client); + inc_reclaim_complete(cstate->session->se_client); out: return status; } @@ -3398,7 +3808,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, copy_clid(new, conf); gen_confirm(new, nn); } else /* case 4 (new client) or cases 2, 3 (client reboot): */ - gen_clid(new, nn); + ; new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); add_to_unconfirmed(new); @@ -3619,12 +4029,11 @@ static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj if (!sop) return NULL; - sop->so_owner.data = kmemdup(owner->data, owner->len, GFP_KERNEL); + xdr_netobj_dup(&sop->so_owner, owner, GFP_KERNEL); if (!sop->so_owner.data) { kmem_cache_free(slab, sop); return NULL; } - sop->so_owner.len = owner->len; INIT_LIST_HEAD(&sop->so_stateids); sop->so_client = clp; @@ -3958,6 +4367,9 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, switch (task->tk_status) { case 0: return 1; + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; case -EBADHANDLE: case -NFS4ERR_BAD_STATEID: /* @@ -3970,7 +4382,7 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, } /*FALLTHRU*/ default: - return -1; + return 1; } } @@ -4076,7 +4488,7 @@ static __be32 lookup_clientid(clientid_t *clid, spin_unlock(&nn->client_lock); return nfserr_expired; } - atomic_inc(&found->cl_refcount); + atomic_inc(&found->cl_rpc_users); spin_unlock(&nn->client_lock); /* Cache the nfs4_client in cstate! */ @@ -4713,7 +5125,6 @@ nfsd4_end_grace(struct nfsd_net *nn) if (nn->grace_ended) return; - dprintk("NFSD: end of grace period\n"); nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 @@ -4749,6 +5160,10 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) unsigned long double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; + if (nn->track_reclaim_completes && + atomic_read(&nn->nr_reclaim_complete) == + nn->reclaim_str_hashtbl_size) + return false; if (!nn->somebody_reclaimed) return false; nn->somebody_reclaimed = false; @@ -4779,6 +5194,7 @@ nfs4_laundromat(struct nfsd_net *nn) new_timeo = 0; goto out; } + dprintk("NFSD: end of grace period\n"); nfsd4_end_grace(nn); INIT_LIST_HEAD(&reaplist); spin_lock(&nn->client_lock); @@ -5705,12 +6121,11 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) if (fl->fl_lmops == &nfsd_posix_mng_ops) { lo = (struct nfs4_lockowner *) fl->fl_owner; - deny->ld_owner.data = kmemdup(lo->lo_owner.so_owner.data, - lo->lo_owner.so_owner.len, GFP_KERNEL); + xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner, + GFP_KERNEL); if (!deny->ld_owner.data) /* We just don't care that much */ goto nevermind; - deny->ld_owner.len = lo->lo_owner.so_owner.len; deny->ld_clientid = lo->lo_owner.so_client->cl_clientid; } else { nevermind: @@ -6458,7 +6873,7 @@ alloc_reclaim(void) } bool -nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn) +nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client_reclaim *crp; @@ -6468,20 +6883,24 @@ nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn) /* * failure => all reset bets are off, nfserr_no_grace... + * + * The caller is responsible for freeing name.data if NULL is returned (it + * will be freed in nfs4_remove_reclaim_record in the normal case). */ struct nfs4_client_reclaim * -nfs4_client_to_reclaim(const char *name, struct nfsd_net *nn) +nfs4_client_to_reclaim(struct xdr_netobj name, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp; - dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", HEXDIR_LEN, name); + dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", name.len, name.data); crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); INIT_LIST_HEAD(&crp->cr_strhash); list_add(&crp->cr_strhash, &nn->reclaim_str_hashtbl[strhashval]); - memcpy(crp->cr_recdir, name, HEXDIR_LEN); + crp->cr_name.data = name.data; + crp->cr_name.len = name.len; crp->cr_clp = NULL; nn->reclaim_str_hashtbl_size++; } @@ -6492,6 +6911,7 @@ void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *crp, struct nfsd_net *nn) { list_del(&crp->cr_strhash); + kfree(crp->cr_name.data); kfree(crp); nn->reclaim_str_hashtbl_size--; } @@ -6515,16 +6935,16 @@ nfs4_release_reclaim(struct nfsd_net *nn) /* * called from OPEN, CLAIM_PREVIOUS with a new clientid. */ struct nfs4_client_reclaim * -nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn) +nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; - dprintk("NFSD: nfs4_find_reclaim_client for recdir %s\n", recdir); + dprintk("NFSD: nfs4_find_reclaim_client for name %.*s\n", name.len, name.data); - strhashval = clientstr_hashval(recdir); + strhashval = clientstr_hashval(name); list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { - if (same_name(crp->cr_recdir, recdir)) { + if (compare_blob(&crp->cr_name, &name) == 0) { return crp; } } @@ -6559,7 +6979,7 @@ nfs4_check_open_reclaim(clientid_t *clid, static inline void put_client(struct nfs4_client *clp) { - atomic_dec(&clp->cl_refcount); + atomic_dec(&clp->cl_rpc_users); } static struct nfs4_client * @@ -6677,7 +7097,7 @@ nfsd_inject_add_lock_to_list(struct nfs4_ol_stateid *lst, return; lockdep_assert_held(&nn->client_lock); - atomic_inc(&clp->cl_refcount); + atomic_inc(&clp->cl_rpc_users); list_add(&lst->st_locks, collect); } @@ -6706,7 +7126,7 @@ static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max, * Despite the fact that these functions deal * with 64-bit integers for "count", we must * ensure that it doesn't blow up the - * clp->cl_refcount. Throw a warning if we + * clp->cl_rpc_users. Throw a warning if we * start to approach INT_MAX here. */ WARN_ON_ONCE(count == (INT_MAX / 2)); @@ -6830,7 +7250,7 @@ nfsd_foreach_client_openowner(struct nfs4_client *clp, u64 max, if (func) { func(oop); if (collect) { - atomic_inc(&clp->cl_refcount); + atomic_inc(&clp->cl_rpc_users); list_add(&oop->oo_perclient, collect); } } @@ -6838,7 +7258,7 @@ nfsd_foreach_client_openowner(struct nfs4_client *clp, u64 max, /* * Despite the fact that these functions deal with * 64-bit integers for "count", we must ensure that - * it doesn't blow up the clp->cl_refcount. Throw a + * it doesn't blow up the clp->cl_rpc_users. Throw a * warning if we start to approach INT_MAX here. */ WARN_ON_ONCE(count == (INT_MAX / 2)); @@ -6968,7 +7388,7 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max, if (dp->dl_time != 0) continue; - atomic_inc(&clp->cl_refcount); + atomic_inc(&clp->cl_rpc_users); WARN_ON(!unhash_delegation_locked(dp)); list_add(&dp->dl_recall_lru, victims); } @@ -6976,7 +7396,7 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max, /* * Despite the fact that these functions deal with * 64-bit integers for "count", we must ensure that - * it doesn't blow up the clp->cl_refcount. Throw a + * it doesn't blow up the clp->cl_rpc_users. Throw a * warning if we start to approach INT_MAX here. */ WARN_ON_ONCE(count == (INT_MAX / 2)); @@ -7262,10 +7682,19 @@ nfs4_state_start_net(struct net *net) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); + if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) + goto skip_grace; printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; + +skip_grace: + printk(KERN_INFO "NFSD: no clients to reclaim, skipping NFSv4 grace period (net %x)\n", + net->ns.inum); + queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_lease * HZ); + nfsd4_end_grace(nn); + return 0; } /* initialization to perform when the nfsd service is started: */ diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 3de42a729093..442811809f3d 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -269,19 +269,13 @@ static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes) return ret; } -/* - * We require the high 32 bits of 'seconds' to be 0, and - * we ignore all 32 bits of 'nseconds'. - */ static __be32 -nfsd4_decode_time(struct nfsd4_compoundargs *argp, struct timespec *tv) +nfsd4_decode_time(struct nfsd4_compoundargs *argp, struct timespec64 *tv) { DECODE_HEAD; - u64 sec; READ_BUF(12); - p = xdr_decode_hyper(p, &sec); - tv->tv_sec = sec; + p = xdr_decode_hyper(p, &tv->tv_sec); tv->tv_nsec = be32_to_cpup(p++); if (tv->tv_nsec >= (u32)1000000000) return nfserr_inval; @@ -320,7 +314,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *iattr, struct nfs4_acl **acl, struct xdr_netobj *label, int *umask) { - struct timespec ts; int expected_len, len = 0; u32 dummy32; char *buf; @@ -422,8 +415,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: len += 12; - status = nfsd4_decode_time(argp, &ts); - iattr->ia_atime = timespec_to_timespec64(ts); + status = nfsd4_decode_time(argp, &iattr->ia_atime); if (status) return status; iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); @@ -442,8 +434,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: len += 12; - status = nfsd4_decode_time(argp, &ts); - iattr->ia_mtime = timespec_to_timespec64(ts); + status = nfsd4_decode_time(argp, &iattr->ia_mtime); if (status) return status; iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); @@ -521,6 +512,7 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs) { DECODE_HEAD; + struct user_namespace *userns = nfsd_user_namespace(argp->rqstp); u32 dummy, uid, gid; char *machine_name; int i; @@ -563,8 +555,8 @@ static __be32 nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_ dummy = be32_to_cpup(p++); READ_BUF(dummy * 4); if (cbs->flavor == (u32)(-1)) { - kuid_t kuid = make_kuid(&init_user_ns, uid); - kgid_t kgid = make_kgid(&init_user_ns, gid); + kuid_t kuid = make_kuid(userns, uid); + kgid_t kgid = make_kgid(userns, gid); if (uid_valid(kuid) && gid_valid(kgid)) { cbs->uid = kuid; cbs->gid = kgid; @@ -1397,7 +1389,6 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, goto xdr_error; } - /* Ignore Implementation ID */ READ_BUF(4); /* nfs_impl_id4 array length */ dummy = be32_to_cpup(p++); @@ -1405,21 +1396,19 @@ nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, goto xdr_error; if (dummy == 1) { - /* nii_domain */ - READ_BUF(4); - dummy = be32_to_cpup(p++); - READ_BUF(dummy); - p += XDR_QUADLEN(dummy); + status = nfsd4_decode_opaque(argp, &exid->nii_domain); + if (status) + goto xdr_error; /* nii_name */ - READ_BUF(4); - dummy = be32_to_cpup(p++); - READ_BUF(dummy); - p += XDR_QUADLEN(dummy); + status = nfsd4_decode_opaque(argp, &exid->nii_name); + if (status) + goto xdr_error; /* nii_date */ - READ_BUF(12); - p += 3; + status = nfsd4_decode_time(argp, &exid->nii_time); + if (status) + goto xdr_error; } DECODE_TAIL; } @@ -2420,8 +2409,10 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, __be32 status; int err; struct nfs4_acl *acl = NULL; +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL void *context = NULL; int contextlen; +#endif bool contextsupport = false; struct nfsd4_compoundres *resp = rqstp->rq_resp; u32 minorversion = resp->cstate.minorversion; @@ -2906,12 +2897,14 @@ out_acl: *p++ = cpu_to_be32(NFS4_CHANGE_TYPE_IS_TIME_METADATA); } +#ifdef CONFIG_NFSD_V4_SECURITY_LABEL if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) { status = nfsd4_encode_security_label(xdr, rqstp, context, contextlen); if (status) goto out; } +#endif attrlen = htonl(xdr->buf->len - attrlen_offset - 4); write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4); diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index da52b594362a..26ad75ae2be0 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -9,6 +9,7 @@ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */ +#include <linux/sunrpc/svc_xprt.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/sunrpc/addr.h> @@ -35,48 +36,12 @@ struct nfsd_drc_bucket { spinlock_t cache_lock; }; -static struct nfsd_drc_bucket *drc_hashtbl; -static struct kmem_cache *drc_slab; - -/* max number of entries allowed in the cache */ -static unsigned int max_drc_entries; - -/* number of significant bits in the hash value */ -static unsigned int maskbits; -static unsigned int drc_hashsize; - -/* - * Stats and other tracking of on the duplicate reply cache. All of these and - * the "rc" fields in nfsdstats are protected by the cache_lock - */ - -/* total number of entries */ -static atomic_t num_drc_entries; - -/* cache misses due only to checksum comparison failures */ -static unsigned int payload_misses; - -/* amount of memory (in bytes) currently consumed by the DRC */ -static unsigned int drc_mem_usage; - -/* longest hash chain seen */ -static unsigned int longest_chain; - -/* size of cache when we saw the longest hash chain */ -static unsigned int longest_chain_cachesize; - static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *vec); static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc); -static struct shrinker nfsd_reply_cache_shrinker = { - .scan_objects = nfsd_reply_cache_scan, - .count_objects = nfsd_reply_cache_count, - .seeks = 1, -}; - /* * Put a cap on the size of the DRC based on the amount of available * low memory in the machine. @@ -94,6 +59,9 @@ static struct shrinker nfsd_reply_cache_shrinker = { * ...with a hard cap of 256k entries. In the worst case, each entry will be * ~1k, so the above numbers should give a rough max of the amount of memory * used in k. + * + * XXX: these limits are per-container, so memory used will increase + * linearly with number of containers. Maybe that's OK. */ static unsigned int nfsd_cache_size_limit(void) @@ -116,17 +84,18 @@ nfsd_hashsize(unsigned int limit) } static u32 -nfsd_cache_hash(__be32 xid) +nfsd_cache_hash(__be32 xid, struct nfsd_net *nn) { - return hash_32(be32_to_cpu(xid), maskbits); + return hash_32(be32_to_cpu(xid), nn->maskbits); } static struct svc_cacherep * -nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum) +nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum, + struct nfsd_net *nn) { struct svc_cacherep *rp; - rp = kmem_cache_alloc(drc_slab, GFP_KERNEL); + rp = kmem_cache_alloc(nn->drc_slab, GFP_KERNEL); if (rp) { rp->c_state = RC_UNUSED; rp->c_type = RC_NOCACHE; @@ -147,91 +116,101 @@ nfsd_reply_cache_alloc(struct svc_rqst *rqstp, __wsum csum) } static void -nfsd_reply_cache_free_locked(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) +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) { - drc_mem_usage -= rp->c_replvec.iov_len; + nn->drc_mem_usage -= 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(&num_drc_entries); - drc_mem_usage -= sizeof(*rp); + atomic_dec(&nn->num_drc_entries); + nn->drc_mem_usage -= sizeof(*rp); } - kmem_cache_free(drc_slab, rp); + kmem_cache_free(nn->drc_slab, rp); } static void -nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) +nfsd_reply_cache_free(struct nfsd_drc_bucket *b, struct svc_cacherep *rp, + struct nfsd_net *nn) { spin_lock(&b->cache_lock); - nfsd_reply_cache_free_locked(b, rp); + nfsd_reply_cache_free_locked(b, rp, nn); spin_unlock(&b->cache_lock); } -int nfsd_reply_cache_init(void) +int nfsd_reply_cache_init(struct nfsd_net *nn) { unsigned int hashsize; unsigned int i; int status = 0; - max_drc_entries = nfsd_cache_size_limit(); - atomic_set(&num_drc_entries, 0); - hashsize = nfsd_hashsize(max_drc_entries); - maskbits = ilog2(hashsize); + nn->max_drc_entries = nfsd_cache_size_limit(); + atomic_set(&nn->num_drc_entries, 0); + hashsize = nfsd_hashsize(nn->max_drc_entries); + nn->maskbits = ilog2(hashsize); - status = register_shrinker(&nfsd_reply_cache_shrinker); + 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) - return status; - - drc_slab = kmem_cache_create("nfsd_drc", sizeof(struct svc_cacherep), - 0, 0, NULL); - if (!drc_slab) goto out_nomem; - drc_hashtbl = kcalloc(hashsize, sizeof(*drc_hashtbl), GFP_KERNEL); - if (!drc_hashtbl) { - drc_hashtbl = vzalloc(array_size(hashsize, - sizeof(*drc_hashtbl))); - if (!drc_hashtbl) - goto out_nomem; + nn->drc_slab = kmem_cache_create("nfsd_drc", + sizeof(struct svc_cacherep), 0, 0, NULL); + if (!nn->drc_slab) + goto out_shrinker; + + nn->drc_hashtbl = kcalloc(hashsize, + sizeof(*nn->drc_hashtbl), GFP_KERNEL); + if (!nn->drc_hashtbl) { + nn->drc_hashtbl = vzalloc(array_size(hashsize, + sizeof(*nn->drc_hashtbl))); + if (!nn->drc_hashtbl) + goto out_slab; } for (i = 0; i < hashsize; i++) { - INIT_LIST_HEAD(&drc_hashtbl[i].lru_head); - spin_lock_init(&drc_hashtbl[i].cache_lock); + INIT_LIST_HEAD(&nn->drc_hashtbl[i].lru_head); + spin_lock_init(&nn->drc_hashtbl[i].cache_lock); } - drc_hashsize = hashsize; + nn->drc_hashsize = hashsize; return 0; +out_slab: + kmem_cache_destroy(nn->drc_slab); +out_shrinker: + unregister_shrinker(&nn->nfsd_reply_cache_shrinker); out_nomem: printk(KERN_ERR "nfsd: failed to allocate reply cache\n"); - nfsd_reply_cache_shutdown(); return -ENOMEM; } -void nfsd_reply_cache_shutdown(void) +void nfsd_reply_cache_shutdown(struct nfsd_net *nn) { struct svc_cacherep *rp; unsigned int i; - unregister_shrinker(&nfsd_reply_cache_shrinker); + unregister_shrinker(&nn->nfsd_reply_cache_shrinker); - for (i = 0; i < drc_hashsize; i++) { - struct list_head *head = &drc_hashtbl[i].lru_head; + for (i = 0; i < nn->drc_hashsize; i++) { + struct list_head *head = &nn->drc_hashtbl[i].lru_head; while (!list_empty(head)) { rp = list_first_entry(head, struct svc_cacherep, c_lru); - nfsd_reply_cache_free_locked(&drc_hashtbl[i], rp); + nfsd_reply_cache_free_locked(&nn->drc_hashtbl[i], + rp, nn); } } - kvfree(drc_hashtbl); - drc_hashtbl = NULL; - drc_hashsize = 0; + kvfree(nn->drc_hashtbl); + nn->drc_hashtbl = NULL; + nn->drc_hashsize = 0; - kmem_cache_destroy(drc_slab); - drc_slab = NULL; + kmem_cache_destroy(nn->drc_slab); + nn->drc_slab = NULL; } /* @@ -246,7 +225,7 @@ lru_put_end(struct nfsd_drc_bucket *b, struct svc_cacherep *rp) } static long -prune_bucket(struct nfsd_drc_bucket *b) +prune_bucket(struct nfsd_drc_bucket *b, struct nfsd_net *nn) { struct svc_cacherep *rp, *tmp; long freed = 0; @@ -258,10 +237,10 @@ prune_bucket(struct nfsd_drc_bucket *b) */ if (rp->c_state == RC_INPROG) continue; - if (atomic_read(&num_drc_entries) <= max_drc_entries && + if (atomic_read(&nn->num_drc_entries) <= nn->max_drc_entries && time_before(jiffies, rp->c_timestamp + RC_EXPIRE)) break; - nfsd_reply_cache_free_locked(b, rp); + nfsd_reply_cache_free_locked(b, rp, nn); freed++; } return freed; @@ -272,18 +251,18 @@ prune_bucket(struct nfsd_drc_bucket *b) * Also prune the oldest ones when the total exceeds the max number of entries. */ static long -prune_cache_entries(void) +prune_cache_entries(struct nfsd_net *nn) { unsigned int i; long freed = 0; - for (i = 0; i < drc_hashsize; i++) { - struct nfsd_drc_bucket *b = &drc_hashtbl[i]; + for (i = 0; i < nn->drc_hashsize; i++) { + struct nfsd_drc_bucket *b = &nn->drc_hashtbl[i]; if (list_empty(&b->lru_head)) continue; spin_lock(&b->cache_lock); - freed += prune_bucket(b); + freed += prune_bucket(b, nn); spin_unlock(&b->cache_lock); } return freed; @@ -292,13 +271,19 @@ prune_cache_entries(void) static unsigned long nfsd_reply_cache_count(struct shrinker *shrink, struct shrink_control *sc) { - return atomic_read(&num_drc_entries); + struct nfsd_net *nn = container_of(shrink, + struct nfsd_net, nfsd_reply_cache_shrinker); + + return atomic_read(&nn->num_drc_entries); } static unsigned long nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { - return prune_cache_entries(); + struct nfsd_net *nn = container_of(shrink, + struct nfsd_net, nfsd_reply_cache_shrinker); + + return prune_cache_entries(nn); } /* * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes @@ -334,11 +319,12 @@ nfsd_cache_csum(struct svc_rqst *rqstp) } static int -nfsd_cache_key_cmp(const struct svc_cacherep *key, const struct svc_cacherep *rp) +nfsd_cache_key_cmp(const struct svc_cacherep *key, + const struct svc_cacherep *rp, struct nfsd_net *nn) { if (key->c_key.k_xid == rp->c_key.k_xid && key->c_key.k_csum != rp->c_key.k_csum) - ++payload_misses; + ++nn->payload_misses; return memcmp(&key->c_key, &rp->c_key, sizeof(key->c_key)); } @@ -349,7 +335,8 @@ nfsd_cache_key_cmp(const struct svc_cacherep *key, const struct svc_cacherep *rp * inserts an empty key on failure. */ static struct svc_cacherep * -nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key) +nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key, + struct nfsd_net *nn) { struct svc_cacherep *rp, *ret = key; struct rb_node **p = &b->rb_head.rb_node, @@ -362,7 +349,7 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key) parent = *p; rp = rb_entry(parent, struct svc_cacherep, c_node); - cmp = nfsd_cache_key_cmp(key, rp); + cmp = nfsd_cache_key_cmp(key, rp, nn); if (cmp < 0) p = &parent->rb_left; else if (cmp > 0) @@ -376,14 +363,14 @@ nfsd_cache_insert(struct nfsd_drc_bucket *b, struct svc_cacherep *key) rb_insert_color(&key->c_node, &b->rb_head); out: /* tally hash chain length stats */ - if (entries > longest_chain) { - longest_chain = entries; - longest_chain_cachesize = atomic_read(&num_drc_entries); - } else if (entries == longest_chain) { + if (entries > nn->longest_chain) { + nn->longest_chain = entries; + nn->longest_chain_cachesize = atomic_read(&nn->num_drc_entries); + } else if (entries == nn->longest_chain) { /* prefer to keep the smallest cachesize possible here */ - longest_chain_cachesize = min_t(unsigned int, - longest_chain_cachesize, - atomic_read(&num_drc_entries)); + nn->longest_chain_cachesize = min_t(unsigned int, + nn->longest_chain_cachesize, + atomic_read(&nn->num_drc_entries)); } lru_put_end(b, ret); @@ -400,11 +387,12 @@ out: int nfsd_cache_lookup(struct svc_rqst *rqstp) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_cacherep *rp, *found; __be32 xid = rqstp->rq_xid; __wsum csum; - u32 hash = nfsd_cache_hash(xid); - struct nfsd_drc_bucket *b = &drc_hashtbl[hash]; + u32 hash = nfsd_cache_hash(xid, nn); + struct nfsd_drc_bucket *b = &nn->drc_hashtbl[hash]; int type = rqstp->rq_cachetype; int rtn = RC_DOIT; @@ -420,16 +408,16 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) * Since the common case is a cache miss followed by an insert, * preallocate an entry. */ - rp = nfsd_reply_cache_alloc(rqstp, csum); + rp = nfsd_reply_cache_alloc(rqstp, csum, nn); if (!rp) { dprintk("nfsd: unable to allocate DRC entry!\n"); return rtn; } spin_lock(&b->cache_lock); - found = nfsd_cache_insert(b, rp); + found = nfsd_cache_insert(b, rp, nn); if (found != rp) { - nfsd_reply_cache_free_locked(NULL, rp); + nfsd_reply_cache_free_locked(NULL, rp, nn); rp = found; goto found_entry; } @@ -438,11 +426,11 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) rqstp->rq_cacherep = rp; rp->c_state = RC_INPROG; - atomic_inc(&num_drc_entries); - drc_mem_usage += sizeof(*rp); + atomic_inc(&nn->num_drc_entries); + nn->drc_mem_usage += sizeof(*rp); /* go ahead and prune the cache */ - prune_bucket(b); + prune_bucket(b, nn); out: spin_unlock(&b->cache_lock); return rtn; @@ -477,7 +465,7 @@ found_entry: break; default: printk(KERN_WARNING "nfsd: bad repcache type %d\n", rp->c_type); - nfsd_reply_cache_free_locked(b, rp); + nfsd_reply_cache_free_locked(b, rp, nn); } goto out; @@ -502,6 +490,7 @@ found_entry: void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) { + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_cacherep *rp = rqstp->rq_cacherep; struct kvec *resv = &rqstp->rq_res.head[0], *cachv; u32 hash; @@ -512,15 +501,15 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) if (!rp) return; - hash = nfsd_cache_hash(rp->c_key.k_xid); - b = &drc_hashtbl[hash]; + hash = nfsd_cache_hash(rp->c_key.k_xid, nn); + b = &nn->drc_hashtbl[hash]; len = resv->iov_len - ((char*)statp - (char*)resv->iov_base); len >>= 2; /* Don't cache excessive amounts of data and XDR failures */ if (!statp || len > (256 >> 2)) { - nfsd_reply_cache_free(b, rp); + nfsd_reply_cache_free(b, rp, nn); return; } @@ -535,18 +524,18 @@ nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) bufsize = len << 2; cachv->iov_base = kmalloc(bufsize, GFP_KERNEL); if (!cachv->iov_base) { - nfsd_reply_cache_free(b, rp); + nfsd_reply_cache_free(b, rp, nn); return; } cachv->iov_len = bufsize; memcpy(cachv->iov_base, statp, bufsize); break; case RC_NOCACHE: - nfsd_reply_cache_free(b, rp); + nfsd_reply_cache_free(b, rp, nn); return; } spin_lock(&b->cache_lock); - drc_mem_usage += bufsize; + nn->drc_mem_usage += bufsize; lru_put_end(b, rp); rp->c_secure = test_bit(RQ_SECURE, &rqstp->rq_flags); rp->c_type = cachetype; @@ -582,21 +571,26 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data) */ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v) { - seq_printf(m, "max entries: %u\n", max_drc_entries); + struct nfsd_net *nn = v; + + seq_printf(m, "max entries: %u\n", nn->max_drc_entries); seq_printf(m, "num entries: %u\n", - atomic_read(&num_drc_entries)); - seq_printf(m, "hash buckets: %u\n", 1 << maskbits); - seq_printf(m, "mem usage: %u\n", drc_mem_usage); + 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", payload_misses); - seq_printf(m, "longest chain len: %u\n", longest_chain); - seq_printf(m, "cachesize at longest: %u\n", longest_chain_cachesize); + seq_printf(m, "payload misses: %u\n", nn->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; } int nfsd_reply_cache_stats_open(struct inode *inode, struct file *file) { - return single_open(file, nfsd_reply_cache_stats_show, NULL); + struct nfsd_net *nn = net_generic(file_inode(file)->i_sb->s_fs_info, + nfsd_net_id); + + return single_open(file, nfsd_reply_cache_stats_show, nn); } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index f2feb2d11bae..0a9a49ded546 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Syscall interface to knfsd. * @@ -15,6 +16,7 @@ #include <linux/sunrpc/gss_krb5_enctypes.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/module.h> +#include <linux/fsnotify.h> #include "idmap.h" #include "nfsd.h" @@ -52,6 +54,7 @@ enum { NFSD_RecoveryDir, NFSD_V4EndGrace, #endif + NFSD_MaxReserved }; /* @@ -439,7 +442,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return rv; if (newthreads < 0) return -EINVAL; - rv = nfsd_svc(newthreads, net); + rv = nfsd_svc(newthreads, net, file->f_cred); if (rv < 0) return rv; } else @@ -537,14 +540,14 @@ out_free: } static ssize_t -nfsd_print_version_support(char *buf, int remaining, const char *sep, - unsigned vers, int minor) +nfsd_print_version_support(struct nfsd_net *nn, char *buf, int remaining, + const char *sep, unsigned vers, int minor) { const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u"; - bool supported = !!nfsd_vers(vers, NFSD_TEST); + bool supported = !!nfsd_vers(nn, vers, NFSD_TEST); if (vers == 4 && minor >= 0 && - !nfsd_minorversion(minor, NFSD_TEST)) + !nfsd_minorversion(nn, minor, NFSD_TEST)) supported = false; if (minor == 0 && supported) /* @@ -599,20 +602,20 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) switch(num) { case 2: case 3: - nfsd_vers(num, cmd); + nfsd_vers(nn, num, cmd); break; case 4: if (*minorp == '.') { - if (nfsd_minorversion(minor, cmd) < 0) + if (nfsd_minorversion(nn, minor, cmd) < 0) return -EINVAL; - } else if ((cmd == NFSD_SET) != nfsd_vers(num, NFSD_TEST)) { + } else if ((cmd == NFSD_SET) != nfsd_vers(nn, num, NFSD_TEST)) { /* * Either we have +4 and no minors are enabled, * or we have -4 and at least one minor is enabled. * In either case, propagate 'cmd' to all minors. */ minor = 0; - while (nfsd_minorversion(minor, cmd) >= 0) + while (nfsd_minorversion(nn, minor, cmd) >= 0) minor++; } break; @@ -624,7 +627,7 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) /* If all get turned off, turn them back on, as * having no versions is BAD */ - nfsd_reset_versions(); + nfsd_reset_versions(nn); } /* Now write current state into reply buffer */ @@ -633,12 +636,12 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) remaining = SIMPLE_TRANSACTION_LIMIT; for (num=2 ; num <= 4 ; num++) { int minor; - if (!nfsd_vers(num, NFSD_AVAIL)) + if (!nfsd_vers(nn, num, NFSD_AVAIL)) continue; minor = -1; do { - len = nfsd_print_version_support(buf, remaining, + len = nfsd_print_version_support(nn, buf, remaining, sep, num, minor); if (len >= remaining) goto out; @@ -717,7 +720,7 @@ static ssize_t __write_ports_names(char *buf, struct net *net) * a socket of a supported family/protocol, and we use it as an * nfsd listener. */ -static ssize_t __write_ports_addfd(char *buf, struct net *net) +static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred *cred) { char *mesg = buf; int fd, err; @@ -736,7 +739,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net) if (err != 0) return err; - err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT); + err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (err < 0) { nfsd_destroy(net); return err; @@ -751,7 +754,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net) * A transport listener is added by writing it's transport name and * a port number. */ -static ssize_t __write_ports_addxprt(char *buf, struct net *net) +static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cred *cred) { char transport[16]; struct svc_xprt *xprt; @@ -769,12 +772,12 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net) return err; err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET, port, SVC_SOCK_ANONYMOUS); + PF_INET, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0) goto out_err; err = svc_create_xprt(nn->nfsd_serv, transport, net, - PF_INET6, port, SVC_SOCK_ANONYMOUS); + PF_INET6, port, SVC_SOCK_ANONYMOUS, cred); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; @@ -799,10 +802,10 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size, return __write_ports_names(buf, net); if (isdigit(buf[0])) - return __write_ports_addfd(buf, net); + return __write_ports_addfd(buf, net, file->f_cred); if (isalpha(buf[0])) - return __write_ports_addxprt(buf, net); + return __write_ports_addxprt(buf, net, file->f_cred); return -EINVAL; } @@ -1146,8 +1149,201 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) * populating the filesystem. */ +/* Basically copying rpc_get_inode. */ +static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode) +{ + struct inode *inode = new_inode(sb); + if (!inode) + return NULL; + /* Following advice from simple_fill_super documentation: */ + inode->i_ino = iunique(sb, NFSD_MaxReserved); + inode->i_mode = mode; + inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); + switch (mode & S_IFMT) { + case S_IFDIR: + inode->i_fop = &simple_dir_operations; + inode->i_op = &simple_dir_inode_operations; + inc_nlink(inode); + default: + break; + } + return inode; +} + +static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + + inode = nfsd_get_inode(dir->i_sb, mode); + if (!inode) + return -ENOMEM; + d_add(dentry, inode); + inc_nlink(dir); + fsnotify_mkdir(dir, dentry); + return 0; +} + +static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *ncl, char *name) +{ + struct inode *dir = parent->d_inode; + struct dentry *dentry; + int ret = -ENOMEM; + + inode_lock(dir); + dentry = d_alloc_name(parent, name); + if (!dentry) + goto out_err; + ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600); + if (ret) + goto out_err; + if (ncl) { + d_inode(dentry)->i_private = ncl; + kref_get(&ncl->cl_ref); + } +out: + inode_unlock(dir); + return dentry; +out_err: + dentry = ERR_PTR(ret); + goto out; +} + +static void clear_ncl(struct inode *inode) +{ + struct nfsdfs_client *ncl = inode->i_private; + + inode->i_private = NULL; + synchronize_rcu(); + kref_put(&ncl->cl_ref, ncl->cl_release); +} + + +static struct nfsdfs_client *__get_nfsdfs_client(struct inode *inode) +{ + struct nfsdfs_client *nc = inode->i_private; + + if (nc) + kref_get(&nc->cl_ref); + return nc; +} + +struct nfsdfs_client *get_nfsdfs_client(struct inode *inode) +{ + struct nfsdfs_client *nc; + + rcu_read_lock(); + nc = __get_nfsdfs_client(inode); + rcu_read_unlock(); + return nc; +} +/* from __rpc_unlink */ +static void nfsdfs_remove_file(struct inode *dir, struct dentry *dentry) +{ + int ret; + + clear_ncl(d_inode(dentry)); + dget(dentry); + ret = simple_unlink(dir, dentry); + d_delete(dentry); + dput(dentry); + WARN_ON_ONCE(ret); +} + +static void nfsdfs_remove_files(struct dentry *root) +{ + struct dentry *dentry, *tmp; + + list_for_each_entry_safe(dentry, tmp, &root->d_subdirs, d_child) { + if (!simple_positive(dentry)) { + WARN_ON_ONCE(1); /* I think this can't happen? */ + continue; + } + nfsdfs_remove_file(d_inode(root), dentry); + } +} + +/* XXX: cut'n'paste from simple_fill_super; figure out if we could share + * code instead. */ +static int nfsdfs_create_files(struct dentry *root, + const struct tree_descr *files) +{ + struct inode *dir = d_inode(root); + struct inode *inode; + struct dentry *dentry; + int i; + + inode_lock(dir); + for (i = 0; files->name && files->name[0]; i++, files++) { + if (!files->name) + continue; + dentry = d_alloc_name(root, files->name); + if (!dentry) + goto out; + inode = nfsd_get_inode(d_inode(root)->i_sb, + S_IFREG | files->mode); + if (!inode) { + dput(dentry); + goto out; + } + inode->i_fop = files->ops; + inode->i_private = __get_nfsdfs_client(dir); + d_add(dentry, inode); + fsnotify_create(dir, dentry); + } + inode_unlock(dir); + return 0; +out: + nfsdfs_remove_files(root); + inode_unlock(dir); + return -ENOMEM; +} + +/* on success, returns positive number unique to that client. */ +struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, + struct nfsdfs_client *ncl, u32 id, + const struct tree_descr *files) +{ + struct dentry *dentry; + char name[11]; + int ret; + + sprintf(name, "%u", id); + + dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name); + if (IS_ERR(dentry)) /* XXX: tossing errors? */ + return NULL; + ret = nfsdfs_create_files(dentry, files); + if (ret) { + nfsd_client_rmdir(dentry); + return NULL; + } + return dentry; +} + +/* Taken from __rpc_rmdir: */ +void nfsd_client_rmdir(struct dentry *dentry) +{ + struct inode *dir = d_inode(dentry->d_parent); + struct inode *inode = d_inode(dentry); + int ret; + + inode_lock(dir); + nfsdfs_remove_files(dentry); + clear_ncl(inode); + dget(dentry); + ret = simple_rmdir(dir, dentry); + WARN_ON_ONCE(ret); + d_delete(dentry); + inode_unlock(dir); +} + static int nfsd_fill_super(struct super_block * sb, void * data, int silent) { + struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, + nfsd_net_id); + struct dentry *dentry; + int ret; + static const struct tree_descr nfsd_files[] = { [NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO}, [NFSD_Export_features] = {"export_features", @@ -1177,7 +1373,15 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent) /* last one */ {""} }; get_net(sb->s_fs_info); - return simple_fill_super(sb, 0x6e667364, nfsd_files); + ret = simple_fill_super(sb, 0x6e667364, nfsd_files); + if (ret) + return ret; + dentry = nfsd_mkdir(sb->s_root, NULL, "clients"); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + nn->nfsd_client_dir = dentry; + return 0; + } static struct dentry *nfsd_mount(struct file_system_type *fs_type, @@ -1231,6 +1435,7 @@ unsigned int nfsd_net_id; static __net_init int nfsd_init_net(struct net *net) { int retval; + struct vfsmount *mnt; struct nfsd_net *nn = net_generic(net, nfsd_net_id); retval = nfsd_export_init(net); @@ -1239,17 +1444,35 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; + nn->nfsd_versions = NULL; + nn->nfsd4_minorversions = NULL; + retval = nfsd_reply_cache_init(nn); + if (retval) + goto out_drc_error; nn->nfsd4_lease = 90; /* default lease time */ nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; + nn->track_reclaim_completes = false; nn->clverifier_counter = prandom_u32(); - nn->clientid_counter = prandom_u32(); + nn->clientid_base = prandom_u32(); + nn->clientid_counter = nn->clientid_base + 1; nn->s2s_cp_cl_id = nn->clientid_counter++; atomic_set(&nn->ntf_refcnt, 0); init_waitqueue_head(&nn->ntf_wq); + + mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL); + if (IS_ERR(mnt)) { + retval = PTR_ERR(mnt); + goto out_mount_err; + } + nn->nfsd_mnt = mnt; return 0; +out_mount_err: + nfsd_reply_cache_shutdown(nn); +out_drc_error: + nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); out_export_error: @@ -1258,8 +1481,13 @@ out_export_error: static __net_exit void nfsd_exit_net(struct net *net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + mntput(nn->nfsd_mnt); + nfsd_reply_cache_shutdown(nn); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); + nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); } static struct pernet_operations nfsd_net_ops = { @@ -1286,13 +1514,8 @@ static int __init init_nfsd(void) retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; - retval = nfsd_fault_inject_init(); /* nfsd fault injection controls */ - if (retval) - goto out_exit_pnfs; + nfsd_fault_inject_init(); /* nfsd fault injection controls */ nfsd_stat_init(); /* Statistics */ - retval = nfsd_reply_cache_init(); - if (retval) - goto out_free_stat; nfsd_lockd_init(); /* lockd->nfsd callbacks */ retval = create_proc_exports_entry(); if (retval) @@ -1306,11 +1529,8 @@ out_free_all: remove_proc_entry("fs/nfs", NULL); out_free_lockd: nfsd_lockd_shutdown(); - nfsd_reply_cache_shutdown(); -out_free_stat: nfsd_stat_shutdown(); nfsd_fault_inject_cleanup(); -out_exit_pnfs: nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); @@ -1323,7 +1543,6 @@ out_unregister_pernet: static void __exit exit_nfsd(void) { - nfsd_reply_cache_shutdown(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); nfsd_stat_shutdown(); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 066899929863..af2947551e9c 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -17,10 +17,12 @@ #include <linux/nfs3.h> #include <linux/nfs4.h> #include <linux/sunrpc/svc.h> +#include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/msg_prot.h> #include <uapi/linux/nfsd/debug.h> +#include "netns.h" #include "stats.h" #include "export.h" @@ -73,7 +75,7 @@ extern const struct seq_operations nfs_exports_op; /* * Function prototypes. */ -int nfsd_svc(int nrservs, struct net *net); +int nfsd_svc(int nrservs, struct net *net, const struct cred *cred); int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); int nfsd_nrthreads(struct net *); @@ -85,6 +87,16 @@ int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_destroy(struct net *net); +struct nfsdfs_client { + struct kref cl_ref; + void (*cl_release)(struct kref *kref); +}; + +struct nfsdfs_client *get_nfsdfs_client(struct inode *); +struct dentry *nfsd_client_mkdir(struct nfsd_net *nn, + struct nfsdfs_client *ncl, u32 id, const struct tree_descr *); +void nfsd_client_rmdir(struct dentry *dentry); + #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) #ifdef CONFIG_NFSD_V2_ACL extern const struct svc_version nfsd_acl_version2; @@ -98,10 +110,12 @@ extern const struct svc_version nfsd_acl_version3; #endif #endif +struct nfsd_net; + enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL }; -int nfsd_vers(int vers, enum vers_op change); -int nfsd_minorversion(u32 minorversion, enum vers_op change); -void nfsd_reset_versions(void); +int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change); +int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change); +void nfsd_reset_versions(struct nfsd_net *nn); int nfsd_create_serv(struct net *net); extern int nfsd_max_blksize; @@ -110,6 +124,12 @@ static inline int nfsd_v4client(struct svc_rqst *rq) { return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4; } +static inline struct user_namespace * +nfsd_user_namespace(const struct svc_rqst *rqstp) +{ + const struct cred *cred = rqstp->rq_xprt->xpt_cred; + return cred ? cred->user_ns : &init_user_ns; +} /* * NFSv4 State diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 89cb484f1cfb..18d94ea984ba 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -32,6 +32,24 @@ extern struct svc_program nfsd_program; static int nfsd(void *vrqstp); +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) +static int nfsd_acl_rpcbind_set(struct net *, + const struct svc_program *, + u32, int, + unsigned short, + unsigned short); +static __be32 nfsd_acl_init_request(struct svc_rqst *, + const struct svc_program *, + struct svc_process_info *); +#endif +static int nfsd_rpcbind_set(struct net *, + const struct svc_program *, + u32, int, + unsigned short, + unsigned short); +static __be32 nfsd_init_request(struct svc_rqst *, + const struct svc_program *, + struct svc_process_info *); /* * nfsd_mutex protects nn->nfsd_serv -- both the pointer itself and the members @@ -86,6 +104,8 @@ static struct svc_program nfsd_acl_program = { .pg_class = "nfsd", .pg_stats = &nfsd_acl_svcstats, .pg_authenticate = &svc_set_client, + .pg_init_request = nfsd_acl_init_request, + .pg_rpcbind_set = nfsd_acl_rpcbind_set, }; static struct svc_stat nfsd_acl_svcstats = { @@ -105,7 +125,6 @@ static const struct svc_version *nfsd_version[] = { #define NFSD_MINVERS 2 #define NFSD_NRVERS ARRAY_SIZE(nfsd_version) -static const struct svc_version *nfsd_versions[NFSD_NRVERS]; struct svc_program nfsd_program = { #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) @@ -113,77 +132,136 @@ struct svc_program nfsd_program = { #endif .pg_prog = NFS_PROGRAM, /* program number */ .pg_nvers = NFSD_NRVERS, /* nr of entries in nfsd_version */ - .pg_vers = nfsd_versions, /* version table */ + .pg_vers = nfsd_version, /* version table */ .pg_name = "nfsd", /* program name */ .pg_class = "nfsd", /* authentication class */ .pg_stats = &nfsd_svcstats, /* version table */ .pg_authenticate = &svc_set_client, /* export authentication */ - + .pg_init_request = nfsd_init_request, + .pg_rpcbind_set = nfsd_rpcbind_set, }; -static bool nfsd_supported_minorversions[NFSD_SUPPORTED_MINOR_VERSION + 1] = { - [0] = 1, - [1] = 1, - [2] = 1, -}; +static bool +nfsd_support_version(int vers) +{ + if (vers >= NFSD_MINVERS && vers < NFSD_NRVERS) + return nfsd_version[vers] != NULL; + return false; +} + +static bool * +nfsd_alloc_versions(void) +{ + bool *vers = kmalloc_array(NFSD_NRVERS, sizeof(bool), GFP_KERNEL); + unsigned i; + + if (vers) { + /* All compiled versions are enabled by default */ + for (i = 0; i < NFSD_NRVERS; i++) + vers[i] = nfsd_support_version(i); + } + return vers; +} + +static bool * +nfsd_alloc_minorversions(void) +{ + bool *vers = kmalloc_array(NFSD_SUPPORTED_MINOR_VERSION + 1, + sizeof(bool), GFP_KERNEL); + unsigned i; + + if (vers) { + /* All minor versions are enabled by default */ + for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) + vers[i] = nfsd_support_version(4); + } + return vers; +} -int nfsd_vers(int vers, enum vers_op change) +void +nfsd_netns_free_versions(struct nfsd_net *nn) +{ + kfree(nn->nfsd_versions); + kfree(nn->nfsd4_minorversions); + nn->nfsd_versions = NULL; + nn->nfsd4_minorversions = NULL; +} + +static void +nfsd_netns_init_versions(struct nfsd_net *nn) +{ + if (!nn->nfsd_versions) { + nn->nfsd_versions = nfsd_alloc_versions(); + nn->nfsd4_minorversions = nfsd_alloc_minorversions(); + if (!nn->nfsd_versions || !nn->nfsd4_minorversions) + nfsd_netns_free_versions(nn); + } +} + +int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change) { if (vers < NFSD_MINVERS || vers >= NFSD_NRVERS) return 0; switch(change) { case NFSD_SET: - nfsd_versions[vers] = nfsd_version[vers]; -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - if (vers < NFSD_ACL_NRVERS) - nfsd_acl_versions[vers] = nfsd_acl_version[vers]; -#endif + if (nn->nfsd_versions) + nn->nfsd_versions[vers] = nfsd_support_version(vers); break; case NFSD_CLEAR: - nfsd_versions[vers] = NULL; -#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) - if (vers < NFSD_ACL_NRVERS) - nfsd_acl_versions[vers] = NULL; -#endif + nfsd_netns_init_versions(nn); + if (nn->nfsd_versions) + nn->nfsd_versions[vers] = false; break; case NFSD_TEST: - return nfsd_versions[vers] != NULL; + if (nn->nfsd_versions) + return nn->nfsd_versions[vers]; + /* Fallthrough */ case NFSD_AVAIL: - return nfsd_version[vers] != NULL; + return nfsd_support_version(vers); } return 0; } static void -nfsd_adjust_nfsd_versions4(void) +nfsd_adjust_nfsd_versions4(struct nfsd_net *nn) { unsigned i; for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) { - if (nfsd_supported_minorversions[i]) + if (nn->nfsd4_minorversions[i]) return; } - nfsd_vers(4, NFSD_CLEAR); + nfsd_vers(nn, 4, NFSD_CLEAR); } -int nfsd_minorversion(u32 minorversion, enum vers_op change) +int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change) { if (minorversion > NFSD_SUPPORTED_MINOR_VERSION && change != NFSD_AVAIL) return -1; + switch(change) { case NFSD_SET: - nfsd_supported_minorversions[minorversion] = true; - nfsd_vers(4, NFSD_SET); + if (nn->nfsd4_minorversions) { + nfsd_vers(nn, 4, NFSD_SET); + nn->nfsd4_minorversions[minorversion] = + nfsd_vers(nn, 4, NFSD_TEST); + } break; case NFSD_CLEAR: - nfsd_supported_minorversions[minorversion] = false; - nfsd_adjust_nfsd_versions4(); + nfsd_netns_init_versions(nn); + if (nn->nfsd4_minorversions) { + nn->nfsd4_minorversions[minorversion] = false; + nfsd_adjust_nfsd_versions4(nn); + } break; case NFSD_TEST: - return nfsd_supported_minorversions[minorversion]; + if (nn->nfsd4_minorversions) + return nn->nfsd4_minorversions[minorversion]; + return nfsd_vers(nn, 4, NFSD_TEST); case NFSD_AVAIL: - return minorversion <= NFSD_SUPPORTED_MINOR_VERSION; + return minorversion <= NFSD_SUPPORTED_MINOR_VERSION && + nfsd_vers(nn, 4, NFSD_AVAIL); } return 0; } @@ -205,7 +283,7 @@ int nfsd_nrthreads(struct net *net) return rv; } -static int nfsd_init_socks(struct net *net) +static int nfsd_init_socks(struct net *net, const struct cred *cred) { int error; struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -214,12 +292,12 @@ static int nfsd_init_socks(struct net *net) return 0; error = svc_create_xprt(nn->nfsd_serv, "udp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS); + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; error = svc_create_xprt(nn->nfsd_serv, "tcp", net, PF_INET, NFS_PORT, - SVC_SOCK_DEFAULTS); + SVC_SOCK_DEFAULTS, cred); if (error < 0) return error; @@ -265,16 +343,12 @@ static void nfsd_shutdown_generic(void) nfsd_racache_shutdown(); } -static bool nfsd_needs_lockd(void) +static bool nfsd_needs_lockd(struct nfsd_net *nn) { -#if defined(CONFIG_NFSD_V3) - return (nfsd_versions[2] != NULL) || (nfsd_versions[3] != NULL); -#else - return (nfsd_versions[2] != NULL); -#endif + return nfsd_vers(nn, 2, NFSD_TEST) || nfsd_vers(nn, 3, NFSD_TEST); } -static int nfsd_startup_net(int nrservs, struct net *net) +static int nfsd_startup_net(int nrservs, struct net *net, const struct cred *cred) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; @@ -285,12 +359,12 @@ static int nfsd_startup_net(int nrservs, struct net *net) ret = nfsd_startup_generic(nrservs); if (ret) return ret; - ret = nfsd_init_socks(net); + ret = nfsd_init_socks(net, cred); if (ret) goto out_socks; - if (nfsd_needs_lockd() && !nn->lockd_up) { - ret = lockd_up(net); + if (nfsd_needs_lockd(nn) && !nn->lockd_up) { + ret = lockd_up(net, cred); if (ret) goto out_socks; nn->lockd_up = 1; @@ -422,20 +496,20 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) nfsd_export_flush(net); } -void nfsd_reset_versions(void) +void nfsd_reset_versions(struct nfsd_net *nn) { int i; for (i = 0; i < NFSD_NRVERS; i++) - if (nfsd_vers(i, NFSD_TEST)) + if (nfsd_vers(nn, i, NFSD_TEST)) return; for (i = 0; i < NFSD_NRVERS; i++) if (i != 4) - nfsd_vers(i, NFSD_SET); + nfsd_vers(nn, i, NFSD_SET); else { int minor = 0; - while (nfsd_minorversion(minor, NFSD_SET) >= 0) + while (nfsd_minorversion(nn, minor, NFSD_SET) >= 0) minor++; } } @@ -503,7 +577,7 @@ int nfsd_create_serv(struct net *net) } if (nfsd_max_blksize == 0) nfsd_max_blksize = nfsd_get_default_max_blksize(); - nfsd_reset_versions(); + nfsd_reset_versions(nn); nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, &nfsd_thread_sv_ops); if (nn->nfsd_serv == NULL) @@ -623,7 +697,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) * this is the first time nrservs is nonzero. */ int -nfsd_svc(int nrservs, struct net *net) +nfsd_svc(int nrservs, struct net *net, const struct cred *cred) { int error; bool nfsd_up_before; @@ -645,7 +719,7 @@ nfsd_svc(int nrservs, struct net *net) nfsd_up_before = nn->nfsd_net_up; - error = nfsd_startup_net(nrservs, net); + error = nfsd_startup_net(nrservs, net, cred); if (error) goto out_destroy; error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, @@ -667,6 +741,101 @@ out: return error; } +#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) +static bool +nfsd_support_acl_version(int vers) +{ + if (vers >= NFSD_ACL_MINVERS && vers < NFSD_ACL_NRVERS) + return nfsd_acl_version[vers] != NULL; + return false; +} + +static int +nfsd_acl_rpcbind_set(struct net *net, const struct svc_program *progp, + u32 version, int family, unsigned short proto, + unsigned short port) +{ + if (!nfsd_support_acl_version(version) || + !nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) + return 0; + return svc_generic_rpcbind_set(net, progp, version, family, + proto, port); +} + +static __be32 +nfsd_acl_init_request(struct svc_rqst *rqstp, + const struct svc_program *progp, + struct svc_process_info *ret) +{ + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + int i; + + if (likely(nfsd_support_acl_version(rqstp->rq_vers) && + nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) + return svc_generic_init_request(rqstp, progp, ret); + + ret->mismatch.lovers = NFSD_ACL_NRVERS; + for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) { + if (nfsd_support_acl_version(rqstp->rq_vers) && + nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.lovers = i; + break; + } + } + if (ret->mismatch.lovers == NFSD_ACL_NRVERS) + return rpc_prog_unavail; + ret->mismatch.hivers = NFSD_ACL_MINVERS; + for (i = NFSD_ACL_NRVERS - 1; i >= NFSD_ACL_MINVERS; i--) { + if (nfsd_support_acl_version(rqstp->rq_vers) && + nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.hivers = i; + break; + } + } + return rpc_prog_mismatch; +} +#endif + +static int +nfsd_rpcbind_set(struct net *net, const struct svc_program *progp, + u32 version, int family, unsigned short proto, + unsigned short port) +{ + if (!nfsd_vers(net_generic(net, nfsd_net_id), version, NFSD_TEST)) + return 0; + return svc_generic_rpcbind_set(net, progp, version, family, + proto, port); +} + +static __be32 +nfsd_init_request(struct svc_rqst *rqstp, + const struct svc_program *progp, + struct svc_process_info *ret) +{ + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + int i; + + if (likely(nfsd_vers(nn, rqstp->rq_vers, NFSD_TEST))) + return svc_generic_init_request(rqstp, progp, ret); + + ret->mismatch.lovers = NFSD_NRVERS; + for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) { + if (nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.lovers = i; + break; + } + } + if (ret->mismatch.lovers == NFSD_NRVERS) + return rpc_prog_unavail; + ret->mismatch.hivers = NFSD_MINVERS; + for (i = NFSD_NRVERS - 1; i >= NFSD_MINVERS; i--) { + if (nfsd_vers(nn, i, NFSD_TEST)) { + ret->mismatch.hivers = i; + break; + } + } + return rpc_prog_mismatch; +} /* * This is the NFS server kernel thread diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 6b2e8b73d36e..b51fe515f06f 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -71,7 +71,7 @@ decode_filename(__be32 *p, char **namp, unsigned int *lenp) } static __be32 * -decode_sattr(__be32 *p, struct iattr *iap) +decode_sattr(__be32 *p, struct iattr *iap, struct user_namespace *userns) { u32 tmp, tmp1; @@ -86,12 +86,12 @@ decode_sattr(__be32 *p, struct iattr *iap) iap->ia_mode = tmp; } if ((tmp = ntohl(*p++)) != (u32)-1) { - iap->ia_uid = make_kuid(&init_user_ns, tmp); + iap->ia_uid = make_kuid(userns, tmp); if (uid_valid(iap->ia_uid)) iap->ia_valid |= ATTR_UID; } if ((tmp = ntohl(*p++)) != (u32)-1) { - iap->ia_gid = make_kgid(&init_user_ns, tmp); + iap->ia_gid = make_kgid(userns, tmp); if (gid_valid(iap->ia_gid)) iap->ia_valid |= ATTR_GID; } @@ -129,6 +129,7 @@ static __be32 * encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat) { + struct user_namespace *userns = nfsd_user_namespace(rqstp); struct dentry *dentry = fhp->fh_dentry; int type; struct timespec64 time; @@ -139,8 +140,8 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, *p++ = htonl(nfs_ftypes[type >> 12]); *p++ = htonl((u32) stat->mode); *p++ = htonl((u32) stat->nlink); - *p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid)); - *p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid)); + *p++ = htonl((u32) from_kuid_munged(userns, stat->uid)); + *p++ = htonl((u32) from_kgid_munged(userns, stat->gid)); if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) { *p++ = htonl(NFS_MAXPATHLEN); @@ -216,7 +217,7 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) p = decode_fh(p, &args->fh); if (!p) return 0; - p = decode_sattr(p, &args->attrs); + p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); return xdr_argsize_check(rqstp, p); } @@ -319,7 +320,7 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) if ( !(p = decode_fh(p, &args->fh)) || !(p = decode_filename(p, &args->name, &args->len))) return 0; - p = decode_sattr(p, &args->attrs); + p = decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); return xdr_argsize_check(rqstp, p); } @@ -398,7 +399,7 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) return 0; p += xdrlen; } - decode_sattr(p, &args->attrs); + decode_sattr(p, &args->attrs, nfsd_user_namespace(rqstp)); return 1; } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 9d6cb246c6c5..5dbd16946e8e 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -39,6 +39,7 @@ #include <linux/refcount.h> #include <linux/sunrpc/svc_xprt.h> #include "nfsfh.h" +#include "nfsd.h" typedef struct { u32 cl_boot; @@ -316,6 +317,10 @@ struct nfs4_client { clientid_t cl_clientid; /* generated by server */ nfs4_verifier cl_confirm; /* generated by server */ u32 cl_minorversion; + /* NFSv4.1 client implementation id: */ + struct xdr_netobj cl_nii_domain; + struct xdr_netobj cl_nii_name; + struct timespec cl_nii_time; /* for v4.0 and v4.1 callbacks: */ struct nfs4_cb_conn cl_cb_conn; @@ -347,9 +352,13 @@ struct nfs4_client { struct nfsd4_clid_slot cl_cs_slot; /* create_session slot */ u32 cl_exchange_flags; /* number of rpc's in progress over an associated session: */ - atomic_t cl_refcount; + atomic_t cl_rpc_users; + struct nfsdfs_client cl_nfsdfs; struct nfs4_op_map cl_spo_must_allow; + /* debugging info directory under nfsd/clients/ : */ + struct dentry *cl_nfsd_dentry; + /* for nfs41 callbacks */ /* We currently support a single back channel with a single slot */ unsigned long cl_cb_slot_busy; @@ -368,7 +377,7 @@ struct nfs4_client { struct nfs4_client_reclaim { struct list_head cr_strhash; /* hash by cr_name */ struct nfs4_client *cr_clp; /* pointer to associated clp */ - char cr_recdir[HEXDIR_LEN]; /* recover dir */ + struct xdr_netobj cr_name; /* recovery dir name */ }; /* A reasonable value for REPLAY_ISIZE was estimated as follows: @@ -620,7 +629,7 @@ void nfs4_put_stid(struct nfs4_stid *s); void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid); void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *); extern void nfs4_release_reclaim(struct nfsd_net *); -extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, +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); @@ -635,9 +644,9 @@ extern void nfsd4_destroy_callback_queue(void); extern void nfsd4_shutdown_callback(struct nfs4_client *); extern void nfsd4_shutdown_copy(struct nfs4_client *clp); extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp); -extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name, +extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name, struct nfsd_net *nn); -extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn); +extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn); struct nfs4_file *find_file(struct knfsd_fh *fh); void put_nfs4_file(struct nfs4_file *fi); @@ -663,7 +672,7 @@ extern void nfsd4_record_grace_done(struct nfsd_net *nn); /* nfs fault injection functions */ #ifdef CONFIG_NFSD_FAULT_INJECTION -int nfsd_fault_inject_init(void); +void nfsd_fault_inject_init(void); void nfsd_fault_inject_cleanup(void); u64 nfsd_inject_print_clients(void); @@ -684,7 +693,7 @@ u64 nfsd_inject_forget_delegations(u64); u64 nfsd_inject_recall_client_delegations(struct sockaddr_storage *, size_t); u64 nfsd_inject_recall_delegations(u64); #else /* CONFIG_NFSD_FAULT_INJECTION */ -static inline int nfsd_fault_inject_init(void) { return 0; } +static inline void nfsd_fault_inject_init(void) {} static inline void nfsd_fault_inject_cleanup(void) {} #endif /* CONFIG_NFSD_FAULT_INJECTION */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 7dc98e14655d..c85783e536d5 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -404,7 +404,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, /* * If utimes(2) and friends are called with times not NULL, we should * not set NFSD_MAY_WRITE bit. Otherwise fh_verify->nfsd_permission - * will return EACCESS, when the caller's effective UID does not match + * will return EACCES, when the caller's effective UID does not match * the owner of the file, and the caller is not privileged. In this * situation, we should return EPERM(notify_change will return this). */ @@ -1786,12 +1786,12 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, rdentry = lookup_one_len(fname, dentry, flen); host_err = PTR_ERR(rdentry); if (IS_ERR(rdentry)) - goto out_nfserr; + goto out_drop_write; if (d_really_is_negative(rdentry)) { dput(rdentry); - err = nfserr_noent; - goto out; + host_err = -ENOENT; + goto out_drop_write; } if (!type) @@ -1805,6 +1805,8 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, host_err = commit_metadata(fhp); dput(rdentry); +out_drop_write: + fh_drop_write(fhp); out_nfserr: err = nfserrno(host_err); out: diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index a7e107309f76..db351247892d 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -120,8 +120,11 @@ void nfsd_put_raparams(struct file *file, struct raparms *ra); static inline int fh_want_write(struct svc_fh *fh) { - int ret = mnt_want_write(fh->fh_export->ex_path.mnt); + int ret; + if (fh->fh_want_write) + return 0; + ret = mnt_want_write(fh->fh_export->ex_path.mnt); if (!ret) fh->fh_want_write = true; return ret; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index feeb6d4bdffd..d64c870f998a 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -410,6 +410,9 @@ struct nfsd4_exchange_id { int spa_how; u32 spo_must_enforce[3]; u32 spo_must_allow[3]; + struct xdr_netobj nii_domain; + struct xdr_netobj nii_name; + struct timespec64 nii_time; }; struct nfsd4_sequence { @@ -472,7 +475,7 @@ struct nfsd4_layoutcommit { u32 lc_reclaim; /* request */ u32 lc_newoffset; /* request */ u64 lc_last_wr; /* request */ - struct timespec lc_mtime; /* request */ + struct timespec64 lc_mtime; /* request */ u32 lc_layout_type; /* request */ u32 lc_up_len; /* layout length */ void *lc_up_layout; /* decoded by callback */ diff --git a/fs/nilfs2/Kconfig b/fs/nilfs2/Kconfig index 80da8eb27393..254d102e79c9 100644 --- a/fs/nilfs2/Kconfig +++ b/fs/nilfs2/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config NILFS2_FS tristate "NILFS2 file system support" select CRC32 diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 9b96d79eea6c..91b9dac6b2cc 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -148,13 +148,8 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp, oldflags = NILFS_I(inode)->i_flags; - /* - * The IMMUTABLE and APPEND_ONLY flags can only be changed by the - * relevant capability. - */ - ret = -EPERM; - if (((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) && - !capable(CAP_LINUX_IMMUTABLE)) + ret = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (ret) goto out; ret = nilfs_transaction_begin(inode->i_sb, &ti, 0); diff --git a/fs/nls/Kconfig b/fs/nls/Kconfig index e2ce79ef48c4..5a63303298e6 100644 --- a/fs/nls/Kconfig +++ b/fs/nls/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Native language support configuration # diff --git a/fs/no-block.c b/fs/no-block.c index 6e40e42a43de..481c0f0ab4bd 100644 --- a/fs/no-block.c +++ b/fs/no-block.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* no-block.c: implementation of routines required for non-BLOCK configuration * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> diff --git a/fs/notify/Kconfig b/fs/notify/Kconfig index 2a24249b30af..c020d26ba223 100644 --- a/fs/notify/Kconfig +++ b/fs/notify/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config FSNOTIFY def_bool n select SRCU diff --git a/fs/notify/dnotify/Kconfig b/fs/notify/dnotify/Kconfig index f9c1ca139d8f..3df7def17eea 100644 --- a/fs/notify/dnotify/Kconfig +++ b/fs/notify/dnotify/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config DNOTIFY bool "Dnotify support" select FSNOTIFY diff --git a/fs/notify/dnotify/Makefile b/fs/notify/dnotify/Makefile index f145251dcadb..121b4dd6b1fe 100644 --- a/fs/notify/dnotify/Makefile +++ b/fs/notify/dnotify/Makefile @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_DNOTIFY) += dnotify.o diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 250369d6901d..c03758c91481 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Directory notifications for Linux. * @@ -5,16 +6,6 @@ * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * dnotify was largly rewritten to use the new fsnotify infrastructure - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2, or (at your option) any - * later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/fs.h> #include <linux/module.h> diff --git a/fs/notify/fanotify/Kconfig b/fs/notify/fanotify/Kconfig index 521dc91d2cb5..8b9103f126ad 100644 --- a/fs/notify/fanotify/Kconfig +++ b/fs/notify/fanotify/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config FANOTIFY bool "Filesystem wide access notification" select FSNOTIFY diff --git a/fs/notify/fanotify/Makefile b/fs/notify/fanotify/Makefile index 0999213e7e6e..25ef222915e5 100644 --- a/fs/notify/fanotify/Makefile +++ b/fs/notify/fanotify/Makefile @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_FANOTIFY) += fanotify.o fanotify_user.o diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index e6fde1a5c072..5778d1347b35 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -288,10 +288,13 @@ struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, /* * For queues with unlimited length lost events are not expected and * can possibly have security implications. Avoid losing events when - * memory is short. + * memory is short. For the limited size queues, avoid OOM killer in the + * target monitoring memcg as it may have security repercussion. */ if (group->max_events == UINT_MAX) gfp |= __GFP_NOFAIL; + else + gfp |= __GFP_RETRY_MAYFAIL; /* Whoever is interested in the event, pays for the allocation. */ memalloc_use_memcg(group->memcg); @@ -355,6 +358,10 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) /* Mark is just getting destroyed or created? */ if (!conn) continue; + if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) + continue; + /* Pairs with smp_wmb() in fsnotify_add_mark_list() */ + smp_rmb(); fsid = conn->fsid; if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1])) continue; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index a90bb19dcfa2..91006f47e420 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -920,6 +920,22 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) return 0; } +static int fanotify_events_supported(struct path *path, __u64 mask) +{ + /* + * Some filesystems such as 'proc' acquire unusual locks when opening + * files. For them fanotify permission events have high chances of + * deadlocking the system - open done when reporting fanotify event + * blocks on this "unusual" lock while another process holding the lock + * waits for fanotify permission event to be answered. Just disallow + * permission events for such filesystems. + */ + if (mask & FANOTIFY_PERM_EVENTS && + path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM) + return -EINVAL; + return 0; +} + static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, int dfd, const char __user *pathname) { @@ -1018,6 +1034,12 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (ret) goto fput_and_out; + if (flags & FAN_MARK_ADD) { + ret = fanotify_events_supported(&path, mask); + if (ret) + goto path_put_and_out; + } + if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) { ret = fanotify_test_fid(&path, &__fsid); if (ret) diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 8c7cbac7183c..2ecef6155fc0 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; see the file COPYING. If not, write to - * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/dcache.h> @@ -108,47 +95,6 @@ void fsnotify_sb_delete(struct super_block *sb) } /* - * fsnotify_nameremove - a filename was removed from a directory - * - * This is mostly called under parent vfs inode lock so name and - * dentry->d_parent should be stable. However there are some corner cases where - * inode lock is not held. So to be on the safe side and be reselient to future - * callers and out of tree users of d_delete(), we do not assume that d_parent - * and d_name are stable and we use dget_parent() and - * take_dentry_name_snapshot() to grab stable references. - */ -void fsnotify_nameremove(struct dentry *dentry, int isdir) -{ - struct dentry *parent; - struct name_snapshot name; - __u32 mask = FS_DELETE; - - /* d_delete() of pseudo inode? (e.g. __ns_get_path() playing tricks) */ - if (IS_ROOT(dentry)) - return; - - if (isdir) - mask |= FS_ISDIR; - - parent = dget_parent(dentry); - /* Avoid unneeded take_dentry_name_snapshot() */ - if (!(d_inode(parent)->i_fsnotify_mask & FS_DELETE) && - !(dentry->d_sb->s_fsnotify_mask & FS_DELETE)) - goto out_dput; - - take_dentry_name_snapshot(&name, dentry); - - fsnotify(d_inode(parent), mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, - &name.name, 0); - - release_dentry_name_snapshot(&name); - -out_dput: - dput(parent); -} -EXPORT_SYMBOL(fsnotify_nameremove); - -/* * Given an inode, first check if we care what happens to our children. Inotify * and dnotify both tell their parents about events. If we care about any event * on a child we run all of our children and set a dentry flag saying that the diff --git a/fs/notify/group.c b/fs/notify/group.c index c03b83662876..0391190305cc 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; see the file COPYING. If not, write to - * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/list.h> diff --git a/fs/notify/inotify/Kconfig b/fs/notify/inotify/Kconfig index 0161c74e76e2..6736e47d94d8 100644 --- a/fs/notify/inotify/Kconfig +++ b/fs/notify/inotify/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config INOTIFY_USER bool "Inotify support for userspace" select FSNOTIFY diff --git a/fs/notify/inotify/Makefile b/fs/notify/inotify/Makefile index a380dabe09de..812237eecf3a 100644 --- a/fs/notify/inotify/Makefile +++ b/fs/notify/inotify/Makefile @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_INOTIFY_USER) += inotify_fsnotify.o inotify_user.o diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index 7e8b131029f8..d510223d302c 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * fs/inotify_user.c - inotify support for userspace * @@ -10,16 +11,6 @@ * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * inotify was largely rewriten to make use of the fsnotify infrastructure - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2, or (at your option) any - * later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/dcache.h> /* d_unlinked */ @@ -99,9 +90,13 @@ int inotify_handle_event(struct fsnotify_group *group, i_mark = container_of(inode_mark, struct inotify_inode_mark, fsn_mark); - /* Whoever is interested in the event, pays for the allocation. */ + /* + * Whoever is interested in the event, pays for the allocation. Do not + * trigger OOM killer in the target monitoring memcg as it may have + * security repercussion. + */ memalloc_use_memcg(group->memcg); - event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT); + event = kmalloc(alloc_len, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); memalloc_unuse_memcg(); if (unlikely(!event)) { diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 7b53598c8804..cce8de32779f 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * fs/inotify_user.c - inotify support for userspace * @@ -10,16 +11,6 @@ * * Copyright (C) 2009 Eric Paris <Red Hat Inc> * inotify was largely rewriten to make use of the fsnotify infrastructure - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2, or (at your option) any - * later version. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/file.h> diff --git a/fs/notify/mark.c b/fs/notify/mark.c index b251105f646f..99ddd126f6f0 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; see the file COPYING. If not, write to - * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ /* @@ -495,10 +482,13 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, conn->type = type; conn->obj = connp; /* Cache fsid of filesystem containing the object */ - if (fsid) + if (fsid) { conn->fsid = *fsid; - else + conn->flags = FSNOTIFY_CONN_FLAG_HAS_FSID; + } else { conn->fsid.val[0] = conn->fsid.val[1] = 0; + conn->flags = 0; + } if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) inode = igrab(fsnotify_conn_inode(conn)); /* @@ -573,7 +563,12 @@ restart: if (err) return err; goto restart; - } else if (fsid && (conn->fsid.val[0] || conn->fsid.val[1]) && + } else if (fsid && !(conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID)) { + conn->fsid = *fsid; + /* Pairs with smp_rmb() in fanotify_get_fsid() */ + smp_wmb(); + conn->flags |= FSNOTIFY_CONN_FLAG_HAS_FSID; + } else if (fsid && (conn->flags & FSNOTIFY_CONN_FLAG_HAS_FSID) && (fsid->val[0] != conn->fsid.val[0] || fsid->val[1] != conn->fsid.val[1])) { /* diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 5f3a54d444b5..75d79d6d3ef0 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -1,19 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; see the file COPYING. If not, write to - * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA. */ /* diff --git a/fs/ntfs/Kconfig b/fs/ntfs/Kconfig index f5a868cc9152..de9fb5cff226 100644 --- a/fs/ntfs/Kconfig +++ b/fs/ntfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config NTFS_FS tristate "NTFS file system support" select NLS diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 8946130c87ad..7202a1e39d70 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * aops.c - NTFS kernel address space operations and page cache handling. * * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc. * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/errno.h> diff --git a/fs/ntfs/aops.h b/fs/ntfs/aops.h index 820d6eabf60f..f0962d46bd67 100644 --- a/fs/ntfs/aops.h +++ b/fs/ntfs/aops.h @@ -1,24 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /** * aops.h - Defines for NTFS kernel address space operations and page cache * handling. Part of the Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_AOPS_H diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 44a39a099b54..d563abc3e136 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * attrib.c - NTFS attribute operations. Part of the Linux-NTFS project. * * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc. * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/buffer_head.h> diff --git a/fs/ntfs/attrib.h b/fs/ntfs/attrib.h index 3c8b74c99b80..fe0890d3d072 100644 --- a/fs/ntfs/attrib.h +++ b/fs/ntfs/attrib.h @@ -1,24 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * attrib.h - Defines for attribute handling in NTFS Linux kernel driver. * Part of the Linux-NTFS project. * * Copyright (c) 2001-2005 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_ATTRIB_H diff --git a/fs/ntfs/bitmap.c b/fs/ntfs/bitmap.c index ec130c588d2b..0675b2400873 100644 --- a/fs/ntfs/bitmap.c +++ b/fs/ntfs/bitmap.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * bitmap.c - NTFS kernel bitmap handling. Part of the Linux-NTFS project. * * Copyright (c) 2004-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifdef NTFS_RW diff --git a/fs/ntfs/bitmap.h b/fs/ntfs/bitmap.h index 72c9ad8be70d..9dd2224ca9c4 100644 --- a/fs/ntfs/bitmap.h +++ b/fs/ntfs/bitmap.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * bitmap.h - Defines for NTFS kernel bitmap handling. Part of the Linux-NTFS * project. * * Copyright (c) 2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_BITMAP_H diff --git a/fs/ntfs/collate.c b/fs/ntfs/collate.c index 4a28ab3898ef..3ab6ec96abfe 100644 --- a/fs/ntfs/collate.c +++ b/fs/ntfs/collate.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * collate.c - NTFS kernel collation handling. Part of the Linux-NTFS project. * * Copyright (c) 2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include "collate.h" diff --git a/fs/ntfs/collate.h b/fs/ntfs/collate.h index aba83347e5fe..f2255619b4f4 100644 --- a/fs/ntfs/collate.h +++ b/fs/ntfs/collate.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * collate.h - Defines for NTFS kernel collation handling. Part of the * Linux-NTFS project. * * Copyright (c) 2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_COLLATE_H diff --git a/fs/ntfs/compress.c b/fs/ntfs/compress.c index df7c32b5fac7..d2f9d6a0ee32 100644 --- a/fs/ntfs/compress.c +++ b/fs/ntfs/compress.c @@ -1,24 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * compress.c - NTFS kernel compressed attributes handling. * Part of the Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/fs.h> diff --git a/fs/ntfs/debug.c b/fs/ntfs/debug.c index 825a54e8f490..a3c1c5656f8f 100644 --- a/fs/ntfs/debug.c +++ b/fs/ntfs/debug.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * debug.c - NTFS kernel debug support. Part of the Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "debug.h" diff --git a/fs/ntfs/debug.h b/fs/ntfs/debug.h index 61bf091e32a8..6fdef388f129 100644 --- a/fs/ntfs/debug.h +++ b/fs/ntfs/debug.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * debug.h - NTFS kernel debug support. Part of the Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_DEBUG_H diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 1a24be9e8405..3c4811469ae8 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * dir.c - NTFS kernel directory operations. Part of the Linux-NTFS project. * * Copyright (c) 2001-2007 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/buffer_head.h> diff --git a/fs/ntfs/dir.h b/fs/ntfs/dir.h index aea7582d561f..0e326753df40 100644 --- a/fs/ntfs/dir.h +++ b/fs/ntfs/dir.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * dir.h - Defines for directory handling in NTFS Linux kernel driver. Part of * the Linux-NTFS project. * * Copyright (c) 2002-2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_DIR_H diff --git a/fs/ntfs/endian.h b/fs/ntfs/endian.h index 927b5bf04b4f..f30c139bf9ae 100644 --- a/fs/ntfs/endian.h +++ b/fs/ntfs/endian.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * endian.h - Defines for endianness handling in NTFS Linux kernel driver. * Part of the Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_ENDIAN_H diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 331910fa8442..f42967b738eb 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * file.c - NTFS kernel file operations. Part of the Linux-NTFS project. * * Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc. - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/backing-dev.h> diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index 0d645f357930..d46c2c03a032 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * index.c - NTFS kernel index handling. Part of the Linux-NTFS project. * * Copyright (c) 2004-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/slab.h> diff --git a/fs/ntfs/index.h b/fs/ntfs/index.h index 8745469c3989..bb3c3ae55138 100644 --- a/fs/ntfs/index.h +++ b/fs/ntfs/index.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * index.h - Defines for NTFS kernel index handling. Part of the Linux-NTFS * project. * * Copyright (c) 2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_INDEX_H diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index fb1a2b49a5da..8baa34baf548 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * inode.c - NTFS kernel inode handling. * * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc. - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/buffer_head.h> diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h index 58c8fd2948d3..98e670fbdd31 100644 --- a/fs/ntfs/inode.h +++ b/fs/ntfs/inode.h @@ -1,24 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * inode.h - Defines for inode structures NTFS Linux kernel driver. Part of * the Linux-NTFS project. * * Copyright (c) 2001-2007 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_INODE_H diff --git a/fs/ntfs/layout.h b/fs/ntfs/layout.h index 809c0e6d8e09..85422761ff43 100644 --- a/fs/ntfs/layout.h +++ b/fs/ntfs/layout.h @@ -1,24 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * layout.h - All NTFS associated on-disk structures. Part of the Linux-NTFS * project. * * Copyright (c) 2001-2005 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_LAYOUT_H diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index 27a24a42f712..eda9972e6159 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * lcnalloc.c - Cluster (de)allocation code. Part of the Linux-NTFS project. * * Copyright (c) 2004-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifdef NTFS_RW diff --git a/fs/ntfs/lcnalloc.h b/fs/ntfs/lcnalloc.h index 2adb04316941..1589a6d8434b 100644 --- a/fs/ntfs/lcnalloc.h +++ b/fs/ntfs/lcnalloc.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * lcnalloc.h - Exports for NTFS kernel cluster (de)allocation. Part of the * Linux-NTFS project. * * Copyright (c) 2004-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_LCNALLOC_H diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index 353379ff6057..a0c40f1be7ac 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * logfile.c - NTFS kernel journal handling. Part of the Linux-NTFS project. * * Copyright (c) 2002-2007 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifdef NTFS_RW diff --git a/fs/ntfs/logfile.h b/fs/ntfs/logfile.h index aa2b6ac3f0a4..429d4909cc72 100644 --- a/fs/ntfs/logfile.h +++ b/fs/ntfs/logfile.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * logfile.h - Defines for NTFS kernel journal ($LogFile) handling. Part of * the Linux-NTFS project. * * Copyright (c) 2000-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_LOGFILE_H diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h index 5becc8acc8f4..842b0bfc3ac9 100644 --- a/fs/ntfs/malloc.h +++ b/fs/ntfs/malloc.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * malloc.h - NTFS kernel memory handling. Part of the Linux-NTFS project. * * Copyright (c) 2001-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_MALLOC_H diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index fb14d17666c8..20c841a906f2 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * mft.c - NTFS kernel mft record operations. Part of the Linux-NTFS project. * * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc. * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/buffer_head.h> diff --git a/fs/ntfs/mft.h b/fs/ntfs/mft.h index b52bf87b99de..17bfefc30271 100644 --- a/fs/ntfs/mft.h +++ b/fs/ntfs/mft.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * mft.h - Defines for mft record handling in NTFS Linux kernel driver. * Part of the Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_MFT_H diff --git a/fs/ntfs/mst.c b/fs/ntfs/mst.c index 5a858d839b65..16b3c884abfc 100644 --- a/fs/ntfs/mst.c +++ b/fs/ntfs/mst.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * mst.c - NTFS multi sector transfer protection handling code. Part of the * Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include "ntfs.h" diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 3986c7a1f6a8..2d3cc9e3395d 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * namei.c - NTFS kernel directory inode operations. Part of the Linux-NTFS * project. * * Copyright (c) 2001-2006 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/dcache.h> diff --git a/fs/ntfs/ntfs.h b/fs/ntfs/ntfs.h index 12de47b96ca9..e81376ea9152 100644 --- a/fs/ntfs/ntfs.h +++ b/fs/ntfs/ntfs.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * ntfs.h - Defines for NTFS Linux kernel driver. * * Copyright (c) 2001-2014 Anton Altaparmakov and Tuxera Inc. * Copyright (C) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_H diff --git a/fs/ntfs/quota.c b/fs/ntfs/quota.c index 9793e68ba1dd..9160480222fd 100644 --- a/fs/ntfs/quota.c +++ b/fs/ntfs/quota.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * quota.c - NTFS kernel quota ($Quota) handling. Part of the Linux-NTFS * project. * * Copyright (c) 2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifdef NTFS_RW diff --git a/fs/ntfs/quota.h b/fs/ntfs/quota.h index 4cbe5594c0b0..fe3132a3d6d2 100644 --- a/fs/ntfs/quota.h +++ b/fs/ntfs/quota.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * quota.h - Defines for NTFS kernel quota ($Quota) handling. Part of the * Linux-NTFS project. * * Copyright (c) 2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_QUOTA_H diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index eac7d6788a10..508744a93180 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /** * runlist.c - NTFS runlist handling code. Part of the Linux-NTFS project. * * Copyright (c) 2001-2007 Anton Altaparmakov * Copyright (c) 2002-2005 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include "debug.h" diff --git a/fs/ntfs/runlist.h b/fs/ntfs/runlist.h index 47728fbb610b..38de0a375f59 100644 --- a/fs/ntfs/runlist.h +++ b/fs/ntfs/runlist.h @@ -1,24 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * runlist.h - Defines for runlist handling in NTFS Linux kernel driver. * Part of the Linux-NTFS project. * * Copyright (c) 2001-2005 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_RUNLIST_H diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 887ea8b3b000..29621d40f448 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project. * * Copyright (c) 2001-2012 Anton Altaparmakov and Tuxera Inc. * Copyright (c) 2001,2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/fs/ntfs/sysctl.c b/fs/ntfs/sysctl.c index a503156ec15f..a030d00af90c 100644 --- a/fs/ntfs/sysctl.c +++ b/fs/ntfs/sysctl.c @@ -1,24 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * sysctl.c - Code for sysctl handling in NTFS Linux kernel driver. Part of * the Linux-NTFS project. Adapted from the old NTFS driver, * Copyright (C) 1997 Martin von Löwis, Régis Duchesne * * Copyright (c) 2002-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifdef DEBUG diff --git a/fs/ntfs/sysctl.h b/fs/ntfs/sysctl.h index d4f8ce920d95..96bb2299d2d5 100644 --- a/fs/ntfs/sysctl.h +++ b/fs/ntfs/sysctl.h @@ -1,24 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * sysctl.h - Defines for sysctl handling in NTFS Linux kernel driver. Part of * the Linux-NTFS project. Adapted from the old NTFS driver, * Copyright (C) 1997 Martin von Löwis, Régis Duchesne * * Copyright (c) 2002-2004 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_SYSCTL_H diff --git a/fs/ntfs/time.h b/fs/ntfs/time.h index 24cd719f1fd2..6b63261300cc 100644 --- a/fs/ntfs/time.h +++ b/fs/ntfs/time.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * time.h - NTFS time conversion functions. Part of the Linux-NTFS project. * * Copyright (c) 2001-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_TIME_H diff --git a/fs/ntfs/types.h b/fs/ntfs/types.h index 8c8053b66984..9a47859e7a06 100644 --- a/fs/ntfs/types.h +++ b/fs/ntfs/types.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * types.h - Defines for NTFS Linux kernel driver specific types. * Part of the Linux-NTFS project. * * Copyright (c) 2001-2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_TYPES_H diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c index 005ca4b0f132..a6b6c64f14a9 100644 --- a/fs/ntfs/unistr.c +++ b/fs/ntfs/unistr.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * unistr.c - NTFS Unicode string handling. Part of the Linux-NTFS project. * * Copyright (c) 2001-2006 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/slab.h> diff --git a/fs/ntfs/upcase.c b/fs/ntfs/upcase.c index e2f72ca98037..4ebe84a78dea 100644 --- a/fs/ntfs/upcase.c +++ b/fs/ntfs/upcase.c @@ -1,24 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * upcase.c - Generate the full NTFS Unicode upcase table in little endian. * Part of the Linux-NTFS project. * * Copyright (c) 2001 Richard Russon <ntfs@flatcap.org> * Copyright (c) 2001-2006 Anton Altaparmakov - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the Free - * Software Foundation; either version 2 of the License, or (at your option) - * any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS source - * in the file COPYING); if not, write to the Free Software Foundation, - * Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include "malloc.h" diff --git a/fs/ntfs/usnjrnl.c b/fs/ntfs/usnjrnl.c index b2bc0d55b036..9097a0b4ef25 100644 --- a/fs/ntfs/usnjrnl.c +++ b/fs/ntfs/usnjrnl.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * usnjrnl.h - NTFS kernel transaction log ($UsnJrnl) handling. Part of the * Linux-NTFS project. * * Copyright (c) 2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifdef NTFS_RW diff --git a/fs/ntfs/usnjrnl.h b/fs/ntfs/usnjrnl.h index 00d8e6bd7c36..85f531b59395 100644 --- a/fs/ntfs/usnjrnl.h +++ b/fs/ntfs/usnjrnl.h @@ -1,23 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * usnjrnl.h - Defines for NTFS kernel transaction log ($UsnJrnl) handling. * Part of the Linux-NTFS project. * * Copyright (c) 2005 Anton Altaparmakov - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_USNJRNL_H diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h index 4f579b02bc76..930a9ae8a053 100644 --- a/fs/ntfs/volume.h +++ b/fs/ntfs/volume.h @@ -1,24 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * volume.h - Defines for volume structures in NTFS Linux kernel driver. Part * of the Linux-NTFS project. * * Copyright (c) 2001-2006 Anton Altaparmakov * Copyright (c) 2002 Richard Russon - * - * This program/include file is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as published - * by the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program/include file is distributed in the hope that it will be - * useful, but WITHOUT ANY WARRANTY; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program (in the main directory of the Linux-NTFS - * distribution in the file COPYING); if not, write to the Free Software - * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_VOLUME_H diff --git a/fs/ocfs2/Kconfig b/fs/ocfs2/Kconfig index 77a8de5f7119..46bba20da6b5 100644 --- a/fs/ocfs2/Kconfig +++ b/fs/ocfs2/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config OCFS2_FS tristate "OCFS2 file system support" depends on NET && SYSFS && CONFIGFS_FS diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 917fadca8a7b..3e7da392aa6f 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -8,15 +9,6 @@ * CREDITS: * Lots of code in this file is copy from linux/fs/ext3/acl.c. * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/init.h> diff --git a/fs/ocfs2/acl.h b/fs/ocfs2/acl.h index 7be0bb756286..127b13432146 100644 --- a/fs/ocfs2/acl.h +++ b/fs/ocfs2/acl.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * acl.h * * Copyright (C) 2004, 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_ACL_H diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index 6f0999015a44..0c335b51043d 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Extent allocs and frees * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> @@ -6205,17 +6191,17 @@ int ocfs2_begin_truncate_log_recovery(struct ocfs2_super *osb, if (le16_to_cpu(tl->tl_used)) { trace_ocfs2_truncate_log_recovery_num(le16_to_cpu(tl->tl_used)); - *tl_copy = kmalloc(tl_bh->b_size, GFP_KERNEL); + /* + * Assuming the write-out below goes well, this copy will be + * passed back to recovery for processing. + */ + *tl_copy = kmemdup(tl_bh->b_data, tl_bh->b_size, GFP_KERNEL); if (!(*tl_copy)) { status = -ENOMEM; mlog_errno(status); goto bail; } - /* Assuming the write-out below goes well, this copy - * will be passed back to recovery for processing. */ - memcpy(*tl_copy, tl_bh->b_data, tl_bh->b_size); - /* All we need to do to clear the truncate log is set * tl_used. */ tl->tl_used = 0; diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h index 250bcacdf9e9..7f973dd76dbc 100644 --- a/fs/ocfs2/alloc.h +++ b/fs/ocfs2/alloc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_ALLOC_H diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 832c1759a09a..a4c905d6b575 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h index 3494a62ed749..70ed4382750d 100644 --- a/fs/ocfs2/aops.h +++ b/fs/ocfs2/aops.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2002, 2004, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_AOPS_H diff --git a/fs/ocfs2/blockcheck.c b/fs/ocfs2/blockcheck.c index 0725e6054650..429e6a8359a5 100644 --- a/fs/ocfs2/blockcheck.c +++ b/fs/ocfs2/blockcheck.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Checksum and ECC codes for the OCFS2 userspace library. * * Copyright (C) 2006, 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/kernel.h> @@ -250,57 +242,29 @@ static struct dentry *blockcheck_debugfs_create(const char *name, static void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *stats) { if (stats) { - debugfs_remove(stats->b_debug_check); - stats->b_debug_check = NULL; - debugfs_remove(stats->b_debug_failure); - stats->b_debug_failure = NULL; - debugfs_remove(stats->b_debug_recover); - stats->b_debug_recover = NULL; - debugfs_remove(stats->b_debug_dir); + debugfs_remove_recursive(stats->b_debug_dir); stats->b_debug_dir = NULL; } } -static int ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent) +static void ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent) { - int rc = -EINVAL; - - if (!stats) - goto out; - stats->b_debug_dir = debugfs_create_dir("blockcheck", parent); - if (!stats->b_debug_dir) - goto out; - - stats->b_debug_check = - blockcheck_debugfs_create("blocks_checked", - stats->b_debug_dir, - &stats->b_check_count); - stats->b_debug_failure = - blockcheck_debugfs_create("checksums_failed", - stats->b_debug_dir, - &stats->b_failure_count); + blockcheck_debugfs_create("blocks_checked", stats->b_debug_dir, + &stats->b_check_count); - stats->b_debug_recover = - blockcheck_debugfs_create("ecc_recoveries", - stats->b_debug_dir, - &stats->b_recover_count); - if (stats->b_debug_check && stats->b_debug_failure && - stats->b_debug_recover) - rc = 0; + blockcheck_debugfs_create("checksums_failed", stats->b_debug_dir, + &stats->b_failure_count); -out: - if (rc) - ocfs2_blockcheck_debug_remove(stats); - return rc; + blockcheck_debugfs_create("ecc_recoveries", stats->b_debug_dir, + &stats->b_recover_count); } #else -static inline int ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent) +static inline void ocfs2_blockcheck_debug_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent) { - return 0; } static inline void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats *stats) @@ -309,10 +273,10 @@ static inline void ocfs2_blockcheck_debug_remove(struct ocfs2_blockcheck_stats * #endif /* CONFIG_DEBUG_FS */ /* Always-called wrappers for starting and stopping the debugfs files */ -int ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent) +void ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent) { - return ocfs2_blockcheck_debug_install(stats, parent); + ocfs2_blockcheck_debug_install(stats, parent); } void ocfs2_blockcheck_stats_debugfs_remove(struct ocfs2_blockcheck_stats *stats) diff --git a/fs/ocfs2/blockcheck.h b/fs/ocfs2/blockcheck.h index d4b69febf70a..8f17d2c85f40 100644 --- a/fs/ocfs2/blockcheck.h +++ b/fs/ocfs2/blockcheck.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Checksum and ECC codes for the OCFS2 userspace library. * * Copyright (C) 2004, 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_BLOCKCHECK_H @@ -33,9 +25,6 @@ struct ocfs2_blockcheck_stats { * ocfs2_blockcheck_stats_debugfs_install() */ struct dentry *b_debug_dir; /* Parent of the debugfs files */ - struct dentry *b_debug_check; /* Exposes b_check_count */ - struct dentry *b_debug_failure; /* Exposes b_failure_count */ - struct dentry *b_debug_recover; /* Exposes b_recover_count */ }; @@ -64,8 +53,8 @@ int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr, struct ocfs2_blockcheck_stats *stats); /* Debug Initialization */ -int ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, - struct dentry *parent); +void ocfs2_blockcheck_stats_debugfs_install(struct ocfs2_blockcheck_stats *stats, + struct dentry *parent); void ocfs2_blockcheck_stats_debugfs_remove(struct ocfs2_blockcheck_stats *stats); /* diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index f9b84f7a3e4b..f0b104e483d8 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Buffer cache handling * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/buffer_head_io.h b/fs/ocfs2/buffer_head_io.h index b1bb70c8ca4d..1c5e533fba04 100644 --- a/fs/ocfs2/buffer_head_io.h +++ b/fs/ocfs2/buffer_head_io.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Buffer cache handling functions defined * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_BUFFER_HEAD_IO_H diff --git a/fs/ocfs2/cluster/Makefile b/fs/ocfs2/cluster/Makefile index 1aefc0350ec3..0e5b73215819 100644 --- a/fs/ocfs2/cluster/Makefile +++ b/fs/ocfs2/cluster/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_OCFS2_FS) += ocfs2_nodemanager.o ocfs2_nodemanager-objs := heartbeat.o masklog.o sys.o nodemanager.o \ diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index f3c20b279eb2..f1b613327ac8 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2004, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/kernel.h> @@ -106,10 +92,6 @@ static struct o2hb_debug_buf *o2hb_db_failedregions; #define O2HB_DEBUG_REGION_PINNED "pinned" static struct dentry *o2hb_debug_dir; -static struct dentry *o2hb_debug_livenodes; -static struct dentry *o2hb_debug_liveregions; -static struct dentry *o2hb_debug_quorumregions; -static struct dentry *o2hb_debug_failedregions; static LIST_HEAD(o2hb_all_regions); @@ -1198,7 +1180,7 @@ bail: if (atomic_read(®->hr_steady_iterations) != 0) { if (atomic_dec_and_test(®->hr_unsteady_iterations)) { printk(KERN_NOTICE "o2hb: Unable to stabilize " - "heartbeart on region %s (%s)\n", + "heartbeat on region %s (%s)\n", config_item_name(®->hr_item), reg->hr_dev_name); atomic_set(®->hr_steady_iterations, 0); @@ -1405,11 +1387,7 @@ static const struct file_operations o2hb_debug_fops = { void o2hb_exit(void) { - debugfs_remove(o2hb_debug_failedregions); - debugfs_remove(o2hb_debug_quorumregions); - debugfs_remove(o2hb_debug_liveregions); - debugfs_remove(o2hb_debug_livenodes); - debugfs_remove(o2hb_debug_dir); + debugfs_remove_recursive(o2hb_debug_dir); kfree(o2hb_db_livenodes); kfree(o2hb_db_liveregions); kfree(o2hb_db_quorumregions); @@ -1433,79 +1411,37 @@ static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir, &o2hb_debug_fops); } -static int o2hb_debug_init(void) +static void o2hb_debug_init(void) { - int ret = -ENOMEM; - o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL); - if (!o2hb_debug_dir) { - mlog_errno(ret); - goto bail; - } - - o2hb_debug_livenodes = o2hb_debug_create(O2HB_DEBUG_LIVENODES, - o2hb_debug_dir, - &o2hb_db_livenodes, - sizeof(*o2hb_db_livenodes), - O2HB_DB_TYPE_LIVENODES, - sizeof(o2hb_live_node_bitmap), - O2NM_MAX_NODES, - o2hb_live_node_bitmap); - if (!o2hb_debug_livenodes) { - mlog_errno(ret); - goto bail; - } - - o2hb_debug_liveregions = o2hb_debug_create(O2HB_DEBUG_LIVEREGIONS, - o2hb_debug_dir, - &o2hb_db_liveregions, - sizeof(*o2hb_db_liveregions), - O2HB_DB_TYPE_LIVEREGIONS, - sizeof(o2hb_live_region_bitmap), - O2NM_MAX_REGIONS, - o2hb_live_region_bitmap); - if (!o2hb_debug_liveregions) { - mlog_errno(ret); - goto bail; - } - o2hb_debug_quorumregions = - o2hb_debug_create(O2HB_DEBUG_QUORUMREGIONS, - o2hb_debug_dir, - &o2hb_db_quorumregions, - sizeof(*o2hb_db_quorumregions), - O2HB_DB_TYPE_QUORUMREGIONS, - sizeof(o2hb_quorum_region_bitmap), - O2NM_MAX_REGIONS, - o2hb_quorum_region_bitmap); - if (!o2hb_debug_quorumregions) { - mlog_errno(ret); - goto bail; - } + o2hb_debug_create(O2HB_DEBUG_LIVENODES, o2hb_debug_dir, + &o2hb_db_livenodes, sizeof(*o2hb_db_livenodes), + O2HB_DB_TYPE_LIVENODES, sizeof(o2hb_live_node_bitmap), + O2NM_MAX_NODES, o2hb_live_node_bitmap); - o2hb_debug_failedregions = - o2hb_debug_create(O2HB_DEBUG_FAILEDREGIONS, - o2hb_debug_dir, - &o2hb_db_failedregions, - sizeof(*o2hb_db_failedregions), - O2HB_DB_TYPE_FAILEDREGIONS, - sizeof(o2hb_failed_region_bitmap), - O2NM_MAX_REGIONS, - o2hb_failed_region_bitmap); - if (!o2hb_debug_failedregions) { - mlog_errno(ret); - goto bail; - } + o2hb_debug_create(O2HB_DEBUG_LIVEREGIONS, o2hb_debug_dir, + &o2hb_db_liveregions, sizeof(*o2hb_db_liveregions), + O2HB_DB_TYPE_LIVEREGIONS, + sizeof(o2hb_live_region_bitmap), O2NM_MAX_REGIONS, + o2hb_live_region_bitmap); - ret = 0; -bail: - if (ret) - o2hb_exit(); + o2hb_debug_create(O2HB_DEBUG_QUORUMREGIONS, o2hb_debug_dir, + &o2hb_db_quorumregions, + sizeof(*o2hb_db_quorumregions), + O2HB_DB_TYPE_QUORUMREGIONS, + sizeof(o2hb_quorum_region_bitmap), O2NM_MAX_REGIONS, + o2hb_quorum_region_bitmap); - return ret; + o2hb_debug_create(O2HB_DEBUG_FAILEDREGIONS, o2hb_debug_dir, + &o2hb_db_failedregions, + sizeof(*o2hb_db_failedregions), + O2HB_DB_TYPE_FAILEDREGIONS, + sizeof(o2hb_failed_region_bitmap), O2NM_MAX_REGIONS, + o2hb_failed_region_bitmap); } -int o2hb_init(void) +void o2hb_init(void) { int i; @@ -1525,7 +1461,7 @@ int o2hb_init(void) o2hb_dependent_users = 0; - return o2hb_debug_init(); + o2hb_debug_init(); } /* if we're already in a callback then we're already serialized by the sem */ diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h index a9e67efc0004..beed31ea86cf 100644 --- a/fs/ocfs2/cluster/heartbeat.h +++ b/fs/ocfs2/cluster/heartbeat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * Function prototypes * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef O2CLUSTER_HEARTBEAT_H @@ -78,7 +63,7 @@ void o2hb_unregister_callback(const char *region_uuid, void o2hb_fill_node_map(unsigned long *map, unsigned bytes); void o2hb_exit(void); -int o2hb_init(void); +void o2hb_init(void); int o2hb_check_node_heartbeating_no_sem(u8 node_num); int o2hb_check_node_heartbeating_from_callback(u8 node_num); void o2hb_stop_all_regions(void); diff --git a/fs/ocfs2/cluster/masklog.c b/fs/ocfs2/cluster/masklog.c index d331c2386b94..1d696c96b8b2 100644 --- a/fs/ocfs2/cluster/masklog.c +++ b/fs/ocfs2/cluster/masklog.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2004, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/module.h> diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index a396096a5099..446e452ac7a6 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef O2CLUSTER_MASKLOG_H diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c index 74a21f6695c8..02bf4a1774cc 100644 --- a/fs/ocfs2/cluster/netdebug.c +++ b/fs/ocfs2/cluster/netdebug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * debug functionality for o2net * * Copyright (C) 2005, 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifdef CONFIG_DEBUG_FS @@ -53,10 +38,6 @@ #define SHOW_SOCK_STATS 1 static struct dentry *o2net_dentry; -static struct dentry *sc_dentry; -static struct dentry *nst_dentry; -static struct dentry *stats_dentry; -static struct dentry *nodes_dentry; static DEFINE_SPINLOCK(o2net_debug_lock); @@ -505,36 +486,23 @@ static const struct file_operations nodes_fops = { void o2net_debugfs_exit(void) { - debugfs_remove(nodes_dentry); - debugfs_remove(stats_dentry); - debugfs_remove(sc_dentry); - debugfs_remove(nst_dentry); - debugfs_remove(o2net_dentry); + debugfs_remove_recursive(o2net_dentry); } -int o2net_debugfs_init(void) +void o2net_debugfs_init(void) { umode_t mode = S_IFREG|S_IRUSR; o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL); - if (o2net_dentry) - nst_dentry = debugfs_create_file(NST_DEBUG_NAME, mode, - o2net_dentry, NULL, &nst_seq_fops); - if (nst_dentry) - sc_dentry = debugfs_create_file(SC_DEBUG_NAME, mode, - o2net_dentry, NULL, &sc_seq_fops); - if (sc_dentry) - stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, mode, - o2net_dentry, NULL, &stats_seq_fops); - if (stats_dentry) - nodes_dentry = debugfs_create_file(NODES_DEBUG_NAME, mode, - o2net_dentry, NULL, &nodes_fops); - if (nodes_dentry) - return 0; - - o2net_debugfs_exit(); - mlog_errno(-ENOMEM); - return -ENOMEM; + + debugfs_create_file(NST_DEBUG_NAME, mode, o2net_dentry, NULL, + &nst_seq_fops); + debugfs_create_file(SC_DEBUG_NAME, mode, o2net_dentry, NULL, + &sc_seq_fops); + debugfs_create_file(STATS_DEBUG_NAME, mode, o2net_dentry, NULL, + &stats_seq_fops); + debugfs_create_file(NODES_DEBUG_NAME, mode, o2net_dentry, NULL, + &nodes_fops); } #endif /* CONFIG_DEBUG_FS */ diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 4ac775e32240..7a7640c59f3c 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -1,22 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2004, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/slab.h> @@ -842,9 +828,7 @@ static int __init init_o2nm(void) { int ret = -1; - ret = o2hb_init(); - if (ret) - goto out; + o2hb_init(); ret = o2net_init(); if (ret) diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h index 09ea2d388bbb..3e0006631cc4 100644 --- a/fs/ocfs2/cluster/nodemanager.h +++ b/fs/ocfs2/cluster/nodemanager.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * Function prototypes * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef O2CLUSTER_NODEMANAGER_H diff --git a/fs/ocfs2/cluster/ocfs2_heartbeat.h b/fs/ocfs2/cluster/ocfs2_heartbeat.h index 3f4151da9709..760d850be11e 100644 --- a/fs/ocfs2/cluster/ocfs2_heartbeat.h +++ b/fs/ocfs2/cluster/ocfs2_heartbeat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * On-disk structures for ocfs2_heartbeat * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef _OCFS2_HEARTBEAT_H diff --git a/fs/ocfs2/cluster/ocfs2_nodemanager.h b/fs/ocfs2/cluster/ocfs2_nodemanager.h index 49b594325bec..21ad307419a8 100644 --- a/fs/ocfs2/cluster/ocfs2_nodemanager.h +++ b/fs/ocfs2/cluster/ocfs2_nodemanager.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -7,22 +8,6 @@ * for the ocfs2_nodemanager module. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef _OCFS2_NODEMANAGER_H diff --git a/fs/ocfs2/cluster/quorum.c b/fs/ocfs2/cluster/quorum.c index 67dcee65fe50..5c424a099280 100644 --- a/fs/ocfs2/cluster/quorum.c +++ b/fs/ocfs2/cluster/quorum.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ /* This quorum hack is only here until we transition to some more rational @@ -90,7 +76,7 @@ static void o2quo_fence_self(void) }; } -/* Indicate that a timeout occurred on a hearbeat region write. The +/* Indicate that a timeout occurred on a heartbeat region write. The * other nodes in the cluster may consider us dead at that time so we * want to "fence" ourselves so that we don't scribble on the disk * after they think they've recovered us. This can't solve all diff --git a/fs/ocfs2/cluster/quorum.h b/fs/ocfs2/cluster/quorum.h index 6649cc6f67c9..6d45ce8b18a1 100644 --- a/fs/ocfs2/cluster/quorum.h +++ b/fs/ocfs2/cluster/quorum.h @@ -1,23 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef O2CLUSTER_QUORUM_H diff --git a/fs/ocfs2/cluster/sys.c b/fs/ocfs2/cluster/sys.c index b7f57271d49c..d6067c3d84c1 100644 --- a/fs/ocfs2/cluster/sys.c +++ b/fs/ocfs2/cluster/sys.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * OCFS2 cluster sysfs interface * * Copyright (C) 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, - * version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #include <linux/kernel.h> diff --git a/fs/ocfs2/cluster/sys.h b/fs/ocfs2/cluster/sys.h index d66b8ab0045e..ce380517cf17 100644 --- a/fs/ocfs2/cluster/sys.h +++ b/fs/ocfs2/cluster/sys.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * Function prototypes for o2cb sysfs interface * * Copyright (C) 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, - * version 2 of the License. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef O2CLUSTER_SYS_H diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index e9f236af1927..48a3398f0bf5 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1,24 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2004 Oracle. All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * ---- * * Callers for this were originally written against a very simple synchronus @@ -1776,7 +1762,7 @@ static void o2net_hb_node_up_cb(struct o2nm_node *node, int node_num, (msecs_to_jiffies(o2net_reconnect_delay()) + 1); if (node_num != o2nm_this_node()) { - /* believe it or not, accept and node hearbeating testing + /* believe it or not, accept and node heartbeating testing * can succeed for this node before we got here.. so * only use set_nn_state to clear the persistent error * if that hasn't already happened */ @@ -2143,8 +2129,7 @@ int o2net_init(void) o2quo_init(); - if (o2net_debugfs_init()) - goto out; + o2net_debugfs_init(); o2net_hand = kzalloc(sizeof(struct o2net_handshake), GFP_KERNEL); o2net_keep_req = kzalloc(sizeof(struct o2net_msg), GFP_KERNEL); diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h index c571e849fda4..de87cbffd175 100644 --- a/fs/ocfs2/cluster/tcp.h +++ b/fs/ocfs2/cluster/tcp.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * Function prototypes * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef O2CLUSTER_TCP_H @@ -124,16 +109,15 @@ struct o2net_send_tracking; struct o2net_sock_container; #ifdef CONFIG_DEBUG_FS -int o2net_debugfs_init(void); +void o2net_debugfs_init(void); void o2net_debugfs_exit(void); void o2net_debug_add_nst(struct o2net_send_tracking *nst); void o2net_debug_del_nst(struct o2net_send_tracking *nst); void o2net_debug_add_sc(struct o2net_sock_container *sc); void o2net_debug_del_sc(struct o2net_sock_container *sc); #else -static inline int o2net_debugfs_init(void) +static inline void o2net_debugfs_init(void) { - return 0; } static inline void o2net_debugfs_exit(void) { diff --git a/fs/ocfs2/cluster/tcp_internal.h b/fs/ocfs2/cluster/tcp_internal.h index 0276f7f8d5e6..e6a2b9dfcd16 100644 --- a/fs/ocfs2/cluster/tcp_internal.h +++ b/fs/ocfs2/cluster/tcp_internal.h @@ -1,22 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * Copyright (C) 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef O2CLUSTER_TCP_INTERNAL_H diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index 290373024d9d..42a61eecdacd 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * dentry cache handling code * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> @@ -310,6 +296,18 @@ int ocfs2_dentry_attach_lock(struct dentry *dentry, out_attach: spin_lock(&dentry_attach_lock); + if (unlikely(dentry->d_fsdata && !alias)) { + /* d_fsdata is set by a racing thread which is doing + * the same thing as this thread is doing. Leave the racing + * thread going ahead and we return here. + */ + spin_unlock(&dentry_attach_lock); + iput(dl->dl_inode); + ocfs2_lock_res_free(&dl->dl_lockres); + kfree(dl); + return 0; + } + dentry->d_fsdata = dl; dl->dl_count++; spin_unlock(&dentry_attach_lock); diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h index 55f58892b153..3686a52ba143 100644 --- a/fs/ocfs2/dcache.h +++ b/fs/ocfs2/dcache.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_DCACHE_H diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 85f21caaa6ec..784426dee56c 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -19,21 +20,6 @@ * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linus Torvalds - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h index 3d8639f38973..e3e7d5dd29e8 100644 --- a/fs/ocfs2/dir.h +++ b/fs/ocfs2/dir.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_DIR_H diff --git a/fs/ocfs2/dlm/Makefile b/fs/ocfs2/dlm/Makefile index ef2854422a6e..38b224372776 100644 --- a/fs/ocfs2/dlm/Makefile +++ b/fs/ocfs2/dlm/Makefile @@ -1,7 +1,7 @@ -ccflags-y := -I$(src)/.. +# SPDX-License-Identifier: GPL-2.0-only +ccflags-y := -I $(srctree)/$(src)/.. obj-$(CONFIG_OCFS2_FS_O2CB) += ocfs2_dlm.o ocfs2_dlm-objs := dlmdomain.o dlmdebug.o dlmthread.o dlmrecovery.o \ dlmmaster.o dlmast.o dlmconvert.o dlmlock.o dlmunlock.o - diff --git a/fs/ocfs2/dlm/dlmapi.h b/fs/ocfs2/dlm/dlmapi.h index 3cfa114aa391..6456c0fbcbb2 100644 --- a/fs/ocfs2/dlm/dlmapi.h +++ b/fs/ocfs2/dlm/dlmapi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * externally exported dlm interfaces * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef DLMAPI_H diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index 39831fc2fd52..4de89af96abf 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * AST and BAST functionality for local and remote nodes * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index d06e27ec4be4..69a429b625cc 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -1,25 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * dlmcommon.h * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef DLMCOMMON_H diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c index 0bb128659d4b..965f45dbe17b 100644 --- a/fs/ocfs2/dlm/dlmconvert.c +++ b/fs/ocfs2/dlm/dlmconvert.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * underlying calls for lock conversion * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ diff --git a/fs/ocfs2/dlm/dlmconvert.h b/fs/ocfs2/dlm/dlmconvert.h index b2e3677df878..12d9c28bc52f 100644 --- a/fs/ocfs2/dlm/dlmconvert.h +++ b/fs/ocfs2/dlm/dlmconvert.h @@ -1,25 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * dlmconvert.h * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef DLMCONVERT_H diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c index 1d6dc8422899..a4b58ba99927 100644 --- a/fs/ocfs2/dlm/dlmdebug.c +++ b/fs/ocfs2/dlm/dlmdebug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * debug functionality for the dlm * * Copyright (C) 2004, 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #include <linux/types.h> @@ -866,7 +851,7 @@ static const struct file_operations debug_state_fops = { /* end - debug state funcs */ /* files in subroot */ -int dlm_debug_init(struct dlm_ctxt *dlm) +void dlm_debug_init(struct dlm_ctxt *dlm) { struct dlm_debug_ctxt *dc = dlm->dlm_debug_ctxt; @@ -875,10 +860,6 @@ int dlm_debug_init(struct dlm_ctxt *dlm) S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_state_fops); - if (!dc->debug_state_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } /* for dumping lockres */ dc->debug_lockres_dentry = @@ -886,20 +867,12 @@ int dlm_debug_init(struct dlm_ctxt *dlm) S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_lockres_fops); - if (!dc->debug_lockres_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } /* for dumping mles */ dc->debug_mle_dentry = debugfs_create_file(DLM_DEBUGFS_MLE_STATE, S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_mle_fops); - if (!dc->debug_mle_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } /* for dumping lockres on the purge list */ dc->debug_purgelist_dentry = @@ -907,15 +880,6 @@ int dlm_debug_init(struct dlm_ctxt *dlm) S_IFREG|S_IRUSR, dlm->dlm_debugfs_subroot, dlm, &debug_purgelist_fops); - if (!dc->debug_purgelist_dentry) { - mlog_errno(-ENOMEM); - goto bail; - } - - return 0; - -bail: - return -ENOMEM; } void dlm_debug_shutdown(struct dlm_ctxt *dlm) @@ -935,24 +899,16 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm) /* subroot - domain dir */ int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm) { - dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name, - dlm_debugfs_root); - if (!dlm->dlm_debugfs_subroot) { - mlog_errno(-ENOMEM); - goto bail; - } - dlm->dlm_debug_ctxt = kzalloc(sizeof(struct dlm_debug_ctxt), GFP_KERNEL); if (!dlm->dlm_debug_ctxt) { mlog_errno(-ENOMEM); - goto bail; + return -ENOMEM; } + dlm->dlm_debugfs_subroot = debugfs_create_dir(dlm->name, + dlm_debugfs_root); return 0; -bail: - dlm_destroy_debugfs_subroot(dlm); - return -ENOMEM; } void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm) @@ -961,14 +917,9 @@ void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm) } /* debugfs root */ -int dlm_create_debugfs_root(void) +void dlm_create_debugfs_root(void) { dlm_debugfs_root = debugfs_create_dir(DLM_DEBUGFS_DIR, NULL); - if (!dlm_debugfs_root) { - mlog_errno(-ENOMEM); - return -ENOMEM; - } - return 0; } void dlm_destroy_debugfs_root(void) diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h index 5ced5482e7d3..7d0c7c9013ce 100644 --- a/fs/ocfs2/dlm/dlmdebug.h +++ b/fs/ocfs2/dlm/dlmdebug.h @@ -1,25 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * dlmdebug.h * * Copyright (C) 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef DLMDEBUG_H @@ -43,20 +28,19 @@ struct debug_lockres { struct dlm_lock_resource *dl_res; }; -int dlm_debug_init(struct dlm_ctxt *dlm); +void dlm_debug_init(struct dlm_ctxt *dlm); void dlm_debug_shutdown(struct dlm_ctxt *dlm); int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm); void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm); -int dlm_create_debugfs_root(void); +void dlm_create_debugfs_root(void); void dlm_destroy_debugfs_root(void); #else -static inline int dlm_debug_init(struct dlm_ctxt *dlm) +static inline void dlm_debug_init(struct dlm_ctxt *dlm) { - return 0; } static inline void dlm_debug_shutdown(struct dlm_ctxt *dlm) { @@ -68,9 +52,8 @@ static inline int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm) static inline void dlm_destroy_debugfs_subroot(struct dlm_ctxt *dlm) { } -static inline int dlm_create_debugfs_root(void) +static inline void dlm_create_debugfs_root(void) { - return 0; } static inline void dlm_destroy_debugfs_root(void) { diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 2acd58ba9b7b..7338b5d4647c 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * defines domain join / leave apis * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #include <linux/module.h> @@ -1896,11 +1881,7 @@ static int dlm_join_domain(struct dlm_ctxt *dlm) goto bail; } - status = dlm_debug_init(dlm); - if (status < 0) { - mlog_errno(status); - goto bail; - } + dlm_debug_init(dlm); snprintf(wq_name, O2NM_MAX_NAME_LEN, "dlm_wq-%s", dlm->name); dlm->dlm_worker = alloc_workqueue(wq_name, WQ_MEM_RECLAIM, 0); @@ -2361,9 +2342,7 @@ static int __init dlm_init(void) goto error; } - status = dlm_create_debugfs_root(); - if (status) - goto error; + dlm_create_debugfs_root(); return 0; error: diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h index 8a9281411c18..7c21664d23d0 100644 --- a/fs/ocfs2/dlm/dlmdomain.h +++ b/fs/ocfs2/dlm/dlmdomain.h @@ -1,25 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * dlmdomain.h * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ #ifndef DLMDOMAIN_H diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c index 74962315794e..baff087f3863 100644 --- a/fs/ocfs2/dlm/dlmlock.c +++ b/fs/ocfs2/dlm/dlmlock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * underlying calls for lock creation * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 826f0567ec43..74b768ca1cd8 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * standalone DLM module * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ @@ -2176,7 +2161,7 @@ put: * think that $RECOVERY is currently mastered by a dead node. If so, * we wait a short time to allow that node to get notified by its own * heartbeat stack, then check again. All $RECOVERY lock resources - * mastered by dead nodes are purged when the hearbeat callback is + * mastered by dead nodes are purged when the heartbeat callback is * fired, so we can know for sure that it is safe to continue once * the node returns a live node or no node. */ static int dlm_pre_master_reco_lockres(struct dlm_ctxt *dlm, diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 802636d50365..064ce5bbc3f6 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * recovery stuff * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ @@ -1124,7 +1109,7 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, { u64 mig_cookie = be64_to_cpu(mres->mig_cookie); int mres_total_locks = be32_to_cpu(mres->total_locks); - int sz, ret = 0, status = 0; + int ret = 0, status = 0; u8 orig_flags = mres->flags, orig_master = mres->master; @@ -1132,9 +1117,6 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, if (!mres->num_locks) return 0; - sz = sizeof(struct dlm_migratable_lockres) + - (mres->num_locks * sizeof(struct dlm_migratable_lock)); - /* add an all-done flag if we reached the last lock */ orig_flags = mres->flags; BUG_ON(total_locks > mres_total_locks); @@ -1148,7 +1130,8 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm, /* send it */ ret = o2net_send_message(DLM_MIG_LOCKRES_MSG, dlm->key, mres, - sz, send_to, &status); + struct_size(mres, ml, mres->num_locks), + send_to, &status); if (ret < 0) { /* XXX: negative status is not handled. * this will end up killing this node. */ diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index 074d5de17bb2..61c51c268460 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * standalone DLM module * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 63d701cd1e2e..e78657742bd8 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,22 +7,6 @@ * underlying calls for unlocking locks * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * */ diff --git a/fs/ocfs2/dlmfs/Makefile b/fs/ocfs2/dlmfs/Makefile index 33431a0296a3..a9874e441bd4 100644 --- a/fs/ocfs2/dlmfs/Makefile +++ b/fs/ocfs2/dlmfs/Makefile @@ -1,4 +1,5 @@ -ccflags-y := -I$(src)/.. +# SPDX-License-Identifier: GPL-2.0-only +ccflags-y := -I $(srctree)/$(src)/.. obj-$(CONFIG_OCFS2_FS) += ocfs2_dlmfs.o diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 98885181e1fe..4f1668c81e1f 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -9,21 +10,6 @@ * which was a template for the fs side of this module. * * Copyright (C) 2003, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ /* Simple VFS hooks based on: */ diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c index 9cecf4857195..525b14ddfba5 100644 --- a/fs/ocfs2/dlmfs/userdlm.c +++ b/fs/ocfs2/dlmfs/userdlm.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -10,21 +11,6 @@ * functions. * * Copyright (C) 2003, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/signal.h> diff --git a/fs/ocfs2/dlmfs/userdlm.h b/fs/ocfs2/dlmfs/userdlm.h index ede94a6e7fd3..4bef7cdef859 100644 --- a/fs/ocfs2/dlmfs/userdlm.h +++ b/fs/ocfs2/dlmfs/userdlm.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Userspace dlm defines * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index af405586c5b1..14207234fa3d 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Code which implements an OCFS2 specific interface to our DLM. * * Copyright (C) 2003, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/types.h> @@ -440,6 +426,7 @@ static void ocfs2_remove_lockres_tracking(struct ocfs2_lock_res *res) static void ocfs2_init_lock_stats(struct ocfs2_lock_res *res) { res->l_lock_refresh = 0; + res->l_lock_wait = 0; memset(&res->l_lock_prmode, 0, sizeof(struct ocfs2_lock_stats)); memset(&res->l_lock_exmode, 0, sizeof(struct ocfs2_lock_stats)); } @@ -474,6 +461,8 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, if (ret) stats->ls_fail++; + + stats->ls_last = ktime_to_us(ktime_get_real()); } static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres) @@ -481,6 +470,21 @@ static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres) lockres->l_lock_refresh++; } +static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres) +{ + struct ocfs2_mask_waiter *mw; + + if (list_empty(&lockres->l_mask_waiters)) { + lockres->l_lock_wait = 0; + return; + } + + mw = list_first_entry(&lockres->l_mask_waiters, + struct ocfs2_mask_waiter, mw_item); + lockres->l_lock_wait = + ktime_to_us(ktime_mono_to_real(mw->mw_lock_start)); +} + static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw) { mw->mw_lock_start = ktime_get(); @@ -496,6 +500,9 @@ static inline void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, static inline void ocfs2_track_lock_refresh(struct ocfs2_lock_res *lockres) { } +static inline void ocfs2_track_lock_wait(struct ocfs2_lock_res *lockres) +{ +} static inline void ocfs2_init_start_time(struct ocfs2_mask_waiter *mw) { } @@ -889,6 +896,7 @@ static void lockres_set_flags(struct ocfs2_lock_res *lockres, list_del_init(&mw->mw_item); mw->mw_status = 0; complete(&mw->mw_complete); + ocfs2_track_lock_wait(lockres); } } static void lockres_or_flags(struct ocfs2_lock_res *lockres, unsigned long or) @@ -1400,6 +1408,7 @@ static void lockres_add_mask_waiter(struct ocfs2_lock_res *lockres, list_add_tail(&mw->mw_item, &lockres->l_mask_waiters); mw->mw_mask = mask; mw->mw_goal = goal; + ocfs2_track_lock_wait(lockres); } /* returns 0 if the mw that was removed was already satisfied, -EBUSY @@ -1416,6 +1425,7 @@ static int __lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres, list_del_init(&mw->mw_item); init_completion(&mw->mw_complete); + ocfs2_track_lock_wait(lockres); } return ret; @@ -3003,6 +3013,8 @@ struct ocfs2_dlm_debug *ocfs2_new_dlm_debug(void) kref_init(&dlm_debug->d_refcnt); INIT_LIST_HEAD(&dlm_debug->d_lockres_tracking); dlm_debug->d_locking_state = NULL; + dlm_debug->d_locking_filter = NULL; + dlm_debug->d_filter_secs = 0; out: return dlm_debug; } @@ -3093,17 +3105,43 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos) * - Lock stats printed * New in version 3 * - Max time in lock stats is in usecs (instead of nsecs) + * New in version 4 + * - Add last pr/ex unlock times and first lock wait time in usecs */ -#define OCFS2_DLM_DEBUG_STR_VERSION 3 +#define OCFS2_DLM_DEBUG_STR_VERSION 4 static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) { int i; char *lvb; struct ocfs2_lock_res *lockres = v; +#ifdef CONFIG_OCFS2_FS_STATS + u64 now, last; + struct ocfs2_dlm_debug *dlm_debug = + ((struct ocfs2_dlm_seq_priv *)m->private)->p_dlm_debug; +#endif if (!lockres) return -EINVAL; +#ifdef CONFIG_OCFS2_FS_STATS + if (!lockres->l_lock_wait && dlm_debug->d_filter_secs) { + now = ktime_to_us(ktime_get_real()); + if (lockres->l_lock_prmode.ls_last > + lockres->l_lock_exmode.ls_last) + last = lockres->l_lock_prmode.ls_last; + else + last = lockres->l_lock_exmode.ls_last; + /* + * Use d_filter_secs field to filter lock resources dump, + * the default d_filter_secs(0) value filters nothing, + * otherwise, only dump the last N seconds active lock + * resources. + */ + if (div_u64(now - last, 1000000) > dlm_debug->d_filter_secs) + return 0; + } +#endif + seq_printf(m, "0x%x\t", OCFS2_DLM_DEBUG_STR_VERSION); if (lockres->l_type == OCFS2_LOCK_TYPE_DENTRY) @@ -3145,6 +3183,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) # define lock_max_prmode(_l) ((_l)->l_lock_prmode.ls_max) # define lock_max_exmode(_l) ((_l)->l_lock_exmode.ls_max) # define lock_refresh(_l) ((_l)->l_lock_refresh) +# define lock_last_prmode(_l) ((_l)->l_lock_prmode.ls_last) +# define lock_last_exmode(_l) ((_l)->l_lock_exmode.ls_last) +# define lock_wait(_l) ((_l)->l_lock_wait) #else # define lock_num_prmode(_l) (0) # define lock_num_exmode(_l) (0) @@ -3155,6 +3196,9 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) # define lock_max_prmode(_l) (0) # define lock_max_exmode(_l) (0) # define lock_refresh(_l) (0) +# define lock_last_prmode(_l) (0ULL) +# define lock_last_exmode(_l) (0ULL) +# define lock_wait(_l) (0ULL) #endif /* The following seq_print was added in version 2 of this output */ seq_printf(m, "%u\t" @@ -3165,7 +3209,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) "%llu\t" "%u\t" "%u\t" - "%u\t", + "%u\t" + "%llu\t" + "%llu\t" + "%llu\t", lock_num_prmode(lockres), lock_num_exmode(lockres), lock_num_prmode_failed(lockres), @@ -3174,7 +3221,10 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v) lock_total_exmode(lockres), lock_max_prmode(lockres), lock_max_exmode(lockres), - lock_refresh(lockres)); + lock_refresh(lockres), + lock_last_prmode(lockres), + lock_last_exmode(lockres), + lock_wait(lockres)); /* End the line */ seq_printf(m, "\n"); @@ -3228,9 +3278,8 @@ static const struct file_operations ocfs2_dlm_debug_fops = { .llseek = seq_lseek, }; -static int ocfs2_dlm_init_debug(struct ocfs2_super *osb) +static void ocfs2_dlm_init_debug(struct ocfs2_super *osb) { - int ret = 0; struct ocfs2_dlm_debug *dlm_debug = osb->osb_dlm_debug; dlm_debug->d_locking_state = debugfs_create_file("locking_state", @@ -3238,16 +3287,11 @@ static int ocfs2_dlm_init_debug(struct ocfs2_super *osb) osb->osb_debug_root, osb, &ocfs2_dlm_debug_fops); - if (!dlm_debug->d_locking_state) { - ret = -EINVAL; - mlog(ML_ERROR, - "Unable to create locking state debugfs file.\n"); - goto out; - } - ocfs2_get_dlm_debug(dlm_debug); -out: - return ret; + dlm_debug->d_locking_filter = debugfs_create_u32("locking_filter", + 0600, + osb->osb_debug_root, + &dlm_debug->d_filter_secs); } static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb) @@ -3256,6 +3300,7 @@ static void ocfs2_dlm_shutdown_debug(struct ocfs2_super *osb) if (dlm_debug) { debugfs_remove(dlm_debug->d_locking_state); + debugfs_remove(dlm_debug->d_locking_filter); ocfs2_put_dlm_debug(dlm_debug); } } @@ -3270,11 +3315,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb) goto local; } - status = ocfs2_dlm_init_debug(osb); - if (status < 0) { - mlog_errno(status); - goto bail; - } + ocfs2_dlm_init_debug(osb); /* launch downconvert thread */ osb->dc_task = kthread_run(ocfs2_downconvert_thread, osb, "ocfs2dc-%s", @@ -4366,7 +4407,6 @@ static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb) static int ocfs2_downconvert_thread(void *arg) { - int status = 0; struct ocfs2_super *osb = arg; /* only quit once we've been asked to stop and there is no more @@ -4384,7 +4424,7 @@ static int ocfs2_downconvert_thread(void *arg) } osb->dc_task = NULL; - return status; + return 0; } void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb) diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index 4ec1c828f6e0..b8fbed25df89 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * description here * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index af2888d23de3..69ed278dd84d 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Functions to facilitate NFS exporting * * Copyright (C) 2002, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/export.h b/fs/ocfs2/export.h index 41a738678c37..d485da0c3439 100644 --- a/fs/ocfs2/export.h +++ b/fs/ocfs2/export.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_EXPORT_H diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 06cb96462bf9..e66a249fe07c 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,20 +7,6 @@ * Block/Cluster mapping functions * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h index 1057586ec19f..e5464f6cee8a 100644 --- a/fs/ocfs2/extent_map.h +++ b/fs/ocfs2/extent_map.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,20 +7,6 @@ * In-memory file extent mappings for OCFS2. * * Copyright (C) 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef _EXTENT_MAP_H diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index d640c5f8a85d..4435df3e5adb 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * File open, close, extend, truncate * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/capability.h> diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index 7eb7f03531f6..4832cbceba5b 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_FILE_H diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index f65f2b2f594d..50f11bfdc8c2 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Code which implements online file check. * * Copyright (C) 2016 SuSE. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/list.h> @@ -193,6 +185,7 @@ int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb) ret = kobject_init_and_add(&entry->fs_kobj, &ocfs2_ktype_filecheck, NULL, "filecheck"); if (ret) { + kobject_put(&entry->fs_kobj); kfree(fcheck); return ret; } diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h index 6a22ee79e8d0..4d006777ac54 100644 --- a/fs/ocfs2/filecheck.h +++ b/fs/ocfs2/filecheck.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Online file check. * * Copyright (C) 2016 SuSE. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ diff --git a/fs/ocfs2/heartbeat.c b/fs/ocfs2/heartbeat.c index d8208b20dc53..60c5f995d30c 100644 --- a/fs/ocfs2/heartbeat.c +++ b/fs/ocfs2/heartbeat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -7,21 +8,6 @@ * up to date, and fire off recovery when needed. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/heartbeat.h b/fs/ocfs2/heartbeat.h index 74b9c5dda28d..5fedb2d35dc0 100644 --- a/fs/ocfs2/heartbeat.h +++ b/fs/ocfs2/heartbeat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_HEARTBEAT_H diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 79279240fb6e..7ad9d6590818 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * vfs' aops, fops, dops and iops * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 9b955f732bca..51a4f7197987 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_INODE_H diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 994726ada857..d6f7b299eb23 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -106,16 +106,9 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags, flags = flags & mask; flags |= oldflags & ~mask; - /* - * The IMMUTABLE and APPEND_ONLY flags can only be changed by - * the relevant capability. - */ - status = -EPERM; - if ((oldflags & OCFS2_IMMUTABLE_FL) || ((flags ^ oldflags) & - (OCFS2_APPEND_FL | OCFS2_IMMUTABLE_FL))) { - if (!capable(CAP_LINUX_IMMUTABLE)) - goto bail_unlock; - } + status = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (status) + goto bail_unlock; handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 46fd3ef2cf21..930e3d388579 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Defines functions of journalling api * * Copyright (C) 2003, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index 497a4171ef61..c0fe6ed08ab1 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Defines journalling api and structures. * * Copyright (C) 2003, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_JOURNAL_H diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 58973e4d2471..158e5af767fd 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Node local data allocation * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> @@ -438,12 +424,11 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) bh = osb->local_alloc_bh; alloc = (struct ocfs2_dinode *) bh->b_data; - alloc_copy = kmalloc(bh->b_size, GFP_NOFS); + alloc_copy = kmemdup(alloc, bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; goto out_commit; } - memcpy(alloc_copy, alloc, bh->b_size); status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), bh, OCFS2_JOURNAL_ACCESS_WRITE); @@ -1286,13 +1271,12 @@ static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb, * local alloc shutdown won't try to double free main bitmap * bits. Make a copy so the sync function knows which bits to * free. */ - alloc_copy = kmalloc(osb->local_alloc_bh->b_size, GFP_NOFS); + alloc_copy = kmemdup(alloc, osb->local_alloc_bh->b_size, GFP_NOFS); if (!alloc_copy) { status = -ENOMEM; mlog_errno(status); goto bail; } - memcpy(alloc_copy, alloc, osb->local_alloc_bh->b_size); status = ocfs2_journal_access_di(handle, INODE_CACHE(local_alloc_inode), diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h index 44a7d1fb2dec..e8a5cea48639 100644 --- a/fs/ocfs2/localalloc.h +++ b/fs/ocfs2/localalloc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_LOCALALLOC_H diff --git a/fs/ocfs2/locks.c b/fs/ocfs2/locks.c index b11acd34001a..7edc4e5c7c2c 100644 --- a/fs/ocfs2/locks.c +++ b/fs/ocfs2/locks.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Userspace file locking support * * Copyright (C) 2007 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/locks.h b/fs/ocfs2/locks.h index 496d488b271f..389fe1fce3a5 100644 --- a/fs/ocfs2/locks.h +++ b/fs/ocfs2/locks.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes for Userspace file locking support * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_LOCKS_H diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index 05220b365fb9..3a44e461828a 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Code to deal with the mess that is clustered mmap. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 1565dd8e8856..758d9661ef1e 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -1,18 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * move_extents.c * * Copyright (C) 2011 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/fs.h> #include <linux/types.h> diff --git a/fs/ocfs2/move_extents.h b/fs/ocfs2/move_extents.h index 4e143e811441..28cac43892c5 100644 --- a/fs/ocfs2/move_extents.h +++ b/fs/ocfs2/move_extents.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * move_extents.h * * Copyright (C) 2011 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_MOVE_EXTENTS_H #define OCFS2_MOVE_EXTENTS_H diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index b7ca84bc3df7..6f8e1c4fdb9c 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -19,21 +20,6 @@ * linux/fs/minix/dir.c * * Copyright (C) 1991, 1992 Linux Torvalds - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h index 1155918d6784..cc091ed02b4a 100644 --- a/fs/ocfs2/namei.h +++ b/fs/ocfs2/namei.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_NAMEI_H diff --git a/fs/ocfs2/ocfs1_fs_compat.h b/fs/ocfs2/ocfs1_fs_compat.h index dfb313bda5dd..01ae48c4834d 100644 --- a/fs/ocfs2/ocfs1_fs_compat.h +++ b/fs/ocfs2/ocfs1_fs_compat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -9,20 +10,6 @@ * mount it. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef _OCFS1_FS_COMPAT_H diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 1f029fbe8b8d..fddbbd60f434 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Defines macros and structures used in OCFS2 * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_H @@ -164,6 +150,7 @@ struct ocfs2_lock_stats { /* Storing max wait in usecs saves 24 bytes per inode */ u32 ls_max; /* Max wait in USEC */ + u64 ls_last; /* Last unlock time in USEC */ }; #endif @@ -205,6 +192,7 @@ struct ocfs2_lock_res { #ifdef CONFIG_OCFS2_FS_STATS struct ocfs2_lock_stats l_lock_prmode; /* PR mode stats */ u32 l_lock_refresh; /* Disk refreshes */ + u64 l_lock_wait; /* First lock wait time */ struct ocfs2_lock_stats l_lock_exmode; /* EX mode stats */ #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -236,6 +224,8 @@ struct ocfs2_orphan_scan { struct ocfs2_dlm_debug { struct kref d_refcnt; struct dentry *d_locking_state; + struct dentry *d_locking_filter; + u32 d_filter_secs; struct list_head d_lockres_tracking; }; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index b86bf5e74348..0db4a7ec58a2 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,20 +7,6 @@ * On-disk structures for OCFS2. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef _OCFS2_FS_H diff --git a/fs/ocfs2/ocfs2_ioctl.h b/fs/ocfs2/ocfs2_ioctl.h index 5b27ff1fa577..d7b31734f6be 100644 --- a/fs/ocfs2/ocfs2_ioctl.h +++ b/fs/ocfs2/ocfs2_ioctl.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Defines OCFS2 ioctls. * * Copyright (C) 2010 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_IOCTL_H diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h index 7051b994c776..b4be84956bc1 100644 --- a/fs/ocfs2/ocfs2_lockid.h +++ b/fs/ocfs2/ocfs2_lockid.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Defines OCFS2 lockid bits. * * Copyright (C) 2002, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_LOCKID_H diff --git a/fs/ocfs2/ocfs2_lockingver.h b/fs/ocfs2/ocfs2_lockingver.h index 2e45c8d2ea7e..5c9c105b33ee 100644 --- a/fs/ocfs2/ocfs2_lockingver.h +++ b/fs/ocfs2/ocfs2_lockingver.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Defines OCFS2 Locking version values. * * Copyright (C) 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License, version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_LOCKINGVER_H diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 1dc9a08e8bdc..ee43e51188be 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -1,18 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * refcounttree.c * * Copyright (C) 2009 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/sort.h> diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h index e9e862be4a1e..0b9014495726 100644 --- a/fs/ocfs2/refcounttree.h +++ b/fs/ocfs2/refcounttree.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * refcounttree.h * * Copyright (C) 2009 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_REFCOUNTTREE_H #define OCFS2_REFCOUNTTREE_H diff --git a/fs/ocfs2/reservations.c b/fs/ocfs2/reservations.c index 6a348b0294ab..0249e8ca1028 100644 --- a/fs/ocfs2/reservations.c +++ b/fs/ocfs2/reservations.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -13,15 +14,6 @@ * Universite Pierre et Marie Curie (Paris VI) * * The rest is copyright (C) 2010 Novell. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/fs.h> diff --git a/fs/ocfs2/reservations.h b/fs/ocfs2/reservations.h index 42c2b804f3fd..6ac88122896d 100644 --- a/fs/ocfs2/reservations.h +++ b/fs/ocfs2/reservations.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Allocation reservations function prototypes and structures. * * Copyright (C) 2010 Novell. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_RESERVATIONS_H diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index 18451e0fab81..24eb52f9059c 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -7,21 +8,6 @@ * Inspired by ext3/resize.c. * * Copyright (C) 2007 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/resize.h b/fs/ocfs2/resize.h index f38841abf10b..0af0c023042c 100644 --- a/fs/ocfs2/resize.h +++ b/fs/ocfs2/resize.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2007 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_RESIZE_H diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c index ea0756d83250..8caeceeaeda7 100644 --- a/fs/ocfs2/slot_map.c +++ b/fs/ocfs2/slot_map.c @@ -1,26 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * slot_map.c * - * - * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/types.h> diff --git a/fs/ocfs2/slot_map.h b/fs/ocfs2/slot_map.h index 601c95fd7003..93b53e73f0f7 100644 --- a/fs/ocfs2/slot_map.h +++ b/fs/ocfs2/slot_map.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * description here * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c index 220cae7bbdbc..dbf8b5735808 100644 --- a/fs/ocfs2/stack_o2cb.c +++ b/fs/ocfs2/stack_o2cb.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Code which interfaces ocfs2 with the o2cb stack. * * Copyright (C) 2007 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/kernel.h> diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index d2fb97b173da..7397064c3f35 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Code which interfaces ocfs2 with fs/dlm and a userspace stack. * * Copyright (C) 2007 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/module.h> diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index c4b029c43464..8aa6a667860c 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -7,15 +8,6 @@ * cluster stacks. * * Copyright (C) 2007, 2009 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/list.h> diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index f2dce10fae54..e9d26cbeb3b8 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,15 +7,6 @@ * Glue to the underlying cluster stack. * * Copyright (C) 2007 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation, version 2. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index f7c972fbed6a..69c21a3843af 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -7,21 +8,6 @@ * Inspired by ext3 block groups. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index 2d2501767c0c..f0a5d30a175d 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Defines sub allocator api * * Copyright (C) 2003, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef _CHAINALLOC_H_ diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8821bc7b9c72..8b2f39506648 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * load/unload driver, mount/dismount volumes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/module.h> @@ -1093,33 +1079,15 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent) osb->osb_debug_root = debugfs_create_dir(osb->uuid_str, ocfs2_debugfs_root); - if (!osb->osb_debug_root) { - status = -EINVAL; - mlog(ML_ERROR, "Unable to create per-mount debugfs root.\n"); - goto read_super_error; - } osb->osb_ctxt = debugfs_create_file("fs_state", S_IFREG|S_IRUSR, osb->osb_debug_root, osb, &ocfs2_osb_debug_fops); - if (!osb->osb_ctxt) { - status = -EINVAL; - mlog_errno(status); - goto read_super_error; - } - if (ocfs2_meta_ecc(osb)) { - status = ocfs2_blockcheck_stats_debugfs_install( - &osb->osb_ecc_stats, - osb->osb_debug_root); - if (status) { - mlog(ML_ERROR, - "Unable to create blockcheck statistics " - "files\n"); - goto read_super_error; - } - } + if (ocfs2_meta_ecc(osb)) + ocfs2_blockcheck_stats_debugfs_install( &osb->osb_ecc_stats, + osb->osb_debug_root); status = ocfs2_mount_volume(sb); if (status < 0) @@ -1606,11 +1574,6 @@ static int __init ocfs2_init(void) goto out2; ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL); - if (!ocfs2_debugfs_root) { - status = -ENOMEM; - mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n"); - goto out3; - } ocfs2_set_locking_protocol(); diff --git a/fs/ocfs2/super.h b/fs/ocfs2/super.h index d4550c8bbc41..76facaf63336 100644 --- a/fs/ocfs2/super.h +++ b/fs/ocfs2/super.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_SUPER_H diff --git a/fs/ocfs2/symlink.h b/fs/ocfs2/symlink.h index 71ee4245e919..167094d1e5aa 100644 --- a/fs/ocfs2/symlink.h +++ b/fs/ocfs2/symlink.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_SYMLINK_H diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c index 5965f3878d49..bb701c4e449f 100644 --- a/fs/ocfs2/sysfile.c +++ b/fs/ocfs2/sysfile.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Initialize, read, write, etc. system files. * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #include <linux/fs.h> diff --git a/fs/ocfs2/sysfile.h b/fs/ocfs2/sysfile.h index cc9ea661ffc1..a83dd962fccb 100644 --- a/fs/ocfs2/sysfile.h +++ b/fs/ocfs2/sysfile.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Function prototypes * * Copyright (C) 2002, 2004 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_SYSFILE_H diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c index 78f09c76ab3c..580852ba05c4 100644 --- a/fs/ocfs2/uptodate.c +++ b/fs/ocfs2/uptodate.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -8,21 +9,6 @@ * * Copyright (C) 2002, 2004, 2005 Oracle. All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. - * * Standard buffer head caching flags (uptodate, etc) are insufficient * in a clustered environment - a buffer may be marked up to date on * our local node but could have been modified by another cluster diff --git a/fs/ocfs2/uptodate.h b/fs/ocfs2/uptodate.h index 0d826fe2da0d..77a30cae4879 100644 --- a/fs/ocfs2/uptodate.h +++ b/fs/ocfs2/uptodate.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -6,21 +7,6 @@ * Cluster uptodate tracking * * Copyright (C) 2002, 2004, 2005 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License as published by the Free Software Foundation; either - * version 2 of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public - * License along with this program; if not, write to the - * Free Software Foundation, Inc., 59 Temple Place - Suite 330, - * Boston, MA 021110-1307, USA. */ #ifndef OCFS2_UPTODATE_H diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 3a24ce3deb01..385f3aaa2448 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * @@ -8,15 +9,6 @@ * CREDITS: * Lots of code in this file is copy from linux/fs/ext3/xattr.c. * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #include <linux/capability.h> diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h index 1633cc15ea1f..9c80382da1f5 100644 --- a/fs/ocfs2/xattr.h +++ b/fs/ocfs2/xattr.h @@ -1,18 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* -*- mode: c; c-basic-offset: 8; -*- * vim: noexpandtab sw=8 ts=8 sts=0: * * xattr.h * * Copyright (C) 2004, 2008 Oracle. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public - * License version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef OCFS2_XATTR_H diff --git a/fs/omfs/Kconfig b/fs/omfs/Kconfig index b1b9a0aba6fd..42b2ec35a05b 100644 --- a/fs/omfs/Kconfig +++ b/fs/omfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config OMFS_FS tristate "SonicBlue Optimized MPEG File System support" depends on BLOCK diff --git a/fs/omfs/Makefile b/fs/omfs/Makefile index 8b82b63f1129..ae16fc3d34a3 100644 --- a/fs/omfs/Makefile +++ b/fs/omfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_OMFS_FS) += omfs.o diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c index 4bee3a72b9f3..a0f45651f3b7 100644 --- a/fs/omfs/dir.c +++ b/fs/omfs/dir.c @@ -1,7 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * OMFS (as used by RIO Karma) directory operations. * Copyright (C) 2005 Bob Copeland <me@bobcopeland.com> - * Released under GPL v2. */ #include <linux/fs.h> diff --git a/fs/omfs/file.c b/fs/omfs/file.c index bf83e6644333..d640b9388238 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -1,7 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * OMFS (as used by RIO Karma) file operations. * Copyright (C) 2005 Bob Copeland <me@bobcopeland.com> - * Released under GPL v2. */ #include <linux/module.h> diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index ee14af9e26f2..08226a835ec3 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -1,7 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Optimized MPEG FS - inode and super operations. * Copyright (C) 2006 Bob Copeland <me@bobcopeland.com> - * Released under GPL v2. */ #include <linux/module.h> #include <linux/sched.h> diff --git a/fs/open.c b/fs/open.c index 9c7d724a6f67..b5b80469b93d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/open.c * diff --git a/fs/openpromfs/Makefile b/fs/openpromfs/Makefile index 4563199b8fe6..843c270cd06f 100644 --- a/fs/openpromfs/Makefile +++ b/fs/openpromfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux Sun Openprom filesystem routines. # diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c index 46655e454c55..e6cb7689fec4 100644 --- a/fs/openpromfs/inode.c +++ b/fs/openpromfs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* inode.c: /proc/openprom handling routines * * Copyright (C) 1996-1999 Jakub Jelinek (jakub@redhat.com) diff --git a/fs/orangefs/Kconfig b/fs/orangefs/Kconfig index 1554c02489de..890c0ae9a453 100644 --- a/fs/orangefs/Kconfig +++ b/fs/orangefs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config ORANGEFS_FS tristate "ORANGEFS (Powered by PVFS) support" select FS_POSIX_ACL diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index a35c17017210..679a3c8e4fb3 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -357,11 +357,28 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, return ret; } +static int orangefs_getflags(struct inode *inode, unsigned long *uval) +{ + __u64 val = 0; + int ret; + + ret = orangefs_inode_getxattr(inode, + "user.pvfs2.meta_hint", + &val, sizeof(val)); + if (ret < 0 && ret != -ENODATA) + return ret; + else if (ret == -ENODATA) + val = 0; + *uval = val; + return 0; +} + /* * Perform a miscellaneous operation on a file. */ static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + struct inode *inode = file_inode(file); int ret = -ENOTTY; __u64 val = 0; unsigned long uval; @@ -375,20 +392,16 @@ static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long ar * and append flags */ if (cmd == FS_IOC_GETFLAGS) { - val = 0; - ret = orangefs_inode_getxattr(file_inode(file), - "user.pvfs2.meta_hint", - &val, sizeof(val)); - if (ret < 0 && ret != -ENODATA) + ret = orangefs_getflags(inode, &uval); + if (ret) return ret; - else if (ret == -ENODATA) - val = 0; - uval = val; gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_ioctl: FS_IOC_GETFLAGS: %llu\n", (unsigned long long)uval); return put_user(uval, (int __user *)arg); } else if (cmd == FS_IOC_SETFLAGS) { + unsigned long old_uval; + ret = 0; if (get_user(uval, (int __user *)arg)) return -EFAULT; @@ -404,11 +417,17 @@ static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long ar gossip_err("orangefs_ioctl: the FS_IOC_SETFLAGS only supports setting one of FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NOATIME_FL\n"); return -EINVAL; } + ret = orangefs_getflags(inode, &old_uval); + if (ret) + return ret; + ret = vfs_ioc_setflags_prepare(inode, old_uval, uval); + if (ret) + return ret; val = uval; gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_ioctl: FS_IOC_SETFLAGS: %llu\n", (unsigned long long)val); - ret = orangefs_inode_setxattr(file_inode(file), + ret = orangefs_inode_setxattr(inode, "user.pvfs2.meta_hint", &val, sizeof(val), 0); } diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 87b1a6fce628..25543a966c48 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -64,7 +64,7 @@ struct client_debug_mask { __u64 mask2; }; -static int orangefs_kernel_debug_init(void); +static void orangefs_kernel_debug_init(void); static int orangefs_debug_help_open(struct inode *, struct file *); static void *help_start(struct seq_file *, loff_t *); @@ -99,7 +99,6 @@ static char *debug_help_string; static char client_debug_string[ORANGEFS_MAX_DEBUG_STRING_LEN]; static char client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN]; -static struct dentry *help_file_dentry; static struct dentry *client_debug_dentry; static struct dentry *debug_dir; @@ -151,10 +150,8 @@ static DEFINE_MUTEX(orangefs_help_file_lock); * initialize kmod debug operations, create orangefs debugfs dir and * ORANGEFS_KMOD_DEBUG_HELP_FILE. */ -int orangefs_debugfs_init(int debug_mask) +void orangefs_debugfs_init(int debug_mask) { - int rc = -ENOMEM; - /* convert input debug mask to a 64-bit unsigned integer */ orangefs_gossip_debug_mask = (unsigned long long)debug_mask; @@ -183,37 +180,21 @@ int orangefs_debugfs_init(int debug_mask) (unsigned long long)orangefs_gossip_debug_mask); debug_dir = debugfs_create_dir("orangefs", NULL); - if (!debug_dir) { - pr_info("%s: debugfs_create_dir failed.\n", __func__); - goto out; - } - help_file_dentry = debugfs_create_file(ORANGEFS_KMOD_DEBUG_HELP_FILE, - 0444, - debug_dir, - debug_help_string, - &debug_help_fops); - if (!help_file_dentry) { - pr_info("%s: debugfs_create_file failed.\n", __func__); - goto out; - } + debugfs_create_file(ORANGEFS_KMOD_DEBUG_HELP_FILE, 0444, debug_dir, + debug_help_string, &debug_help_fops); orangefs_debug_disabled = 0; - rc = orangefs_kernel_debug_init(); - -out: - - return rc; + orangefs_kernel_debug_init(); } /* * initialize the kernel-debug file. */ -static int orangefs_kernel_debug_init(void) +static void orangefs_kernel_debug_init(void) { int rc = -ENOMEM; - struct dentry *ret; char *k_buffer = NULL; gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: start\n", __func__); @@ -230,24 +211,11 @@ static int orangefs_kernel_debug_init(void) pr_info("%s: overflow 1!\n", __func__); } - ret = debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE, - 0444, - debug_dir, - k_buffer, - &kernel_debug_fops); - if (!ret) { - pr_info("%s: failed to create %s.\n", - __func__, - ORANGEFS_KMOD_DEBUG_FILE); - goto out; - } - - rc = 0; + debugfs_create_file(ORANGEFS_KMOD_DEBUG_FILE, 0444, debug_dir, k_buffer, + &kernel_debug_fops); out: - gossip_debug(GOSSIP_DEBUGFS_DEBUG, "%s: rc:%d:\n", __func__, rc); - return rc; } @@ -353,12 +321,6 @@ static int orangefs_client_debug_init(void) debug_dir, c_buffer, &kernel_debug_fops); - if (!client_debug_dentry) { - pr_info("%s: failed to create updated %s.\n", - __func__, - ORANGEFS_CLIENT_DEBUG_FILE); - goto out; - } rc = 0; diff --git a/fs/orangefs/orangefs-debugfs.h b/fs/orangefs/orangefs-debugfs.h index 51147f9ce3d6..502f6dedccde 100644 --- a/fs/orangefs/orangefs-debugfs.h +++ b/fs/orangefs/orangefs-debugfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -int orangefs_debugfs_init(int); +void orangefs_debugfs_init(int); void orangefs_debugfs_cleanup(void); int orangefs_prepare_debugfs_help_string(int); int orangefs_debugfs_new_client_mask(void __user *); diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c index 82cf8b3e568b..c010c1fddafc 100644 --- a/fs/orangefs/orangefs-mod.c +++ b/fs/orangefs/orangefs-mod.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * (C) 2001 Clemson University and The University of Chicago * @@ -128,9 +129,7 @@ static int __init orangefs_init(void) if (ret) goto cleanup_key_table; - ret = orangefs_debugfs_init(module_parm_debug_mask); - if (ret) - goto debugfs_init_failed; + orangefs_debugfs_init(module_parm_debug_mask); ret = orangefs_sysfs_init(); if (ret) @@ -160,8 +159,6 @@ cleanup_device: orangefs_dev_cleanup(); sysfs_init_failed: - -debugfs_init_failed: orangefs_debugfs_cleanup(); cleanup_key_table: diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index 2ef91be2a04e..444e2da4f60e 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config OVERLAY_FS tristate "Overlay filesystem support" select EXPORTFS diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile index 46e1ff8ac056..9164c585eb2f 100644 --- a/fs/overlayfs/Makefile +++ b/fs/overlayfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the overlay filesystem. # diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 56feaa739979..b801c6353100 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/module.h> @@ -37,7 +34,7 @@ static int ovl_ccup_get(char *buf, const struct kernel_param *param) } module_param_call(check_copy_up, ovl_ccup_set, ovl_ccup_get, NULL, 0644); -MODULE_PARM_DESC(ovl_check_copy_up, "Obsolete; does nothing"); +MODULE_PARM_DESC(check_copy_up, "Obsolete; does nothing"); int ovl_copy_xattr(struct dentry *old, struct dentry *new) { diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 93872bb50230..702aa63f6774 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/fs.h> @@ -21,7 +18,7 @@ static unsigned short ovl_redirect_max = 256; module_param_named(redirect_max, ovl_redirect_max, ushort, 0644); -MODULE_PARM_DESC(ovl_redirect_max, +MODULE_PARM_DESC(redirect_max, "Maximum length of absolute redirect xattr value"); static int ovl_set_redirect(struct dentry *dentry, bool samedir); diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index cc1c9e5606ba..cb8ec1f65c03 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Overlayfs NFS export support. * * Amir Goldstein <amir73il@gmail.com> * * Copyright (C) 2017-2018 CTERA Networks. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/fs.h> diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 540a8b845145..e235a635d9ec 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -1,9 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/cred.h> @@ -409,36 +406,16 @@ static long ovl_real_ioctl(struct file *file, unsigned int cmd, return ret; } -static unsigned int ovl_get_inode_flags(struct inode *inode) -{ - unsigned int flags = READ_ONCE(inode->i_flags); - unsigned int ovl_iflags = 0; - - if (flags & S_SYNC) - ovl_iflags |= FS_SYNC_FL; - if (flags & S_APPEND) - ovl_iflags |= FS_APPEND_FL; - if (flags & S_IMMUTABLE) - ovl_iflags |= FS_IMMUTABLE_FL; - if (flags & S_NOATIME) - ovl_iflags |= FS_NOATIME_FL; - - return ovl_iflags; -} - -static long ovl_ioctl_set_flags(struct file *file, unsigned long arg) +static long ovl_ioctl_set_flags(struct file *file, unsigned int cmd, + unsigned long arg, unsigned int iflags) { long ret; struct inode *inode = file_inode(file); - unsigned int flags; - unsigned int old_flags; + unsigned int old_iflags; if (!inode_owner_or_capable(inode)) return -EACCES; - if (get_user(flags, (int __user *) arg)) - return -EFAULT; - ret = mnt_want_write_file(file); if (ret) return ret; @@ -447,8 +424,8 @@ static long ovl_ioctl_set_flags(struct file *file, unsigned long arg) /* Check the capability before cred override */ ret = -EPERM; - old_flags = ovl_get_inode_flags(inode); - if (((flags ^ old_flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) && + old_iflags = READ_ONCE(inode->i_flags); + if (((iflags ^ old_iflags) & (S_APPEND | S_IMMUTABLE)) && !capable(CAP_LINUX_IMMUTABLE)) goto unlock; @@ -456,7 +433,7 @@ static long ovl_ioctl_set_flags(struct file *file, unsigned long arg) if (ret) goto unlock; - ret = ovl_real_ioctl(file, FS_IOC_SETFLAGS, arg); + ret = ovl_real_ioctl(file, cmd, arg); ovl_copyflags(ovl_inode_real(inode), inode); unlock: @@ -468,17 +445,79 @@ unlock: } +static unsigned int ovl_fsflags_to_iflags(unsigned int flags) +{ + unsigned int iflags = 0; + + if (flags & FS_SYNC_FL) + iflags |= S_SYNC; + if (flags & FS_APPEND_FL) + iflags |= S_APPEND; + if (flags & FS_IMMUTABLE_FL) + iflags |= S_IMMUTABLE; + if (flags & FS_NOATIME_FL) + iflags |= S_NOATIME; + + return iflags; +} + +static long ovl_ioctl_set_fsflags(struct file *file, unsigned int cmd, + unsigned long arg) +{ + unsigned int flags; + + if (get_user(flags, (int __user *) arg)) + return -EFAULT; + + return ovl_ioctl_set_flags(file, cmd, arg, + ovl_fsflags_to_iflags(flags)); +} + +static unsigned int ovl_fsxflags_to_iflags(unsigned int xflags) +{ + unsigned int iflags = 0; + + if (xflags & FS_XFLAG_SYNC) + iflags |= S_SYNC; + if (xflags & FS_XFLAG_APPEND) + iflags |= S_APPEND; + if (xflags & FS_XFLAG_IMMUTABLE) + iflags |= S_IMMUTABLE; + if (xflags & FS_XFLAG_NOATIME) + iflags |= S_NOATIME; + + return iflags; +} + +static long ovl_ioctl_set_fsxflags(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct fsxattr fa; + + memset(&fa, 0, sizeof(fa)); + if (copy_from_user(&fa, (void __user *) arg, sizeof(fa))) + return -EFAULT; + + return ovl_ioctl_set_flags(file, cmd, arg, + ovl_fsxflags_to_iflags(fa.fsx_xflags)); +} + static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { long ret; switch (cmd) { case FS_IOC_GETFLAGS: + case FS_IOC_FSGETXATTR: ret = ovl_real_ioctl(file, cmd, arg); break; case FS_IOC_SETFLAGS: - ret = ovl_ioctl_set_flags(file, arg); + ret = ovl_ioctl_set_fsflags(file, cmd, arg); + break; + + case FS_IOC_FSSETXATTR: + ret = ovl_ioctl_set_fsxflags(file, cmd, arg); break; default: diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b48273e846ad..7663aeb85fa3 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/fs.h> @@ -553,15 +550,15 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, int xinobits = ovl_xino_bits(inode->i_sb); /* - * When NFS export is enabled and d_ino is consistent with st_ino - * (samefs or i_ino has enough bits to encode layer), set the same - * value used for d_ino to i_ino, because nfsd readdirplus compares - * d_ino values to i_ino values of child entries. When called from + * When d_ino is consistent with st_ino (samefs or i_ino has enough + * bits to encode layer), set the same value used for st_ino to i_ino, + * so inode number exposed via /proc/locks and a like will be + * consistent with d_ino and st_ino values. An i_ino value inconsistent + * with d_ino also causes nfsd readdirplus to fail. When called from * ovl_new_inode(), ino arg is 0, so i_ino will be updated to real * upper inode i_ino on ovl_inode_init() or ovl_inode_update(). */ - if (inode->i_sb->s_export_op && - (ovl_same_sb(inode->i_sb) || xinobits)) { + if (ovl_same_sb(inode->i_sb) || xinobits) { inode->i_ino = ino; if (xinobits && fsid && !(ino >> (64 - xinobits))) inode->i_ino |= (unsigned long)fsid << (64 - xinobits); @@ -777,6 +774,54 @@ struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, return inode; } +bool ovl_lookup_trap_inode(struct super_block *sb, struct dentry *dir) +{ + struct inode *key = d_inode(dir); + struct inode *trap; + bool res; + + trap = ilookup5(sb, (unsigned long) key, ovl_inode_test, key); + if (!trap) + return false; + + res = IS_DEADDIR(trap) && !ovl_inode_upper(trap) && + !ovl_inode_lower(trap); + + iput(trap); + return res; +} + +/* + * Create an inode cache entry for layer root dir, that will intentionally + * fail ovl_verify_inode(), so any lookup that will find some layer root + * will fail. + */ +struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir) +{ + struct inode *key = d_inode(dir); + struct inode *trap; + + if (!d_is_dir(dir)) + return ERR_PTR(-ENOTDIR); + + trap = iget5_locked(sb, (unsigned long) key, ovl_inode_test, + ovl_inode_set, key); + if (!trap) + return ERR_PTR(-ENOMEM); + + if (!(trap->i_state & I_NEW)) { + /* Conflicting layer roots? */ + iput(trap); + return ERR_PTR(-ELOOP); + } + + trap->i_mode = S_IFDIR; + trap->i_flags = S_DEAD; + unlock_new_inode(trap); + + return trap; +} + /* * Does overlay inode need to be hashed by lower inode? */ diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index efd372312ef1..e9717c2f7d45 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Novell Inc. * Copyright (C) 2016 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/fs.h> @@ -18,6 +15,7 @@ #include "overlayfs.h" struct ovl_lookup_data { + struct super_block *sb; struct qstr name; bool is_dir; bool opaque; @@ -244,6 +242,12 @@ static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, if (!d->metacopy || d->last) goto out; } else { + if (ovl_lookup_trap_inode(d->sb, this)) { + /* Caught in a trap of overlapping layers */ + err = -ELOOP; + goto out_err; + } + if (last_element) d->is_dir = true; if (d->last) @@ -819,6 +823,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, int err; bool metacopy = false; struct ovl_lookup_data d = { + .sb = dentry->d_sb, .name = dentry->d_name, .is_dir = false, .opaque = false, diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index d26efed9f80a..6934bcf030f0 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -1,10 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * * Copyright (C) 2011 Novell Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/kernel.h> @@ -270,6 +267,7 @@ void ovl_clear_flag(unsigned long flag, struct inode *inode); bool ovl_test_flag(unsigned long flag, struct inode *inode); bool ovl_inuse_trylock(struct dentry *dentry); void ovl_inuse_unlock(struct dentry *dentry); +bool ovl_is_inuse(struct dentry *dentry); bool ovl_need_index(struct dentry *dentry); int ovl_nlink_start(struct dentry *dentry); void ovl_nlink_end(struct dentry *dentry); @@ -376,6 +374,8 @@ struct ovl_inode_params { struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev); struct inode *ovl_lookup_inode(struct super_block *sb, struct dentry *real, bool is_upper); +bool ovl_lookup_trap_inode(struct super_block *sb, struct dentry *dir); +struct inode *ovl_get_trap_inode(struct super_block *sb, struct dentry *dir); struct inode *ovl_get_inode(struct super_block *sb, struct ovl_inode_params *oip); static inline void ovl_copyattr(struct inode *from, struct inode *to) diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index ec237035333a..28a2d12a1029 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -1,11 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * * Copyright (C) 2011 Novell Inc. * Copyright (C) 2016 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ struct ovl_config { @@ -29,6 +26,8 @@ struct ovl_sb { struct ovl_layer { struct vfsmount *mnt; + /* Trap in ovl inode cache */ + struct inode *trap; struct ovl_sb *fs; /* Index of this layer in fs root (upper idx == 0) */ int idx; @@ -65,6 +64,10 @@ struct ovl_fs { /* Did we take the inuse lock? */ bool upperdir_locked; bool workdir_locked; + /* Traps in ovl inode cache */ + struct inode *upperdir_trap; + struct inode *workdir_trap; + struct inode *indexdir_trap; /* Inode numbers in all layers do not use the high xino_bits */ unsigned int xino_bits; }; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index cc8303a806b4..47a91c9733a5 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/fs.h> diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 5ec4fc2f5d7e..b368e2e102fa 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2011 Novell Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <uapi/linux/magic.h> @@ -31,29 +28,29 @@ struct ovl_dir_cache; static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR); module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); -MODULE_PARM_DESC(ovl_redirect_dir_def, +MODULE_PARM_DESC(redirect_dir, "Default to on or off for the redirect_dir feature"); static bool ovl_redirect_always_follow = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW); module_param_named(redirect_always_follow, ovl_redirect_always_follow, bool, 0644); -MODULE_PARM_DESC(ovl_redirect_always_follow, +MODULE_PARM_DESC(redirect_always_follow, "Follow redirects even if redirect_dir feature is turned off"); static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX); module_param_named(index, ovl_index_def, bool, 0644); -MODULE_PARM_DESC(ovl_index_def, +MODULE_PARM_DESC(index, "Default to on or off for the inodes index feature"); static bool ovl_nfs_export_def = IS_ENABLED(CONFIG_OVERLAY_FS_NFS_EXPORT); module_param_named(nfs_export, ovl_nfs_export_def, bool, 0644); -MODULE_PARM_DESC(ovl_nfs_export_def, +MODULE_PARM_DESC(nfs_export, "Default to on or off for the NFS export feature"); static bool ovl_xino_auto_def = IS_ENABLED(CONFIG_OVERLAY_FS_XINO_AUTO); module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644); -MODULE_PARM_DESC(ovl_xino_auto_def, +MODULE_PARM_DESC(xino_auto, "Auto enable xino feature"); static void ovl_entry_stack_free(struct ovl_entry *oe) @@ -66,7 +63,7 @@ static void ovl_entry_stack_free(struct ovl_entry *oe) static bool ovl_metacopy_def = IS_ENABLED(CONFIG_OVERLAY_FS_METACOPY); module_param_named(metacopy, ovl_metacopy_def, bool, 0644); -MODULE_PARM_DESC(ovl_metacopy_def, +MODULE_PARM_DESC(metacopy, "Default to on or off for the metadata only copy up feature"); static void ovl_dentry_release(struct dentry *dentry) @@ -215,6 +212,9 @@ static void ovl_free_fs(struct ovl_fs *ofs) { unsigned i; + iput(ofs->indexdir_trap); + iput(ofs->workdir_trap); + iput(ofs->upperdir_trap); dput(ofs->indexdir); dput(ofs->workdir); if (ofs->workdir_locked) @@ -223,8 +223,10 @@ static void ovl_free_fs(struct ovl_fs *ofs) if (ofs->upperdir_locked) ovl_inuse_unlock(ofs->upper_mnt->mnt_root); mntput(ofs->upper_mnt); - for (i = 0; i < ofs->numlower; i++) + for (i = 0; i < ofs->numlower; i++) { + iput(ofs->lower_layers[i].trap); mntput(ofs->lower_layers[i].mnt); + } for (i = 0; i < ofs->numlowerfs; i++) free_anon_bdev(ofs->lower_fs[i].pseudo_dev); kfree(ofs->lower_layers); @@ -983,7 +985,26 @@ static const struct xattr_handler *ovl_xattr_handlers[] = { NULL }; -static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) +static int ovl_setup_trap(struct super_block *sb, struct dentry *dir, + struct inode **ptrap, const char *name) +{ + struct inode *trap; + int err; + + trap = ovl_get_trap_inode(sb, dir); + err = PTR_ERR_OR_ZERO(trap); + if (err) { + if (err == -ELOOP) + pr_err("overlayfs: conflicting %s path\n", name); + return err; + } + + *ptrap = trap; + return 0; +} + +static int ovl_get_upper(struct super_block *sb, struct ovl_fs *ofs, + struct path *upperpath) { struct vfsmount *upper_mnt; int err; @@ -1003,6 +1024,11 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) if (err) goto out; + err = ovl_setup_trap(sb, upperpath->dentry, &ofs->upperdir_trap, + "upperdir"); + if (err) + goto out; + upper_mnt = clone_private_mount(upperpath); err = PTR_ERR(upper_mnt); if (IS_ERR(upper_mnt)) { @@ -1029,7 +1055,8 @@ out: return err; } -static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath) +static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, + struct path *workpath) { struct vfsmount *mnt = ofs->upper_mnt; struct dentry *temp; @@ -1044,6 +1071,10 @@ static int ovl_make_workdir(struct ovl_fs *ofs, struct path *workpath) if (!ofs->workdir) goto out; + err = ovl_setup_trap(sb, ofs->workdir, &ofs->workdir_trap, "workdir"); + if (err) + goto out; + /* * Upper should support d_type, else whiteouts are visible. Given * workdir and upper are on same fs, we can do iterate_dir() on @@ -1104,7 +1135,8 @@ out: return err; } -static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) +static int ovl_get_workdir(struct super_block *sb, struct ovl_fs *ofs, + struct path *upperpath) { int err; struct path workpath = { }; @@ -1135,19 +1167,16 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } - err = ovl_make_workdir(ofs, &workpath); - if (err) - goto out; + err = ovl_make_workdir(sb, ofs, &workpath); - err = 0; out: path_put(&workpath); return err; } -static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe, - struct path *upperpath) +static int ovl_get_indexdir(struct super_block *sb, struct ovl_fs *ofs, + struct ovl_entry *oe, struct path *upperpath) { struct vfsmount *mnt = ofs->upper_mnt; int err; @@ -1166,6 +1195,11 @@ static int ovl_get_indexdir(struct ovl_fs *ofs, struct ovl_entry *oe, ofs->indexdir = ovl_workdir_create(ofs, OVL_INDEXDIR_NAME, true); if (ofs->indexdir) { + err = ovl_setup_trap(sb, ofs->indexdir, &ofs->indexdir_trap, + "indexdir"); + if (err) + goto out; + /* * Verify upper root is exclusively associated with index dir. * Older kernels stored upper fh in "trusted.overlay.origin" @@ -1253,8 +1287,8 @@ static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) return ofs->numlowerfs; } -static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack, - unsigned int numlower) +static int ovl_get_lower_layers(struct super_block *sb, struct ovl_fs *ofs, + struct path *stack, unsigned int numlower) { int err; unsigned int i; @@ -1272,16 +1306,28 @@ static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack, for (i = 0; i < numlower; i++) { struct vfsmount *mnt; + struct inode *trap; int fsid; err = fsid = ovl_get_fsid(ofs, &stack[i]); if (err < 0) goto out; + err = -EBUSY; + if (ovl_is_inuse(stack[i].dentry)) { + pr_err("overlayfs: lowerdir is in-use as upperdir/workdir\n"); + goto out; + } + + err = ovl_setup_trap(sb, stack[i].dentry, &trap, "lowerdir"); + if (err) + goto out; + mnt = clone_private_mount(&stack[i]); err = PTR_ERR(mnt); if (IS_ERR(mnt)) { pr_err("overlayfs: failed to clone lowerpath\n"); + iput(trap); goto out; } @@ -1291,6 +1337,7 @@ static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack, */ mnt->mnt_flags |= MNT_READONLY | MNT_NOATIME; + ofs->lower_layers[ofs->numlower].trap = trap; ofs->lower_layers[ofs->numlower].mnt = mnt; ofs->lower_layers[ofs->numlower].idx = i + 1; ofs->lower_layers[ofs->numlower].fsid = fsid; @@ -1385,7 +1432,7 @@ static struct ovl_entry *ovl_get_lowerstack(struct super_block *sb, goto out_err; } - err = ovl_get_lower_layers(ofs, stack, numlower); + err = ovl_get_lower_layers(sb, ofs, stack, numlower); if (err) goto out_err; @@ -1417,6 +1464,77 @@ out_err: goto out; } +/* + * Check if this layer root is a descendant of: + * - another layer of this overlayfs instance + * - upper/work dir of any overlayfs instance + */ +static int ovl_check_layer(struct super_block *sb, struct dentry *dentry, + const char *name) +{ + struct dentry *next = dentry, *parent; + int err = 0; + + if (!dentry) + return 0; + + parent = dget_parent(next); + + /* Walk back ancestors to root (inclusive) looking for traps */ + while (!err && parent != next) { + if (ovl_is_inuse(parent)) { + err = -EBUSY; + pr_err("overlayfs: %s path overlapping in-use upperdir/workdir\n", + name); + } else if (ovl_lookup_trap_inode(sb, parent)) { + err = -ELOOP; + pr_err("overlayfs: overlapping %s path\n", name); + } + next = parent; + parent = dget_parent(next); + dput(next); + } + + dput(parent); + + return err; +} + +/* + * Check if any of the layers or work dirs overlap. + */ +static int ovl_check_overlapping_layers(struct super_block *sb, + struct ovl_fs *ofs) +{ + int i, err; + + if (ofs->upper_mnt) { + err = ovl_check_layer(sb, ofs->upper_mnt->mnt_root, "upperdir"); + if (err) + return err; + + /* + * Checking workbasedir avoids hitting ovl_is_inuse(parent) of + * this instance and covers overlapping work and index dirs, + * unless work or index dir have been moved since created inside + * workbasedir. In that case, we already have their traps in + * inode cache and we will catch that case on lookup. + */ + err = ovl_check_layer(sb, ofs->workbasedir, "workdir"); + if (err) + return err; + } + + for (i = 0; i < ofs->numlower; i++) { + err = ovl_check_layer(sb, ofs->lower_layers[i].mnt->mnt_root, + "lowerdir"); + if (err) + return err; + } + + return 0; +} + static int ovl_fill_super(struct super_block *sb, void *data, int silent) { struct path upperpath = { }; @@ -1456,17 +1574,20 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (ofs->config.xino != OVL_XINO_OFF) ofs->xino_bits = BITS_PER_LONG - 32; + /* alloc/destroy_inode needed for setting up traps in inode cache */ + sb->s_op = &ovl_super_operations; + if (ofs->config.upperdir) { if (!ofs->config.workdir) { pr_err("overlayfs: missing 'workdir'\n"); goto out_err; } - err = ovl_get_upper(ofs, &upperpath); + err = ovl_get_upper(sb, ofs, &upperpath); if (err) goto out_err; - err = ovl_get_workdir(ofs, &upperpath); + err = ovl_get_workdir(sb, ofs, &upperpath); if (err) goto out_err; @@ -1487,7 +1608,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags |= SB_RDONLY; if (!(ovl_force_readonly(ofs)) && ofs->config.index) { - err = ovl_get_indexdir(ofs, oe, &upperpath); + err = ovl_get_indexdir(sb, ofs, oe, &upperpath); if (err) goto out_free_oe; @@ -1500,6 +1621,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) } + err = ovl_check_overlapping_layers(sb, ofs); + if (err) + goto out_free_oe; + /* Show index=off in /proc/mounts for forced r/o mount */ if (!ofs->indexdir) { ofs->config.index = false; @@ -1521,7 +1646,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) cap_lower(cred->cap_effective, CAP_SYS_RESOURCE); sb->s_magic = OVERLAYFS_SUPER_MAGIC; - sb->s_op = &ovl_super_operations; sb->s_xattr = ovl_xattr_handlers; sb->s_fs_info = ofs; sb->s_flags |= SB_POSIXACL; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 4035e640f402..f5678a3f8350 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -1,10 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011 Novell Inc. * Copyright (C) 2016 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. */ #include <linux/fs.h> @@ -652,6 +649,18 @@ void ovl_inuse_unlock(struct dentry *dentry) } } +bool ovl_is_inuse(struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + bool inuse; + + spin_lock(&inode->i_lock); + inuse = (inode->i_state & I_OVL_INUSE); + spin_unlock(&inode->i_lock); + + return inuse; +} + /* * Does this overlay dentry need to be indexed on copy up? */ diff --git a/fs/pnode.c b/fs/pnode.c index 7ea6cfb65077..49f6d7ff2139 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -1,10 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/pnode.c * * (C) Copyright IBM Corporation 2005. - * Released under GPL v2. * Author : Ram Pai (linuxram@us.ibm.com) - * */ #include <linux/mnt_namespace.h> #include <linux/mount.h> @@ -262,7 +261,6 @@ static int propagate_one(struct mount *m) child = copy_tree(last_source, last_source->mnt.mnt_root, type); if (IS_ERR(child)) return PTR_ERR(child); - child->mnt.mnt_flags &= ~MNT_LOCKED; mnt_set_mountpoint(m, mp, child); last_dest = m; last_source = child; diff --git a/fs/pnode.h b/fs/pnode.h index 3960a83666cf..49a058c73e4c 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -1,9 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * linux/fs/pnode.h * * (C) Copyright IBM Corporation 2005. - * Released under GPL v2. - * */ #ifndef _LINUX_PNODE_H #define _LINUX_PNODE_H diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 2fd0fde16fe1..84ad1c90d535 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2002,2003 by Andreas Gruenbacher <a.gruenbacher@computer.org> * diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig index 817c02b13b1d..4c3dcb718961 100644 --- a/fs/proc/Kconfig +++ b/fs/proc/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config PROC_FS bool "/proc file system support" if EXPERT default y @@ -97,3 +98,7 @@ config PROC_CHILDREN Say Y if you are running any user-space software which takes benefit from this interface. For example, rkt is such a piece of software. + +config PROC_PID_ARCH_STATUS + def_bool n + depends on PROC_FS diff --git a/fs/proc/array.c b/fs/proc/array.c index 2edbb657f859..46dcb6f0eccf 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -381,9 +381,9 @@ static inline void task_context_switch_counts(struct seq_file *m, static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Cpus_allowed:\t%*pb\n", - cpumask_pr_args(&task->cpus_allowed)); + cpumask_pr_args(task->cpus_ptr)); seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", - cpumask_pr_args(&task->cpus_allowed)); + cpumask_pr_args(task->cpus_ptr)); } static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) @@ -462,7 +462,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ - if (permitted && (task->flags & PF_DUMPCORE)) { + if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); diff --git a/fs/proc/base.c b/fs/proc/base.c index b6ccb6c57706..77eb628ecc7f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -510,7 +510,7 @@ static ssize_t lstats_write(struct file *file, const char __user *buf, if (!task) return -ESRCH; - clear_all_latency_tracing(task); + clear_tsk_latency_tracing(task); put_task_struct(task); return count; @@ -532,8 +532,7 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns, unsigned long totalpages = totalram_pages() + total_swap_pages; unsigned long points = 0; - points = oom_badness(task, NULL, NULL, totalpages) * - 1000 / totalpages; + points = oom_badness(task, totalpages) * 1000 / totalpages; seq_printf(m, "%lu\n", points); return 0; @@ -1962,9 +1961,12 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { - down_read(&mm->mmap_sem); - exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); - up_read(&mm->mmap_sem); + status = down_read_killable(&mm->mmap_sem); + if (!status) { + exact_vma_exists = !!find_exact_vma(mm, vm_start, + vm_end); + up_read(&mm->mmap_sem); + } } mmput(mm); @@ -2010,8 +2012,11 @@ static int map_files_get_link(struct dentry *dentry, struct path *path) if (rc) goto out_mmput; + rc = down_read_killable(&mm->mmap_sem); + if (rc) + goto out_mmput; + rc = -ENOENT; - down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); if (vma && vma->vm_file) { *path = vma->vm_file->f_path; @@ -2107,7 +2112,11 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, if (!mm) goto out_put_task; - down_read(&mm->mmap_sem); + result = ERR_PTR(-EINTR); + if (down_read_killable(&mm->mmap_sem)) + goto out_put_mm; + + result = ERR_PTR(-ENOENT); vma = find_exact_vma(mm, vm_start, vm_end); if (!vma) goto out_no_vma; @@ -2118,6 +2127,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, out_no_vma: up_read(&mm->mmap_sem); +out_put_mm: mmput(mm); out_put_task: put_task_struct(task); @@ -2160,7 +2170,12 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) mm = get_task_mm(task); if (!mm) goto out_put_task; - down_read(&mm->mmap_sem); + + ret = down_read_killable(&mm->mmap_sem); + if (ret) { + mmput(mm); + goto out_put_task; + } nr_files = 0; @@ -3061,6 +3076,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_STACKLEAK_METRICS ONE("stack_depth", S_IRUGO, proc_stack_depth), #endif +#ifdef CONFIG_PROC_PID_ARCH_STATUS + ONE("arch_status", S_IRUGO, proc_pid_arch_status), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) @@ -3077,8 +3095,7 @@ static const struct file_operations proc_tgid_base_operations = { struct pid *tgid_pidfd_to_pid(const struct file *file) { - if (!d_is_dir(file->f_path.dentry) || - (file->f_op != &proc_tgid_base_operations)) + if (file->f_op != &proc_tgid_base_operations) return ERR_PTR(-EBADF); return proc_pid(file_inode(file)); @@ -3449,6 +3466,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif +#ifdef CONFIG_PROC_PID_ARCH_STATUS + ONE("arch_status", S_IRUGO, proc_pid_arch_status), +#endif }; static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c index 954caf0b7fee..dfe6ce3505ce 100644 --- a/fs/proc/consoles.c +++ b/fs/proc/consoles.c @@ -1,7 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2010 Werner Fink, Jiri Slaby - * - * Licensed under GPLv2 */ #include <linux/console.h> diff --git a/fs/proc/generic.c b/fs/proc/generic.c index e39bac94dead..64e9ee1b129e 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * proc/fs/generic.c --- generic routines for the proc-fs * diff --git a/fs/proc/internal.h b/fs/proc/internal.h index d1671e97f7fe..cd0c8d5ce9a1 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* Internal procfs definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/proc_fs.h> diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 568d90e17c17..465ea0153b2a 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -120,7 +120,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) show_val_kb(m, "Committed_AS: ", committed); seq_printf(m, "VmallocTotal: %8lu kB\n", (unsigned long)VMALLOC_TOTAL >> 10); - show_val_kb(m, "VmallocUsed: ", 0ul); + show_val_kb(m, "VmallocUsed: ", vmalloc_nr_pages()); show_val_kb(m, "VmallocChunk: ", 0ul); show_val_kb(m, "Percpu: ", pcpu_nr_pages()); diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 3b63be64e436..14c2badb8fd9 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* nommu.c: mmu-less memory info files * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/init.h> diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index a7b12435519e..76ae278df1c4 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/proc/net.c * diff --git a/fs/proc/root.c b/fs/proc/root.c index 8b145e7b9661..522199e9525e 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -211,7 +211,7 @@ static struct file_system_type proc_fs_type = { .init_fs_context = proc_init_fs_context, .parameters = &proc_fs_parameters, .kill_sb = proc_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .fs_flags = FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM, }; void __init proc_root_init(void) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 01d4eb0e6bd1..dedca3da428a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -166,7 +166,11 @@ static void *m_start(struct seq_file *m, loff_t *ppos) if (!mm || !mmget_not_zero(mm)) return NULL; - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) { + mmput(mm); + return ERR_PTR(-EINTR); + } + hold_task_mempolicy(priv); priv->tail_vma = get_gate_vma(mm); @@ -417,17 +421,53 @@ struct mem_size_stats { unsigned long shared_hugetlb; unsigned long private_hugetlb; u64 pss; + u64 pss_anon; + u64 pss_file; + u64 pss_shmem; u64 pss_locked; u64 swap_pss; bool check_shmem_swap; }; +static void smaps_page_accumulate(struct mem_size_stats *mss, + struct page *page, unsigned long size, unsigned long pss, + bool dirty, bool locked, bool private) +{ + mss->pss += pss; + + if (PageAnon(page)) + mss->pss_anon += pss; + else if (PageSwapBacked(page)) + mss->pss_shmem += pss; + else + mss->pss_file += pss; + + if (locked) + mss->pss_locked += pss; + + if (dirty || PageDirty(page)) { + if (private) + mss->private_dirty += size; + else + mss->shared_dirty += size; + } else { + if (private) + mss->private_clean += size; + else + mss->shared_clean += size; + } +} + static void smaps_account(struct mem_size_stats *mss, struct page *page, bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; + /* + * First accumulate quantities that depend only on |size| and the type + * of the compound page. + */ if (PageAnon(page)) { mss->anonymous += size; if (!PageSwapBacked(page) && !dirty && !PageDirty(page)) @@ -440,42 +480,25 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, mss->referenced += size; /* + * Then accumulate quantities that may depend on sharing, or that may + * differ page-by-page. + * * page_count(page) == 1 guarantees the page is mapped exactly once. * If any subpage of the compound page mapped with PTE it would elevate * page_count(). */ if (page_count(page) == 1) { - if (dirty || PageDirty(page)) - mss->private_dirty += size; - else - mss->private_clean += size; - mss->pss += (u64)size << PSS_SHIFT; - if (locked) - mss->pss_locked += (u64)size << PSS_SHIFT; + smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty, + locked, true); return; } - for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); - unsigned long pss = (PAGE_SIZE << PSS_SHIFT); - - if (mapcount >= 2) { - if (dirty || PageDirty(page)) - mss->shared_dirty += PAGE_SIZE; - else - mss->shared_clean += PAGE_SIZE; - mss->pss += pss / mapcount; - if (locked) - mss->pss_locked += pss / mapcount; - } else { - if (dirty || PageDirty(page)) - mss->private_dirty += PAGE_SIZE; - else - mss->private_clean += PAGE_SIZE; - mss->pss += pss; - if (locked) - mss->pss_locked += pss; - } + unsigned long pss = PAGE_SIZE << PSS_SHIFT; + if (mapcount >= 2) + pss /= mapcount; + smaps_page_accumulate(mss, page, PAGE_SIZE, pss, dirty, locked, + mapcount < 2); } } @@ -754,10 +777,23 @@ static void smap_gather_stats(struct vm_area_struct *vma, seq_put_decimal_ull_width(m, str, (val) >> 10, 8) /* Show the contents common for smaps and smaps_rollup */ -static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss) +static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, + bool rollup_mode) { SEQ_PUT_DEC("Rss: ", mss->resident); SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + if (rollup_mode) { + /* + * These are meaningful only for smaps_rollup, otherwise two of + * them are zero, and the other one is the same as Pss. + */ + SEQ_PUT_DEC(" kB\nPss_Anon: ", + mss->pss_anon >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_File: ", + mss->pss_file >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nPss_Shmem: ", + mss->pss_shmem >> PSS_SHIFT); + } SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean); SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty); SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean); @@ -794,7 +830,7 @@ static int show_smap(struct seq_file *m, void *v) SEQ_PUT_DEC(" kB\nMMUPageSize: ", vma_mmu_pagesize(vma)); seq_puts(m, " kB\n"); - __show_smap(m, &mss); + __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %d\n", transparent_hugepage_enabled(vma)); @@ -828,7 +864,10 @@ static int show_smaps_rollup(struct seq_file *m, void *v) memset(&mss, 0, sizeof(mss)); - down_read(&mm->mmap_sem); + ret = down_read_killable(&mm->mmap_sem); + if (ret) + goto out_put_mm; + hold_task_mempolicy(priv); for (vma = priv->mm->mmap; vma; vma = vma->vm_next) { @@ -841,12 +880,13 @@ static int show_smaps_rollup(struct seq_file *m, void *v) seq_pad(m, ' '); seq_puts(m, "[rollup]\n"); - __show_smap(m, &mss); + __show_smap(m, &mss, true); release_task_mempolicy(priv); up_read(&mm->mmap_sem); - mmput(mm); +out_put_mm: + mmput(mm); out_put_task: put_task_struct(priv->task); priv->task = NULL; @@ -1132,7 +1172,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, goto out_mm; } - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) { + 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) { @@ -1539,7 +1582,9 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, /* overflow ? */ if (end < start_vaddr || end > end_vaddr) end = end_vaddr; - down_read(&mm->mmap_sem); + ret = down_read_killable(&mm->mmap_sem); + if (ret) + goto out_free; ret = walk_page_range(start_vaddr, end, &pagemap_walk); up_read(&mm->mmap_sem); start_vaddr = end; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 36bf0f2e102e..7907e6419e57 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -211,7 +211,11 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!mm || !mmget_not_zero(mm)) return NULL; - down_read(&mm->mmap_sem); + if (down_read_killable(&mm->mmap_sem)) { + mmput(mm); + return ERR_PTR(-EINTR); + } + /* start from the Nth VMA */ for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) if (n-- == 0) diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 3fe90443c1bb..57957c91c6df 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/proc/vmcore.c Interface for accessing the crash * dump from the system's previous life. @@ -165,7 +166,7 @@ void __weak elfcorehdr_free(unsigned long long addr) */ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, false); + return read_from_oldmem(buf, count, ppos, 0, sev_active()); } /* @@ -173,7 +174,7 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) */ ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, sme_active()); + return read_from_oldmem(buf, count, ppos, 0, mem_encrypt_active()); } /* @@ -373,7 +374,7 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, buflen); start = m->paddr + *fpos - m->offset; tmp = read_from_oldmem(buffer, tsz, &start, - userbuf, sme_active()); + userbuf, mem_encrypt_active()); if (tmp < 0) return tmp; buflen -= tsz; diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 0d19d191ae70..8f0369aad22a 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config PSTORE tristate "Persistent store support" select CRYPTO if PSTORE_COMPRESS diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c index b8a0931568f8..bfbfc2698070 100644 --- a/fs/pstore/ftrace.c +++ b/fs/pstore/ftrace.c @@ -1,14 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2012 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include <linux/kernel.h> @@ -120,27 +112,13 @@ static struct dentry *pstore_ftrace_dir; void pstore_register_ftrace(void) { - struct dentry *file; - if (!psinfo->write) return; pstore_ftrace_dir = debugfs_create_dir("pstore", NULL); - if (!pstore_ftrace_dir) { - pr_err("%s: unable to create pstore directory\n", __func__); - return; - } - - file = debugfs_create_file("record_ftrace", 0600, pstore_ftrace_dir, - NULL, &pstore_knob_fops); - if (!file) { - pr_err("%s: unable to create record_ftrace file\n", __func__); - goto err_file; - } - return; -err_file: - debugfs_remove(pstore_ftrace_dir); + debugfs_create_file("record_ftrace", 0600, pstore_ftrace_dir, NULL, + &pstore_knob_fops); } void pstore_unregister_ftrace(void) diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 29e94e0b6d73..7fbe8f058220 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -1,20 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Persistent Storage - ramfs parts. * * Copyright (C) 2010 Intel Corporation <tony.luck@intel.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #include <linux/module.h> @@ -330,22 +318,21 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) goto fail; inode->i_mode = S_IFREG | 0444; inode->i_fop = &pstore_file_operations; - private = kzalloc(sizeof(*private), GFP_KERNEL); - if (!private) - goto fail_alloc; - private->record = record; - scnprintf(name, sizeof(name), "%s-%s-%llu%s", pstore_type_to_name(record->type), record->psi->name, record->id, record->compressed ? ".enc.z" : ""); + private = kzalloc(sizeof(*private), GFP_KERNEL); + if (!private) + goto fail_inode; + dentry = d_alloc_name(root, name); if (!dentry) goto fail_private; + private->record = record; inode->i_size = private->total_size = size; - inode->i_private = private; if (record->time.tv_sec) @@ -361,7 +348,7 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) fail_private: free_pstore_private(private); -fail_alloc: +fail_inode: iput(inode); fail: diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 75887a269b64..3d7024662d29 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Persistent Storage - platform driver interface parts. * * Copyright (C) 2007-2008 Google, Inc. * Copyright (C) 2010 Intel Corporation <tony.luck@intel.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #define pr_fmt(fmt) "pstore: " fmt @@ -347,8 +335,10 @@ static void allocate_buf_for_compression(void) static void free_buf_for_compression(void) { - if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && tfm) + if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && tfm) { crypto_free_comp(tfm); + tfm = NULL; + } kfree(big_oops_buf); big_oops_buf = NULL; big_oops_buf_sz = 0; @@ -606,7 +596,8 @@ int pstore_register(struct pstore_info *psi) return -EINVAL; } - allocate_buf_for_compression(); + if (psi->flags & PSTORE_FLAGS_DMESG) + allocate_buf_for_compression(); if (pstore_is_mounted()) pstore_get_records(0); diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c index 97fcef74e5af..d8542ec2f38c 100644 --- a/fs/pstore/pmsg.c +++ b/fs/pstore/pmsg.c @@ -1,14 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2014 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include <linux/cdev.h> diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index c5c685589e36..2bb3468fc93a 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * RAM Oops/Panic logger * * Copyright (C) 2010 Marco Stornelli <marco.stornelli@gmail.com> * Copyright (C) 2011 Kees Cook <keescook@chromium.org> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -669,6 +655,7 @@ static int ramoops_parse_dt(struct platform_device *pdev, struct ramoops_platform_data *pdata) { struct device_node *of_node = pdev->dev.of_node; + struct device_node *parent_node; struct resource *res; u32 value; int ret; @@ -703,6 +690,26 @@ static int ramoops_parse_dt(struct platform_device *pdev, #undef parse_size + /* + * Some old Chromebooks relied on the kernel setting the + * console_size and pmsg_size to the record size since that's + * what the downstream kernel did. These same Chromebooks had + * "ramoops" straight under the root node which isn't + * according to the current upstream bindings (though it was + * arguably acceptable under a prior version of the bindings). + * Let's make those old Chromebooks work by detecting that + * we're not a child of "reserved-memory" and mimicking the + * expected behavior. + */ + parent_node = of_get_parent(of_node); + if (!of_node_name_eq(parent_node, "reserved-memory") && + !pdata->console_size && !pdata->ftrace_size && + !pdata->pmsg_size && !pdata->ecc_info.ecc_size) { + pdata->console_size = pdata->record_size; + pdata->pmsg_size = pdata->record_size; + } + of_node_put(parent_node); + return 0; } @@ -800,26 +807,36 @@ static int ramoops_probe(struct platform_device *pdev) cxt->pstore.data = cxt; /* - * Since bufsize is only used for dmesg crash dumps, it - * must match the size of the dprz record (after PRZ header - * and ECC bytes have been accounted for). + * Prepare frontend flags based on which areas are initialized. + * For ramoops_init_przs() cases, the "max count" variable tells + * if there are regions present. For ramoops_init_prz() cases, + * the single region size is how to check. */ - cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; - cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); - if (!cxt->pstore.buf) { - pr_err("cannot allocate pstore crash dump buffer\n"); - err = -ENOMEM; - goto fail_clear; - } - - cxt->pstore.flags = PSTORE_FLAGS_DMESG; + cxt->pstore.flags = 0; + if (cxt->max_dump_cnt) + cxt->pstore.flags |= PSTORE_FLAGS_DMESG; if (cxt->console_size) cxt->pstore.flags |= PSTORE_FLAGS_CONSOLE; - if (cxt->ftrace_size) + if (cxt->max_ftrace_cnt) cxt->pstore.flags |= PSTORE_FLAGS_FTRACE; if (cxt->pmsg_size) cxt->pstore.flags |= PSTORE_FLAGS_PMSG; + /* + * Since bufsize is only used for dmesg crash dumps, it + * must match the size of the dprz record (after PRZ header + * and ECC bytes have been accounted for). + */ + if (cxt->pstore.flags & PSTORE_FLAGS_DMESG) { + cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; + cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); + if (!cxt->pstore.buf) { + pr_err("cannot allocate pstore crash dump buffer\n"); + err = -ENOMEM; + goto fail_clear; + } + } + err = pstore_register(&cxt->pstore); if (err) { pr_err("registering with pstore failed\n"); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index f375c0735351..8823f65888f0 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -1,15 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012 Google, Inc. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/fs/qnx4/Kconfig b/fs/qnx4/Kconfig index 5f6089994042..45b5b98376c4 100644 --- a/fs/qnx4/Kconfig +++ b/fs/qnx4/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config QNX4FS_FS tristate "QNX4 file system support (read only)" depends on BLOCK diff --git a/fs/qnx4/Makefile b/fs/qnx4/Makefile index 4a283b3f87f8..42d4fc263a3d 100644 --- a/fs/qnx4/Makefile +++ b/fs/qnx4/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux qnx4-filesystem routines. # diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c index 48c70aa4a3ec..922d083bbc7c 100644 --- a/fs/qnx4/inode.c +++ b/fs/qnx4/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * QNX4 file system, Linux implementation. * diff --git a/fs/qnx6/Kconfig b/fs/qnx6/Kconfig index edbba5c17cc8..6a9d6bce1586 100644 --- a/fs/qnx6/Kconfig +++ b/fs/qnx6/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config QNX6FS_FS tristate "QNX6 file system support (read only)" depends on BLOCK && CRC32 diff --git a/fs/qnx6/Makefile b/fs/qnx6/Makefile index 5e6bae6fae50..bd4e6c8efbc6 100644 --- a/fs/qnx6/Makefile +++ b/fs/qnx6/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux qnx4-filesystem routines. # diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 59cf45f6be49..0f8b0ff1ba43 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * QNX6 file system, Linux implementation. * diff --git a/fs/quota/Kconfig b/fs/quota/Kconfig index 4a09975aac90..7218314ca13f 100644 --- a/fs/quota/Kconfig +++ b/fs/quota/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Quota configuration # diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 9ad72ea7f71f..be9c471cdbc8 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -223,9 +223,9 @@ static void put_quota_format(struct quota_format_type *fmt) /* * Dquot List Management: - * The quota code uses three lists for dquot management: the inuse_list, - * free_dquots, and dquot_hash[] array. A single dquot structure may be - * on all three lists, depending on its current state. + * The quota code uses four lists for dquot management: the inuse_list, + * free_dquots, dqi_dirty_list, and dquot_hash[] array. A single dquot + * structure may be on some of those lists, depending on its current state. * * All dquots are placed to the end of inuse_list when first created, and this * list is used for invalidate operation, which must look at every dquot. @@ -236,6 +236,11 @@ static void put_quota_format(struct quota_format_type *fmt) * dqstats.free_dquots gives the number of dquots on the list. When * dquot is invalidated it's completely released from memory. * + * Dirty dquots are added to the dqi_dirty_list of quota_info when mark + * dirtied, and this list is searched when writing dirty dquots back to + * quota file. Note that some filesystems do dirty dquot tracking on their + * own (e.g. in a journal) and thus don't use dqi_dirty_list. + * * Dquots with a specific identity (device, type and id) are placed on * one of the dquot_hash[] hash chains. The provides an efficient search * mechanism to locate a specific dquot. @@ -1996,8 +2001,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) &warn_to[cnt]); if (ret) goto over_quota; - ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0, - &warn_to[cnt]); + ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, + DQUOT_SPACE_WARN, &warn_to[cnt]); if (ret) { spin_lock(&transfer_to[cnt]->dq_dqb_lock); dquot_decr_inodes(transfer_to[cnt], inode_usage); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index fd5dd806f1b9..cb13fb76dbee 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -331,9 +331,9 @@ static int quota_state_to_flags(struct qc_state *state) return flags; } -static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs) +static int quota_getstate(struct super_block *sb, int type, + struct fs_quota_stat *fqs) { - int type; struct qc_state state; int ret; @@ -349,14 +349,7 @@ static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs) if (!fqs->qs_flags) return -ENOSYS; fqs->qs_incoredqs = state.s_incoredqs; - /* - * GETXSTATE quotactl has space for just one set of time limits so - * report them for the first enabled quota type - */ - for (type = 0; type < MAXQUOTAS; type++) - if (state.s_state[type].flags & QCI_ACCT_ENABLED) - break; - BUG_ON(type == MAXQUOTAS); + fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; @@ -391,22 +384,22 @@ static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs) return 0; } -static int quota_getxstate(struct super_block *sb, void __user *addr) +static int quota_getxstate(struct super_block *sb, int type, void __user *addr) { struct fs_quota_stat fqs; int ret; if (!sb->s_qcop->get_state) return -ENOSYS; - ret = quota_getstate(sb, &fqs); + ret = quota_getstate(sb, type, &fqs); if (!ret && copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return ret; } -static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs) +static int quota_getstatev(struct super_block *sb, int type, + struct fs_quota_statv *fqs) { - int type; struct qc_state state; int ret; @@ -422,14 +415,7 @@ static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs) if (!fqs->qs_flags) return -ENOSYS; fqs->qs_incoredqs = state.s_incoredqs; - /* - * GETXSTATV quotactl has space for just one set of time limits so - * report them for the first enabled quota type - */ - for (type = 0; type < MAXQUOTAS; type++) - if (state.s_state[type].flags & QCI_ACCT_ENABLED) - break; - BUG_ON(type == MAXQUOTAS); + fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; @@ -455,7 +441,7 @@ static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs) return 0; } -static int quota_getxstatev(struct super_block *sb, void __user *addr) +static int quota_getxstatev(struct super_block *sb, int type, void __user *addr) { struct fs_quota_statv fqs; int ret; @@ -474,7 +460,7 @@ static int quota_getxstatev(struct super_block *sb, void __user *addr) default: return -EINVAL; } - ret = quota_getstatev(sb, &fqs); + ret = quota_getstatev(sb, type, &fqs); if (!ret && copy_to_user(addr, &fqs, sizeof(fqs))) return -EFAULT; return ret; @@ -744,9 +730,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, case Q_XQUOTARM: return quota_rmxquota(sb, addr); case Q_XGETQSTAT: - return quota_getxstate(sb, addr); + return quota_getxstate(sb, type, addr); case Q_XGETQSTATV: - return quota_getxstatev(sb, addr); + return quota_getxstatev(sb, type, addr); case Q_XSETQLIM: return quota_setxquota(sb, type, id, addr); case Q_XGETQUOTA: diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c index bb3f59bcfcf5..a6f856f341dc 100644 --- a/fs/quota/quota_tree.c +++ b/fs/quota/quota_tree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * vfsv0 quota IO operations on file */ diff --git a/fs/quota/quota_v1.c b/fs/quota/quota_v1.c index 9f2b2573b83c..c740e5572eb8 100644 --- a/fs/quota/quota_v1.c +++ b/fs/quota/quota_v1.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only #include <linux/errno.h> #include <linux/fs.h> #include <linux/quota.h> diff --git a/fs/quota/quota_v2.c b/fs/quota/quota_v2.c index 3c30034e733f..53429c29c784 100644 --- a/fs/quota/quota_v2.c +++ b/fs/quota/quota_v2.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * vfsv0 quota IO operations on file */ diff --git a/fs/ramfs/Makefile b/fs/ramfs/Makefile index c71e65dcad25..d1198adb562e 100644 --- a/fs/ramfs/Makefile +++ b/fs/ramfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux ramfs routines. # diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 3ac1f2387083..414695454956 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* file-nommu.c: no-MMU version of ramfs * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> diff --git a/fs/ramfs/internal.h b/fs/ramfs/internal.h index a9d8ae88fa15..3257fc1809d9 100644 --- a/fs/ramfs/internal.h +++ b/fs/ramfs/internal.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: ramfs internal definitions * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ diff --git a/fs/read_write.c b/fs/read_write.c index c543d965e288..1f5088dec566 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1565,6 +1565,58 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, } #endif +/** + * generic_copy_file_range - copy data between two files + * @file_in: file structure to read from + * @pos_in: file offset to read from + * @file_out: file structure to write data to + * @pos_out: file offset to write data to + * @len: amount of data to copy + * @flags: copy flags + * + * This is a generic filesystem helper to copy data from one file to another. + * It has no constraints on the source or destination file owners - the files + * can belong to different superblocks and different filesystem types. Short + * copies are allowed. + * + * This should be called from the @file_out filesystem, as per the + * ->copy_file_range() method. + * + * Returns the number of bytes copied or a negative error indicating the + * failure. + */ + +ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags) +{ + return do_splice_direct(file_in, &pos_in, file_out, &pos_out, + len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); +} +EXPORT_SYMBOL(generic_copy_file_range); + +static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t len, unsigned int flags) +{ + /* + * Although we now allow filesystems to handle cross sb copy, passing + * a file of the wrong filesystem type to filesystem driver can result + * in an attempt to dereference the wrong type of ->private_data, so + * avoid doing that until we really have a good reason. NFS defines + * several different file_system_type structures, but they all end up + * using the same ->copy_file_range() function pointer. + */ + if (file_out->f_op->copy_file_range && + file_out->f_op->copy_file_range == file_in->f_op->copy_file_range) + return file_out->f_op->copy_file_range(file_in, pos_in, + file_out, pos_out, + len, flags); + + return generic_copy_file_range(file_in, pos_in, file_out, pos_out, len, + flags); +} + /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to @@ -1574,17 +1626,15 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); ssize_t ret; if (flags != 0) return -EINVAL; - if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - return -EISDIR; - if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - return -EINVAL; + ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, + flags); + if (unlikely(ret)) + return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) @@ -1594,15 +1644,6 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (unlikely(ret)) return ret; - if (!(file_in->f_mode & FMODE_READ) || - !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND)) - return -EBADF; - - /* this could be relaxed once a method supports cross-fs copies */ - if (inode_in->i_sb != inode_out->i_sb) - return -EXDEV; - if (len == 0) return 0; @@ -1612,7 +1653,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * Try cloning first, this is supported by more file systems, and * more efficient if both clone and copy are supported (e.g. NFS). */ - if (file_in->f_op->remap_file_range) { + if (file_in->f_op->remap_file_range && + file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) { loff_t cloned; cloned = file_in->f_op->remap_file_range(file_in, pos_in, @@ -1625,16 +1667,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, } } - if (file_out->f_op->copy_file_range) { - ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, - pos_out, len, flags); - if (ret != -EOPNOTSUPP) - goto done; - } - - ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, - len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0); - + ret = do_copy_file_range(file_in, pos_in, file_out, pos_out, len, + flags); + WARN_ON_ONCE(ret == -EOPNOTSUPP); done: if (ret > 0) { fsnotify_access(file_in); @@ -1951,25 +1986,10 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, return ret; /* If can't alter the file contents, we're done. */ - if (!(remap_flags & REMAP_FILE_DEDUP)) { - /* Update the timestamps, since we can alter file contents. */ - if (!(file_out->f_mode & FMODE_NOCMTIME)) { - ret = file_update_time(file_out); - if (ret) - return ret; - } - - /* - * Clear the security bits if the process is not being run by - * root. This keeps people from modifying setuid and setgid - * binaries. - */ - ret = file_remove_privs(file_out); - if (ret) - return ret; - } + if (!(remap_flags & REMAP_FILE_DEDUP)) + ret = file_modified(file_out); - return 0; + return ret; } EXPORT_SYMBOL(generic_remap_file_range_prep); @@ -1977,29 +1997,21 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags) { - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); loff_t ret; WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); - if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - return -EISDIR; - if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - return -EINVAL; - /* * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on * the same mount. Practically, they only need to be on the same file * system. */ - if (inode_in->i_sb != inode_out->i_sb) + if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) return -EXDEV; - if (!(file_in->f_mode & FMODE_READ) || - !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND)) - return -EBADF; + ret = generic_file_rw_checks(file_in, file_out); + if (ret < 0) + return ret; if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; diff --git a/fs/reiserfs/Kconfig b/fs/reiserfs/Kconfig index 86e71c0caf48..8fd54ed8f844 100644 --- a/fs/reiserfs/Kconfig +++ b/fs/reiserfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config REISERFS_FS tristate "Reiserfs support" select CRC32 diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index acbbaf7a0bb2..45e1a5d11af3 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -74,13 +74,11 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) err = -EPERM; goto setflags_out; } - if (((flags ^ REISERFS_I(inode)-> - i_attrs) & (REISERFS_IMMUTABLE_FL | - REISERFS_APPEND_FL)) - && !capable(CAP_LINUX_IMMUTABLE)) { - err = -EPERM; + err = vfs_ioc_setflags_prepare(inode, + REISERFS_I(inode)->i_attrs, + flags); + if (err) goto setflags_out; - } if ((flags & REISERFS_NOTAIL_FL) && S_ISREG(inode->i_mode)) { int result; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 32d8986c26fb..b5b26d8a192c 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -450,6 +450,15 @@ fail: static inline __u32 xattr_hash(const char *msg, int len) { + /* + * csum_partial() gives different results for little-endian and + * big endian hosts. Images created on little-endian hosts and + * mounted on big-endian hosts(and vice versa) will see csum mismatches + * when trying to fetch xattrs. Treating the hash as __wsum_t would + * lower the frequency of mismatch. This is an endianness bug in + * reiserfs. The return statement would result in a sparse warning. Do + * not fix the sparse warning so as to not hide a reminder of the bug. + */ return csum_partial(msg, len, 0); } diff --git a/fs/romfs/Kconfig b/fs/romfs/Kconfig index ce2d6bcc6266..ad4c45788896 100644 --- a/fs/romfs/Kconfig +++ b/fs/romfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config ROMFS_FS tristate "ROM file system support" depends on BLOCK || MTD diff --git a/fs/romfs/internal.h b/fs/romfs/internal.h index 95217b830118..e90df22bdc82 100644 --- a/fs/romfs/internal.h +++ b/fs/romfs/internal.h @@ -1,12 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* RomFS internal definitions * * Copyright © 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/romfs_fs.h> diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index 1118a0dc6b45..2c4a23113fb5 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* NOMMU mmap support for RomFS on MTD devices * * Copyright © 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/mm.h> diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c index f86f51f99ace..6b2b4362089e 100644 --- a/fs/romfs/storage.c +++ b/fs/romfs/storage.c @@ -1,12 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* RomFS storage access routines * * Copyright © 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. */ #include <linux/fs.h> diff --git a/fs/select.c b/fs/select.c index 6cbc9ff56ba0..a4d8f6e8b63c 100644 --- a/fs/select.c +++ b/fs/select.c @@ -758,10 +758,9 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, return ret; ret = core_sys_select(n, inp, outp, exp, to); + restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND); ret = poll_select_copy_remaining(&end_time, tsp, type, ret); - restore_user_sigmask(sigmask, &sigsaved); - return ret; } @@ -1106,8 +1105,7 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1142,8 +1140,7 @@ SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1350,10 +1347,9 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp, return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); + restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND); ret = poll_select_copy_remaining(&end_time, tsp, type, ret); - restore_user_sigmask(sigmask, &sigsaved); - return ret; } @@ -1425,8 +1421,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1461,8 +1456,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; diff --git a/fs/seq_file.c b/fs/seq_file.c index abe27ec43176..04f09689cd6d 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -384,6 +384,17 @@ void seq_escape(struct seq_file *m, const char *s, const char *esc) } EXPORT_SYMBOL(seq_escape); +void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz) +{ + char *buf; + size_t size = seq_get_buf(m, &buf); + int ret; + + ret = string_escape_mem_ascii(src, isz, buf, size); + seq_commit(m, ret < size ? ret : -1); +} +EXPORT_SYMBOL(seq_escape_mem_ascii); + void seq_vprintf(struct seq_file *m, const char *f, va_list args) { int len; diff --git a/fs/splice.c b/fs/splice.c index 25212dcca2df..14cb602d9a2f 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * "splice": joining two ropes together by interweaving their strands. * diff --git a/fs/squashfs/Kconfig b/fs/squashfs/Kconfig index 1adb3346b9d6..916e78fabcaa 100644 --- a/fs/squashfs/Kconfig +++ b/fs/squashfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config SQUASHFS tristate "SquashFS 4.0 - Squashed file system support" depends on BLOCK diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index f098b9f1c396..4f9b9fb59362 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * block.c */ diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 0839efa720b3..5062326d0efb 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * cache.c */ diff --git a/fs/squashfs/decompressor.c b/fs/squashfs/decompressor.c index 836639810ea0..d57bef91ab08 100644 --- a/fs/squashfs/decompressor.c +++ b/fs/squashfs/decompressor.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * decompressor.c */ diff --git a/fs/squashfs/decompressor.h b/fs/squashfs/decompressor.h index 0f5a8e4e58da..ec8617523e56 100644 --- a/fs/squashfs/decompressor.h +++ b/fs/squashfs/decompressor.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef DECOMPRESSOR_H #define DECOMPRESSOR_H /* @@ -6,20 +7,6 @@ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * decompressor.h */ diff --git a/fs/squashfs/decompressor_multi.c b/fs/squashfs/decompressor_multi.c index d6008a636479..c181dee235bb 100644 --- a/fs/squashfs/decompressor_multi.c +++ b/fs/squashfs/decompressor_multi.c @@ -1,9 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Minchan Kim <minchan@kernel.org> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/types.h> #include <linux/mutex.h> diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c index 23a9c28ad8ea..2a2a2d106440 100644 --- a/fs/squashfs/decompressor_multi_percpu.c +++ b/fs/squashfs/decompressor_multi_percpu.c @@ -1,9 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/types.h> diff --git a/fs/squashfs/decompressor_single.c b/fs/squashfs/decompressor_single.c index a6c75929a00e..550c3e592032 100644 --- a/fs/squashfs/decompressor_single.c +++ b/fs/squashfs/decompressor_single.c @@ -1,9 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/types.h> diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c index a5845f94a2a1..a2ade63eccdf 100644 --- a/fs/squashfs/dir.c +++ b/fs/squashfs/dir.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * dir.c */ diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c index 8073b6532cf0..ae2c87bb0fbe 100644 --- a/fs/squashfs/export.c +++ b/fs/squashfs/export.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * export.c */ diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index f1c1430ae721..7b1128398976 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * file.c */ diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c index a9ba8d96776a..54c17b7c85fd 100644 --- a/fs/squashfs/file_cache.c +++ b/fs/squashfs/file_cache.c @@ -1,9 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/fs.h> diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index 80db1b86a27c..a4894cc59447 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -1,9 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/fs.h> diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c index 0681feab4a84..49602b9a42e1 100644 --- a/fs/squashfs/fragment.c +++ b/fs/squashfs/fragment.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * fragment.c */ diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c index d38ea3dab951..6be5afe7287d 100644 --- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * id.c */ diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index e9793b1e49a5..24463145b351 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * inode.c */ diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c index 95da65366548..c4e47e0588c7 100644 --- a/fs/squashfs/lz4_wrapper.c +++ b/fs/squashfs/lz4_wrapper.c @@ -1,9 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013, 2014 * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/buffer_head.h> diff --git a/fs/squashfs/lzo_wrapper.c b/fs/squashfs/lzo_wrapper.c index 934c17e96590..aa3c3dafc33d 100644 --- a/fs/squashfs/lzo_wrapper.c +++ b/fs/squashfs/lzo_wrapper.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2010 LG Electronics * Chan Jeong <chan.jeong@lge.com> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * lzo_wrapper.c */ diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c index 40c10d9974c9..11e4539b9eae 100644 --- a/fs/squashfs/namei.c +++ b/fs/squashfs/namei.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * namei.c */ diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c index 9b7b1b6a7892..520d323a99ce 100644 --- a/fs/squashfs/page_actor.c +++ b/fs/squashfs/page_actor.c @@ -1,9 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/kernel.h> diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h index 98537eab27e2..2e3073ace009 100644 --- a/fs/squashfs/page_actor.h +++ b/fs/squashfs/page_actor.h @@ -1,11 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ #ifndef PAGE_ACTOR_H #define PAGE_ACTOR_H /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #ifndef CONFIG_SQUASHFS_FILE_DIRECT diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index f89f8a74c6ce..2797763ed046 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * squashfs.h */ diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 4e6853f084d0..7187bd1a30ea 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef SQUASHFS_FS #define SQUASHFS_FS /* @@ -6,20 +7,6 @@ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * squashfs_fs.h */ diff --git a/fs/squashfs/squashfs_fs_i.h b/fs/squashfs/squashfs_fs_i.h index d09fcd6fb85d..2c82d6f2a456 100644 --- a/fs/squashfs/squashfs_fs_i.h +++ b/fs/squashfs/squashfs_fs_i.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef SQUASHFS_FS_I #define SQUASHFS_FS_I /* @@ -6,20 +7,6 @@ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * squashfs_fs_i.h */ diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index ef69c31947bf..34c21ffb6df3 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef SQUASHFS_FS_SB #define SQUASHFS_FS_SB /* @@ -6,20 +7,6 @@ * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * squashfs_fs_sb.h */ diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 767046d9f65d..effa638d6d85 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * super.c */ diff --git a/fs/squashfs/symlink.c b/fs/squashfs/symlink.c index befeba0fa70a..1430613183e6 100644 --- a/fs/squashfs/symlink.c +++ b/fs/squashfs/symlink.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * symlink.c */ diff --git a/fs/squashfs/xattr.c b/fs/squashfs/xattr.c index 1548b3784548..e1e3f3dd5a06 100644 --- a/fs/squashfs/xattr.c +++ b/fs/squashfs/xattr.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2010 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * xattr.c */ diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index afe70f815e3d..184129afd456 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -1,23 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2010 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * xattr.h */ diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index c89607d690c4..d99e08464554 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2010 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * xattr_id.c */ diff --git a/fs/squashfs/xz_wrapper.c b/fs/squashfs/xz_wrapper.c index 6bfaef73d065..4b2f2051a6dc 100644 --- a/fs/squashfs/xz_wrapper.c +++ b/fs/squashfs/xz_wrapper.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * xz_wrapper.c */ diff --git a/fs/squashfs/zlib_wrapper.c b/fs/squashfs/zlib_wrapper.c index 2ec24d128bce..f2226afa1625 100644 --- a/fs/squashfs/zlib_wrapper.c +++ b/fs/squashfs/zlib_wrapper.c @@ -1,23 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009 * Phillip Lougher <phillip@squashfs.org.uk> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. - * * zlib_wrapper.c */ diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c index eeaabf881159..b448c2a1d0ed 100644 --- a/fs/squashfs/zstd_wrapper.c +++ b/fs/squashfs/zstd_wrapper.c @@ -1,19 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * Squashfs - a compressed read only filesystem for Linux * * Copyright (c) 2016-present, Facebook, Inc. * All rights reserved. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2, - * or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * zstd_wrapper.c */ diff --git a/fs/stack.c b/fs/stack.c index 664ed35558bd..4ef2c056269d 100644 --- a/fs/stack.c +++ b/fs/stack.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/fs.h> #include <linux/fs_stack.h> diff --git a/fs/sysfs/Kconfig b/fs/sysfs/Kconfig index b2756014508c..b0fe1cce33a0 100644 --- a/fs/sysfs/Kconfig +++ b/fs/sysfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config SYSFS bool "sysfs file system support" if EXPERT default y diff --git a/fs/sysfs/Makefile b/fs/sysfs/Makefile index 6eff6e1205a5..0906b9e522fe 100644 --- a/fs/sysfs/Makefile +++ b/fs/sysfs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the sysfs virtual filesystem # diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 57038604d4a8..d41c21fef138 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -175,6 +175,26 @@ int sysfs_create_group(struct kobject *kobj, } EXPORT_SYMBOL_GPL(sysfs_create_group); +static int internal_create_groups(struct kobject *kobj, int update, + const struct attribute_group **groups) +{ + int error = 0; + int i; + + if (!groups) + return 0; + + for (i = 0; groups[i]; i++) { + error = internal_create_group(kobj, update, groups[i]); + if (error) { + while (--i >= 0) + sysfs_remove_group(kobj, groups[i]); + break; + } + } + return error; +} + /** * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups * @kobj: The kobject to create the group on @@ -191,25 +211,29 @@ EXPORT_SYMBOL_GPL(sysfs_create_group); int sysfs_create_groups(struct kobject *kobj, const struct attribute_group **groups) { - int error = 0; - int i; - - if (!groups) - return 0; - - for (i = 0; groups[i]; i++) { - error = sysfs_create_group(kobj, groups[i]); - if (error) { - while (--i >= 0) - sysfs_remove_group(kobj, groups[i]); - break; - } - } - return error; + return internal_create_groups(kobj, 0, groups); } EXPORT_SYMBOL_GPL(sysfs_create_groups); /** + * sysfs_update_groups - given a directory kobject, create a bunch of attribute groups + * @kobj: The kobject to update the group on + * @groups: The attribute groups to update, NULL terminated + * + * This function update a bunch of attribute groups. If an error occurs when + * updating a group, all previously updated groups will be removed together + * with already existing (not updated) attributes. + * + * Returns 0 on success or error code from sysfs_update_group on failure. + */ +int sysfs_update_groups(struct kobject *kobj, + const struct attribute_group **groups) +{ + return internal_create_groups(kobj, 1, groups); +} +EXPORT_SYMBOL_GPL(sysfs_update_groups); + +/** * sysfs_update_group - given a directory kobject, update an attribute group * @kobj: The kobject to update the group on * @grp: The attribute group to update diff --git a/fs/sysv/Kconfig b/fs/sysv/Kconfig index 33aeb4b75db1..d4edf7d9ae10 100644 --- a/fs/sysv/Kconfig +++ b/fs/sysv/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config SYSV_FS tristate "System V/Xenix/V7/Coherent file system support" depends on BLOCK diff --git a/fs/sysv/Makefile b/fs/sysv/Makefile index 7a75e70a4b61..17d12ba04b18 100644 --- a/fs/sysv/Makefile +++ b/fs/sysv/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux SystemV/Coherent filesystem routines. # diff --git a/fs/sysv/super.c b/fs/sysv/super.c index d3b2f54d6449..d788b1daa7eb 100644 --- a/fs/sysv/super.c +++ b/fs/sysv/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/sysv/inode.c * diff --git a/fs/tracefs/Makefile b/fs/tracefs/Makefile index 82fa35b656c4..7c35a282b484 100644 --- a/fs/tracefs/Makefile +++ b/fs/tracefs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only tracefs-objs := inode.o obj-$(CONFIG_TRACING) += tracefs.o diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 7098c49f3693..eeeae0475da9 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * inode.c - part of tracefs, a pseudo file system for activating tracing * @@ -5,12 +6,7 @@ * * Copyright (C) 2014 Red Hat Inc, author: Steven Rostedt <srostedt@redhat.com> * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * * tracefs is the file system that is used by the tracing infrastructure. - * */ #include <linux/module.h> @@ -509,9 +505,12 @@ static int __tracefs_remove(struct dentry *dentry, struct dentry *parent) switch (dentry->d_inode->i_mode & S_IFMT) { case S_IFDIR: ret = simple_rmdir(parent->d_inode, dentry); + if (!ret) + fsnotify_rmdir(parent->d_inode, dentry); break; default: simple_unlink(parent->d_inode, dentry); + fsnotify_unlink(parent->d_inode, dentry); break; } if (!ret) diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index 9da2f135121b..06c35c64162b 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config UBIFS_FS tristate "UBIFS file system support" select CRC16 diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 7ef22baf9d15..80d7301ab76d 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index 591f2c7a48f0..ad292c5a43a9 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/compress.c b/fs/ubifs/compress.c index 565cb56d7225..99c53ad11e93 100644 --- a/fs/ubifs/compress.c +++ b/fs/ubifs/compress.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * Copyright (C) 2006, 2007 University of Szeged, Hungary * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) * Zoltan Sogor diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c index 4aaedf2d7f44..22be7aeb96c4 100644 --- a/fs/ubifs/crypto.c +++ b/fs/ubifs/crypto.c @@ -29,8 +29,8 @@ int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn, { struct ubifs_info *c = inode->i_sb->s_fs_info; void *p = &dn->data; - struct page *ret; unsigned int pad_len = round_up(in_len, UBIFS_CIPHER_BLOCK_SIZE); + int err; ubifs_assert(c, pad_len <= *out_len); dn->compr_size = cpu_to_le16(in_len); @@ -39,11 +39,11 @@ int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn, if (pad_len != in_len) memset(p + in_len, 0, pad_len - in_len); - ret = fscrypt_encrypt_page(inode, virt_to_page(&dn->data), pad_len, - offset_in_page(&dn->data), block, GFP_NOFS); - if (IS_ERR(ret)) { - ubifs_err(c, "fscrypt_encrypt_page failed: %ld", PTR_ERR(ret)); - return PTR_ERR(ret); + err = fscrypt_encrypt_block_inplace(inode, virt_to_page(p), pad_len, + offset_in_page(p), block, GFP_NOFS); + if (err) { + ubifs_err(c, "fscrypt_encrypt_block_inplace() failed: %d", err); + return err; } *out_len = pad_len; @@ -64,10 +64,11 @@ int ubifs_decrypt(const struct inode *inode, struct ubifs_data_node *dn, } ubifs_assert(c, dlen <= UBIFS_BLOCK_SIZE); - err = fscrypt_decrypt_page(inode, virt_to_page(&dn->data), dlen, - offset_in_page(&dn->data), block); + err = fscrypt_decrypt_block_inplace(inode, virt_to_page(&dn->data), + dlen, offset_in_page(&dn->data), + block); if (err) { - ubifs_err(c, "fscrypt_decrypt_page failed: %i", err); + ubifs_err(c, "fscrypt_decrypt_block_inplace() failed: %d", err); return err; } *out_len = clen; diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 3a2613038e88..a5f10d79e0dd 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ @@ -2812,115 +2800,69 @@ static const struct file_operations dfs_fops = { * dbg_debugfs_init_fs - initialize debugfs for UBIFS instance. * @c: UBIFS file-system description object * - * This function creates all debugfs files for this instance of UBIFS. Returns - * zero in case of success and a negative error code in case of failure. + * This function creates all debugfs files for this instance of UBIFS. * * Note, the only reason we have not merged this function with the * 'ubifs_debugging_init()' function is because it is better to initialize * debugfs interfaces at the very end of the mount process, and remove them at * the very beginning of the mount process. */ -int dbg_debugfs_init_fs(struct ubifs_info *c) +void dbg_debugfs_init_fs(struct ubifs_info *c) { - int err, n; + int n; const char *fname; - struct dentry *dent; struct ubifs_debug_info *d = c->dbg; - if (!IS_ENABLED(CONFIG_DEBUG_FS)) - return 0; - n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME, c->vi.ubi_num, c->vi.vol_id); if (n == UBIFS_DFS_DIR_LEN) { /* The array size is too small */ fname = UBIFS_DFS_DIR_NAME; - dent = ERR_PTR(-EINVAL); - goto out; + return; } fname = d->dfs_dir_name; - dent = debugfs_create_dir(fname, dfs_rootdir); - if (IS_ERR_OR_NULL(dent)) - goto out; - d->dfs_dir = dent; + d->dfs_dir = debugfs_create_dir(fname, dfs_rootdir); fname = "dump_lprops"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_dump_lprops = dent; + d->dfs_dump_lprops = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, + &dfs_fops); fname = "dump_budg"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_dump_budg = dent; + d->dfs_dump_budg = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, + &dfs_fops); fname = "dump_tnc"; - dent = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_dump_tnc = dent; + d->dfs_dump_tnc = debugfs_create_file(fname, S_IWUSR, d->dfs_dir, c, + &dfs_fops); fname = "chk_general"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_gen = dent; + d->dfs_chk_gen = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + d->dfs_dir, c, &dfs_fops); fname = "chk_index"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_index = dent; + d->dfs_chk_index = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + d->dfs_dir, c, &dfs_fops); fname = "chk_orphans"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_orph = dent; + d->dfs_chk_orph = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + d->dfs_dir, c, &dfs_fops); fname = "chk_lprops"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_lprops = dent; + d->dfs_chk_lprops = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + d->dfs_dir, c, &dfs_fops); fname = "chk_fs"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_chk_fs = dent; + d->dfs_chk_fs = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + d->dfs_dir, c, &dfs_fops); fname = "tst_recovery"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_tst_rcvry = dent; + d->dfs_tst_rcvry = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + d->dfs_dir, c, &dfs_fops); fname = "ro_error"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, d->dfs_dir, c, - &dfs_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - d->dfs_ro_error = dent; - - return 0; - -out_remove: - debugfs_remove_recursive(d->dfs_dir); -out: - err = dent ? PTR_ERR(dent) : -ENODEV; - ubifs_err(c, "cannot create \"%s\" debugfs file or directory, error %d\n", - fname, err); - return err; + d->dfs_ro_error = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + d->dfs_dir, c, &dfs_fops); } /** @@ -2929,8 +2871,7 @@ out: */ void dbg_debugfs_exit_fs(struct ubifs_info *c) { - if (IS_ENABLED(CONFIG_DEBUG_FS)) - debugfs_remove_recursive(c->dbg->dfs_dir); + debugfs_remove_recursive(c->dbg->dfs_dir); } struct ubifs_global_debug_info ubifs_dbg; @@ -3006,75 +2947,38 @@ static const struct file_operations dfs_global_fops = { * * UBIFS uses debugfs file-system to expose various debugging knobs to * user-space. This function creates "ubifs" directory in the debugfs - * file-system. Returns zero in case of success and a negative error code in - * case of failure. + * file-system. */ -int dbg_debugfs_init(void) +void dbg_debugfs_init(void) { - int err; const char *fname; - struct dentry *dent; - - if (!IS_ENABLED(CONFIG_DEBUG_FS)) - return 0; fname = "ubifs"; - dent = debugfs_create_dir(fname, NULL); - if (IS_ERR_OR_NULL(dent)) - goto out; - dfs_rootdir = dent; + dfs_rootdir = debugfs_create_dir(fname, NULL); fname = "chk_general"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, - &dfs_global_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - dfs_chk_gen = dent; + dfs_chk_gen = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, + NULL, &dfs_global_fops); fname = "chk_index"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, - &dfs_global_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - dfs_chk_index = dent; + dfs_chk_index = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + dfs_rootdir, NULL, &dfs_global_fops); fname = "chk_orphans"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, - &dfs_global_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - dfs_chk_orph = dent; + dfs_chk_orph = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + dfs_rootdir, NULL, &dfs_global_fops); fname = "chk_lprops"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, - &dfs_global_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - dfs_chk_lprops = dent; + dfs_chk_lprops = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + dfs_rootdir, NULL, &dfs_global_fops); fname = "chk_fs"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, - &dfs_global_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - dfs_chk_fs = dent; + dfs_chk_fs = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, + NULL, &dfs_global_fops); fname = "tst_recovery"; - dent = debugfs_create_file(fname, S_IRUSR | S_IWUSR, dfs_rootdir, NULL, - &dfs_global_fops); - if (IS_ERR_OR_NULL(dent)) - goto out_remove; - dfs_tst_rcvry = dent; - - return 0; - -out_remove: - debugfs_remove_recursive(dfs_rootdir); -out: - err = dent ? PTR_ERR(dent) : -ENODEV; - pr_err("UBIFS error (pid %d): cannot create \"%s\" debugfs file or directory, error %d\n", - current->pid, fname, err); - return err; + dfs_tst_rcvry = debugfs_create_file(fname, S_IRUSR | S_IWUSR, + dfs_rootdir, NULL, &dfs_global_fops); } /** @@ -3082,8 +2986,7 @@ out: */ void dbg_debugfs_exit(void) { - if (IS_ENABLED(CONFIG_DEBUG_FS)) - debugfs_remove_recursive(dfs_rootdir); + debugfs_remove_recursive(dfs_rootdir); } void ubifs_assert_failed(struct ubifs_info *c, const char *expr, diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 64c6977c189b..7763639a426b 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -1,21 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ @@ -309,9 +297,9 @@ int dbg_leb_unmap(struct ubifs_info *c, int lnum); int dbg_leb_map(struct ubifs_info *c, int lnum); /* Debugfs-related stuff */ -int dbg_debugfs_init(void); +void dbg_debugfs_init(void); void dbg_debugfs_exit(void); -int dbg_debugfs_init_fs(struct ubifs_info *c); +void dbg_debugfs_init_fs(struct ubifs_info *c); void dbg_debugfs_exit_fs(struct ubifs_info *c); #endif /* !__UBIFS_DEBUG_H__ */ diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 1a379b596b0d..0b98e3c8b461 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * Copyright (C) 2006, 2007 University of Szeged, Hungary * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter * Zoltan Sogor diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 512e7d9c60cd..e5f8de62fc51 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 5deaae7fcead..873e6e1c92b5 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index bf75fdc76fc3..62cb3db44e6e 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index d124117efd42..8ceb51478800 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * Copyright (C) 2006, 2007 University of Szeged, Hungary * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter * Zoltan Sogor diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 6b05b3ec500e..034ad14710d1 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -1,22 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * Copyright (C) 2006, 2007 University of Szeged, Hungary * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Zoltan Sogor * Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter @@ -119,18 +107,11 @@ static int setflags(struct inode *inode, int flags) if (err) return err; - /* - * The IMMUTABLE and APPEND_ONLY flags can only be changed by - * the relevant capability. - */ mutex_lock(&ui->ui_mutex); oldflags = ubifs2ioctl(ui->flags); - if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - err = -EPERM; - goto out_unlock; - } - } + err = vfs_ioc_setflags_prepare(inode, oldflags, flags); + if (err) + goto out_unlock; ui->flags = ioctl2ubifs(flags); ubifs_set_inode_flags(inode); diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 74a7306978d0..4fd9683b8245 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h index 2feff6cbbb77..afa704ff5ca0 100644 --- a/fs/ubifs/key.h +++ b/fs/ubifs/key.h @@ -1,21 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index 15fd854149bb..cd85d7d4c515 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index fa8d775c9753..29826c51883a 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index b0c5f06128b5..e21abf250951 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index 1f88caffdf2a..ff5e0411cf2d 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index 5ea51bbd14c7..b42a768709c0 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index 78a6e97f846e..c97a4d537d83 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -1,21 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 2f1618f300fb..cb72688032cd 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Author: Adrian Hunter */ diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index 8526b7ec4707..3fc589881825 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 5c8a81a019a4..b28ac4dfb407 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 2afc8b1d4c3b..12c2afdb5804 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ @@ -748,7 +736,7 @@ int ubifs_read_superblock(struct ubifs_info *c) goto out; } - if (!IS_ENABLED(CONFIG_UBIFS_FS_ENCRYPTION) && c->encrypted) { + if (!IS_ENABLED(CONFIG_FS_ENCRYPTION) && c->encrypted) { ubifs_err(c, "file system contains encrypted files but UBIFS" " was built without crypto support."); err = -EINVAL; @@ -941,7 +929,7 @@ int ubifs_enable_encryption(struct ubifs_info *c) int err; struct ubifs_sb_node *sup = c->sup_node; - if (!IS_ENABLED(CONFIG_UBIFS_FS_ENCRYPTION)) + if (!IS_ENABLED(CONFIG_FS_ENCRYPTION)) return -EOPNOTSUPP; if (c->encrypted) diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c index ea88926163f4..c69cdb5e65bc 100644 --- a/fs/ubifs/scan.c +++ b/fs/ubifs/scan.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c index 5eb5958723d4..d00a6f20ac7b 100644 --- a/fs/ubifs/shrinker.c +++ b/fs/ubifs/shrinker.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 04b8ecfd3470..fd1977b568f0 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ @@ -1477,9 +1465,7 @@ static int mount_ubifs(struct ubifs_info *c) if (err) goto out_infos; - err = dbg_debugfs_init_fs(c); - if (err) - goto out_infos; + dbg_debugfs_init_fs(c); c->mounting = 0; @@ -2364,9 +2350,7 @@ static int __init ubifs_init(void) if (err) goto out_shrinker; - err = dbg_debugfs_init(); - if (err) - goto out_compr; + dbg_debugfs_init(); err = register_filesystem(&ubifs_fs_type); if (err) { @@ -2378,7 +2362,6 @@ static int __init ubifs_init(void) out_dbg: dbg_debugfs_exit(); -out_compr: ubifs_compressors_exit(); out_shrinker: unregister_shrinker(&ubifs_shrinker_info); diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index ebf8c26f5b22..f5a823cb0e43 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index dbcd2c350b65..a384a0f9ff32 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c index d1815e959007..6f293f662d98 100644 --- a/fs/ubifs/tnc_misc.c +++ b/fs/ubifs/tnc_misc.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Adrian Hunter * Artem Bityutskiy (Битюцкий Артём) */ diff --git a/fs/ubifs/ubifs-media.h b/fs/ubifs/ubifs-media.h index 8b7c1844014f..86f0f2be116c 100644 --- a/fs/ubifs/ubifs-media.h +++ b/fs/ubifs/ubifs-media.h @@ -1,21 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 379b9f791ff6..745b23e5b406 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1,21 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ @@ -2015,13 +2003,17 @@ int ubifs_xattr_set(struct inode *host, const char *name, const void *value, size_t size, int flags, bool check_lock); ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf, size_t size); -int ubifs_purge_xattrs(struct inode *host); #ifdef CONFIG_UBIFS_FS_XATTR void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum); +int ubifs_purge_xattrs(struct inode *host); #else static inline void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum) { } +static inline int ubifs_purge_xattrs(struct inode *host) +{ + return 0; +} #endif #ifdef CONFIG_UBIFS_FS_SECURITY diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index acab3181ab35..9aefbb60074f 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This file is part of UBIFS. * * Copyright (C) 2006-2008 Nokia Corporation. * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published by - * the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, write to the Free Software Foundation, Inc., 51 - * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - * * Authors: Artem Bityutskiy (Битюцкий Артём) * Adrian Hunter */ @@ -527,7 +515,7 @@ int ubifs_purge_xattrs(struct inode *host) fname_name(&nm) = xent->name; fname_len(&nm) = le16_to_cpu(xent->nlen); - xino = ubifs_iget(c->vfs_sb, xent->inum); + xino = ubifs_iget(c->vfs_sb, le64_to_cpu(xent->inum)); if (IS_ERR(xino)) { err = PTR_ERR(xino); ubifs_err(c, "dead directory entry '%s', error %d", diff --git a/fs/udf/Kconfig b/fs/udf/Kconfig index aa415054ad0a..6848de581ce1 100644 --- a/fs/udf/Kconfig +++ b/fs/udf/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config UDF_FS tristate "UDF file system support" select CRC_ITU_T diff --git a/fs/udf/Makefile b/fs/udf/Makefile index eb880f66c23a..63981cd333e3 100644 --- a/fs/udf/Makefile +++ b/fs/udf/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the linux udf-filesystem routines. # diff --git a/fs/udf/inode.c b/fs/udf/inode.c index e7276932e433..9bb18311a22f 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -470,13 +470,15 @@ static struct buffer_head *udf_getblk(struct inode *inode, udf_pblk_t block, return NULL; } -/* Extend the file by 'blocks' blocks, return the number of extents added */ +/* Extend the file with new blocks totaling 'new_block_bytes', + * return the number of extents added + */ static int udf_do_extend_file(struct inode *inode, struct extent_position *last_pos, struct kernel_long_ad *last_ext, - sector_t blocks) + loff_t new_block_bytes) { - sector_t add; + uint32_t add; int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK); struct super_block *sb = inode->i_sb; struct kernel_lb_addr prealloc_loc = {}; @@ -486,7 +488,7 @@ static int udf_do_extend_file(struct inode *inode, /* The previous extent is fake and we should not extend by anything * - there's nothing to do... */ - if (!blocks && fake) + if (!new_block_bytes && fake) return 0; iinfo = UDF_I(inode); @@ -517,13 +519,12 @@ static int udf_do_extend_file(struct inode *inode, /* Can we merge with the previous extent? */ if ((last_ext->extLength & UDF_EXTENT_FLAG_MASK) == EXT_NOT_RECORDED_NOT_ALLOCATED) { - add = ((1 << 30) - sb->s_blocksize - - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK)) >> - sb->s_blocksize_bits; - if (add > blocks) - add = blocks; - blocks -= add; - last_ext->extLength += add << sb->s_blocksize_bits; + add = (1 << 30) - sb->s_blocksize - + (last_ext->extLength & UDF_EXTENT_LENGTH_MASK); + if (add > new_block_bytes) + add = new_block_bytes; + new_block_bytes -= add; + last_ext->extLength += add; } if (fake) { @@ -544,28 +545,27 @@ static int udf_do_extend_file(struct inode *inode, } /* Managed to do everything necessary? */ - if (!blocks) + if (!new_block_bytes) goto out; /* All further extents will be NOT_RECORDED_NOT_ALLOCATED */ last_ext->extLocation.logicalBlockNum = 0; last_ext->extLocation.partitionReferenceNum = 0; - add = (1 << (30-sb->s_blocksize_bits)) - 1; - last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - (add << sb->s_blocksize_bits); + add = (1 << 30) - sb->s_blocksize; + last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | add; /* Create enough extents to cover the whole hole */ - while (blocks > add) { - blocks -= add; + while (new_block_bytes > add) { + new_block_bytes -= add; err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) return err; count++; } - if (blocks) { + if (new_block_bytes) { last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED | - (blocks << sb->s_blocksize_bits); + new_block_bytes; err = udf_add_aext(inode, last_pos, &last_ext->extLocation, last_ext->extLength, 1); if (err) @@ -596,6 +596,24 @@ out: return count; } +/* Extend the final block of the file to final_block_len bytes */ +static void udf_do_extend_final_block(struct inode *inode, + struct extent_position *last_pos, + struct kernel_long_ad *last_ext, + uint32_t final_block_len) +{ + struct super_block *sb = inode->i_sb; + uint32_t added_bytes; + + added_bytes = final_block_len - + (last_ext->extLength & (sb->s_blocksize - 1)); + last_ext->extLength += added_bytes; + UDF_I(inode)->i_lenExtents += added_bytes; + + udf_write_aext(inode, last_pos, &last_ext->extLocation, + last_ext->extLength, 1); +} + static int udf_extend_file(struct inode *inode, loff_t newsize) { @@ -605,10 +623,12 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) int8_t etype; struct super_block *sb = inode->i_sb; sector_t first_block = newsize >> sb->s_blocksize_bits, offset; + unsigned long partial_final_block; int adsize; struct udf_inode_info *iinfo = UDF_I(inode); struct kernel_long_ad extent; - int err; + int err = 0; + int within_final_block; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT) adsize = sizeof(struct short_ad); @@ -618,18 +638,8 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) BUG(); etype = inode_bmap(inode, first_block, &epos, &eloc, &elen, &offset); + within_final_block = (etype != -1); - /* File has extent covering the new size (could happen when extending - * inside a block)? */ - if (etype != -1) - return 0; - if (newsize & (sb->s_blocksize - 1)) - offset++; - /* Extended file just to the boundary of the last file block? */ - if (offset == 0) - return 0; - - /* Truncate is extending the file by 'offset' blocks */ if ((!epos.bh && epos.offset == udf_file_entry_alloc_offset(inode)) || (epos.bh && epos.offset == sizeof(struct allocExtDesc))) { /* File has no extents at all or has empty last @@ -643,7 +653,22 @@ static int udf_extend_file(struct inode *inode, loff_t newsize) &extent.extLength, 0); extent.extLength |= etype << 30; } - err = udf_do_extend_file(inode, &epos, &extent, offset); + + partial_final_block = newsize & (sb->s_blocksize - 1); + + /* File has extent covering the new size (could happen when extending + * inside a block)? + */ + if (within_final_block) { + /* Extending file within the last file block */ + udf_do_extend_final_block(inode, &epos, &extent, + partial_final_block); + } else { + loff_t add = ((loff_t)offset << sb->s_blocksize_bits) | + partial_final_block; + err = udf_do_extend_file(inode, &epos, &extent, add); + } + if (err < 0) goto out; err = 0; @@ -745,6 +770,7 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, /* Are we beyond EOF? */ if (etype == -1) { int ret; + loff_t hole_len; isBeyondEOF = true; if (count) { if (c) @@ -760,7 +786,8 @@ static sector_t inode_getblk(struct inode *inode, sector_t block, startnum = (offset > 0); } /* Create extents for the hole between EOF and offset */ - ret = udf_do_extend_file(inode, &prev_epos, laarr, offset); + hole_len = (loff_t)offset << inode->i_blkbits; + ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len); if (ret < 0) { *err = ret; newblock = 0; diff --git a/fs/ufs/Kconfig b/fs/ufs/Kconfig index 0bf6e16f8d79..fcb41516ea59 100644 --- a/fs/ufs/Kconfig +++ b/fs/ufs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config UFS_FS tristate "UFS file system support (read only)" depends on BLOCK diff --git a/fs/ufs/Makefile b/fs/ufs/Makefile index ec4a6b49fa13..042344c85be0 100644 --- a/fs/ufs/Makefile +++ b/fs/ufs/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # Makefile for the Linux ufs filesystem routines. # diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 84c0c5178cd2..3d247c0d92aa 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/ufs/super.c * diff --git a/fs/unicode/Kconfig b/fs/unicode/Kconfig index b560a879edf7..2c27b9a5cd6c 100644 --- a/fs/unicode/Kconfig +++ b/fs/unicode/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only # # UTF-8 normalization # diff --git a/fs/unicode/README.utf8data b/fs/unicode/README.utf8data index 9307cf0727de..c73786807d3b 100644 --- a/fs/unicode/README.utf8data +++ b/fs/unicode/README.utf8data @@ -5,29 +5,15 @@ The full set of files can be found here: http://www.unicode.org/Public/12.1.0/ucd/ -Note! - -The URL's listed below are not stable. That's because Unicode 12.1.0 -has not been officially released yet; it is scheduled to be released -on May 8, 2019. We taking Unicode 12.1.0 a few weeks early because it -contains a new Japanese character which is required in order to -specify Japenese dates after May 1, 2019, when Crown Prince Naruhito -ascends to the Chrysanthemum Throne. (Isn't internationalization fun? -The abdication of Emperor Akihito of Japan is requiring dozens of -software packages to be updated with only a month's notice. :-) - -We will update the URL's (and any needed changes to the checksums) -after the final Unicode 12.1.0 is released. - Individual source links: - https://www.unicode.org/Public/12.1.0/ucd/CaseFolding-12.1.0d2.txt - https://www.unicode.org/Public/12.1.0/ucd/DerivedAge-12.1.0d3.txt - https://www.unicode.org/Public/12.1.0/ucd/extracted/DerivedCombiningClass-12.1.0d2.txt - https://www.unicode.org/Public/12.1.0/ucd/DerivedCoreProperties-12.1.0d2.txt - https://www.unicode.org/Public/12.1.0/ucd/NormalizationCorrections-12.1.0d1.txt - https://www.unicode.org/Public/12.1.0/ucd/NormalizationTest-12.1.0d3.txt - https://www.unicode.org/Public/12.1.0/ucd/UnicodeData-12.1.0d2.txt + https://www.unicode.org/Public/12.1.0/ucd/CaseFolding.txt + https://www.unicode.org/Public/12.1.0/ucd/DerivedAge.txt + https://www.unicode.org/Public/12.1.0/ucd/extracted/DerivedCombiningClass.txt + https://www.unicode.org/Public/12.1.0/ucd/DerivedCoreProperties.txt + https://www.unicode.org/Public/12.1.0/ucd/NormalizationCorrections.txt + https://www.unicode.org/Public/12.1.0/ucd/NormalizationTest.txt + https://www.unicode.org/Public/12.1.0/ucd/UnicodeData.txt md5sums (verify by running "md5sum -c README.utf8data"): diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index 6afab4fdce90..71ca4d047d65 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -73,6 +73,34 @@ int utf8_strncasecmp(const struct unicode_map *um, } EXPORT_SYMBOL(utf8_strncasecmp); +/* String cf is expected to be a valid UTF-8 casefolded + * string. + */ +int utf8_strncasecmp_folded(const struct unicode_map *um, + const struct qstr *cf, + const struct qstr *s1) +{ + const struct utf8data *data = utf8nfdicf(um->version); + struct utf8cursor cur1; + int c1, c2; + int i = 0; + + if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0) + return -EINVAL; + + do { + c1 = utf8byte(&cur1); + c2 = cf->name[i++]; + if (c1 < 0) + return -EINVAL; + if (c1 != c2) + return 1; + } while (c1); + + return 0; +} +EXPORT_SYMBOL(utf8_strncasecmp_folded); + int utf8_casefold(const struct unicode_map *um, const struct qstr *str, unsigned char *dest, size_t dlen) { diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c index 20d440c3f2db..1d2d2e5b906a 100644 --- a/fs/unicode/utf8-norm.c +++ b/fs/unicode/utf8-norm.c @@ -1,16 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2014 SGI. * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #include "utf8n.h" @@ -714,6 +705,8 @@ int utf8byte(struct utf8cursor *u8c) } leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s); + if (!leaf) + return -1; ccc = LEAF_CCC(leaf); } diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c index 80752013fce0..6c1a36bbf6ad 100644 --- a/fs/unicode/utf8-selftest.c +++ b/fs/unicode/utf8-selftest.c @@ -1,16 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Kernel module for testing utf-8 support. * * Copyright 2017 Collabora Ltd. - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h index a120638014c1..0acd530c2c79 100644 --- a/fs/unicode/utf8n.h +++ b/fs/unicode/utf8n.h @@ -1,16 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2014 SGI. * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #ifndef UTF8NORM_H diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 3b30301c90ec..ccbdbd62f0d8 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * fs/userfaultfd.c * @@ -5,9 +6,6 @@ * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. - * * Some part derived from fs/eventfd.c (anon inode setup) and * mm/ksm.c (mm hashing). */ @@ -42,6 +40,16 @@ enum userfaultfd_state { /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. + * + * Locking order: + * fd_wqh.lock + * fault_pending_wqh.lock + * fault_wqh.lock + * event_wqh.lock + * + * To avoid deadlocks, IRQs must be disabled when taking any of the above locks, + * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's + * also taken in IRQ context. */ struct userfaultfd_ctx { /* waitqueue head for the pending (i.e. not read) userfaults */ @@ -460,7 +468,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) blocking_state = return_to_userland ? TASK_INTERRUPTIBLE : TASK_KILLABLE; - spin_lock(&ctx->fault_pending_wqh.lock); + spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). @@ -472,7 +480,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) * __add_wait_queue. */ set_current_state(blocking_state); - spin_unlock(&ctx->fault_pending_wqh.lock); + spin_unlock_irq(&ctx->fault_pending_wqh.lock); if (!is_vm_hugetlb_page(vmf->vma)) must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, @@ -554,13 +562,13 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) * kernel stack can be released after the list_del_init. */ if (!list_empty_careful(&uwq.wq.entry)) { - spin_lock(&ctx->fault_pending_wqh.lock); + spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * No need of list_del_init(), the uwq on the stack * will be freed shortly anyway. */ list_del(&uwq.wq.entry); - spin_unlock(&ctx->fault_pending_wqh.lock); + spin_unlock_irq(&ctx->fault_pending_wqh.lock); } /* @@ -585,7 +593,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, init_waitqueue_entry(&ewq->wq, current); release_new_ctx = NULL; - spin_lock(&ctx->event_wqh.lock); + spin_lock_irq(&ctx->event_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland * through poll/read(). @@ -615,15 +623,15 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, break; } - spin_unlock(&ctx->event_wqh.lock); + spin_unlock_irq(&ctx->event_wqh.lock); wake_up_poll(&ctx->fd_wqh, EPOLLIN); schedule(); - spin_lock(&ctx->event_wqh.lock); + spin_lock_irq(&ctx->event_wqh.lock); } __set_current_state(TASK_RUNNING); - spin_unlock(&ctx->event_wqh.lock); + spin_unlock_irq(&ctx->event_wqh.lock); if (release_new_ctx) { struct vm_area_struct *vma; @@ -920,10 +928,10 @@ wakeup: * the last page faults that may have been already waiting on * the fault_*wqh. */ - spin_lock(&ctx->fault_pending_wqh.lock); + spin_lock_irq(&ctx->fault_pending_wqh.lock); __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range); __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range); - spin_unlock(&ctx->fault_pending_wqh.lock); + spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* Flush pending events that may still wait on event_wqh */ wake_up_all(&ctx->event_wqh); @@ -1136,7 +1144,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(ctx, fork_nctx, msg); - spin_lock(&ctx->event_wqh.lock); + spin_lock_irq(&ctx->event_wqh.lock); if (!list_empty(&fork_event)) { /* * The fork thread didn't abort, so we can @@ -1182,7 +1190,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, if (ret) userfaultfd_ctx_put(fork_nctx); } - spin_unlock(&ctx->event_wqh.lock); + spin_unlock_irq(&ctx->event_wqh.lock); } return ret; @@ -1221,14 +1229,14 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf, static void __wake_userfault(struct userfaultfd_ctx *ctx, struct userfaultfd_wake_range *range) { - spin_lock(&ctx->fault_pending_wqh.lock); + spin_lock_irq(&ctx->fault_pending_wqh.lock); /* wake all in the range and autoremove */ if (waitqueue_active(&ctx->fault_pending_wqh)) __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, range); if (waitqueue_active(&ctx->fault_wqh)) __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range); - spin_unlock(&ctx->fault_pending_wqh.lock); + spin_unlock_irq(&ctx->fault_pending_wqh.lock); } static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx, @@ -1883,7 +1891,7 @@ static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) wait_queue_entry_t *wq; unsigned long pending = 0, total = 0; - spin_lock(&ctx->fault_pending_wqh.lock); + spin_lock_irq(&ctx->fault_pending_wqh.lock); list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) { pending++; total++; @@ -1891,7 +1899,7 @@ static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f) list_for_each_entry(wq, &ctx->fault_wqh.head, entry) { total++; } - spin_unlock(&ctx->fault_pending_wqh.lock); + spin_unlock_irq(&ctx->fault_pending_wqh.lock); /* * If more protocols will be added, there will be all shown diff --git a/fs/xattr.c b/fs/xattr.c index 0d6a6a4af861..90dd78f0eb27 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* File: fs/xattr.c diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 99af5e5bda9f..e685299eb3d2 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only config XFS_FS tristate "XFS filesystem support" depends on BLOCK diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 1dfc6df2e2bd..b74a47169297 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -4,8 +4,8 @@ # All Rights Reserved. # -ccflags-y += -I$(src) # needed for trace events -ccflags-y += -I$(src)/libxfs +ccflags-y += -I $(srctree)/$(src) # needed for trace events +ccflags-y += -I $(srctree)/$(src)/libxfs ccflags-$(CONFIG_XFS_DEBUG) += -g @@ -62,6 +62,7 @@ xfs-y += xfs_aops.o \ xfs_attr_inactive.o \ xfs_attr_list.o \ xfs_bmap_util.o \ + xfs_bio_io.o \ xfs_buf.o \ xfs_dir2_readdir.o \ xfs_discard.o \ @@ -80,9 +81,11 @@ xfs-y += xfs_aops.o \ xfs_iops.o \ xfs_inode.o \ xfs_itable.o \ + xfs_iwalk.o \ xfs_message.o \ xfs_mount.o \ xfs_mru_cache.o \ + xfs_pwork.o \ xfs_reflink.o \ xfs_stats.o \ xfs_super.o \ @@ -104,12 +107,8 @@ xfs-y += xfs_log.o \ xfs_rmap_item.o \ xfs_log_recover.o \ xfs_trans_ail.o \ - xfs_trans_bmap.o \ xfs_trans_buf.o \ - xfs_trans_extfree.o \ - xfs_trans_inode.o \ - xfs_trans_refcount.o \ - xfs_trans_rmap.o \ + xfs_trans_inode.o # optional features xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \ diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index fdd9d6ede25c..16bb9a328678 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -3,12 +3,7 @@ * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ -#include <linux/mm.h> #include <linux/sched/mm.h> -#include <linux/highmem.h> -#include <linux/slab.h> -#include <linux/swap.h> -#include <linux/blkdev.h> #include <linux/backing-dev.h> #include "kmem.h" #include "xfs_message.h" diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 8e6b3ba81c03..267655acd426 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -124,4 +124,12 @@ kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags) return kmem_zone_alloc(zone, flags | KM_ZERO); } +static inline struct page * +kmem_to_page(void *addr) +{ + if (is_vmalloc_addr(addr)) + return vmalloc_to_page(addr); + return virt_to_page(addr); +} + #endif /* __XFS_SUPPORT_KMEM_H__ */ diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index b0c89f54d1bb..5de296b34ab1 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -10,6 +10,7 @@ #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_trans_resv.h" +#include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_btree.h" @@ -44,6 +45,12 @@ xfs_get_aghdr_buf( return bp; } +static inline bool is_log_ag(struct xfs_mount *mp, struct aghdr_init_data *id) +{ + return mp->m_sb.sb_logstart > 0 && + id->agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart); +} + /* * Generic btree root block init function */ @@ -53,40 +60,85 @@ xfs_btroot_init( struct xfs_buf *bp, struct aghdr_init_data *id) { - xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno, 0); + xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno); } -/* - * Alloc btree root block init functions - */ +/* Finish initializing a free space btree. */ static void -xfs_bnoroot_init( +xfs_freesp_init_recs( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { struct xfs_alloc_rec *arec; + struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); - xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno, 0); arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); + + if (is_log_ag(mp, id)) { + struct xfs_alloc_rec *nrec; + xfs_agblock_t start = XFS_FSB_TO_AGBNO(mp, + mp->m_sb.sb_logstart); + + ASSERT(start >= mp->m_ag_prealloc_blocks); + if (start != mp->m_ag_prealloc_blocks) { + /* + * Modify first record to pad stripe align of log + */ + arec->ar_blockcount = cpu_to_be32(start - + mp->m_ag_prealloc_blocks); + nrec = arec + 1; + + /* + * Insert second record at start of internal log + * which then gets trimmed. + */ + nrec->ar_startblock = cpu_to_be32( + be32_to_cpu(arec->ar_startblock) + + be32_to_cpu(arec->ar_blockcount)); + arec = nrec; + be16_add_cpu(&block->bb_numrecs, 1); + } + /* + * Change record start to after the internal log + */ + be32_add_cpu(&arec->ar_startblock, mp->m_sb.sb_logblocks); + } + + /* + * Calculate the record block count and check for the case where + * the log might have consumed all available space in the AG. If + * so, reset the record count to 0 to avoid exposure of an invalid + * record start block. + */ arec->ar_blockcount = cpu_to_be32(id->agsize - be32_to_cpu(arec->ar_startblock)); + if (!arec->ar_blockcount) + block->bb_numrecs = 0; } +/* + * Alloc btree root block init functions + */ static void -xfs_cntroot_init( +xfs_bnoroot_init( struct xfs_mount *mp, struct xfs_buf *bp, struct aghdr_init_data *id) { - struct xfs_alloc_rec *arec; + xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, id->agno); + xfs_freesp_init_recs(mp, bp, id); +} - xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno, 0); - arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1); - arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks); - arec->ar_blockcount = cpu_to_be32(id->agsize - - be32_to_cpu(arec->ar_startblock)); +static void +xfs_cntroot_init( + struct xfs_mount *mp, + struct xfs_buf *bp, + struct aghdr_init_data *id) +{ + xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, id->agno); + xfs_freesp_init_recs(mp, bp, id); } /* @@ -101,7 +153,7 @@ xfs_rmaproot_init( struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_rmap_rec *rrec; - xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno, 0); + xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno); /* * mark the AG header regions as static metadata The BNO @@ -149,6 +201,18 @@ xfs_rmaproot_init( rrec->rm_offset = 0; be16_add_cpu(&block->bb_numrecs, 1); } + + /* account for the log space */ + if (is_log_ag(mp, id)) { + rrec = XFS_RMAP_REC_ADDR(block, + be16_to_cpu(block->bb_numrecs) + 1); + rrec->rm_startblock = cpu_to_be32( + XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart)); + rrec->rm_blockcount = cpu_to_be32(mp->m_sb.sb_logblocks); + rrec->rm_owner = cpu_to_be64(XFS_RMAP_OWN_LOG); + rrec->rm_offset = 0; + be16_add_cpu(&block->bb_numrecs, 1); + } } /* @@ -209,6 +273,14 @@ xfs_agfblock_init( agf->agf_refcount_level = cpu_to_be32(1); agf->agf_refcount_blocks = cpu_to_be32(1); } + + if (is_log_ag(mp, id)) { + int64_t logblocks = mp->m_sb.sb_logblocks; + + be32_add_cpu(&agf->agf_freeblks, -logblocks); + agf->agf_longest = cpu_to_be32(id->agsize - + XFS_FSB_TO_AGBNO(mp, mp->m_sb.sb_logstart) - logblocks); + } } static void diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index e2ba2a3b63b2..87a9747f1d36 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -9,20 +9,12 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_alloc.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_trans.h" -#include "xfs_bit.h" -#include "xfs_bmap.h" -#include "xfs_bmap_btree.h" -#include "xfs_ag_resv.h" -#include "xfs_trans_space.h" #include "xfs_rmap_btree.h" #include "xfs_btree.h" #include "xfs_refcount_btree.h" diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index a9ff3cf82cce..372ad55631fc 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -13,7 +13,6 @@ #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" -#include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_rmap.h" #include "xfs_alloc_btree.h" @@ -21,7 +20,6 @@ #include "xfs_extent_busy.h" #include "xfs_errortag.h" #include "xfs_error.h" -#include "xfs_cksum.h" #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_buf_item.h" @@ -41,8 +39,6 @@ struct workqueue_struct *xfs_alloc_wq; STATIC int xfs_alloc_ag_vextent_exact(xfs_alloc_arg_t *); STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *); STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *); -STATIC int xfs_alloc_ag_vextent_small(xfs_alloc_arg_t *, - xfs_btree_cur_t *, xfs_agblock_t *, xfs_extlen_t *, int *); /* * Size of the AGFL. For CRC-enabled filesystes we steal a couple of slots in @@ -555,7 +551,7 @@ static xfs_failaddr_t xfs_agfl_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_agfl *agfl = XFS_BUF_TO_AGFL(bp); int i; @@ -596,7 +592,7 @@ static void xfs_agfl_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; /* @@ -621,7 +617,7 @@ static void xfs_agfl_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; xfs_failaddr_t fa; @@ -700,6 +696,107 @@ xfs_alloc_update_counters( */ /* + * Deal with the case where only small freespaces remain. Either return the + * contents of the last freespace record, or allocate space from the freelist if + * there is nothing in the tree. + */ +STATIC int /* error */ +xfs_alloc_ag_vextent_small( + struct xfs_alloc_arg *args, /* allocation argument structure */ + struct xfs_btree_cur *ccur, /* optional by-size cursor */ + xfs_agblock_t *fbnop, /* result block number */ + xfs_extlen_t *flenp, /* result length */ + int *stat) /* status: 0-freelist, 1-normal/none */ +{ + int error = 0; + xfs_agblock_t fbno = NULLAGBLOCK; + xfs_extlen_t flen = 0; + int i = 0; + + /* + * If a cntbt cursor is provided, try to allocate the largest record in + * the tree. Try the AGFL if the cntbt is empty, otherwise fail the + * allocation. Make sure to respect minleft even when pulling from the + * freelist. + */ + if (ccur) + error = xfs_btree_decrement(ccur, 0, &i); + if (error) + goto error; + if (i) { + error = xfs_alloc_get_rec(ccur, &fbno, &flen, &i); + if (error) + goto error; + XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error); + goto out; + } + + if (args->minlen != 1 || args->alignment != 1 || + args->resv == XFS_AG_RESV_AGFL || + (be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_flcount) <= + args->minleft)) + goto out; + + error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno, 0); + if (error) + goto error; + if (fbno == NULLAGBLOCK) + goto out; + + xfs_extent_busy_reuse(args->mp, args->agno, fbno, 1, + xfs_alloc_allow_busy_reuse(args->datatype)); + + if (xfs_alloc_is_userdata(args->datatype)) { + struct xfs_buf *bp; + + bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno); + if (!bp) { + error = -EFSCORRUPTED; + goto error; + } + xfs_trans_binval(args->tp, bp); + } + *fbnop = args->agbno = fbno; + *flenp = args->len = 1; + XFS_WANT_CORRUPTED_GOTO(args->mp, + fbno < be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length), + error); + args->wasfromfl = 1; + trace_xfs_alloc_small_freelist(args); + + /* + * If we're feeding an AGFL block to something that doesn't live in the + * free space, we need to clear out the OWN_AG rmap. + */ + error = xfs_rmap_free(args->tp, args->agbp, args->agno, fbno, 1, + &XFS_RMAP_OINFO_AG); + if (error) + goto error; + + *stat = 0; + return 0; + +out: + /* + * Can't do the allocation, give up. + */ + if (flen < args->minlen) { + args->agbno = NULLAGBLOCK; + trace_xfs_alloc_small_notenough(args); + flen = 0; + } + *fbnop = fbno; + *flenp = flen; + *stat = 1; + trace_xfs_alloc_small_done(args); + return 0; + +error: + trace_xfs_alloc_small_error(args); + return error; +} + +/* * Allocate a variable extent in the allocation group agno. * Type and bno are used to determine where in the allocation group the * extent will start. @@ -1583,112 +1680,6 @@ out_nominleft: } /* - * Deal with the case where only small freespaces remain. - * Either return the contents of the last freespace record, - * or allocate space from the freelist if there is nothing in the tree. - */ -STATIC int /* error */ -xfs_alloc_ag_vextent_small( - xfs_alloc_arg_t *args, /* allocation argument structure */ - xfs_btree_cur_t *ccur, /* by-size cursor */ - xfs_agblock_t *fbnop, /* result block number */ - xfs_extlen_t *flenp, /* result length */ - int *stat) /* status: 0-freelist, 1-normal/none */ -{ - int error; - xfs_agblock_t fbno; - xfs_extlen_t flen; - int i; - - if ((error = xfs_btree_decrement(ccur, 0, &i))) - goto error0; - if (i) { - if ((error = xfs_alloc_get_rec(ccur, &fbno, &flen, &i))) - goto error0; - XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0); - } - /* - * Nothing in the btree, try the freelist. Make sure - * to respect minleft even when pulling from the - * freelist. - */ - else if (args->minlen == 1 && args->alignment == 1 && - args->resv != XFS_AG_RESV_AGFL && - (be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_flcount) - > args->minleft)) { - error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno, 0); - if (error) - goto error0; - if (fbno != NULLAGBLOCK) { - xfs_extent_busy_reuse(args->mp, args->agno, fbno, 1, - xfs_alloc_allow_busy_reuse(args->datatype)); - - if (xfs_alloc_is_userdata(args->datatype)) { - xfs_buf_t *bp; - - bp = xfs_btree_get_bufs(args->mp, args->tp, - args->agno, fbno, 0); - if (!bp) { - error = -EFSCORRUPTED; - goto error0; - } - xfs_trans_binval(args->tp, bp); - } - args->len = 1; - args->agbno = fbno; - XFS_WANT_CORRUPTED_GOTO(args->mp, - args->agbno + args->len <= - be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length), - error0); - args->wasfromfl = 1; - trace_xfs_alloc_small_freelist(args); - - /* - * If we're feeding an AGFL block to something that - * doesn't live in the free space, we need to clear - * out the OWN_AG rmap. - */ - error = xfs_rmap_free(args->tp, args->agbp, args->agno, - fbno, 1, &XFS_RMAP_OINFO_AG); - if (error) - goto error0; - - *stat = 0; - return 0; - } - /* - * Nothing in the freelist. - */ - else - flen = 0; - } - /* - * Can't allocate from the freelist for some reason. - */ - else { - fbno = NULLAGBLOCK; - flen = 0; - } - /* - * Can't do the allocation, give up. - */ - if (flen < args->minlen) { - args->agbno = NULLAGBLOCK; - trace_xfs_alloc_small_notenough(args); - flen = 0; - } - *fbnop = fbno; - *flenp = flen; - *stat = 1; - trace_xfs_alloc_small_done(args); - return 0; - -error0: - trace_xfs_alloc_small_error(args); - return error; -} - -/* * Free the extent starting at agno/bno for length. */ STATIC int @@ -2095,7 +2086,7 @@ xfs_free_agfl_block( if (error) return error; - bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno, 0); + bp = xfs_btree_get_bufs(tp->t_mountp, tp, agno, agbno); if (!bp) return -EFSCORRUPTED; xfs_trans_binval(tp, bp); @@ -2586,7 +2577,7 @@ static xfs_failaddr_t xfs_agf_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_agf *agf = XFS_BUF_TO_AGF(bp); if (xfs_sb_version_hascrc(&mp->m_sb)) { @@ -2644,7 +2635,7 @@ static void xfs_agf_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_sb_version_hascrc(&mp->m_sb) && @@ -2661,7 +2652,7 @@ static void xfs_agf_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; xfs_failaddr_t fa; @@ -3146,7 +3137,7 @@ xfs_alloc_has_record( /* * Walk all the blocks in the AGFL. The @walk_fn can return any negative - * error code or XFS_BTREE_QUERY_RANGE_ABORT. + * error code or XFS_ITER_*. */ int xfs_agfl_walk( diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c index 9fe949f6055e..2a94543857a1 100644 --- a/fs/xfs/libxfs/xfs_alloc_btree.c +++ b/fs/xfs/libxfs/xfs_alloc_btree.c @@ -17,7 +17,6 @@ #include "xfs_extent_busy.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_trans.h" @@ -292,7 +291,7 @@ static xfs_failaddr_t xfs_allocbt_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_perag *pag = bp->b_pag; xfs_failaddr_t fa; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index c441f41f14e8..d48fcf11cc35 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -9,23 +9,18 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_attr_sf.h" #include "xfs_inode.h" -#include "xfs_alloc.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" #include "xfs_attr.h" #include "xfs_attr_leaf.h" #include "xfs_attr_remote.h" -#include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_trace.h" diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index 3b0dce06e454..ff28ebf3b635 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -112,7 +112,13 @@ typedef struct xfs_attr_list_context { struct xfs_inode *dp; /* inode */ struct attrlist_cursor_kern *cursor; /* position in list */ char *alist; /* output buffer */ - int seen_enough; /* T/F: seen enough of list? */ + + /* + * Abort attribute list iteration if non-zero. Can be used to pass + * error values to the xfs_attr_list caller. + */ + int seen_enough; + ssize_t count; /* num used entries */ int dupcnt; /* count dup hashvals seen */ int bufsize; /* total buffer size */ diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 1f6e3965ff74..70eb941d02e4 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -10,14 +10,12 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap_btree.h" #include "xfs_bmap.h" #include "xfs_attr_sf.h" @@ -27,7 +25,6 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_buf_item.h" -#include "xfs_cksum.h" #include "xfs_dir2.h" #include "xfs_log.h" @@ -240,7 +237,7 @@ xfs_attr3_leaf_verify( struct xfs_buf *bp) { struct xfs_attr3_icleaf_hdr ichdr; - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *entries; uint32_t end; /* must be 32bit - see below */ @@ -313,7 +310,7 @@ static void xfs_attr3_leaf_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_attr3_leaf_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; @@ -343,7 +340,7 @@ static void xfs_attr3_leaf_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_sb_version_hascrc(&mp->m_sb) && @@ -865,7 +862,7 @@ xfs_attr_shortform_allfit( struct xfs_attr3_icleaf_hdr leafhdr; int bytes; int i; - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &leafhdr, leaf); @@ -1525,7 +1522,7 @@ xfs_attr_leaf_order( { struct xfs_attr3_icleaf_hdr ichdr1; struct xfs_attr3_icleaf_hdr ichdr2; - struct xfs_mount *mp = leaf1_bp->b_target->bt_mount; + struct xfs_mount *mp = leaf1_bp->b_mount; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr1, leaf1_bp->b_addr); xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr2, leaf2_bp->b_addr); @@ -2568,7 +2565,7 @@ xfs_attr_leaf_lasthash( { struct xfs_attr3_icleaf_hdr ichdr; struct xfs_attr_leaf_entry *entries; - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, bp->b_addr); entries = xfs_attr3_leaf_entryp(bp->b_addr); diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index 65ff600a8067..4eb30d357045 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -16,18 +16,10 @@ #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_inode.h" -#include "xfs_alloc.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" #include "xfs_attr.h" -#include "xfs_attr_leaf.h" -#include "xfs_attr_remote.h" -#include "xfs_trans_space.h" #include "xfs_trace.h" -#include "xfs_cksum.h" -#include "xfs_buf_item.h" #include "xfs_error.h" #define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */ @@ -111,7 +103,7 @@ __xfs_attr3_rmt_read_verify( bool check_crc, xfs_failaddr_t *failaddr) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; char *ptr; int len; xfs_daddr_t bno; @@ -175,7 +167,7 @@ static void xfs_attr3_rmt_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; int blksize = mp->m_attr_geo->blksize; char *ptr; @@ -535,7 +527,7 @@ xfs_attr_rmtval_set( dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock), dblkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); - bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt, 0); + bp = xfs_buf_get(mp->m_ddev_targp, dblkno, dblkcnt); if (!bp) return -ENOMEM; bp->b_ops = &xfs_attr3_rmt_buf_ops; diff --git a/fs/xfs/libxfs/xfs_bit.c b/fs/xfs/libxfs/xfs_bit.c index 40ce5f3094d1..7071ff98fdbc 100644 --- a/fs/xfs/libxfs/xfs_bit.c +++ b/fs/xfs/libxfs/xfs_bit.c @@ -5,7 +5,6 @@ */ #include "xfs.h" #include "xfs_log_format.h" -#include "xfs_bit.h" /* * XFS bit manipulation routines, used in non-realtime code. diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 356ebd1cbe82..baf0b72c0a37 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -13,14 +13,10 @@ #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" -#include "xfs_extfree_item.h" #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" @@ -32,7 +28,6 @@ #include "xfs_trans_space.h" #include "xfs_buf_item.h" #include "xfs_trace.h" -#include "xfs_symlink.h" #include "xfs_attr_leaf.h" #include "xfs_filestream.h" #include "xfs_rmap.h" @@ -370,7 +365,7 @@ xfs_bmap_check_leaf_extents( bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno)); if (!bp) { bp_release = 1; - error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp, + error = xfs_btree_read_bufl(mp, NULL, bno, &bp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) @@ -454,7 +449,7 @@ xfs_bmap_check_leaf_extents( bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno)); if (!bp) { bp_release = 1; - error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp, + error = xfs_btree_read_bufl(mp, NULL, bno, &bp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) @@ -619,7 +614,7 @@ xfs_bmap_btree_to_extents( XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, xfs_btree_check_lptr(cur, cbno, 1)); #endif - error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp, XFS_BMAP_BTREE_REF, + error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) return error; @@ -732,7 +727,7 @@ xfs_bmap_extents_to_btree( cur->bc_private.b.allocated++; ip->i_d.di_nblocks++; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L); - abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0); + abp = xfs_btree_get_bufl(mp, tp, args.fsbno); if (!abp) { error = -EFSCORRUPTED; goto out_unreserve_dquot; @@ -878,7 +873,7 @@ xfs_bmap_local_to_extents( ASSERT(args.fsbno != NULLFSBLOCK); ASSERT(args.len == 1); tp->t_firstblock = args.fsbno; - bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0); + bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno); /* * Initialize the block, copy the data and log the remote buffer. @@ -1203,7 +1198,7 @@ xfs_iread_extents( * pointer (leftmost) at each level. */ while (level-- > 0) { - error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, + error = xfs_btree_read_bufl(mp, tp, bno, &bp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) goto out; @@ -1276,7 +1271,7 @@ xfs_iread_extents( */ if (bno == NULLFSBLOCK) break; - error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, + error = xfs_btree_read_bufl(mp, tp, bno, &bp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) goto out; diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index aff82ed112c9..fbb18ba5d905 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -11,10 +11,8 @@ #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_alloc.h" #include "xfs_btree.h" #include "xfs_bmap_btree.h" @@ -22,7 +20,6 @@ #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_rmap.h" /* @@ -411,7 +408,7 @@ static xfs_failaddr_t xfs_bmbt_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_failaddr_t fa; unsigned int level; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index bbdae2b4559f..f1048efa4268 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -11,16 +11,13 @@ #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_buf_item.h" #include "xfs_btree.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_alloc.h" #include "xfs_log.h" @@ -276,7 +273,7 @@ xfs_btree_lblock_calc_crc( struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_buf_log_item *bip = bp->b_log_item; - if (!xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb)) + if (!xfs_sb_version_hascrc(&bp->b_mount->m_sb)) return; if (bip) block->bb_u.l.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn); @@ -288,7 +285,7 @@ xfs_btree_lblock_verify_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; if (xfs_sb_version_hascrc(&mp->m_sb)) { if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.l.bb_lsn))) @@ -314,7 +311,7 @@ xfs_btree_sblock_calc_crc( struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_buf_log_item *bip = bp->b_log_item; - if (!xfs_sb_version_hascrc(&bp->b_target->bt_mount->m_sb)) + if (!xfs_sb_version_hascrc(&bp->b_mount->m_sb)) return; if (bip) block->bb_u.s.bb_lsn = cpu_to_be64(bip->bli_item.li_lsn); @@ -326,7 +323,7 @@ xfs_btree_sblock_verify_crc( struct xfs_buf *bp) { struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; if (xfs_sb_version_hascrc(&mp->m_sb)) { if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.s.bb_lsn))) @@ -691,14 +688,13 @@ xfs_buf_t * /* buffer for fsbno */ xfs_btree_get_bufl( xfs_mount_t *mp, /* file system mount point */ xfs_trans_t *tp, /* transaction pointer */ - xfs_fsblock_t fsbno, /* file system block number */ - uint lock) /* lock flags for get_buf */ + xfs_fsblock_t fsbno) /* file system block number */ { xfs_daddr_t d; /* real disk block address */ ASSERT(fsbno != NULLFSBLOCK); d = XFS_FSB_TO_DADDR(mp, fsbno); - return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock); + return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, 0); } /* @@ -710,15 +706,14 @@ xfs_btree_get_bufs( xfs_mount_t *mp, /* file system mount point */ xfs_trans_t *tp, /* transaction pointer */ xfs_agnumber_t agno, /* allocation group number */ - xfs_agblock_t agbno, /* allocation group block number */ - uint lock) /* lock flags for get_buf */ + xfs_agblock_t agbno) /* allocation group block number */ { xfs_daddr_t d; /* real disk block address */ ASSERT(agno != NULLAGNUMBER); ASSERT(agbno != NULLAGBLOCK); d = XFS_AGB_TO_DADDR(mp, agno, agbno); - return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, lock); + return xfs_trans_get_buf(tp, mp->m_ddev_targp, d, mp->m_bsize, 0); } /* @@ -845,7 +840,6 @@ xfs_btree_read_bufl( struct xfs_mount *mp, /* file system mount point */ struct xfs_trans *tp, /* transaction pointer */ xfs_fsblock_t fsbno, /* file system block number */ - uint lock, /* lock flags for read_buf */ struct xfs_buf **bpp, /* buffer for fsbno */ int refval, /* ref count value for buffer */ const struct xfs_buf_ops *ops) @@ -858,7 +852,7 @@ xfs_btree_read_bufl( return -EFSCORRUPTED; d = XFS_FSB_TO_DADDR(mp, fsbno); error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d, - mp->m_bsize, lock, &bp, ops); + mp->m_bsize, 0, &bp, ops); if (error) return error; if (bp) @@ -1185,11 +1179,10 @@ xfs_btree_init_block( xfs_btnum_t btnum, __u16 level, __u16 numrecs, - __u64 owner, - unsigned int flags) + __u64 owner) { xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn, - btnum, level, numrecs, owner, flags); + btnum, level, numrecs, owner, 0); } STATIC void @@ -1288,7 +1281,6 @@ STATIC int xfs_btree_get_buf_block( struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr, - int flags, struct xfs_btree_block **block, struct xfs_buf **bpp) { @@ -1296,14 +1288,11 @@ xfs_btree_get_buf_block( xfs_daddr_t d; int error; - /* need to sort out how callers deal with failures first */ - ASSERT(!(flags & XBF_TRYLOCK)); - error = xfs_btree_ptr_to_daddr(cur, ptr, &d); if (error) return error; *bpp = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, - mp->m_bsize, flags); + mp->m_bsize, 0); if (!*bpp) return -ENOMEM; @@ -2706,7 +2695,7 @@ __xfs_btree_split( XFS_BTREE_STATS_INC(cur, alloc); /* Set up the new block as "right". */ - error = xfs_btree_get_buf_block(cur, &rptr, 0, &right, &rbp); + error = xfs_btree_get_buf_block(cur, &rptr, &right, &rbp); if (error) goto error0; @@ -2961,7 +2950,7 @@ xfs_btree_new_iroot( XFS_BTREE_STATS_INC(cur, alloc); /* Copy the root into a real block. */ - error = xfs_btree_get_buf_block(cur, &nptr, 0, &cblock, &cbp); + error = xfs_btree_get_buf_block(cur, &nptr, &cblock, &cbp); if (error) goto error0; @@ -3058,7 +3047,7 @@ xfs_btree_new_root( XFS_BTREE_STATS_INC(cur, alloc); /* Set up the new block. */ - error = xfs_btree_get_buf_block(cur, &lptr, 0, &new, &nbp); + error = xfs_btree_get_buf_block(cur, &lptr, &new, &nbp); if (error) goto error0; @@ -4433,7 +4422,7 @@ xfs_btree_lblock_v5hdr_verify( struct xfs_buf *bp, uint64_t owner) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); if (!xfs_sb_version_hascrc(&mp->m_sb)) @@ -4454,7 +4443,7 @@ xfs_btree_lblock_verify( struct xfs_buf *bp, unsigned int max_recs) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); /* numrecs verification */ @@ -4484,7 +4473,7 @@ xfs_failaddr_t xfs_btree_sblock_v5hdr_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_perag *pag = bp->b_pag; @@ -4510,7 +4499,7 @@ xfs_btree_sblock_verify( struct xfs_buf *bp, unsigned int max_recs) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_agblock_t agno; diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index e3b3e9dce5da..fa3cd8ab9aba 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -301,8 +301,7 @@ struct xfs_buf * /* buffer for fsbno */ xfs_btree_get_bufl( struct xfs_mount *mp, /* file system mount point */ struct xfs_trans *tp, /* transaction pointer */ - xfs_fsblock_t fsbno, /* file system block number */ - uint lock); /* lock flags for get_buf */ + xfs_fsblock_t fsbno); /* file system block number */ /* * Get a buffer for the block, return it with no data read. @@ -313,8 +312,7 @@ xfs_btree_get_bufs( struct xfs_mount *mp, /* file system mount point */ struct xfs_trans *tp, /* transaction pointer */ xfs_agnumber_t agno, /* allocation group number */ - xfs_agblock_t agbno, /* allocation group block number */ - uint lock); /* lock flags for get_buf */ + xfs_agblock_t agbno); /* allocation group block number */ /* * Check for the cursor referring to the last block at the given level. @@ -345,7 +343,6 @@ xfs_btree_read_bufl( struct xfs_mount *mp, /* file system mount point */ struct xfs_trans *tp, /* transaction pointer */ xfs_fsblock_t fsbno, /* file system block number */ - uint lock, /* lock flags for read_buf */ struct xfs_buf **bpp, /* buffer for fsbno */ int refval, /* ref count value for buffer */ const struct xfs_buf_ops *ops); @@ -383,8 +380,7 @@ xfs_btree_init_block( xfs_btnum_t btnum, __u16 level, __u16 numrecs, - __u64 owner, - unsigned int flags); + __u64 owner); void xfs_btree_init_block_int( @@ -469,8 +465,8 @@ uint xfs_btree_compute_maxlevels(uint *limits, unsigned long len); unsigned long long xfs_btree_calc_size(uint *limits, unsigned long long len); /* return codes */ -#define XFS_BTREE_QUERY_RANGE_CONTINUE 0 /* keep iterating */ -#define XFS_BTREE_QUERY_RANGE_ABORT 1 /* stop iterating */ +#define XFS_BTREE_QUERY_RANGE_CONTINUE (XFS_ITER_CONTINUE) /* keep iterating */ +#define XFS_BTREE_QUERY_RANGE_ABORT (XFS_ITER_ABORT) /* stop iterating */ typedef int (*xfs_btree_query_range_fn)(struct xfs_btree_cur *cur, union xfs_btree_rec *rec, void *priv); diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index e2737e2ac2ae..d1c77fd0815d 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -12,20 +12,14 @@ #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" -#include "xfs_alloc.h" #include "xfs_bmap.h" -#include "xfs_attr.h" #include "xfs_attr_leaf.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_buf_item.h" #include "xfs_log.h" @@ -126,7 +120,7 @@ xfs_da3_blkinfo_verify( struct xfs_buf *bp, struct xfs_da3_blkinfo *hdr3) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_da_blkinfo *hdr = &hdr3->hdr; if (!xfs_verify_magic16(bp, hdr->magic)) @@ -148,7 +142,7 @@ static xfs_failaddr_t xfs_da3_node_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_da_intnode *hdr = bp->b_addr; struct xfs_da3_icnode_hdr ichdr; const struct xfs_dir_ops *ops; @@ -186,7 +180,7 @@ static void xfs_da3_node_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_da3_node_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; diff --git a/fs/xfs/libxfs/xfs_da_format.c b/fs/xfs/libxfs/xfs_da_format.c index b39053dcb643..b1ae572496b6 100644 --- a/fs/xfs/libxfs/xfs_da_format.c +++ b/fs/xfs/libxfs/xfs_da_format.c @@ -11,11 +11,8 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_dir2.h" -#include "xfs_dir2_priv.h" /* * Shortform directory ops diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 1c6bf2105939..eb2be2a6a25a 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -9,8 +9,6 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" -#include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_trans.h" diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c index 156ce95c9c45..67840723edbb 100644 --- a/fs/xfs/libxfs/xfs_dir2.c +++ b/fs/xfs/libxfs/xfs_dir2.c @@ -5,20 +5,16 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" -#include "xfs_ialloc.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index b7d6d78f4ce2..a6fb0cc2085e 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -6,22 +6,19 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap.h" #include "xfs_buf_item.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_log.h" /* @@ -50,7 +47,7 @@ static xfs_failaddr_t xfs_dir3_block_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; if (!xfs_verify_magic(bp, hdr3->magic)) @@ -71,7 +68,7 @@ static void xfs_dir3_block_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_sb_version_hascrc(&mp->m_sb) && @@ -88,7 +85,7 @@ static void xfs_dir3_block_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c index b7b9ce002cb9..2c79be4c3153 100644 --- a/fs/xfs/libxfs/xfs_dir2_data.c +++ b/fs/xfs/libxfs/xfs_dir2_data.c @@ -6,19 +6,16 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_dir2.h" -#include "xfs_dir2_priv.h" #include "xfs_error.h" #include "xfs_trans.h" #include "xfs_buf_item.h" -#include "xfs_cksum.h" #include "xfs_log.h" static xfs_failaddr_t xfs_dir2_data_freefind_verify( @@ -50,14 +47,13 @@ __xfs_dir3_data_check( int i; /* leaf index */ int lastfree; /* last entry was unused */ xfs_dir2_leaf_entry_t *lep=NULL; /* block leaf entries */ - xfs_mount_t *mp; /* filesystem mount point */ + struct xfs_mount *mp = bp->b_mount; char *p; /* current data position */ int stale; /* count of stale leaves */ struct xfs_name name; const struct xfs_dir_ops *ops; struct xfs_da_geometry *geo; - mp = bp->b_target->bt_mount; geo = mp->m_dir_geo; /* @@ -249,7 +245,7 @@ static xfs_failaddr_t xfs_dir3_data_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; if (!xfs_verify_magic(bp, hdr3->magic)) @@ -298,7 +294,7 @@ static void xfs_dir3_data_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_sb_version_hascrc(&mp->m_sb) && @@ -315,7 +311,7 @@ static void xfs_dir3_data_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index 9c2a0a13ed61..a53e4585a2f3 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -6,12 +6,11 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_bmap.h" #include "xfs_dir2.h" @@ -20,8 +19,6 @@ #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_buf_item.h" -#include "xfs_cksum.h" -#include "xfs_log.h" /* * Local function declarations. @@ -144,7 +141,7 @@ static xfs_failaddr_t xfs_dir3_leaf_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_dir2_leaf *leaf = bp->b_addr; xfs_failaddr_t fa; @@ -159,7 +156,7 @@ static void xfs_dir3_leaf_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_sb_version_hascrc(&mp->m_sb) && @@ -176,7 +173,7 @@ static void xfs_dir3_leaf_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dir3_leaf_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index 16731d2d684b..afcc6642690a 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -6,12 +6,11 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_bmap.h" #include "xfs_dir2.h" @@ -20,7 +19,6 @@ #include "xfs_trace.h" #include "xfs_trans.h" #include "xfs_buf_item.h" -#include "xfs_cksum.h" #include "xfs_log.h" /* @@ -84,7 +82,7 @@ static xfs_failaddr_t xfs_dir3_free_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_dir2_free_hdr *hdr = bp->b_addr; if (!xfs_verify_magic(bp, hdr->magic)) @@ -110,7 +108,7 @@ static void xfs_dir3_free_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_sb_version_hascrc(&mp->m_sb) && @@ -127,7 +125,7 @@ static void xfs_dir3_free_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; struct xfs_dir3_blk_hdr *hdr3 = bp->b_addr; xfs_failaddr_t fa; diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c index 585dfdb7b6b6..033589257f54 100644 --- a/fs/xfs/libxfs/xfs_dir2_sf.c +++ b/fs/xfs/libxfs/xfs_dir2_sf.c @@ -5,16 +5,13 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" -#include "xfs_error.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_trace.h" diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index 88fa11071f9f..e8bd688a4073 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -16,8 +16,6 @@ #include "xfs_trans.h" #include "xfs_qm.h" #include "xfs_error.h" -#include "xfs_cksum.h" -#include "xfs_trace.h" int xfs_calc_dquots_per_chunk( @@ -224,7 +222,7 @@ static xfs_failaddr_t xfs_dquot_buf_verify_struct( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; return xfs_dquot_buf_verify(mp, bp, false); } @@ -233,7 +231,7 @@ static void xfs_dquot_buf_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; if (!xfs_dquot_buf_verify_crc(mp, bp, false)) return; @@ -250,7 +248,7 @@ static void xfs_dquot_buf_readahead_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; if (!xfs_dquot_buf_verify_crc(mp, bp, true) || xfs_dquot_buf_verify(mp, bp, true) != NULL) { @@ -268,7 +266,7 @@ static void xfs_dquot_buf_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_dquot_buf_verify(mp, bp, false); } diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 9bb3c48843ec..c968b60cee15 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -1071,7 +1071,7 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) #define XFS_INO_MASK(k) (uint32_t)((1ULL << (k)) - 1) #define XFS_INO_OFFSET_BITS(mp) (mp)->m_sb.sb_inopblog #define XFS_INO_AGBNO_BITS(mp) (mp)->m_sb.sb_agblklog -#define XFS_INO_AGINO_BITS(mp) (mp)->m_agino_log +#define XFS_INO_AGINO_BITS(mp) ((mp)->m_ino_geo.agino_log) #define XFS_INO_AGNO_BITS(mp) (mp)->m_agno_log #define XFS_INO_BITS(mp) \ XFS_INO_AGNO_BITS(mp) + XFS_INO_AGINO_BITS(mp) diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index e7382c780ed7..52d03a3a02a4 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -97,7 +97,7 @@ struct getbmapx { * For use by backup and restore programs to set the XFS on-disk inode * fields di_dmevmask and di_dmstate. These must be set to exactly and * only values previously obtained via xfs_bulkstat! (Specifically the - * xfs_bstat_t fields bs_dmevmask and bs_dmstate.) + * struct xfs_bstat fields bs_dmevmask and bs_dmstate.) */ #ifndef HAVE_FSDMIDATA struct fsdmidata { @@ -328,7 +328,7 @@ typedef struct xfs_bstime { __s32 tv_nsec; /* and nanoseconds */ } xfs_bstime_t; -typedef struct xfs_bstat { +struct xfs_bstat { __u64 bs_ino; /* inode number */ __u16 bs_mode; /* type and mode */ __u16 bs_nlink; /* number of links */ @@ -356,7 +356,53 @@ typedef struct xfs_bstat { __u32 bs_dmevmask; /* DMIG event mask */ __u16 bs_dmstate; /* DMIG state info */ __u16 bs_aextents; /* attribute number of extents */ -} xfs_bstat_t; +}; + +/* New bulkstat structure that reports v5 features and fixes padding issues */ +struct xfs_bulkstat { + uint64_t bs_ino; /* inode number */ + uint64_t bs_size; /* file size */ + + uint64_t bs_blocks; /* number of blocks */ + uint64_t bs_xflags; /* extended flags */ + + uint64_t bs_atime; /* access time, seconds */ + uint64_t bs_mtime; /* modify time, seconds */ + + uint64_t bs_ctime; /* inode change time, seconds */ + uint64_t bs_btime; /* creation time, seconds */ + + uint32_t bs_gen; /* generation count */ + uint32_t bs_uid; /* user id */ + uint32_t bs_gid; /* group id */ + uint32_t bs_projectid; /* project id */ + + uint32_t bs_atime_nsec; /* access time, nanoseconds */ + uint32_t bs_mtime_nsec; /* modify time, nanoseconds */ + uint32_t bs_ctime_nsec; /* inode change time, nanoseconds */ + uint32_t bs_btime_nsec; /* creation time, nanoseconds */ + + uint32_t bs_blksize; /* block size */ + uint32_t bs_rdev; /* device value */ + uint32_t bs_cowextsize_blks; /* cow extent size hint, blocks */ + uint32_t bs_extsize_blks; /* extent size hint, blocks */ + + uint32_t bs_nlink; /* number of links */ + uint32_t bs_extents; /* number of extents */ + uint32_t bs_aextents; /* attribute number of extents */ + uint16_t bs_version; /* structure version */ + uint16_t bs_forkoff; /* inode fork offset in bytes */ + + uint16_t bs_sick; /* sick inode metadata */ + uint16_t bs_checked; /* checked inode metadata */ + uint16_t bs_mode; /* type and mode */ + uint16_t bs_pad2; /* zeroed */ + + uint64_t bs_pad[7]; /* zeroed */ +}; + +#define XFS_BULKSTAT_VERSION_V1 (1) +#define XFS_BULKSTAT_VERSION_V5 (5) /* bs_sick flags */ #define XFS_BS_SICK_INODE (1 << 0) /* inode core */ @@ -374,7 +420,7 @@ typedef struct xfs_bstat { * to retain compatibility with "old" filesystems). */ static inline uint32_t -bstat_get_projid(struct xfs_bstat *bs) +bstat_get_projid(const struct xfs_bstat *bs) { return (uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo; } @@ -382,23 +428,79 @@ bstat_get_projid(struct xfs_bstat *bs) /* * The user-level BulkStat Request interface structure. */ -typedef struct xfs_fsop_bulkreq { +struct xfs_fsop_bulkreq { __u64 __user *lastip; /* last inode # pointer */ __s32 icount; /* count of entries in buffer */ void __user *ubuffer;/* user buffer for inode desc. */ __s32 __user *ocount; /* output count pointer */ -} xfs_fsop_bulkreq_t; - +}; /* * Structures returned from xfs_inumbers routine (XFS_IOC_FSINUMBERS). */ -typedef struct xfs_inogrp { +struct xfs_inogrp { __u64 xi_startino; /* starting inode number */ __s32 xi_alloccount; /* # bits set in allocmask */ __u64 xi_allocmask; /* mask of allocated inodes */ -} xfs_inogrp_t; +}; +/* New inumbers structure that reports v5 features and fixes padding issues */ +struct xfs_inumbers { + uint64_t xi_startino; /* starting inode number */ + uint64_t xi_allocmask; /* mask of allocated inodes */ + uint8_t xi_alloccount; /* # bits set in allocmask */ + uint8_t xi_version; /* version */ + uint8_t xi_padding[6]; /* zero */ +}; + +#define XFS_INUMBERS_VERSION_V1 (1) +#define XFS_INUMBERS_VERSION_V5 (5) + +/* Header for bulk inode requests. */ +struct xfs_bulk_ireq { + uint64_t ino; /* I/O: start with this inode */ + uint32_t flags; /* I/O: operation flags */ + uint32_t icount; /* I: count of entries in buffer */ + uint32_t ocount; /* O: count of entries filled out */ + uint32_t agno; /* I: see comment for IREQ_AGNO */ + uint64_t reserved[5]; /* must be zero */ +}; + +/* + * Only return results from the specified @agno. If @ino is zero, start + * with the first inode of @agno. + */ +#define XFS_BULK_IREQ_AGNO (1 << 0) + +/* + * Return bulkstat information for a single inode, where @ino value is a + * special value, not a literal inode number. See the XFS_BULK_IREQ_SPECIAL_* + * values below. Not compatible with XFS_BULK_IREQ_AGNO. + */ +#define XFS_BULK_IREQ_SPECIAL (1 << 1) + +#define XFS_BULK_IREQ_FLAGS_ALL (XFS_BULK_IREQ_AGNO | \ + XFS_BULK_IREQ_SPECIAL) + +/* Operate on the root directory inode. */ +#define XFS_BULK_IREQ_SPECIAL_ROOT (1) + +/* + * ioctl structures for v5 bulkstat and inumbers requests + */ +struct xfs_bulkstat_req { + struct xfs_bulk_ireq hdr; + struct xfs_bulkstat bulkstat[]; +}; +#define XFS_BULKSTAT_REQ_SIZE(nr) (sizeof(struct xfs_bulkstat_req) + \ + (nr) * sizeof(struct xfs_bulkstat)) + +struct xfs_inumbers_req { + struct xfs_bulk_ireq hdr; + struct xfs_inumbers inumbers[]; +}; +#define XFS_INUMBERS_REQ_SIZE(nr) (sizeof(struct xfs_inumbers_req) + \ + (nr) * sizeof(struct xfs_inumbers)) /* * Error injection. @@ -529,7 +631,7 @@ typedef struct xfs_swapext xfs_off_t sx_offset; /* offset into file */ xfs_off_t sx_length; /* leng from offset */ char sx_pad[16]; /* pad space, unused */ - xfs_bstat_t sx_stat; /* stat of target b4 copy */ + struct xfs_bstat sx_stat; /* stat of target b4 copy */ } xfs_swapext_t; /* @@ -701,6 +803,8 @@ struct xfs_scrub_metadata { #define XFS_IOC_FSGEOMETRY_V4 _IOR ('X', 124, struct xfs_fsop_geom_v4) #define XFS_IOC_GOINGDOWN _IOR ('X', 125, uint32_t) #define XFS_IOC_FSGEOMETRY _IOR ('X', 126, struct xfs_fsop_geom) +#define XFS_IOC_BULKSTAT _IOR ('X', 127, struct xfs_bulkstat_req) +#define XFS_IOC_INUMBERS _IOR ('X', 128, struct xfs_inumbers_req) /* XFS_IOC_GETFSUUID ---------- deprecated 140 */ diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h index 49ddfeac19f2..272005ac8c88 100644 --- a/fs/xfs/libxfs/xfs_health.h +++ b/fs/xfs/libxfs/xfs_health.h @@ -185,6 +185,6 @@ xfs_inode_is_healthy(struct xfs_inode *ip) void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo); void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); -void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bstat *bs); +void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs); #endif /* __XFS_HEALTH_H__ */ diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index fe9898875097..04377ab75863 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -12,17 +12,14 @@ #include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_alloc.h" -#include "xfs_rtalloc.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_bmap.h" -#include "xfs_cksum.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_icreate_item.h" @@ -31,20 +28,6 @@ #include "xfs_log.h" #include "xfs_rmap.h" - -/* - * Allocation group level functions. - */ -int -xfs_ialloc_cluster_alignment( - struct xfs_mount *mp) -{ - if (xfs_sb_version_hasalign(&mp->m_sb) && - mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp)) - return mp->m_sb.sb_inoalignmt; - return 1; -} - /* * Lookup a record by ino in the btree given by cur. */ @@ -299,7 +282,7 @@ xfs_ialloc_inode_init( * sizes, manipulate the inodes in buffers which are multiples of the * blocks size. */ - nbufs = length / mp->m_blocks_per_cluster; + nbufs = length / M_IGEO(mp)->blocks_per_cluster; /* * Figure out what version number to use in the inodes we create. If @@ -343,9 +326,10 @@ xfs_ialloc_inode_init( * Get the block. */ d = XFS_AGB_TO_DADDR(mp, agno, agbno + - (j * mp->m_blocks_per_cluster)); + (j * M_IGEO(mp)->blocks_per_cluster)); fbuf = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, - mp->m_bsize * mp->m_blocks_per_cluster, + mp->m_bsize * + M_IGEO(mp)->blocks_per_cluster, XBF_UNMAPPED); if (!fbuf) return -ENOMEM; @@ -353,7 +337,7 @@ xfs_ialloc_inode_init( /* Initialize the inode buffers and log them appropriately. */ fbuf->b_ops = &xfs_inode_buf_ops; xfs_buf_zero(fbuf, 0, BBTOB(fbuf->b_length)); - for (i = 0; i < mp->m_inodes_per_cluster; i++) { + for (i = 0; i < M_IGEO(mp)->inodes_per_cluster; i++) { int ioffset = i << mp->m_sb.sb_inodelog; uint isize = xfs_dinode_size(version); @@ -616,24 +600,26 @@ error: * Allocate new inodes in the allocation group specified by agbp. * Return 0 for success, else error code. */ -STATIC int /* error code or 0 */ +STATIC int xfs_ialloc_ag_alloc( - xfs_trans_t *tp, /* transaction pointer */ - xfs_buf_t *agbp, /* alloc group buffer */ - int *alloc) + struct xfs_trans *tp, + struct xfs_buf *agbp, + int *alloc) { - xfs_agi_t *agi; /* allocation group header */ - xfs_alloc_arg_t args; /* allocation argument structure */ - xfs_agnumber_t agno; - int error; - xfs_agino_t newino; /* new first inode's number */ - xfs_agino_t newlen; /* new number of inodes */ - int isaligned = 0; /* inode allocation at stripe unit */ - /* boundary */ - uint16_t allocmask = (uint16_t) -1; /* init. to full chunk */ + struct xfs_agi *agi; + struct xfs_alloc_arg args; + xfs_agnumber_t agno; + int error; + xfs_agino_t newino; /* new first inode's number */ + xfs_agino_t newlen; /* new number of inodes */ + int isaligned = 0; /* inode allocation at stripe */ + /* unit boundary */ + /* init. to full chunk */ + uint16_t allocmask = (uint16_t) -1; struct xfs_inobt_rec_incore rec; - struct xfs_perag *pag; - int do_sparse = 0; + struct xfs_perag *pag; + struct xfs_ino_geometry *igeo = M_IGEO(tp->t_mountp); + int do_sparse = 0; memset(&args, 0, sizeof(args)); args.tp = tp; @@ -644,7 +630,7 @@ xfs_ialloc_ag_alloc( #ifdef DEBUG /* randomly do sparse inode allocations */ if (xfs_sb_version_hassparseinodes(&tp->t_mountp->m_sb) && - args.mp->m_ialloc_min_blks < args.mp->m_ialloc_blks) + igeo->ialloc_min_blks < igeo->ialloc_blks) do_sparse = prandom_u32() & 1; #endif @@ -652,12 +638,12 @@ xfs_ialloc_ag_alloc( * Locking will ensure that we don't have two callers in here * at one time. */ - newlen = args.mp->m_ialloc_inos; - if (args.mp->m_maxicount && + newlen = igeo->ialloc_inos; + if (igeo->maxicount && percpu_counter_read_positive(&args.mp->m_icount) + newlen > - args.mp->m_maxicount) + igeo->maxicount) return -ENOSPC; - args.minlen = args.maxlen = args.mp->m_ialloc_blks; + args.minlen = args.maxlen = igeo->ialloc_blks; /* * First try to allocate inodes contiguous with the last-allocated * chunk of inodes. If the filesystem is striped, this will fill @@ -667,7 +653,7 @@ xfs_ialloc_ag_alloc( newino = be32_to_cpu(agi->agi_newino); agno = be32_to_cpu(agi->agi_seqno); args.agbno = XFS_AGINO_TO_AGBNO(args.mp, newino) + - args.mp->m_ialloc_blks; + igeo->ialloc_blks; if (do_sparse) goto sparse_alloc; if (likely(newino != NULLAGINO && @@ -690,10 +676,10 @@ xfs_ialloc_ag_alloc( * but not to use them in the actual exact allocation. */ args.alignment = 1; - args.minalignslop = args.mp->m_cluster_align - 1; + args.minalignslop = igeo->cluster_align - 1; /* Allow space for the inode btree to split. */ - args.minleft = args.mp->m_in_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels - 1; if ((error = xfs_alloc_vextent(&args))) return error; @@ -720,12 +706,12 @@ xfs_ialloc_ag_alloc( * pieces, so don't need alignment anyway. */ isaligned = 0; - if (args.mp->m_sinoalign) { + if (igeo->ialloc_align) { ASSERT(!(args.mp->m_flags & XFS_MOUNT_NOALIGN)); args.alignment = args.mp->m_dalign; isaligned = 1; } else - args.alignment = args.mp->m_cluster_align; + args.alignment = igeo->cluster_align; /* * Need to figure out where to allocate the inode blocks. * Ideally they should be spaced out through the a.g. @@ -741,7 +727,7 @@ xfs_ialloc_ag_alloc( /* * Allow space for the inode btree to split. */ - args.minleft = args.mp->m_in_maxlevels - 1; + args.minleft = igeo->inobt_maxlevels - 1; if ((error = xfs_alloc_vextent(&args))) return error; } @@ -754,7 +740,7 @@ xfs_ialloc_ag_alloc( args.type = XFS_ALLOCTYPE_NEAR_BNO; args.agbno = be32_to_cpu(agi->agi_root); args.fsbno = XFS_AGB_TO_FSB(args.mp, agno, args.agbno); - args.alignment = args.mp->m_cluster_align; + args.alignment = igeo->cluster_align; if ((error = xfs_alloc_vextent(&args))) return error; } @@ -764,7 +750,7 @@ xfs_ialloc_ag_alloc( * the sparse allocation length is smaller than a full chunk. */ if (xfs_sb_version_hassparseinodes(&args.mp->m_sb) && - args.mp->m_ialloc_min_blks < args.mp->m_ialloc_blks && + igeo->ialloc_min_blks < igeo->ialloc_blks && args.fsbno == NULLFSBLOCK) { sparse_alloc: args.type = XFS_ALLOCTYPE_NEAR_BNO; @@ -773,7 +759,7 @@ sparse_alloc: args.alignment = args.mp->m_sb.sb_spino_align; args.prod = 1; - args.minlen = args.mp->m_ialloc_min_blks; + args.minlen = igeo->ialloc_min_blks; args.maxlen = args.minlen; /* @@ -789,7 +775,7 @@ sparse_alloc: args.min_agbno = args.mp->m_sb.sb_inoalignmt; args.max_agbno = round_down(args.mp->m_sb.sb_agblocks, args.mp->m_sb.sb_inoalignmt) - - args.mp->m_ialloc_blks; + igeo->ialloc_blks; error = xfs_alloc_vextent(&args); if (error) @@ -1006,7 +992,7 @@ xfs_ialloc_ag_select( * space needed for alignment of inode chunks when checking the * longest contiguous free space in the AG - this prevents us * from getting ENOSPC because we have free space larger than - * m_ialloc_blks but alignment constraints prevent us from using + * ialloc_blks but alignment constraints prevent us from using * it. * * If we can't find an AG with space for full alignment slack to @@ -1015,9 +1001,9 @@ xfs_ialloc_ag_select( * if we fail allocation due to alignment issues then it is most * likely a real ENOSPC condition. */ - ineed = mp->m_ialloc_min_blks; + ineed = M_IGEO(mp)->ialloc_min_blks; if (flags && ineed > 1) - ineed += mp->m_cluster_align; + ineed += M_IGEO(mp)->cluster_align; longest = pag->pagf_longest; if (!longest) longest = pag->pagf_flcount > 0; @@ -1703,6 +1689,7 @@ xfs_dialloc( int noroom = 0; xfs_agnumber_t start_agno; struct xfs_perag *pag; + struct xfs_ino_geometry *igeo = M_IGEO(mp); int okalloc = 1; if (*IO_agbp) { @@ -1733,9 +1720,9 @@ xfs_dialloc( * Read rough value of mp->m_icount by percpu_counter_read_positive, * which will sacrifice the preciseness but improve the performance. */ - if (mp->m_maxicount && - percpu_counter_read_positive(&mp->m_icount) + mp->m_ialloc_inos - > mp->m_maxicount) { + if (igeo->maxicount && + percpu_counter_read_positive(&mp->m_icount) + igeo->ialloc_inos + > igeo->maxicount) { noroom = 1; okalloc = 0; } @@ -1852,7 +1839,8 @@ xfs_difree_inode_chunk( if (!xfs_inobt_issparse(rec->ir_holemask)) { /* not sparse, calculate extent info directly */ xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - mp->m_ialloc_blks, &XFS_RMAP_OINFO_INODES); + M_IGEO(mp)->ialloc_blks, + &XFS_RMAP_OINFO_INODES); return; } @@ -2261,7 +2249,7 @@ xfs_imap_lookup( /* check that the returned record contains the required inode */ if (rec.ir_startino > agino || - rec.ir_startino + mp->m_ialloc_inos <= agino) + rec.ir_startino + M_IGEO(mp)->ialloc_inos <= agino) return -EINVAL; /* for untrusted inodes check it is allocated first */ @@ -2352,7 +2340,7 @@ xfs_imap( * If the inode cluster size is the same as the blocksize or * smaller we get to the buffer by simple arithmetics. */ - if (mp->m_blocks_per_cluster == 1) { + if (M_IGEO(mp)->blocks_per_cluster == 1) { offset = XFS_INO_TO_OFFSET(mp, ino); ASSERT(offset < mp->m_sb.sb_inopblock); @@ -2368,8 +2356,8 @@ xfs_imap( * find the location. Otherwise we have to do a btree * lookup to find the location. */ - if (mp->m_inoalign_mask) { - offset_agbno = agbno & mp->m_inoalign_mask; + if (M_IGEO(mp)->inoalign_mask) { + offset_agbno = agbno & M_IGEO(mp)->inoalign_mask; chunk_agbno = agbno - offset_agbno; } else { error = xfs_imap_lookup(mp, tp, agno, agino, agbno, @@ -2381,13 +2369,13 @@ xfs_imap( out_map: ASSERT(agbno >= chunk_agbno); cluster_agbno = chunk_agbno + - ((offset_agbno / mp->m_blocks_per_cluster) * - mp->m_blocks_per_cluster); + ((offset_agbno / M_IGEO(mp)->blocks_per_cluster) * + M_IGEO(mp)->blocks_per_cluster); offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) + XFS_INO_TO_OFFSET(mp, ino); imap->im_blkno = XFS_AGB_TO_DADDR(mp, agno, cluster_agbno); - imap->im_len = XFS_FSB_TO_BB(mp, mp->m_blocks_per_cluster); + imap->im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster); imap->im_boffset = (unsigned short)(offset << mp->m_sb.sb_inodelog); /* @@ -2409,20 +2397,6 @@ out_map: } /* - * Compute and fill in value of m_in_maxlevels. - */ -void -xfs_ialloc_compute_maxlevels( - xfs_mount_t *mp) /* file system mount structure */ -{ - uint inodes; - - inodes = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG; - mp->m_in_maxlevels = xfs_btree_compute_maxlevels(mp->m_inobt_mnr, - inodes); -} - -/* * Log specified fields for the ag hdr (inode section). The growth of the agi * structure over time requires that we interpret the buffer as two logical * regions delineated by the end of the unlinked list. This is due to the size @@ -2493,7 +2467,7 @@ static xfs_failaddr_t xfs_agi_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_agi *agi = XFS_BUF_TO_AGI(bp); int i; @@ -2545,7 +2519,7 @@ static void xfs_agi_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; if (xfs_sb_version_hascrc(&mp->m_sb) && @@ -2562,7 +2536,7 @@ static void xfs_agi_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; xfs_failaddr_t fa; @@ -2768,3 +2742,110 @@ xfs_ialloc_count_inodes( *freecount = ci.freecount; return 0; } + +/* + * Initialize inode-related geometry information. + * + * Compute the inode btree min and max levels and set maxicount. + * + * Set the inode cluster size. This may still be overridden by the file + * system block size if it is larger than the chosen cluster size. + * + * For v5 filesystems, scale the cluster size with the inode size to keep a + * constant ratio of inode per cluster buffer, but only if mkfs has set the + * inode alignment value appropriately for larger cluster sizes. + * + * Then compute the inode cluster alignment information. + */ +void +xfs_ialloc_setup_geometry( + struct xfs_mount *mp) +{ + struct xfs_sb *sbp = &mp->m_sb; + struct xfs_ino_geometry *igeo = M_IGEO(mp); + uint64_t icount; + uint inodes; + + /* Compute inode btree geometry. */ + igeo->agino_log = sbp->sb_inopblog + sbp->sb_agblklog; + igeo->inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1); + igeo->inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0); + igeo->inobt_mnr[0] = igeo->inobt_mxr[0] / 2; + igeo->inobt_mnr[1] = igeo->inobt_mxr[1] / 2; + + igeo->ialloc_inos = max_t(uint16_t, XFS_INODES_PER_CHUNK, + sbp->sb_inopblock); + igeo->ialloc_blks = igeo->ialloc_inos >> sbp->sb_inopblog; + + if (sbp->sb_spino_align) + igeo->ialloc_min_blks = sbp->sb_spino_align; + else + igeo->ialloc_min_blks = igeo->ialloc_blks; + + /* Compute and fill in value of m_ino_geo.inobt_maxlevels. */ + inodes = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG; + igeo->inobt_maxlevels = xfs_btree_compute_maxlevels(igeo->inobt_mnr, + inodes); + + /* Set the maximum inode count for this filesystem. */ + if (sbp->sb_imax_pct) { + /* + * Make sure the maximum inode count is a multiple + * of the units we allocate inodes in. + */ + icount = sbp->sb_dblocks * sbp->sb_imax_pct; + do_div(icount, 100); + do_div(icount, igeo->ialloc_blks); + igeo->maxicount = XFS_FSB_TO_INO(mp, + icount * igeo->ialloc_blks); + } else { + igeo->maxicount = 0; + } + + /* + * Compute the desired size of an inode cluster buffer size, which + * starts at 8K and (on v5 filesystems) scales up with larger inode + * sizes. + * + * Preserve the desired inode cluster size because the sparse inodes + * feature uses that desired size (not the actual size) to compute the + * sparse inode alignment. The mount code validates this value, so we + * cannot change the behavior. + */ + igeo->inode_cluster_size_raw = XFS_INODE_BIG_CLUSTER_SIZE; + if (xfs_sb_version_hascrc(&mp->m_sb)) { + int new_size = igeo->inode_cluster_size_raw; + + new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE; + if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size)) + igeo->inode_cluster_size_raw = new_size; + } + + /* Calculate inode cluster ratios. */ + if (igeo->inode_cluster_size_raw > mp->m_sb.sb_blocksize) + igeo->blocks_per_cluster = XFS_B_TO_FSBT(mp, + igeo->inode_cluster_size_raw); + else + igeo->blocks_per_cluster = 1; + igeo->inode_cluster_size = XFS_FSB_TO_B(mp, igeo->blocks_per_cluster); + igeo->inodes_per_cluster = XFS_FSB_TO_INO(mp, igeo->blocks_per_cluster); + + /* Calculate inode cluster alignment. */ + if (xfs_sb_version_hasalign(&mp->m_sb) && + mp->m_sb.sb_inoalignmt >= igeo->blocks_per_cluster) + igeo->cluster_align = mp->m_sb.sb_inoalignmt; + else + igeo->cluster_align = 1; + igeo->inoalign_mask = igeo->cluster_align - 1; + igeo->cluster_align_inodes = XFS_FSB_TO_INO(mp, igeo->cluster_align); + + /* + * If we are using stripe alignment, check whether + * the stripe unit is a multiple of the inode alignment + */ + if (mp->m_dalign && igeo->inoalign_mask && + !(mp->m_dalign & igeo->inoalign_mask)) + igeo->ialloc_align = mp->m_dalign; + else + igeo->ialloc_align = 0; +} diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index e936b7cc9389..323592d563d5 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -23,16 +23,6 @@ struct xfs_icluster { * sparse chunks */ }; -/* Calculate and return the number of filesystem blocks per inode cluster */ -static inline int -xfs_icluster_size_fsb( - struct xfs_mount *mp) -{ - if (mp->m_sb.sb_blocksize >= mp->m_inode_cluster_size) - return 1; - return mp->m_inode_cluster_size >> mp->m_sb.sb_blocklog; -} - /* * Make an inode pointer out of the buffer/offset. */ @@ -96,13 +86,6 @@ xfs_imap( uint flags); /* flags for inode btree lookup */ /* - * Compute and fill in value of m_in_maxlevels. - */ -void -xfs_ialloc_compute_maxlevels( - struct xfs_mount *mp); /* file system mount structure */ - -/* * Log specified fields for the ag hdr (inode section) */ void @@ -168,5 +151,6 @@ int xfs_inobt_insert_rec(struct xfs_btree_cur *cur, uint16_t holemask, int *stat); int xfs_ialloc_cluster_alignment(struct xfs_mount *mp); +void xfs_ialloc_setup_geometry(struct xfs_mount *mp); #endif /* __XFS_IALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 1080381ff243..b82992f795aa 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -11,14 +11,12 @@ #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_trans.h" #include "xfs_rmap.h" @@ -28,7 +26,7 @@ xfs_inobt_get_minrecs( struct xfs_btree_cur *cur, int level) { - return cur->bc_mp->m_inobt_mnr[level != 0]; + return M_IGEO(cur->bc_mp)->inobt_mnr[level != 0]; } STATIC struct xfs_btree_cur * @@ -164,7 +162,7 @@ xfs_inobt_get_maxrecs( struct xfs_btree_cur *cur, int level) { - return cur->bc_mp->m_inobt_mxr[level != 0]; + return M_IGEO(cur->bc_mp)->inobt_mxr[level != 0]; } STATIC void @@ -255,7 +253,7 @@ static xfs_failaddr_t xfs_inobt_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); xfs_failaddr_t fa; unsigned int level; @@ -281,10 +279,11 @@ xfs_inobt_verify( /* level verification */ level = be16_to_cpu(block->bb_level); - if (level >= mp->m_in_maxlevels) + if (level >= M_IGEO(mp)->inobt_maxlevels) return __this_address; - return xfs_btree_sblock_verify(bp, mp->m_inobt_mxr[level != 0]); + return xfs_btree_sblock_verify(bp, + M_IGEO(mp)->inobt_mxr[level != 0]); } static void @@ -546,14 +545,53 @@ xfs_inobt_max_size( xfs_agblock_t agblocks = xfs_ag_block_count(mp, agno); /* Bail out if we're uninitialized, which can happen in mkfs. */ - if (mp->m_inobt_mxr[0] == 0) + if (M_IGEO(mp)->inobt_mxr[0] == 0) return 0; - return xfs_btree_calc_size(mp->m_inobt_mnr, + /* + * The log is permanently allocated, so the space it occupies will + * never be available for the kinds of things that would require btree + * expansion. We therefore can pretend the space isn't there. + */ + if (mp->m_sb.sb_logstart && + XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno) + agblocks -= mp->m_sb.sb_logblocks; + + return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr, (uint64_t)agblocks * mp->m_sb.sb_inopblock / XFS_INODES_PER_CHUNK); } +/* Read AGI and create inobt cursor. */ +int +xfs_inobt_cur( + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_agnumber_t agno, + xfs_btnum_t which, + struct xfs_btree_cur **curpp, + struct xfs_buf **agi_bpp) +{ + struct xfs_btree_cur *cur; + int error; + + ASSERT(*agi_bpp == NULL); + ASSERT(*curpp == NULL); + + error = xfs_ialloc_read_agi(mp, tp, agno, agi_bpp); + if (error) + return error; + + cur = xfs_inobt_init_cursor(mp, tp, *agi_bpp, agno, which); + if (!cur) { + xfs_trans_brelse(tp, *agi_bpp); + *agi_bpp = NULL; + return -ENOMEM; + } + *curpp = cur; + return 0; +} + static int xfs_inobt_count_blocks( struct xfs_mount *mp, @@ -562,15 +600,14 @@ xfs_inobt_count_blocks( xfs_btnum_t btnum, xfs_extlen_t *tree_blocks) { - struct xfs_buf *agbp; - struct xfs_btree_cur *cur; + struct xfs_buf *agbp = NULL; + struct xfs_btree_cur *cur = NULL; int error; - error = xfs_ialloc_read_agi(mp, tp, agno, &agbp); + error = xfs_inobt_cur(mp, tp, agno, btnum, &cur, &agbp); if (error) return error; - cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, btnum); error = xfs_btree_count_blocks(cur, tree_blocks); xfs_btree_del_cursor(cur, error); xfs_trans_brelse(tp, agbp); @@ -610,5 +647,5 @@ xfs_iallocbt_calc_size( struct xfs_mount *mp, unsigned long long len) { - return xfs_btree_calc_size(mp->m_inobt_mnr, len); + return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr, len); } diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h index ebdd0c6b8766..951305ecaae1 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.h +++ b/fs/xfs/libxfs/xfs_ialloc_btree.h @@ -64,5 +64,8 @@ int xfs_finobt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp, xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used); extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp, unsigned long long len); +int xfs_inobt_cur(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_agnumber_t agno, xfs_btnum_t btnum, + struct xfs_btree_cur **curpp, struct xfs_buf **agi_bpp); #endif /* __XFS_IALLOC_BTREE_H__ */ diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index bc690f2409fa..27aa3f2bc4bc 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -3,18 +3,14 @@ * Copyright (c) 2017 Christoph Hellwig. */ -#include <linux/cache.h> -#include <linux/kernel.h> -#include <linux/slab.h> #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_inode.h" -#include "xfs_inode_fork.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_bmap.h" #include "xfs_trace.h" /* diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index e021d5133ccb..28ab3c5255e1 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -10,11 +10,9 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_errortag.h" #include "xfs_error.h" -#include "xfs_cksum.h" #include "xfs_icache.h" #include "xfs_trans.h" #include "xfs_ialloc.h" @@ -33,12 +31,9 @@ xfs_inobp_check( xfs_buf_t *bp) { int i; - int j; xfs_dinode_t *dip; - j = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog; - - for (i = 0; i < j; i++) { + for (i = 0; i < M_IGEO(mp)->inodes_per_cluster; i++) { dip = xfs_buf_offset(bp, i * mp->m_sb.sb_inodesize); if (!dip->di_next_unlinked) { xfs_alert(mp, @@ -80,7 +75,7 @@ xfs_inode_buf_verify( struct xfs_buf *bp, bool readahead) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_agnumber_t agno; int i; int ni; diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index f9acf1d436f6..bf3e04018246 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -3,10 +3,10 @@ * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. */ -#include <linux/log2.h> #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" @@ -19,12 +19,10 @@ #include "xfs_bmap.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_attr_sf.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_dir2_priv.h" #include "xfs_attr_leaf.h" -#include "xfs_shared.h" kmem_zone_t *xfs_ifork_zone; diff --git a/fs/xfs/libxfs/xfs_log_rlimit.c b/fs/xfs/libxfs/xfs_log_rlimit.c index 1b542ec11d5d..7f55eb3f3653 100644 --- a/fs/xfs/libxfs/xfs_log_rlimit.c +++ b/fs/xfs/libxfs/xfs_log_rlimit.c @@ -12,9 +12,7 @@ #include "xfs_mount.h" #include "xfs_da_format.h" #include "xfs_trans_space.h" -#include "xfs_inode.h" #include "xfs_da_btree.h" -#include "xfs_attr_leaf.h" #include "xfs_bmap_btree.h" /* diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 542aa1475b5f..51bb9bdb0e84 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -9,7 +9,6 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_btree.h" @@ -19,7 +18,6 @@ #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_trans.h" #include "xfs_bit.h" #include "xfs_refcount.h" diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 6f47ab876d90..38529dbacd55 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -12,12 +12,10 @@ #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_btree.h" -#include "xfs_bmap.h" #include "xfs_refcount_btree.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_trans.h" #include "xfs_bit.h" #include "xfs_rmap.h" @@ -203,7 +201,7 @@ STATIC xfs_failaddr_t xfs_refcountbt_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_perag *pag = bp->b_pag; xfs_failaddr_t fa; @@ -427,6 +425,15 @@ xfs_refcountbt_calc_reserves( tree_len = be32_to_cpu(agf->agf_refcount_blocks); xfs_trans_brelse(tp, agbp); + /* + * The log is permanently allocated, so the space it occupies will + * never be available for the kinds of things that would require btree + * expansion. We therefore can pretend the space isn't there. + */ + if (mp->m_sb.sb_logstart && + XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno) + agblocks -= mp->m_sb.sb_logblocks; + *ask += xfs_refcountbt_max_size(mp, agblocks); *used += tree_len; diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 8ed885507dd8..e6aeb390b2fb 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -10,24 +10,17 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" -#include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_btree.h" #include "xfs_trans.h" #include "xfs_alloc.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" -#include "xfs_trans_space.h" #include "xfs_trace.h" #include "xfs_errortag.h" #include "xfs_error.h" -#include "xfs_extent_busy.h" -#include "xfs_bmap.h" #include "xfs_inode.h" -#include "xfs_ialloc.h" /* * Lookup the first record less than or equal to [bno, len, owner, offset] diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index 5738e11055e6..fc78efa52c94 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -9,18 +9,14 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_alloc.h" #include "xfs_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_error.h" #include "xfs_extent_busy.h" #include "xfs_ag_resv.h" @@ -292,7 +288,7 @@ static xfs_failaddr_t xfs_rmapbt_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp); struct xfs_perag *pag = bp->b_pag; xfs_failaddr_t fa; @@ -578,6 +574,15 @@ xfs_rmapbt_calc_reserves( tree_len = be32_to_cpu(agf->agf_rmap_blocks); xfs_trans_brelse(tp, agbp); + /* + * The log is permanently allocated, so the space it occupies will + * never be available for the kinds of things that would require btree + * expansion. We therefore can pretend the space isn't there. + */ + if (mp->m_sb.sb_logstart && + XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno) + agblocks -= mp->m_sb.sb_logblocks; + /* Reserve 1% of the AG or enough for 1 block per record. */ *ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks)); *used += tree_len; diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c index eaaff67e9626..8ea1efc97b41 100644 --- a/fs/xfs/libxfs/xfs_rtbitmap.c +++ b/fs/xfs/libxfs/xfs_rtbitmap.c @@ -13,15 +13,7 @@ #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" -#include "xfs_bmap_btree.h" -#include "xfs_alloc.h" -#include "xfs_error.h" #include "xfs_trans.h" -#include "xfs_trans_space.h" -#include "xfs_trace.h" -#include "xfs_buf.h" -#include "xfs_icache.h" #include "xfs_rtalloc.h" diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index e76a3e5d28d7..a08dd8f40346 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -10,26 +10,19 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" -#include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_inode.h" #include "xfs_ialloc.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_cksum.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_bmap_btree.h" #include "xfs_alloc_btree.h" -#include "xfs_ialloc_btree.h" #include "xfs_log.h" #include "xfs_rmap_btree.h" -#include "xfs_bmap.h" #include "xfs_refcount_btree.h" #include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_health.h" /* @@ -686,7 +679,7 @@ xfs_sb_read_verify( struct xfs_buf *bp) { struct xfs_sb sb; - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp); int error; @@ -752,7 +745,7 @@ xfs_sb_write_verify( struct xfs_buf *bp) { struct xfs_sb sb; - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; int error; @@ -800,12 +793,14 @@ const struct xfs_buf_ops xfs_sb_quiet_buf_ops = { * * Mount initialization code establishing various mount * fields from the superblock associated with the given - * mount structure + * mount structure. + * + * Inode geometry are calculated in xfs_ialloc_setup_geometry. */ void xfs_sb_mount_common( - struct xfs_mount *mp, - struct xfs_sb *sbp) + struct xfs_mount *mp, + struct xfs_sb *sbp) { mp->m_agfrotor = mp->m_agirotor = 0; mp->m_maxagi = mp->m_sb.sb_agcount; @@ -813,7 +808,6 @@ xfs_sb_mount_common( mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT; mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT; mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1; - mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog; mp->m_blockmask = sbp->sb_blocksize - 1; mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG; mp->m_blockwmask = mp->m_blockwsize - 1; @@ -823,11 +817,6 @@ xfs_sb_mount_common( mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2; mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2; - mp->m_inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1); - mp->m_inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0); - mp->m_inobt_mnr[0] = mp->m_inobt_mxr[0] / 2; - mp->m_inobt_mnr[1] = mp->m_inobt_mxr[1] / 2; - mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 1); mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 0); mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2; @@ -844,14 +833,6 @@ xfs_sb_mount_common( mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2; mp->m_bsize = XFS_FSB_TO_BB(mp, 1); - mp->m_ialloc_inos = max_t(uint16_t, XFS_INODES_PER_CHUNK, - sbp->sb_inopblock); - mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog; - - if (sbp->sb_spino_align) - mp->m_ialloc_min_blks = sbp->sb_spino_align; - else - mp->m_ialloc_min_blks = mp->m_ialloc_blks; mp->m_alloc_set_aside = xfs_alloc_set_aside(mp); mp->m_ag_max_usable = xfs_alloc_ag_max_usable(mp); } @@ -939,7 +920,7 @@ xfs_log_sb( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; - struct xfs_buf *bp = xfs_trans_getsb(tp, mp, 0); + struct xfs_buf *bp = xfs_trans_getsb(tp, mp); mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount); mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree); @@ -1005,7 +986,7 @@ xfs_update_secondary_sbs( bp = xfs_buf_get(mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_SB_DADDR), - XFS_FSS_TO_BB(mp, 1), 0); + XFS_FSS_TO_BB(mp, 1)); /* * If we get an error reading or writing alternate superblocks, * continue. xfs_repair chooses the "best" superblock based @@ -1069,7 +1050,7 @@ xfs_sync_sb_buf( if (error) return error; - bp = xfs_trans_getsb(tp, mp, 0); + bp = xfs_trans_getsb(tp, mp); xfs_log_sb(tp); xfs_trans_bhold(tp, bp); xfs_trans_set_sync(tp); diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h index 4e909791aeac..e0641b7337b3 100644 --- a/fs/xfs/libxfs/xfs_shared.h +++ b/fs/xfs/libxfs/xfs_shared.h @@ -65,7 +65,6 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp, #define XFS_TRANS_DQ_DIRTY 0x10 /* at least one dquot in trx dirty */ #define XFS_TRANS_RESERVE 0x20 /* OK to use reserved data blocks */ #define XFS_TRANS_NO_WRITECOUNT 0x40 /* do not elevate SB writecount */ -#define XFS_TRANS_NOFS 0x80 /* pass KM_NOFS to kmem_alloc */ /* * LOWMODE is used by the allocator to activate the lowspace algorithm - when * free space is running low the extent allocator may choose to allocate an @@ -136,4 +135,52 @@ void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp, struct xfs_inode *ip, struct xfs_ifork *ifp); xfs_failaddr_t xfs_symlink_shortform_verify(struct xfs_inode *ip); +/* Computed inode geometry for the filesystem. */ +struct xfs_ino_geometry { + /* Maximum inode count in this filesystem. */ + uint64_t maxicount; + + /* Actual inode cluster buffer size, in bytes. */ + unsigned int inode_cluster_size; + + /* + * Desired inode cluster buffer size, in bytes. This value is not + * rounded up to at least one filesystem block, which is necessary for + * the sole purpose of validating sb_spino_align. Runtime code must + * only ever use inode_cluster_size. + */ + unsigned int inode_cluster_size_raw; + + /* Inode cluster sizes, adjusted to be at least 1 fsb. */ + unsigned int inodes_per_cluster; + unsigned int blocks_per_cluster; + + /* Inode cluster alignment. */ + unsigned int cluster_align; + unsigned int cluster_align_inodes; + unsigned int inoalign_mask; /* mask sb_inoalignmt if used */ + + unsigned int inobt_mxr[2]; /* max inobt btree records */ + unsigned int inobt_mnr[2]; /* min inobt btree records */ + unsigned int inobt_maxlevels; /* max inobt btree levels. */ + + /* Size of inode allocations under normal operation. */ + unsigned int ialloc_inos; + unsigned int ialloc_blks; + + /* Minimum inode blocks for a sparse allocation. */ + unsigned int ialloc_min_blks; + + /* stripe unit inode alignment */ + unsigned int ialloc_align; + + unsigned int agino_log; /* #bits for agino in inum */ +}; + +/* Keep iterating the data structure. */ +#define XFS_ITER_CONTINUE (0) + +/* Stop iterating the data structure. */ +#define XFS_ITER_ABORT (1) + #endif /* __XFS_SHARED_H__ */ diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index a0ccc253c43d..3b8260ca7d1b 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -11,12 +11,8 @@ #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_bmap_btree.h" #include "xfs_inode.h" #include "xfs_error.h" -#include "xfs_trace.h" -#include "xfs_symlink.h" -#include "xfs_cksum.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_log.h" @@ -90,7 +86,7 @@ static xfs_failaddr_t xfs_symlink_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_dsymlink_hdr *dsl = bp->b_addr; if (!xfs_sb_version_hascrc(&mp->m_sb)) @@ -116,7 +112,7 @@ static void xfs_symlink_read_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; /* no verification of non-crc buffers */ @@ -136,7 +132,7 @@ static void xfs_symlink_write_verify( struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; struct xfs_buf_log_item *bip = bp->b_log_item; xfs_failaddr_t fa; diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 83f4ee2afc49..d12bbd526e7c 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -15,12 +15,10 @@ #include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_bmap_btree.h" -#include "xfs_ialloc.h" #include "xfs_quota.h" #include "xfs_trans.h" #include "xfs_qm.h" #include "xfs_trans_space.h" -#include "xfs_trace.h" #define _ALLOC true #define _FREE false @@ -136,9 +134,10 @@ STATIC uint xfs_calc_inobt_res( struct xfs_mount *mp) { - return xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1), - XFS_FSB_TO_B(mp, 1)); + return xfs_calc_buf_res(M_IGEO(mp)->inobt_maxlevels, + XFS_FSB_TO_B(mp, 1)) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1), + XFS_FSB_TO_B(mp, 1)); } /* @@ -167,7 +166,7 @@ xfs_calc_finobt_res( * includes: * * the allocation btrees: 2 trees * (max depth - 1) * block size - * the inode chunk: m_ialloc_blks * N + * the inode chunk: m_ino_geo.ialloc_blks * N * * The size N of the inode chunk reservation depends on whether it is for * allocation or free and which type of create transaction is in use. An inode @@ -193,7 +192,7 @@ xfs_calc_inode_chunk_res( size = XFS_FSB_TO_B(mp, 1); } - res += xfs_calc_buf_res(mp->m_ialloc_blks, size); + res += xfs_calc_buf_res(M_IGEO(mp)->ialloc_blks, size); return res; } @@ -307,7 +306,7 @@ xfs_calc_iunlink_remove_reservation( struct xfs_mount *mp) { return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) + - 2 * max_t(uint, XFS_FSB_TO_B(mp, 1), mp->m_inode_cluster_size); + 2 * M_IGEO(mp)->inode_cluster_size; } /* @@ -345,7 +344,7 @@ STATIC uint xfs_calc_iunlink_add_reservation(xfs_mount_t *mp) { return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) + - max_t(uint, XFS_FSB_TO_B(mp, 1), mp->m_inode_cluster_size); + M_IGEO(mp)->inode_cluster_size; } /* diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h index a62fb950bef1..88221c7a04cc 100644 --- a/fs/xfs/libxfs/xfs_trans_space.h +++ b/fs/xfs/libxfs/xfs_trans_space.h @@ -56,9 +56,9 @@ #define XFS_DIRREMOVE_SPACE_RES(mp) \ XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK) #define XFS_IALLOC_SPACE_RES(mp) \ - ((mp)->m_ialloc_blks + \ + (M_IGEO(mp)->ialloc_blks + \ (xfs_sb_version_hasfinobt(&mp->m_sb) ? 2 : 1 * \ - ((mp)->m_in_maxlevels - 1))) + (M_IGEO(mp)->inobt_maxlevels - 1))) /* * Space reservation values for various transactions. @@ -94,7 +94,8 @@ #define XFS_SYMLINK_SPACE_RES(mp,nl,b) \ (XFS_IALLOC_SPACE_RES(mp) + XFS_DIRENTER_SPACE_RES(mp,nl) + (b)) #define XFS_IFREE_SPACE_RES(mp) \ - (xfs_sb_version_hasfinobt(&mp->m_sb) ? (mp)->m_in_maxlevels : 0) + (xfs_sb_version_hasfinobt(&mp->m_sb) ? \ + M_IGEO(mp)->inobt_maxlevels : 0) #endif /* __XFS_TRANS_SPACE_H__ */ diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c index d51acc95bc00..4f595546a639 100644 --- a/fs/xfs/libxfs/xfs_types.c +++ b/fs/xfs/libxfs/xfs_types.c @@ -7,19 +7,10 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" -#include "xfs_log_format.h" #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" -#include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_inode.h" -#include "xfs_btree.h" -#include "xfs_rmap.h" -#include "xfs_alloc_btree.h" -#include "xfs_alloc.h" -#include "xfs_ialloc.h" /* Find the size of the AG, in blocks. */ xfs_agblock_t @@ -87,14 +78,14 @@ xfs_agino_range( * Calculate the first inode, which will be in the first * cluster-aligned block after the AGFL. */ - bno = round_up(XFS_AGFL_BLOCK(mp) + 1, mp->m_cluster_align); + bno = round_up(XFS_AGFL_BLOCK(mp) + 1, M_IGEO(mp)->cluster_align); *first = XFS_AGB_TO_AGINO(mp, bno); /* * Calculate the last inode, which will be at the end of the * last (aligned) cluster that can be allocated in the AG. */ - bno = round_down(eoag, mp->m_cluster_align); + bno = round_down(eoag, M_IGEO(mp)->cluster_align); *last = XFS_AGB_TO_AGINO(mp, bno) - 1; } diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index adaeabdefdd3..16b09b941441 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -9,20 +9,13 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" -#include "xfs_log_format.h" -#include "xfs_trans.h" #include "xfs_sb.h" -#include "xfs_inode.h" #include "xfs_alloc.h" #include "xfs_ialloc.h" #include "xfs_rmap.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" -#include "scrub/trace.h" /* Superblock */ @@ -646,7 +639,7 @@ xchk_agfl_block( xchk_agfl_block_xref(sc, agbno); if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) - return XFS_BTREE_QUERY_RANGE_ABORT; + return XFS_ITER_ABORT; return 0; } @@ -737,7 +730,7 @@ xchk_agfl( /* Check the blocks in the AGFL. */ error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(sc->sa.agf_bp), sc->sa.agfl_bp, xchk_agfl_block, &sai); - if (error == XFS_BTREE_QUERY_RANGE_ABORT) { + if (error == XFS_ITER_ABORT) { error = 0; goto out_free; } diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 64e31f87d490..7a1a38b636a9 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -9,22 +9,17 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_sb.h" -#include "xfs_inode.h" #include "xfs_alloc.h" #include "xfs_alloc_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" -#include "xfs_refcount.h" #include "xfs_refcount_btree.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index 44883e9112ad..a43d1813c4ff 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -9,19 +9,12 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" -#include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_alloc.h" #include "xfs_rmap.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" -#include "scrub/trace.h" /* * Set us up to scrub free space btrees. diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c index dce74ec57038..1afc58bf71dd 100644 --- a/fs/xfs/scrub/attr.c +++ b/fs/xfs/scrub/attr.c @@ -9,26 +9,62 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" -#include "xfs_dir2.h" #include "xfs_attr.h" #include "xfs_attr_leaf.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/dabtree.h" -#include "scrub/trace.h" +#include "scrub/attr.h" -#include <linux/posix_acl_xattr.h> -#include <linux/xattr.h> +/* + * Allocate enough memory to hold an attr value and attr block bitmaps, + * reallocating the buffer if necessary. Buffer contents are not preserved + * across a reallocation. + */ +int +xchk_setup_xattr_buf( + struct xfs_scrub *sc, + size_t value_size, + xfs_km_flags_t flags) +{ + size_t sz; + struct xchk_xattr_buf *ab = sc->buf; + + /* + * We need enough space to read an xattr value from the file or enough + * space to hold three copies of the xattr free space bitmap. We don't + * need the buffer space for both purposes at the same time. + */ + sz = 3 * sizeof(long) * BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); + sz = max_t(size_t, sz, value_size); + + /* + * If there's already a buffer, figure out if we need to reallocate it + * to accommodate a larger size. + */ + if (ab) { + if (sz <= ab->sz) + return 0; + kmem_free(ab); + sc->buf = NULL; + } + + /* + * Don't zero the buffer upon allocation to avoid runtime overhead. + * All users must be careful never to read uninitialized contents. + */ + ab = kmem_alloc_large(sizeof(*ab) + sz, flags); + if (!ab) + return -ENOMEM; + + ab->sz = sz; + sc->buf = ab; + return 0; +} /* Set us up to scrub an inode's extended attributes. */ int @@ -36,19 +72,18 @@ xchk_setup_xattr( struct xfs_scrub *sc, struct xfs_inode *ip) { - size_t sz; + int error; /* - * Allocate the buffer without the inode lock held. We need enough - * space to read every xattr value in the file or enough space to - * hold three copies of the xattr free space bitmap. (Not both at - * the same time.) + * We failed to get memory while checking attrs, so this time try to + * get all the memory we're ever going to need. Allocate the buffer + * without the inode lock held, which means we can sleep. */ - sz = max_t(size_t, XATTR_SIZE_MAX, 3 * sizeof(long) * - BITS_TO_LONGS(sc->mp->m_attr_geo->blksize)); - sc->buf = kmem_zalloc_large(sz, KM_SLEEP); - if (!sc->buf) - return -ENOMEM; + if (sc->flags & XCHK_TRY_HARDER) { + error = xchk_setup_xattr_buf(sc, XATTR_SIZE_MAX, KM_SLEEP); + if (error) + return error; + } return xchk_setup_inode_contents(sc, ip, 0); } @@ -83,7 +118,7 @@ xchk_xattr_listent( sx = container_of(context, struct xchk_xattr, context); if (xchk_should_terminate(sx->sc, &error)) { - context->seen_enough = 1; + context->seen_enough = error; return; } @@ -99,6 +134,19 @@ xchk_xattr_listent( return; } + /* + * Try to allocate enough memory to extrat the attr value. If that + * doesn't work, we overload the seen_enough variable to convey + * the error message back to the main scrub function. + */ + error = xchk_setup_xattr_buf(sx->sc, valuelen, KM_MAYFAIL); + if (error == -ENOMEM) + error = -EDEADLOCK; + if (error) { + context->seen_enough = error; + return; + } + args.flags = ATTR_KERNOTIME; if (flags & XFS_ATTR_ROOT) args.flags |= ATTR_ROOT; @@ -111,8 +159,8 @@ xchk_xattr_listent( args.namelen = namelen; args.hashval = xfs_da_hashname(args.name, args.namelen); args.trans = context->tp; - args.value = sx->sc->buf; - args.valuelen = XATTR_SIZE_MAX; + args.value = xchk_xattr_valuebuf(sx->sc); + args.valuelen = valuelen; error = xfs_attr_get_ilocked(context->dp, &args); if (error == -EEXIST) @@ -125,7 +173,7 @@ xchk_xattr_listent( args.blkno); fail_xref: if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) - context->seen_enough = 1; + context->seen_enough = XFS_ITER_ABORT; return; } @@ -170,13 +218,12 @@ xchk_xattr_check_freemap( unsigned long *map, struct xfs_attr3_icleaf_hdr *leafhdr) { - unsigned long *freemap; - unsigned long *dstmap; + unsigned long *freemap = xchk_xattr_freemap(sc); + unsigned long *dstmap = xchk_xattr_dstmap(sc); unsigned int mapsize = sc->mp->m_attr_geo->blksize; int i; /* Construct bitmap of freemap contents. */ - freemap = (unsigned long *)sc->buf + BITS_TO_LONGS(mapsize); bitmap_zero(freemap, mapsize); for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (!xchk_xattr_set_map(sc, freemap, @@ -186,7 +233,6 @@ xchk_xattr_check_freemap( } /* Look for bits that are set in freemap and are marked in use. */ - dstmap = freemap + BITS_TO_LONGS(mapsize); return bitmap_and(dstmap, freemap, map, mapsize) == 0; } @@ -201,13 +247,13 @@ xchk_xattr_entry( char *buf_end, struct xfs_attr_leafblock *leaf, struct xfs_attr3_icleaf_hdr *leafhdr, - unsigned long *usedmap, struct xfs_attr_leaf_entry *ent, int idx, unsigned int *usedbytes, __u32 *last_hashval) { struct xfs_mount *mp = ds->state->mp; + unsigned long *usedmap = xchk_xattr_usedmap(ds->sc); char *name_end; struct xfs_attr_leaf_name_local *lentry; struct xfs_attr_leaf_name_remote *rentry; @@ -267,16 +313,26 @@ xchk_xattr_block( struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *ent; struct xfs_attr_leaf_entry *entries; - unsigned long *usedmap = ds->sc->buf; + unsigned long *usedmap; char *buf_end; size_t off; __u32 last_hashval = 0; unsigned int usedbytes = 0; unsigned int hdrsize; int i; + int error; if (*last_checked == blk->blkno) return 0; + + /* Allocate memory for block usage checking. */ + error = xchk_setup_xattr_buf(ds->sc, 0, KM_MAYFAIL); + if (error == -ENOMEM) + return -EDEADLOCK; + if (error) + return error; + usedmap = xchk_xattr_usedmap(ds->sc); + *last_checked = blk->blkno; bitmap_zero(usedmap, mp->m_attr_geo->blksize); @@ -324,7 +380,7 @@ xchk_xattr_block( /* Check the entry and nameval. */ xchk_xattr_entry(ds, level, buf_end, leaf, &leafhdr, - usedmap, ent, i, &usedbytes, &last_hashval); + ent, i, &usedbytes, &last_hashval); if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) goto out; @@ -464,6 +520,10 @@ xchk_xattr( error = xfs_attr_list_int_ilocked(&sx.context); if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error)) goto out; + + /* Did our listent function try to return any errors? */ + if (sx.context.seen_enough < 0) + error = sx.context.seen_enough; out: return error; } diff --git a/fs/xfs/scrub/attr.h b/fs/xfs/scrub/attr.h new file mode 100644 index 000000000000..13a1d2e8424d --- /dev/null +++ b/fs/xfs/scrub/attr.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#ifndef __XFS_SCRUB_ATTR_H__ +#define __XFS_SCRUB_ATTR_H__ + +/* + * Temporary storage for online scrub and repair of extended attributes. + */ +struct xchk_xattr_buf { + /* Size of @buf, in bytes. */ + size_t sz; + + /* + * Memory buffer -- either used for extracting attr values while + * walking the attributes; or for computing attr block bitmaps when + * checking the attribute tree. + * + * Each bitmap contains enough bits to track every byte in an attr + * block (rounded up to the size of an unsigned long). The attr block + * used space bitmap starts at the beginning of the buffer; the free + * space bitmap follows immediately after; and we have a third buffer + * for storing intermediate bitmap results. + */ + uint8_t buf[0]; +}; + +/* A place to store attribute values. */ +static inline uint8_t * +xchk_xattr_valuebuf( + struct xfs_scrub *sc) +{ + struct xchk_xattr_buf *ab = sc->buf; + + return ab->buf; +} + +/* A bitmap of space usage computed by walking an attr leaf block. */ +static inline unsigned long * +xchk_xattr_usedmap( + struct xfs_scrub *sc) +{ + struct xchk_xattr_buf *ab = sc->buf; + + return (unsigned long *)ab->buf; +} + +/* A bitmap of free space computed by walking attr leaf block free info. */ +static inline unsigned long * +xchk_xattr_freemap( + struct xfs_scrub *sc) +{ + return xchk_xattr_usedmap(sc) + + BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); +} + +/* A bitmap used to hold temporary results. */ +static inline unsigned long * +xchk_xattr_dstmap( + struct xfs_scrub *sc) +{ + return xchk_xattr_freemap(sc) + + BITS_TO_LONGS(sc->mp->m_attr_geo->blksize); +} + +int xchk_setup_xattr_buf(struct xfs_scrub *sc, size_t value_size, + xfs_km_flags_t flags); + +#endif /* __XFS_SCRUB_ATTR_H__ */ diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c index fdadc9e1dc49..3d47d111be5a 100644 --- a/fs/xfs/scrub/bitmap.c +++ b/fs/xfs/scrub/bitmap.c @@ -10,11 +10,6 @@ #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_btree.h" -#include "scrub/xfs_scrub.h" -#include "scrub/scrub.h" -#include "scrub/common.h" -#include "scrub/trace.h" -#include "scrub/repair.h" #include "scrub/bitmap.h" /* diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index a703cd58a90e..1bd29fdc2ab5 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -9,27 +9,19 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" #include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_inode_fork.h" #include "xfs_alloc.h" -#include "xfs_rtalloc.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" -#include "xfs_refcount.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" -#include "scrub/trace.h" /* Set us up with an inode's bmap. */ int diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index 117910db51b8..f52a7b8256f9 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -9,14 +9,7 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" -#include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" -#include "xfs_inode.h" -#include "xfs_alloc.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index 973aa59975e3..18876056e5e0 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -9,22 +9,16 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_inode.h" #include "xfs_icache.h" -#include "xfs_itable.h" #include "xfs_alloc.h" #include "xfs_alloc_btree.h" -#include "xfs_bmap.h" -#include "xfs_bmap_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" -#include "xfs_refcount.h" #include "xfs_refcount_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" @@ -32,11 +26,9 @@ #include "xfs_trans_priv.h" #include "xfs_attr.h" #include "xfs_reflink.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" -#include "scrub/btree.h" #include "scrub/repair.h" #include "scrub/health.h" diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c index 90527b094878..94c4f1de1922 100644 --- a/fs/xfs/scrub/dabtree.c +++ b/fs/xfs/scrub/dabtree.c @@ -9,20 +9,12 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_inode_fork.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_attr_leaf.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index a38a22785a1a..1e2e11721eb9 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -9,24 +9,14 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" #include "xfs_icache.h" -#include "xfs_itable.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" -#include "xfs_ialloc.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" -#include "scrub/trace.h" #include "scrub/dabtree.h" /* Set us up to scrub directories. */ diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 07c11e3e6437..fc3f510c9034 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -9,22 +9,10 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" -#include "xfs_log_format.h" -#include "xfs_trans.h" #include "xfs_sb.h" -#include "xfs_inode.h" #include "xfs_alloc.h" #include "xfs_ialloc.h" -#include "xfs_rmap.h" -#include "xfs_error.h" -#include "xfs_errortag.h" -#include "xfs_icache.h" #include "xfs_health.h" -#include "xfs_bmap.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index 23cf8e2f25db..b2f602811e9d 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -7,18 +7,10 @@ #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" -#include "xfs_log_format.h" -#include "xfs_trans.h" #include "xfs_sb.h" -#include "xfs_inode.h" #include "xfs_health.h" #include "scrub/scrub.h" -#include "scrub/health.h" /* * Scrub and In-Core Filesystem Health Assessments diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index 693eb51f5efb..681758704fda 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -9,21 +9,14 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_alloc.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_icache.h" #include "xfs_rmap.h" -#include "xfs_log.h" -#include "xfs_trans_priv.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" @@ -230,7 +223,7 @@ xchk_iallocbt_check_cluster( int error = 0; nr_inodes = min_t(unsigned int, XFS_INODES_PER_CHUNK, - mp->m_inodes_per_cluster); + M_IGEO(mp)->inodes_per_cluster); /* Map this inode cluster */ agbno = XFS_AGINO_TO_AGBNO(mp, irec->ir_startino + cluster_base); @@ -251,8 +244,9 @@ xchk_iallocbt_check_cluster( */ ir_holemask = (irec->ir_holemask & cluster_mask); imap.im_blkno = XFS_AGB_TO_DADDR(mp, agno, agbno); - imap.im_len = XFS_FSB_TO_BB(mp, mp->m_blocks_per_cluster); - imap.im_boffset = XFS_INO_TO_OFFSET(mp, irec->ir_startino); + imap.im_len = XFS_FSB_TO_BB(mp, M_IGEO(mp)->blocks_per_cluster); + imap.im_boffset = XFS_INO_TO_OFFSET(mp, irec->ir_startino) << + mp->m_sb.sb_inodelog; if (imap.im_boffset != 0 && cluster_base != 0) { ASSERT(imap.im_boffset == 0 || cluster_base == 0); @@ -275,12 +269,12 @@ xchk_iallocbt_check_cluster( /* If any part of this is a hole, skip it. */ if (ir_holemask) { xchk_xref_is_not_owned_by(bs->sc, agbno, - mp->m_blocks_per_cluster, + M_IGEO(mp)->blocks_per_cluster, &XFS_RMAP_OINFO_INODES); return 0; } - xchk_xref_is_owned_by(bs->sc, agbno, mp->m_blocks_per_cluster, + xchk_xref_is_owned_by(bs->sc, agbno, M_IGEO(mp)->blocks_per_cluster, &XFS_RMAP_OINFO_INODES); /* Grab the inode cluster buffer. */ @@ -332,7 +326,7 @@ xchk_iallocbt_check_clusters( */ for (cluster_base = 0; cluster_base < XFS_INODES_PER_CHUNK; - cluster_base += bs->sc->mp->m_inodes_per_cluster) { + cluster_base += M_IGEO(bs->sc->mp)->inodes_per_cluster) { error = xchk_iallocbt_check_cluster(bs, irec, cluster_base); if (error) break; @@ -354,6 +348,7 @@ xchk_iallocbt_rec_alignment( { struct xfs_mount *mp = bs->sc->mp; struct xchk_iallocbt *iabt = bs->private; + struct xfs_ino_geometry *igeo = M_IGEO(mp); /* * finobt records have different positioning requirements than inobt @@ -371,7 +366,7 @@ xchk_iallocbt_rec_alignment( unsigned int imask; imask = min_t(unsigned int, XFS_INODES_PER_CHUNK, - mp->m_cluster_align_inodes) - 1; + igeo->cluster_align_inodes) - 1; if (irec->ir_startino & imask) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); return; @@ -399,17 +394,17 @@ xchk_iallocbt_rec_alignment( } /* inobt records must be aligned to cluster and inoalignmnt size. */ - if (irec->ir_startino & (mp->m_cluster_align_inodes - 1)) { + if (irec->ir_startino & (igeo->cluster_align_inodes - 1)) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); return; } - if (irec->ir_startino & (mp->m_inodes_per_cluster - 1)) { + if (irec->ir_startino & (igeo->inodes_per_cluster - 1)) { xchk_btree_set_corrupt(bs->sc, bs->cur, 0); return; } - if (mp->m_inodes_per_cluster <= XFS_INODES_PER_CHUNK) + if (igeo->inodes_per_cluster <= XFS_INODES_PER_CHUNK) return; /* @@ -418,7 +413,7 @@ xchk_iallocbt_rec_alignment( * after this one. */ iabt->next_startino = irec->ir_startino + XFS_INODES_PER_CHUNK; - iabt->next_cluster_ino = irec->ir_startino + mp->m_inodes_per_cluster; + iabt->next_cluster_ino = irec->ir_startino + igeo->inodes_per_cluster; } /* Scrub an inobt/finobt record. */ diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c index e213efc194a1..6d483ab29e63 100644 --- a/fs/xfs/scrub/inode.c +++ b/fs/xfs/scrub/inode.c @@ -9,27 +9,17 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_icache.h" -#include "xfs_inode_buf.h" -#include "xfs_inode_fork.h" #include "xfs_ialloc.h" #include "xfs_da_format.h" #include "xfs_reflink.h" #include "xfs_rmap.h" -#include "xfs_bmap.h" #include "xfs_bmap_util.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" -#include "scrub/trace.h" /* * Grab total control of the inode metadata. It doesn't matter here if diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c index d5d197f1b80f..c962bd534690 100644 --- a/fs/xfs/scrub/parent.c +++ b/fs/xfs/scrub/parent.c @@ -9,21 +9,13 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" #include "xfs_icache.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" -#include "xfs_ialloc.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" -#include "scrub/trace.h" /* Set us up to scrub parents. */ int diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 5dfe2b5924db..0a33b4421c32 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -9,24 +9,13 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_inode_fork.h" -#include "xfs_alloc.h" -#include "xfs_bmap.h" #include "xfs_quota.h" #include "xfs_qm.h" -#include "xfs_dquot.h" -#include "xfs_dquot_item.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" -#include "scrub/trace.h" /* Convert a scrub type code to a DQ flag, or return 0 if error. */ static inline uint @@ -144,7 +133,7 @@ xchk_quota_item( if (bsoft > bhard) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); - if (ihard > mp->m_maxicount) + if (ihard > M_IGEO(mp)->maxicount) xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset); if (isoft > ihard) xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset); diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 708b4158eb90..93b3793bc5b3 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -7,22 +7,12 @@ #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" -#include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" -#include "xfs_alloc.h" #include "xfs_rmap.h" #include "xfs_refcount.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" -#include "scrub/trace.h" /* * Set us up to scrub reference count btrees. diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index eb358f0f5e0a..4cfeec57fb05 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -9,29 +9,21 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_icache.h" #include "xfs_alloc.h" #include "xfs_alloc_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" #include "xfs_rmap.h" #include "xfs_rmap_btree.h" -#include "xfs_refcount.h" #include "xfs_refcount_btree.h" #include "xfs_extent_busy.h" #include "xfs_ag_resv.h" -#include "xfs_trans_space.h" #include "xfs_quota.h" -#include "xfs_attr.h" -#include "xfs_reflink.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" @@ -357,7 +349,7 @@ xrep_init_btblock( bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, fsb), XFS_FSB_TO_BB(mp, 1), 0); xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); - xfs_btree_init_block(mp, bp, btnum, 0, 0, sc->sa.agno, 0); + xfs_btree_init_block(mp, bp, btnum, 0, 0, sc->sa.agno); xfs_trans_buf_set_type(tp, bp, XFS_BLFT_BTREE_BUF); xfs_trans_log_buf(tp, bp, 0, bp->b_length); bp->b_ops = ops; @@ -672,7 +664,7 @@ xrep_findroot_agfl_walk( { xfs_agblock_t *agbno = priv; - return (*agbno == bno) ? XFS_BTREE_QUERY_RANGE_ABORT : 0; + return (*agbno == bno) ? XFS_ITER_ABORT : 0; } /* Does this block match the btree information passed in? */ @@ -702,7 +694,7 @@ xrep_findroot_block( if (owner == XFS_RMAP_OWN_AG) { error = xfs_agfl_walk(mp, ri->agf, ri->agfl_bp, xrep_findroot_agfl_walk, &agbno); - if (error == XFS_BTREE_QUERY_RANGE_ABORT) + if (error == XFS_ITER_ABORT) return 0; if (error) return error; diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c index 92a140c5b55e..8d4cefd761c1 100644 --- a/fs/xfs/scrub/rmap.c +++ b/fs/xfs/scrub/rmap.c @@ -9,21 +9,12 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_btree.h" -#include "xfs_bit.h" -#include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" -#include "xfs_alloc.h" -#include "xfs_ialloc.h" #include "xfs_rmap.h" #include "xfs_refcount.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/btree.h" -#include "scrub/trace.h" /* * Set us up to scrub reverse mapping btrees. diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c index dbe115b075f7..c642bc206c41 100644 --- a/fs/xfs/scrub/rtbitmap.c +++ b/fs/xfs/scrub/rtbitmap.c @@ -9,19 +9,12 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_sb.h" -#include "xfs_alloc.h" #include "xfs_rtalloc.h" #include "xfs_inode.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" -#include "scrub/trace.h" /* Set us up with the realtime metadata locked. */ int diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index f630389ee176..15c8c5f3f688 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -9,36 +9,16 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" #include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_icache.h" -#include "xfs_itable.h" -#include "xfs_alloc.h" -#include "xfs_alloc_btree.h" -#include "xfs_bmap.h" -#include "xfs_bmap_btree.h" -#include "xfs_ialloc.h" -#include "xfs_ialloc_btree.h" -#include "xfs_refcount.h" -#include "xfs_refcount_btree.h" -#include "xfs_rmap.h" -#include "xfs_rmap_btree.h" #include "xfs_quota.h" #include "xfs_qm.h" #include "xfs_errortag.h" #include "xfs_error.h" -#include "xfs_log.h" -#include "xfs_trans_priv.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" -#include "scrub/btree.h" #include "scrub/repair.h" #include "scrub/health.h" diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c index f7ebaa946999..99c0b1234c3c 100644 --- a/fs/xfs/scrub/symlink.c +++ b/fs/xfs/scrub/symlink.c @@ -9,19 +9,11 @@ #include "xfs_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_btree.h" -#include "xfs_bit.h" #include "xfs_log_format.h" -#include "xfs_trans.h" -#include "xfs_sb.h" #include "xfs_inode.h" -#include "xfs_inode_fork.h" #include "xfs_symlink.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" #include "scrub/common.h" -#include "scrub/trace.h" /* Set us up to scrub a symbolic link. */ int diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 96feaf8dcdec..9eaab2eb5ed3 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -10,15 +10,9 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_da_format.h" #include "xfs_inode.h" #include "xfs_btree.h" -#include "xfs_trans.h" -#include "xfs_bit.h" -#include "scrub/xfs_scrub.h" #include "scrub/scrub.h" -#include "scrub/common.h" /* Figure out which block the btree cursor was pointing to. */ static inline xfs_fsblock_t diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index 8039e35147dd..cbda40d40326 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -4,16 +4,14 @@ * All Rights Reserved. */ #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" -#include "xfs_acl.h" #include "xfs_attr.h" #include "xfs_trace.h" -#include <linux/slab.h> -#include <linux/xattr.h> #include <linux/posix_acl_xattr.h> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index a6f0f4761a37..761248ee2778 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -12,16 +12,11 @@ #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" -#include "xfs_alloc.h" -#include "xfs_error.h" #include "xfs_iomap.h" #include "xfs_trace.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" -#include "xfs_bmap_btree.h" #include "xfs_reflink.h" -#include <linux/writeback.h> /* * structure owned by writepages passed to individual writepage calls @@ -138,8 +133,7 @@ xfs_setfilesize_trans_alloc( struct xfs_trans *tp; int error; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, - XFS_TRANS_NOFS, &tp); + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp); if (error) return error; @@ -240,9 +234,17 @@ xfs_end_ioend( struct xfs_inode *ip = XFS_I(ioend->io_inode); xfs_off_t offset = ioend->io_offset; size_t size = ioend->io_size; + unsigned int nofs_flag; int error; /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + + /* * Just clean up the in-memory strutures if the fs has been shut down. */ if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { @@ -282,6 +284,8 @@ done: list_del_init(&ioend->io_list); xfs_destroy_ioend(ioend, error); } + + memalloc_nofs_restore(nofs_flag); } /* @@ -290,13 +294,9 @@ done: static bool xfs_ioend_can_merge( struct xfs_ioend *ioend, - int ioend_error, struct xfs_ioend *next) { - int next_error; - - next_error = blk_status_to_errno(next->io_bio->bi_status); - if (ioend_error != next_error) + if (ioend->io_bio->bi_status != next->io_bio->bi_status) return false; if ((ioend->io_fork == XFS_COW_FORK) ^ (next->io_fork == XFS_COW_FORK)) return false; @@ -305,11 +305,28 @@ xfs_ioend_can_merge( return false; if (ioend->io_offset + ioend->io_size != next->io_offset) return false; - if (xfs_ioend_is_append(ioend) != xfs_ioend_is_append(next)) - return false; return true; } +/* + * If the to be merged ioend has a preallocated transaction for file + * size updates we need to ensure the ioend it is merged into also + * has one. If it already has one we can simply cancel the transaction + * as it is guaranteed to be clean. + */ +static void +xfs_ioend_merge_append_transactions( + struct xfs_ioend *ioend, + struct xfs_ioend *next) +{ + if (!ioend->io_append_trans) { + ioend->io_append_trans = next->io_append_trans; + next->io_append_trans = NULL; + } else { + xfs_setfilesize_ioend(next, -ECANCELED); + } +} + /* Try to merge adjacent completions. */ STATIC void xfs_ioend_try_merge( @@ -317,25 +334,16 @@ xfs_ioend_try_merge( struct list_head *more_ioends) { struct xfs_ioend *next_ioend; - int ioend_error; - int error; - - if (list_empty(more_ioends)) - return; - - ioend_error = blk_status_to_errno(ioend->io_bio->bi_status); while (!list_empty(more_ioends)) { next_ioend = list_first_entry(more_ioends, struct xfs_ioend, io_list); - if (!xfs_ioend_can_merge(ioend, ioend_error, next_ioend)) + if (!xfs_ioend_can_merge(ioend, next_ioend)) break; list_move_tail(&next_ioend->io_list, &ioend->io_list); ioend->io_size += next_ioend->io_size; - if (ioend->io_append_trans) { - error = xfs_setfilesize_ioend(next_ioend, 1); - ASSERT(error == 1); - } + if (next_ioend->io_append_trans) + xfs_ioend_merge_append_transactions(ioend, next_ioend); } } @@ -626,7 +634,7 @@ allocate_blocks: * reference to the ioend to ensure that the ioend completion is only done once * all bios have been submitted and the ioend is really done. * - * If @fail is non-zero, it means that we have a situation where some part of + * If @status is non-zero, it means that we have a situation where some part of * the submission process has failed after we have marked paged for writeback * and unlocked them. In this situation, we need to fail the bio and ioend * rather than submit it to IO. This typically only happens on a filesystem @@ -638,21 +646,19 @@ xfs_submit_ioend( struct xfs_ioend *ioend, int status) { + unsigned int nofs_flag; + + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + /* Convert CoW extents to regular */ if (!status && ioend->io_fork == XFS_COW_FORK) { - /* - * Yuk. This can do memory allocation, but is not a - * transactional operation so everything is done in GFP_KERNEL - * context. That can deadlock, because we hold pages in - * writeback state and GFP_KERNEL allocations can block on them. - * Hence we must operate in nofs conditions here. - */ - unsigned nofs_flag; - - nofs_flag = memalloc_nofs_save(); status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode), ioend->io_offset, ioend->io_size); - memalloc_nofs_restore(nofs_flag); } /* Reserve log space if we might write beyond the on-disk inode size. */ @@ -663,9 +669,10 @@ xfs_submit_ioend( !ioend->io_append_trans) status = xfs_setfilesize_trans_alloc(ioend); + memalloc_nofs_restore(nofs_flag); + ioend->io_bio->bi_private = ioend; ioend->io_bio->bi_end_io = xfs_end_bio; - ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); /* * If we are failing the IO now, just mark the ioend with an @@ -679,7 +686,6 @@ xfs_submit_ioend( return status; } - ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint; submit_bio(ioend->io_bio); return 0; } @@ -691,7 +697,8 @@ xfs_alloc_ioend( xfs_exntst_t state, xfs_off_t offset, struct block_device *bdev, - sector_t sector) + sector_t sector, + struct writeback_control *wbc) { struct xfs_ioend *ioend; struct bio *bio; @@ -699,6 +706,9 @@ xfs_alloc_ioend( bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset); bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = sector; + bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); + bio->bi_write_hint = inode->i_write_hint; + wbc_init_bio(wbc, bio); ioend = container_of(bio, struct xfs_ioend, io_inline_bio); INIT_LIST_HEAD(&ioend->io_list); @@ -719,24 +729,22 @@ xfs_alloc_ioend( * so that the bi_private linkage is set up in the right direction for the * traversal in xfs_destroy_ioend(). */ -static void +static struct bio * xfs_chain_bio( - struct xfs_ioend *ioend, - struct writeback_control *wbc, - struct block_device *bdev, - sector_t sector) + struct bio *prev) { struct bio *new; new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); - bio_set_dev(new, bdev); - new->bi_iter.bi_sector = sector; - bio_chain(ioend->io_bio, new); - bio_get(ioend->io_bio); /* for xfs_destroy_ioend */ - ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); - ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint; - submit_bio(ioend->io_bio); - ioend->io_bio = new; + bio_copy_dev(new, prev);/* also copies over blkcg information */ + new->bi_iter.bi_sector = bio_end_sector(prev); + new->bi_opf = prev->bi_opf; + new->bi_write_hint = prev->bi_write_hint; + + bio_chain(prev, new); + bio_get(prev); /* for xfs_destroy_ioend */ + submit_bio(prev); + return new; } /* @@ -758,6 +766,7 @@ xfs_add_to_ioend( struct block_device *bdev = xfs_find_bdev_for_inode(inode); unsigned len = i_blocksize(inode); unsigned poff = offset & (PAGE_SIZE - 1); + bool merged, same_page = false; sector_t sector; sector = xfs_fsb_to_db(ip, wpc->imap.br_startblock) + @@ -771,18 +780,23 @@ xfs_add_to_ioend( if (wpc->ioend) list_add(&wpc->ioend->io_list, iolist); wpc->ioend = xfs_alloc_ioend(inode, wpc->fork, - wpc->imap.br_state, offset, bdev, sector); + wpc->imap.br_state, offset, bdev, sector, wbc); } - if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, true)) { - if (iop) - atomic_inc(&iop->write_count); - if (bio_full(wpc->ioend->io_bio)) - xfs_chain_bio(wpc->ioend, wbc, bdev, sector); + merged = __bio_try_merge_page(wpc->ioend->io_bio, page, len, poff, + &same_page); + + if (iop && !same_page) + atomic_inc(&iop->write_count); + + if (!merged) { + if (bio_full(wpc->ioend->io_bio, len)) + wpc->ioend->io_bio = xfs_chain_bio(wpc->ioend->io_bio); bio_add_page(wpc->ioend->io_bio, page, len, poff); } wpc->ioend->io_size += len; + wbc_account_io(wbc, page, len); } STATIC void diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index f62b03186c62..45a1ea240cbb 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -28,7 +28,6 @@ extern const struct address_space_operations xfs_dax_aops; int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size); -extern void xfs_count_page_state(struct page *, int *, int *); extern struct block_device *xfs_find_bdev_for_inode(struct inode *); extern struct dax_device *xfs_find_daxdev_for_inode(struct inode *); diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 228821b2ebe0..dc93c51c17de 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -15,18 +15,13 @@ #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_inode.h" -#include "xfs_alloc.h" #include "xfs_attr_remote.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap.h" #include "xfs_attr.h" #include "xfs_attr_leaf.h" -#include "xfs_error.h" #include "xfs_quota.h" -#include "xfs_trace.h" #include "xfs_dir2.h" -#include "xfs_defer.h" /* * Look at all the extents for this logical region, @@ -121,7 +116,7 @@ xfs_attr3_leaf_inactive( int size; int tmp; int i; - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c index 3d213a7394c5..58fc820a70c6 100644 --- a/fs/xfs/xfs_attr_list.c +++ b/fs/xfs/xfs_attr_list.c @@ -6,25 +6,20 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" #include "xfs_mount.h" #include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap.h" #include "xfs_attr.h" #include "xfs_attr_sf.h" -#include "xfs_attr_remote.h" #include "xfs_attr_leaf.h" #include "xfs_error.h" #include "xfs_trace.h" -#include "xfs_buf_item.h" -#include "xfs_cksum.h" #include "xfs_dir2.h" STATIC int diff --git a/fs/xfs/xfs_bio_io.c b/fs/xfs/xfs_bio_io.c new file mode 100644 index 000000000000..e2148f2d5d6b --- /dev/null +++ b/fs/xfs/xfs_bio_io.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Christoph Hellwig. + */ +#include "xfs.h" + +static inline unsigned int bio_max_vecs(unsigned int count) +{ + return min_t(unsigned, howmany(count, PAGE_SIZE), BIO_MAX_PAGES); +} + +int +xfs_rw_bdev( + struct block_device *bdev, + sector_t sector, + unsigned int count, + char *data, + unsigned int op) + +{ + unsigned int is_vmalloc = is_vmalloc_addr(data); + unsigned int left = count; + int error; + struct bio *bio; + + if (is_vmalloc && op == REQ_OP_WRITE) + flush_kernel_vmap_range(data, count); + + bio = bio_alloc(GFP_KERNEL, bio_max_vecs(left)); + bio_set_dev(bio, bdev); + bio->bi_iter.bi_sector = sector; + bio->bi_opf = op | REQ_META | REQ_SYNC; + + do { + struct page *page = kmem_to_page(data); + unsigned int off = offset_in_page(data); + unsigned int len = min_t(unsigned, left, PAGE_SIZE - off); + + while (bio_add_page(bio, page, len, off) != len) { + struct bio *prev = bio; + + bio = bio_alloc(GFP_KERNEL, bio_max_vecs(left)); + bio_copy_dev(bio, prev); + bio->bi_iter.bi_sector = bio_end_sector(prev); + bio->bi_opf = prev->bi_opf; + bio_chain(prev, bio); + + submit_bio(prev); + } + + data += len; + left -= len; + } while (left > 0); + + error = submit_bio_wait(bio); + bio_put(bio); + + if (is_vmalloc && op == REQ_OP_READ) + invalidate_kernel_vmap_range(data, count); + return error; +} diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index ce45f066995e..9fa4a7ee8cfc 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -9,17 +9,16 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" +#include "xfs_shared.h" #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" -#include "xfs_buf_item.h" #include "xfs_bmap_item.h" #include "xfs_log.h" #include "xfs_bmap.h" #include "xfs_icache.h" -#include "xfs_trace.h" #include "xfs_bmap_btree.h" #include "xfs_trans_space.h" @@ -96,15 +95,6 @@ xfs_bui_item_format( } /* - * Pinning has no meaning for an bui item, so just return. - */ -STATIC void -xfs_bui_item_pin( - struct xfs_log_item *lip) -{ -} - -/* * The unpin operation is the last place an BUI is manipulated in the log. It is * either inserted in the AIL or aborted in the event of a log I/O error. In * either case, the BUI transaction has been successfully committed to make it @@ -123,71 +113,22 @@ xfs_bui_item_unpin( } /* - * BUI items have no locking or pushing. However, since BUIs are pulled from - * the AIL when their corresponding BUDs are committed to disk, their situation - * is very similar to being pinned. Return XFS_ITEM_PINNED so that the caller - * will eventually flush the log. This should help in getting the BUI out of - * the AIL. - */ -STATIC uint -xfs_bui_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) -{ - return XFS_ITEM_PINNED; -} - -/* * The BUI has been either committed or aborted if the transaction has been * cancelled. If the transaction was cancelled, an BUD isn't going to be * constructed and thus we free the BUI here directly. */ STATIC void -xfs_bui_item_unlock( +xfs_bui_item_release( struct xfs_log_item *lip) { - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) - xfs_bui_release(BUI_ITEM(lip)); -} - -/* - * The BUI is logged only once and cannot be moved in the log, so simply return - * the lsn at which it's been logged. - */ -STATIC xfs_lsn_t -xfs_bui_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ - return lsn; + xfs_bui_release(BUI_ITEM(lip)); } -/* - * The BUI dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ -STATIC void -xfs_bui_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ -} - -/* - * This is the ops vector shared by all bui log items. - */ static const struct xfs_item_ops xfs_bui_item_ops = { .iop_size = xfs_bui_item_size, .iop_format = xfs_bui_item_format, - .iop_pin = xfs_bui_item_pin, .iop_unpin = xfs_bui_item_unpin, - .iop_unlock = xfs_bui_item_unlock, - .iop_committed = xfs_bui_item_committed, - .iop_push = xfs_bui_item_push, - .iop_committing = xfs_bui_item_committing, + .iop_release = xfs_bui_item_release, }; /* @@ -249,126 +190,241 @@ xfs_bud_item_format( } /* - * Pinning has no meaning for an bud item, so just return. + * The BUD is either committed or aborted if the transaction is cancelled. If + * the transaction is cancelled, drop our reference to the BUI and free the + * BUD. */ STATIC void -xfs_bud_item_pin( +xfs_bud_item_release( struct xfs_log_item *lip) { + struct xfs_bud_log_item *budp = BUD_ITEM(lip); + + xfs_bui_release(budp->bud_buip); + kmem_zone_free(xfs_bud_zone, budp); } -/* - * Since pinning has no meaning for an bud item, unpinning does - * not either. - */ -STATIC void -xfs_bud_item_unpin( - struct xfs_log_item *lip, - int remove) +static const struct xfs_item_ops xfs_bud_item_ops = { + .flags = XFS_ITEM_RELEASE_WHEN_COMMITTED, + .iop_size = xfs_bud_item_size, + .iop_format = xfs_bud_item_format, + .iop_release = xfs_bud_item_release, +}; + +static struct xfs_bud_log_item * +xfs_trans_get_bud( + struct xfs_trans *tp, + struct xfs_bui_log_item *buip) { + struct xfs_bud_log_item *budp; + + budp = kmem_zone_zalloc(xfs_bud_zone, KM_SLEEP); + xfs_log_item_init(tp->t_mountp, &budp->bud_item, XFS_LI_BUD, + &xfs_bud_item_ops); + budp->bud_buip = buip; + budp->bud_format.bud_bui_id = buip->bui_format.bui_id; + + xfs_trans_add_item(tp, &budp->bud_item); + return budp; } /* - * There isn't much you can do to push on an bud item. It is simply stuck - * waiting for the log to be flushed to disk. + * Finish an bmap update and log it to the BUD. Note that the + * transaction is marked dirty regardless of whether the bmap update + * succeeds or fails to support the BUI/BUD lifecycle rules. */ -STATIC uint -xfs_bud_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) +static int +xfs_trans_log_finish_bmap_update( + struct xfs_trans *tp, + struct xfs_bud_log_item *budp, + enum xfs_bmap_intent_type type, + struct xfs_inode *ip, + int whichfork, + xfs_fileoff_t startoff, + xfs_fsblock_t startblock, + xfs_filblks_t *blockcount, + xfs_exntst_t state) { - return XFS_ITEM_PINNED; + int error; + + error = xfs_bmap_finish_one(tp, ip, type, whichfork, startoff, + startblock, blockcount, state); + + /* + * Mark the transaction dirty, even on error. This ensures the + * transaction is aborted, which: + * + * 1.) releases the BUI and frees the BUD + * 2.) shuts down the filesystem + */ + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags); + + return error; } -/* - * The BUD is either committed or aborted if the transaction is cancelled. If - * the transaction is cancelled, drop our reference to the BUI and free the - * BUD. - */ -STATIC void -xfs_bud_item_unlock( - struct xfs_log_item *lip) +/* Sort bmap intents by inode. */ +static int +xfs_bmap_update_diff_items( + void *priv, + struct list_head *a, + struct list_head *b) { - struct xfs_bud_log_item *budp = BUD_ITEM(lip); + struct xfs_bmap_intent *ba; + struct xfs_bmap_intent *bb; - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) { - xfs_bui_release(budp->bud_buip); - kmem_zone_free(xfs_bud_zone, budp); - } + ba = container_of(a, struct xfs_bmap_intent, bi_list); + bb = container_of(b, struct xfs_bmap_intent, bi_list); + return ba->bi_owner->i_ino - bb->bi_owner->i_ino; } -/* - * When the bud item is committed to disk, all we need to do is delete our - * reference to our partner bui item and then free ourselves. Since we're - * freeing ourselves we must return -1 to keep the transaction code from - * further referencing this item. - */ -STATIC xfs_lsn_t -xfs_bud_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +/* Get an BUI. */ +STATIC void * +xfs_bmap_update_create_intent( + struct xfs_trans *tp, + unsigned int count) { - struct xfs_bud_log_item *budp = BUD_ITEM(lip); + struct xfs_bui_log_item *buip; + + ASSERT(count == XFS_BUI_MAX_FAST_EXTENTS); + ASSERT(tp != NULL); + + buip = xfs_bui_init(tp->t_mountp); + ASSERT(buip != NULL); /* - * Drop the BUI reference regardless of whether the BUD has been - * aborted. Once the BUD transaction is constructed, it is the sole - * responsibility of the BUD to release the BUI (even if the BUI is - * aborted due to log I/O error). + * Get a log_item_desc to point at the new item. */ - xfs_bui_release(budp->bud_buip); - kmem_zone_free(xfs_bud_zone, budp); + xfs_trans_add_item(tp, &buip->bui_item); + return buip; +} - return (xfs_lsn_t)-1; +/* Set the map extent flags for this mapping. */ +static void +xfs_trans_set_bmap_flags( + struct xfs_map_extent *bmap, + enum xfs_bmap_intent_type type, + int whichfork, + xfs_exntst_t state) +{ + bmap->me_flags = 0; + switch (type) { + case XFS_BMAP_MAP: + case XFS_BMAP_UNMAP: + bmap->me_flags = type; + break; + default: + ASSERT(0); + } + if (state == XFS_EXT_UNWRITTEN) + bmap->me_flags |= XFS_BMAP_EXTENT_UNWRITTEN; + if (whichfork == XFS_ATTR_FORK) + bmap->me_flags |= XFS_BMAP_EXTENT_ATTR_FORK; } -/* - * The BUD dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ +/* Log bmap updates in the intent item. */ STATIC void -xfs_bud_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +xfs_bmap_update_log_item( + struct xfs_trans *tp, + void *intent, + struct list_head *item) { + struct xfs_bui_log_item *buip = intent; + struct xfs_bmap_intent *bmap; + uint next_extent; + struct xfs_map_extent *map; + + bmap = container_of(item, struct xfs_bmap_intent, bi_list); + + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags); + + /* + * atomic_inc_return gives us the value after the increment; + * we want to use it as an array index so we need to subtract 1 from + * it. + */ + next_extent = atomic_inc_return(&buip->bui_next_extent) - 1; + ASSERT(next_extent < buip->bui_format.bui_nextents); + map = &buip->bui_format.bui_extents[next_extent]; + map->me_owner = bmap->bi_owner->i_ino; + map->me_startblock = bmap->bi_bmap.br_startblock; + map->me_startoff = bmap->bi_bmap.br_startoff; + map->me_len = bmap->bi_bmap.br_blockcount; + xfs_trans_set_bmap_flags(map, bmap->bi_type, bmap->bi_whichfork, + bmap->bi_bmap.br_state); } -/* - * This is the ops vector shared by all bud log items. - */ -static const struct xfs_item_ops xfs_bud_item_ops = { - .iop_size = xfs_bud_item_size, - .iop_format = xfs_bud_item_format, - .iop_pin = xfs_bud_item_pin, - .iop_unpin = xfs_bud_item_unpin, - .iop_unlock = xfs_bud_item_unlock, - .iop_committed = xfs_bud_item_committed, - .iop_push = xfs_bud_item_push, - .iop_committing = xfs_bud_item_committing, -}; +/* Get an BUD so we can process all the deferred rmap updates. */ +STATIC void * +xfs_bmap_update_create_done( + struct xfs_trans *tp, + void *intent, + unsigned int count) +{ + return xfs_trans_get_bud(tp, intent); +} -/* - * Allocate and initialize an bud item with the given number of extents. - */ -struct xfs_bud_log_item * -xfs_bud_init( - struct xfs_mount *mp, - struct xfs_bui_log_item *buip) +/* Process a deferred rmap update. */ +STATIC int +xfs_bmap_update_finish_item( + struct xfs_trans *tp, + struct list_head *item, + void *done_item, + void **state) +{ + struct xfs_bmap_intent *bmap; + xfs_filblks_t count; + int error; + + bmap = container_of(item, struct xfs_bmap_intent, bi_list); + count = bmap->bi_bmap.br_blockcount; + error = xfs_trans_log_finish_bmap_update(tp, done_item, + bmap->bi_type, + bmap->bi_owner, bmap->bi_whichfork, + bmap->bi_bmap.br_startoff, + bmap->bi_bmap.br_startblock, + &count, + bmap->bi_bmap.br_state); + if (!error && count > 0) { + ASSERT(bmap->bi_type == XFS_BMAP_UNMAP); + bmap->bi_bmap.br_blockcount = count; + return -EAGAIN; + } + kmem_free(bmap); + return error; +} +/* Abort all pending BUIs. */ +STATIC void +xfs_bmap_update_abort_intent( + void *intent) { - struct xfs_bud_log_item *budp; + xfs_bui_release(intent); +} - budp = kmem_zone_zalloc(xfs_bud_zone, KM_SLEEP); - xfs_log_item_init(mp, &budp->bud_item, XFS_LI_BUD, &xfs_bud_item_ops); - budp->bud_buip = buip; - budp->bud_format.bud_bui_id = buip->bui_format.bui_id; +/* Cancel a deferred rmap update. */ +STATIC void +xfs_bmap_update_cancel_item( + struct list_head *item) +{ + struct xfs_bmap_intent *bmap; - return budp; + bmap = container_of(item, struct xfs_bmap_intent, bi_list); + kmem_free(bmap); } +const struct xfs_defer_op_type xfs_bmap_update_defer_type = { + .max_items = XFS_BUI_MAX_FAST_EXTENTS, + .diff_items = xfs_bmap_update_diff_items, + .create_intent = xfs_bmap_update_create_intent, + .abort_intent = xfs_bmap_update_abort_intent, + .log_item = xfs_bmap_update_log_item, + .create_done = xfs_bmap_update_create_done, + .finish_item = xfs_bmap_update_finish_item, + .cancel_item = xfs_bmap_update_cancel_item, +}; + /* * Process a bmap update intent item that was recovered from the log. * We need to update some inode's bmbt. diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h index 89e043a88bb8..ad479cc73de8 100644 --- a/fs/xfs/xfs_bmap_item.h +++ b/fs/xfs/xfs_bmap_item.h @@ -75,8 +75,6 @@ extern struct kmem_zone *xfs_bui_zone; extern struct kmem_zone *xfs_bud_zone; struct xfs_bui_log_item *xfs_bui_init(struct xfs_mount *); -struct xfs_bud_log_item *xfs_bud_init(struct xfs_mount *, - struct xfs_bui_log_item *); void xfs_bui_item_free(struct xfs_bui_log_item *); void xfs_bui_release(struct xfs_bui_log_item *); int xfs_bui_recover(struct xfs_trans *parent_tp, struct xfs_bui_log_item *buip); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 06d07f1e310b..98c6a7a71427 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -12,12 +12,10 @@ #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_da_format.h" #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_trans.h" -#include "xfs_extfree_item.h" #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" @@ -28,11 +26,8 @@ #include "xfs_trans_space.h" #include "xfs_trace.h" #include "xfs_icache.h" -#include "xfs_log.h" -#include "xfs_rmap_btree.h" #include "xfs_iomap.h" #include "xfs_reflink.h" -#include "xfs_refcount.h" /* Kernel only BMAP related definitions and functions */ @@ -276,7 +271,7 @@ xfs_bmap_count_tree( struct xfs_btree_block *block, *nextblock; int numrecs; - error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF, + error = xfs_btree_read_bufl(mp, tp, bno, &bp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) return error; @@ -287,7 +282,7 @@ xfs_bmap_count_tree( /* Not at node above leaves, count this level of nodes */ nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib); while (nextbno != NULLFSBLOCK) { - error = xfs_btree_read_bufl(mp, tp, nextbno, 0, &nbp, + error = xfs_btree_read_bufl(mp, tp, nextbno, &nbp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) @@ -321,7 +316,7 @@ xfs_bmap_count_tree( if (nextbno == NULLFSBLOCK) break; bno = nextbno; - error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, + error = xfs_btree_read_bufl(mp, tp, bno, &bp, XFS_BMAP_BTREE_REF, &xfs_bmbt_buf_ops); if (error) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 548344e25128..ca0849043f54 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -4,24 +4,9 @@ * All Rights Reserved. */ #include "xfs.h" -#include <linux/stddef.h> -#include <linux/errno.h> -#include <linux/gfp.h> -#include <linux/pagemap.h> -#include <linux/init.h> -#include <linux/vmalloc.h> -#include <linux/bio.h> -#include <linux/sysctl.h> -#include <linux/proc_fs.h> -#include <linux/workqueue.h> -#include <linux/percpu.h> -#include <linux/blkdev.h> -#include <linux/hash.h> -#include <linux/kthread.h> -#include <linux/migrate.h> #include <linux/backing-dev.h> -#include <linux/freezer.h> +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" @@ -213,7 +198,7 @@ xfs_buf_free_maps( } } -struct xfs_buf * +static struct xfs_buf * _xfs_buf_alloc( struct xfs_buftarg *target, struct xfs_buf_map *map, @@ -243,6 +228,7 @@ _xfs_buf_alloc( sema_init(&bp->b_sema, 0); /* held, no waiters */ spin_lock_init(&bp->b_lock); bp->b_target = target; + bp->b_mount = target->bt_mount; bp->b_flags = flags; /* @@ -263,12 +249,11 @@ _xfs_buf_alloc( bp->b_maps[i].bm_len = map[i].bm_len; bp->b_length += map[i].bm_len; } - bp->b_io_length = bp->b_length; atomic_set(&bp->b_pin_count, 0); init_waitqueue_head(&bp->b_waiters); - XFS_STATS_INC(target->bt_mount, xb_create); + XFS_STATS_INC(bp->b_mount, xb_create); trace_xfs_buf_init(bp, _RET_IP_); return bp; @@ -425,12 +410,12 @@ retry: current->comm, current->pid, __func__, gfp_mask); - XFS_STATS_INC(bp->b_target->bt_mount, xb_page_retries); + XFS_STATS_INC(bp->b_mount, xb_page_retries); congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } - XFS_STATS_INC(bp->b_target->bt_mount, xb_page_found); + XFS_STATS_INC(bp->b_mount, xb_page_found); nbytes = min_t(size_t, size, PAGE_SIZE - offset); size -= nbytes; @@ -909,83 +894,6 @@ xfs_buf_read_uncached( return 0; } -/* - * Return a buffer allocated as an empty buffer and associated to external - * memory via xfs_buf_associate_memory() back to it's empty state. - */ -void -xfs_buf_set_empty( - struct xfs_buf *bp, - size_t numblks) -{ - if (bp->b_pages) - _xfs_buf_free_pages(bp); - - bp->b_pages = NULL; - bp->b_page_count = 0; - bp->b_addr = NULL; - bp->b_length = numblks; - bp->b_io_length = numblks; - - ASSERT(bp->b_map_count == 1); - bp->b_bn = XFS_BUF_DADDR_NULL; - bp->b_maps[0].bm_bn = XFS_BUF_DADDR_NULL; - bp->b_maps[0].bm_len = bp->b_length; -} - -static inline struct page * -mem_to_page( - void *addr) -{ - if ((!is_vmalloc_addr(addr))) { - return virt_to_page(addr); - } else { - return vmalloc_to_page(addr); - } -} - -int -xfs_buf_associate_memory( - xfs_buf_t *bp, - void *mem, - size_t len) -{ - int rval; - int i = 0; - unsigned long pageaddr; - unsigned long offset; - size_t buflen; - int page_count; - - pageaddr = (unsigned long)mem & PAGE_MASK; - offset = (unsigned long)mem - pageaddr; - buflen = PAGE_ALIGN(len + offset); - page_count = buflen >> PAGE_SHIFT; - - /* Free any previous set of page pointers */ - if (bp->b_pages) - _xfs_buf_free_pages(bp); - - bp->b_pages = NULL; - bp->b_addr = mem; - - rval = _xfs_buf_get_pages(bp, page_count); - if (rval) - return rval; - - bp->b_offset = offset; - - for (i = 0; i < bp->b_page_count; i++) { - bp->b_pages[i] = mem_to_page((void *)pageaddr); - pageaddr += PAGE_SIZE; - } - - bp->b_io_length = BTOBB(len); - bp->b_length = BTOBB(buflen); - - return 0; -} - xfs_buf_t * xfs_buf_get_uncached( struct xfs_buftarg *target, @@ -1180,7 +1088,7 @@ xfs_buf_lock( trace_xfs_buf_lock(bp, _RET_IP_); if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE)) - xfs_log_force(bp->b_target->bt_mount, 0); + xfs_log_force(bp->b_mount, 0); down(&bp->b_sema); trace_xfs_buf_lock_done(bp, _RET_IP_); @@ -1269,7 +1177,7 @@ xfs_buf_ioend_async( struct xfs_buf *bp) { INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work); - queue_work(bp->b_ioend_wq, &bp->b_ioend_work); + queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work); } void @@ -1288,7 +1196,7 @@ xfs_buf_ioerror_alert( struct xfs_buf *bp, const char *func) { - xfs_alert(bp->b_target->bt_mount, + xfs_alert(bp->b_mount, "metadata I/O error in \"%s\" at daddr 0x%llx len %d error %d", func, (uint64_t)XFS_BUF_ADDR(bp), bp->b_length, -bp->b_error); @@ -1307,10 +1215,8 @@ xfs_bwrite( XBF_WRITE_FAIL | XBF_DONE); error = xfs_buf_submit(bp); - if (error) { - xfs_force_shutdown(bp->b_target->bt_mount, - SHUTDOWN_META_IO_ERROR); - } + if (error) + xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR); return error; } @@ -1436,21 +1342,8 @@ _xfs_buf_ioapply( */ bp->b_error = 0; - /* - * Initialize the I/O completion workqueue if we haven't yet or the - * submitter has not opted to specify a custom one. - */ - if (!bp->b_ioend_wq) - bp->b_ioend_wq = bp->b_target->bt_mount->m_buf_workqueue; - if (bp->b_flags & XBF_WRITE) { op = REQ_OP_WRITE; - if (bp->b_flags & XBF_SYNCIO) - op_flags = REQ_SYNC; - if (bp->b_flags & XBF_FUA) - op_flags |= REQ_FUA; - if (bp->b_flags & XBF_FLUSH) - op_flags |= REQ_PREFLUSH; /* * Run the write verifier callback function if it exists. If @@ -1460,12 +1353,12 @@ _xfs_buf_ioapply( if (bp->b_ops) { bp->b_ops->verify_write(bp); if (bp->b_error) { - xfs_force_shutdown(bp->b_target->bt_mount, + xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE); return; } } else if (bp->b_bn != XFS_BUF_DADDR_NULL) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; /* * non-crc filesystems don't attach verifiers during @@ -1497,7 +1390,7 @@ _xfs_buf_ioapply( * subsequent call. */ offset = bp->b_offset; - size = BBTOB(bp->b_io_length); + size = BBTOB(bp->b_length); blk_start_plug(&plug); for (i = 0; i < bp->b_map_count; i++) { xfs_buf_ioapply_map(bp, i, &offset, &size, op, op_flags); @@ -1543,7 +1436,7 @@ __xfs_buf_submit( ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); /* on shutdown we stale and complete the buffer immediately */ - if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) { + if (XFS_FORCED_SHUTDOWN(bp->b_mount)) { xfs_buf_ioerror(bp, -EIO); bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); @@ -1613,16 +1506,11 @@ xfs_buf_offset( return page_address(page) + (offset & (PAGE_SIZE-1)); } -/* - * Move data into or out of a buffer. - */ void -xfs_buf_iomove( - xfs_buf_t *bp, /* buffer to process */ - size_t boff, /* starting buffer offset */ - size_t bsize, /* length to copy */ - void *data, /* data address */ - xfs_buf_rw_t mode) /* read/write/zero flag */ +xfs_buf_zero( + struct xfs_buf *bp, + size_t boff, + size_t bsize) { size_t bend; @@ -1635,23 +1523,13 @@ xfs_buf_iomove( page_offset = (boff + bp->b_offset) & ~PAGE_MASK; page = bp->b_pages[page_index]; csize = min_t(size_t, PAGE_SIZE - page_offset, - BBTOB(bp->b_io_length) - boff); + BBTOB(bp->b_length) - boff); ASSERT((csize + page_offset) <= PAGE_SIZE); - switch (mode) { - case XBRW_ZERO: - memset(page_address(page) + page_offset, 0, csize); - break; - case XBRW_READ: - memcpy(data, page_address(page) + page_offset, csize); - break; - case XBRW_WRITE: - memcpy(page_address(page) + page_offset, data, csize); - } + memset(page_address(page) + page_offset, 0, csize); boff += csize; - data += csize; } } @@ -2198,8 +2076,7 @@ void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref) * This allows userspace to disrupt buffer caching for debug/testing * purposes. */ - if (XFS_TEST_ERROR(false, bp->b_target->bt_mount, - XFS_ERRTAG_BUF_LRU_REF)) + if (XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_LRU_REF)) lru_ref = 0; atomic_set(&bp->b_lru_ref, lru_ref); @@ -2215,7 +2092,7 @@ xfs_verify_magic( struct xfs_buf *bp, __be32 dmagic) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; int idx; idx = xfs_sb_version_hascrc(&mp->m_sb); @@ -2233,7 +2110,7 @@ xfs_verify_magic16( struct xfs_buf *bp, __be16 dmagic) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; int idx; idx = xfs_sb_version_hascrc(&mp->m_sb); diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index d0b96e071cec..c6e57a3f409e 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -21,12 +21,6 @@ #define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) -typedef enum { - XBRW_READ = 1, /* transfer into target memory */ - XBRW_WRITE = 2, /* transfer from target memory */ - XBRW_ZERO = 3, /* Zero target memory */ -} xfs_buf_rw_t; - #define XBF_READ (1 << 0) /* buffer intended for reading from device */ #define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ #define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ @@ -34,12 +28,7 @@ typedef enum { #define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ #define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ #define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ -#define XBF_WRITE_FAIL (1 << 24)/* async writes have failed on this buffer */ - -/* I/O hints for the BIO layer */ -#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ -#define XBF_FUA (1 << 11)/* force cache write through mode */ -#define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */ +#define XBF_WRITE_FAIL (1 << 7) /* async writes have failed on this buffer */ /* flags used only as arguments to access routines */ #define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */ @@ -49,7 +38,6 @@ typedef enum { #define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ #define _XBF_KMEM (1 << 21)/* backed by heap memory */ #define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ -#define _XBF_COMPOUND (1 << 23)/* compound buffer */ typedef unsigned int xfs_buf_flags_t; @@ -62,15 +50,11 @@ typedef unsigned int xfs_buf_flags_t; { XBF_DONE, "DONE" }, \ { XBF_STALE, "STALE" }, \ { XBF_WRITE_FAIL, "WRITE_FAIL" }, \ - { XBF_SYNCIO, "SYNCIO" }, \ - { XBF_FUA, "FUA" }, \ - { XBF_FLUSH, "FLUSH" }, \ { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\ { XBF_UNMAPPED, "UNMAPPED" }, /* ditto */\ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ - { _XBF_DELWRI_Q, "DELWRI_Q" }, \ - { _XBF_COMPOUND, "COMPOUND" } + { _XBF_DELWRI_Q, "DELWRI_Q" } /* @@ -161,13 +145,13 @@ typedef struct xfs_buf { wait_queue_head_t b_waiters; /* unpin waiters */ 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) */ void *b_addr; /* virtual address of buffer */ struct work_struct b_ioend_work; - struct workqueue_struct *b_ioend_wq; /* I/O completion wq */ xfs_buf_iodone_t b_iodone; /* I/O completion function */ struct completion b_iowait; /* queue for I/O waiters */ - void *b_log_item; + struct xfs_buf_log_item *b_log_item; struct list_head b_li_list; /* Log items list head */ struct xfs_trans *b_transp; struct page **b_pages; /* array of page pointers */ @@ -175,7 +159,6 @@ typedef struct xfs_buf { struct xfs_buf_map *b_maps; /* compound buffer map */ struct xfs_buf_map __b_map; /* inline compound buffer map */ int b_map_count; - int b_io_length; /* IO size in BBs */ atomic_t b_pin_count; /* pin count */ atomic_t b_io_remaining; /* #outstanding I/O requests */ unsigned int b_page_count; /* size of page array */ @@ -209,21 +192,6 @@ struct xfs_buf *xfs_buf_incore(struct xfs_buftarg *target, xfs_daddr_t blkno, size_t numblks, xfs_buf_flags_t flags); -struct xfs_buf *_xfs_buf_alloc(struct xfs_buftarg *target, - struct xfs_buf_map *map, int nmaps, - xfs_buf_flags_t flags); - -static inline struct xfs_buf * -xfs_buf_alloc( - struct xfs_buftarg *target, - xfs_daddr_t blkno, - size_t numblks, - xfs_buf_flags_t flags) -{ - DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); - return _xfs_buf_alloc(target, &map, 1, flags); -} - struct xfs_buf *xfs_buf_get_map(struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, xfs_buf_flags_t flags); @@ -239,11 +207,10 @@ static inline struct xfs_buf * xfs_buf_get( struct xfs_buftarg *target, xfs_daddr_t blkno, - size_t numblks, - xfs_buf_flags_t flags) + size_t numblks) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); - return xfs_buf_get_map(target, &map, 1, flags); + return xfs_buf_get_map(target, &map, 1, 0); } static inline struct xfs_buf * @@ -269,9 +236,6 @@ xfs_buf_readahead( return xfs_buf_readahead_map(target, &map, 1, ops); } -void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks); -int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length); - struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, int flags); int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr, @@ -305,10 +269,7 @@ static inline int xfs_buf_submit(struct xfs_buf *bp) return __xfs_buf_submit(bp, wait); } -extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, - xfs_buf_rw_t); -#define xfs_buf_zero(bp, off, len) \ - xfs_buf_iomove((bp), (off), (len), NULL, XBRW_ZERO) +void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize); /* Buffer Utility Routines */ extern void *xfs_buf_offset(struct xfs_buf *, size_t); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 65b32acfa0f6..7dcaec54a20b 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -5,19 +5,17 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" -#include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_trans_priv.h" -#include "xfs_error.h" #include "xfs_trace.h" #include "xfs_log.h" -#include "xfs_inode.h" kmem_zone_t *xfs_buf_item_zone; @@ -520,7 +518,7 @@ xfs_buf_item_push( /* has a previous flush failed due to IO errors? */ if ((bp->b_flags & XBF_WRITE_FAIL) && ___ratelimit(&xfs_buf_write_fail_rl_state, "XFS: Failing async write")) { - xfs_warn(bp->b_target->bt_mount, + xfs_warn(bp->b_mount, "Failing async write on buffer block 0x%llx. Retrying async write.", (long long)bp->b_bn); } @@ -594,7 +592,7 @@ xfs_buf_item_put( * free the item. */ STATIC void -xfs_buf_item_unlock( +xfs_buf_item_release( struct xfs_log_item *lip) { struct xfs_buf_log_item *bip = BUF_ITEM(lip); @@ -609,7 +607,7 @@ xfs_buf_item_unlock( &lip->li_flags); #endif - trace_xfs_buf_item_unlock(bip); + trace_xfs_buf_item_release(bip); /* * The bli dirty state should match whether the blf has logged segments @@ -639,6 +637,14 @@ xfs_buf_item_unlock( xfs_buf_relse(bp); } +STATIC void +xfs_buf_item_committing( + struct xfs_log_item *lip, + xfs_lsn_t commit_lsn) +{ + return xfs_buf_item_release(lip); +} + /* * This is called to find out where the oldest active copy of the * buf log item in the on disk log resides now that the last log @@ -671,25 +677,15 @@ xfs_buf_item_committed( return lsn; } -STATIC void -xfs_buf_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t commit_lsn) -{ -} - -/* - * This is the ops vector shared by all buf log items. - */ static const struct xfs_item_ops xfs_buf_item_ops = { .iop_size = xfs_buf_item_size, .iop_format = xfs_buf_item_format, .iop_pin = xfs_buf_item_pin, .iop_unpin = xfs_buf_item_unpin, - .iop_unlock = xfs_buf_item_unlock, + .iop_release = xfs_buf_item_release, + .iop_committing = xfs_buf_item_committing, .iop_committed = xfs_buf_item_committed, .iop_push = xfs_buf_item_push, - .iop_committing = xfs_buf_item_committing }; STATIC int @@ -743,7 +739,7 @@ xfs_buf_item_init( * this buffer. If we do already have one, there is * nothing to do here so return. */ - ASSERT(bp->b_target->bt_mount == mp); + ASSERT(bp->b_mount == mp); if (bip) { ASSERT(bip->bli_item.li_type == XFS_LI_BUF); ASSERT(!bp->b_transp); @@ -980,9 +976,9 @@ xfs_buf_item_relse( */ void xfs_buf_attach_iodone( - xfs_buf_t *bp, - void (*cb)(xfs_buf_t *, xfs_log_item_t *), - xfs_log_item_t *lip) + struct xfs_buf *bp, + void (*cb)(struct xfs_buf *, struct xfs_log_item *), + struct xfs_log_item *lip) { ASSERT(xfs_buf_islocked(bp)); diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index 90f65f891fab..4a054b11011a 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -39,7 +39,7 @@ struct xfs_buf_log_item; * locked, and which 128 byte chunks of the buffer are dirty. */ struct xfs_buf_log_item { - xfs_log_item_t bli_item; /* common item structure */ + struct xfs_log_item bli_item; /* common item structure */ struct xfs_buf *bli_buf; /* real buffer pointer */ unsigned int bli_flags; /* misc flags */ unsigned int bli_recur; /* lock recursion count */ @@ -55,8 +55,8 @@ bool xfs_buf_item_put(struct xfs_buf_log_item *); void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint); bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_attach_iodone(struct xfs_buf *, - void(*)(struct xfs_buf *, xfs_log_item_t *), - xfs_log_item_t *); + void(*)(struct xfs_buf *, struct xfs_log_item *), + struct xfs_log_item *); void xfs_buf_iodone_callbacks(struct xfs_buf *); void xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *); bool xfs_buf_resubmit_failed_buffers(struct xfs_buf *, diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c index 5142e64e2345..283df898dd9f 100644 --- a/fs/xfs/xfs_dir2_readdir.c +++ b/fs/xfs/xfs_dir2_readdir.c @@ -6,17 +6,14 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" -#include "xfs_error.h" #include "xfs_trace.h" #include "xfs_bmap.h" #include "xfs_trans.h" diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index d0df0ed50f4b..8ec7aab89044 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -4,19 +4,17 @@ * All Rights Reserved. */ #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_quota.h" -#include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_alloc_btree.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_extent_busy.h" -#include "xfs_discard.h" #include "xfs_trace.h" #include "xfs_log.h" diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index a1af984e4913..fb1ad4483081 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -14,16 +14,12 @@ #include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" -#include "xfs_alloc.h" #include "xfs_quota.h" -#include "xfs_error.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_trans_space.h" #include "xfs_trans_priv.h" #include "xfs_qm.h" -#include "xfs_cksum.h" #include "xfs_trace.h" #include "xfs_log.h" #include "xfs_bmap_btree.h" @@ -1243,7 +1239,7 @@ xfs_qm_exit(void) /* * Iterate every dquot of a particular type. The caller must ensure that the * particular quota type is active. iter_fn can return negative error codes, - * or XFS_BTREE_QUERY_RANGE_ABORT to indicate that it wants to stop iterating. + * or XFS_ITER_ABORT to indicate that it wants to stop iterating. */ int xfs_qm_dqiterate( diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index 64bd8640f6e8..4fe85709d55d 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -34,7 +34,6 @@ typedef struct xfs_dquot { uint dq_flags; /* various flags (XFS_DQ_*) */ struct list_head q_lru; /* global free list of dquots */ struct xfs_mount*q_mount; /* filesystem this relates to */ - struct xfs_trans*q_transp; /* trans this belongs to currently */ uint q_nrefs; /* # active refs from inodes */ xfs_daddr_t q_blkno; /* blkno of dquot buffer */ int q_bufoffset; /* off of dq in buffer (# dquots) */ diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 7dedd17c4813..282ec5af293e 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -5,13 +5,13 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_quota.h" -#include "xfs_error.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_trans_priv.h" @@ -94,18 +94,6 @@ xfs_qm_dquot_logitem_unpin( wake_up(&dqp->q_pinwait); } -STATIC xfs_lsn_t -xfs_qm_dquot_logitem_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ - /* - * We always re-log the entire dquot when it becomes dirty, - * so, the latest copy _is_ the only one that matters. - */ - return lsn; -} - /* * This is called to wait for the given dquot to be unpinned. * Most of these pin/unpin routines are plagiarized from inode code. @@ -209,14 +197,8 @@ out_unlock: return rval; } -/* - * Unlock the dquot associated with the log item. - * Clear the fields of the dquot and dquot log item that - * are specific to the current transaction. If the - * hold flags is set, do not unlock the dquot. - */ STATIC void -xfs_qm_dquot_logitem_unlock( +xfs_qm_dquot_logitem_release( struct xfs_log_item *lip) { struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; @@ -224,11 +206,6 @@ xfs_qm_dquot_logitem_unlock( ASSERT(XFS_DQ_IS_LOCKED(dqp)); /* - * Clear the transaction pointer in the dquot - */ - dqp->q_transp = NULL; - - /* * dquots are never 'held' from getting unlocked at the end of * a transaction. Their locking and unlocking is hidden inside the * transaction layer, within trans_commit. Hence, no LI_HOLD flag @@ -237,30 +214,22 @@ xfs_qm_dquot_logitem_unlock( xfs_dqunlock(dqp); } -/* - * this needs to stamp an lsn into the dquot, I think. - * rpc's that look at user dquot's would then have to - * push on the dependency recorded in the dquot - */ STATIC void xfs_qm_dquot_logitem_committing( struct xfs_log_item *lip, - xfs_lsn_t lsn) + xfs_lsn_t commit_lsn) { + return xfs_qm_dquot_logitem_release(lip); } -/* - * This is the ops vector for dquots - */ static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_size = xfs_qm_dquot_logitem_size, .iop_format = xfs_qm_dquot_logitem_format, .iop_pin = xfs_qm_dquot_logitem_pin, .iop_unpin = xfs_qm_dquot_logitem_unpin, - .iop_unlock = xfs_qm_dquot_logitem_unlock, - .iop_committed = xfs_qm_dquot_logitem_committed, + .iop_release = xfs_qm_dquot_logitem_release, + .iop_committing = xfs_qm_dquot_logitem_committing, .iop_push = xfs_qm_dquot_logitem_push, - .iop_committing = xfs_qm_dquot_logitem_committing, .iop_error = xfs_dquot_item_error }; @@ -320,26 +289,6 @@ xfs_qm_qoff_logitem_format( } /* - * Pinning has no meaning for an quotaoff item, so just return. - */ -STATIC void -xfs_qm_qoff_logitem_pin( - struct xfs_log_item *lip) -{ -} - -/* - * Since pinning has no meaning for an quotaoff item, unpinning does - * not either. - */ -STATIC void -xfs_qm_qoff_logitem_unpin( - struct xfs_log_item *lip, - int remove) -{ -} - -/* * There isn't much you can do to push a quotaoff item. It is simply * stuck waiting for the log to be flushed to disk. */ @@ -351,28 +300,6 @@ xfs_qm_qoff_logitem_push( return XFS_ITEM_LOCKED; } -/* - * Quotaoff items have no locking or pushing, so return failure - * so that the caller doesn't bother with us. - */ -STATIC void -xfs_qm_qoff_logitem_unlock( - struct xfs_log_item *lip) -{ -} - -/* - * The quotaoff-start-item is logged only once and cannot be moved in the log, - * so simply return the lsn at which it's been logged. - */ -STATIC xfs_lsn_t -xfs_qm_qoff_logitem_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ - return lsn; -} - STATIC xfs_lsn_t xfs_qm_qoffend_logitem_committed( struct xfs_log_item *lip, @@ -396,50 +323,17 @@ xfs_qm_qoffend_logitem_committed( return (xfs_lsn_t)-1; } -/* - * XXX rcc - don't know quite what to do with this. I think we can - * just ignore it. The only time that isn't the case is if we allow - * the client to somehow see that quotas have been turned off in which - * we can't allow that to get back until the quotaoff hits the disk. - * So how would that happen? Also, do we need different routines for - * quotaoff start and quotaoff end? I suspect the answer is yes but - * to be sure, I need to look at the recovery code and see how quota off - * recovery is handled (do we roll forward or back or do something else). - * If we roll forwards or backwards, then we need two separate routines, - * one that does nothing and one that stamps in the lsn that matters - * (truly makes the quotaoff irrevocable). If we do something else, - * then maybe we don't need two. - */ -STATIC void -xfs_qm_qoff_logitem_committing( - struct xfs_log_item *lip, - xfs_lsn_t commit_lsn) -{ -} - static const struct xfs_item_ops xfs_qm_qoffend_logitem_ops = { .iop_size = xfs_qm_qoff_logitem_size, .iop_format = xfs_qm_qoff_logitem_format, - .iop_pin = xfs_qm_qoff_logitem_pin, - .iop_unpin = xfs_qm_qoff_logitem_unpin, - .iop_unlock = xfs_qm_qoff_logitem_unlock, .iop_committed = xfs_qm_qoffend_logitem_committed, .iop_push = xfs_qm_qoff_logitem_push, - .iop_committing = xfs_qm_qoff_logitem_committing }; -/* - * This is the ops vector shared by all quotaoff-start log items. - */ static const struct xfs_item_ops xfs_qm_qoff_logitem_ops = { .iop_size = xfs_qm_qoff_logitem_size, .iop_format = xfs_qm_qoff_logitem_format, - .iop_pin = xfs_qm_qoff_logitem_pin, - .iop_unpin = xfs_qm_qoff_logitem_unpin, - .iop_unlock = xfs_qm_qoff_logitem_unlock, - .iop_committed = xfs_qm_qoff_logitem_committed, .iop_push = xfs_qm_qoff_logitem_push, - .iop_committing = xfs_qm_qoff_logitem_committing }; /* diff --git a/fs/xfs/xfs_dquot_item.h b/fs/xfs/xfs_dquot_item.h index db9df710a308..1aed34ccdabc 100644 --- a/fs/xfs/xfs_dquot_item.h +++ b/fs/xfs/xfs_dquot_item.h @@ -12,13 +12,13 @@ struct xfs_mount; struct xfs_qoff_logitem; typedef struct xfs_dq_logitem { - xfs_log_item_t qli_item; /* common portion */ + struct xfs_log_item qli_item; /* common portion */ struct xfs_dquot *qli_dquot; /* dquot ptr */ xfs_lsn_t qli_flush_lsn; /* lsn at last flush */ } xfs_dq_logitem_t; typedef struct xfs_qoff_logitem { - xfs_log_item_t qql_item; /* common portion */ + struct xfs_log_item qql_item; /* common portion */ struct xfs_qoff_logitem *qql_start_lip; /* qoff-start logitem, if any */ unsigned int qql_flags; } xfs_qoff_logitem_t; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index a1e177f66404..544c9482a0ef 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -4,6 +4,7 @@ * All Rights Reserved. */ #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_fs.h" #include "xfs_log_format.h" @@ -353,7 +354,7 @@ xfs_buf_verifier_error( size_t bufsz, xfs_failaddr_t failaddr) { - struct xfs_mount *mp = bp->b_target->bt_mount; + struct xfs_mount *mp = bp->b_mount; xfs_failaddr_t fa; int sz; diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index f2284ceb129f..f1372f9046e3 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -4,18 +4,16 @@ * All Rights Reserved. */ #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_export.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_inode_item.h" -#include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_log.h" #include "xfs_pnfs.h" diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 74ddf66f4cfe..86f6512d6864 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -9,14 +9,18 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_bit.h" +#include "xfs_shared.h" #include "xfs_mount.h" +#include "xfs_defer.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" -#include "xfs_buf_item.h" #include "xfs_extfree_item.h" #include "xfs_log.h" #include "xfs_btree.h" #include "xfs_rmap.h" +#include "xfs_alloc.h" +#include "xfs_bmap.h" +#include "xfs_trace.h" kmem_zone_t *xfs_efi_zone; @@ -107,15 +111,6 @@ xfs_efi_item_format( /* - * Pinning has no meaning for an efi item, so just return. - */ -STATIC void -xfs_efi_item_pin( - struct xfs_log_item *lip) -{ -} - -/* * The unpin operation is the last place an EFI is manipulated in the log. It is * either inserted in the AIL or aborted in the event of a log I/O error. In * either case, the EFI transaction has been successfully committed to make it @@ -133,71 +128,22 @@ xfs_efi_item_unpin( } /* - * Efi items have no locking or pushing. However, since EFIs are pulled from - * the AIL when their corresponding EFDs are committed to disk, their situation - * is very similar to being pinned. Return XFS_ITEM_PINNED so that the caller - * will eventually flush the log. This should help in getting the EFI out of - * the AIL. - */ -STATIC uint -xfs_efi_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) -{ - return XFS_ITEM_PINNED; -} - -/* * The EFI has been either committed or aborted if the transaction has been * cancelled. If the transaction was cancelled, an EFD isn't going to be * constructed and thus we free the EFI here directly. */ STATIC void -xfs_efi_item_unlock( +xfs_efi_item_release( struct xfs_log_item *lip) { - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) - xfs_efi_release(EFI_ITEM(lip)); -} - -/* - * The EFI is logged only once and cannot be moved in the log, so simply return - * the lsn at which it's been logged. - */ -STATIC xfs_lsn_t -xfs_efi_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ - return lsn; -} - -/* - * The EFI dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ -STATIC void -xfs_efi_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ + xfs_efi_release(EFI_ITEM(lip)); } -/* - * This is the ops vector shared by all efi log items. - */ static const struct xfs_item_ops xfs_efi_item_ops = { .iop_size = xfs_efi_item_size, .iop_format = xfs_efi_item_format, - .iop_pin = xfs_efi_item_pin, .iop_unpin = xfs_efi_item_unpin, - .iop_unlock = xfs_efi_item_unlock, - .iop_committed = xfs_efi_item_committed, - .iop_push = xfs_efi_item_push, - .iop_committing = xfs_efi_item_committing + .iop_release = xfs_efi_item_release, }; @@ -349,136 +295,298 @@ xfs_efd_item_format( } /* - * Pinning has no meaning for an efd item, so just return. + * The EFD is either committed or aborted if the transaction is cancelled. If + * the transaction is cancelled, drop our reference to the EFI and free the EFD. */ STATIC void -xfs_efd_item_pin( +xfs_efd_item_release( struct xfs_log_item *lip) { + struct xfs_efd_log_item *efdp = EFD_ITEM(lip); + + xfs_efi_release(efdp->efd_efip); + xfs_efd_item_free(efdp); } +static const struct xfs_item_ops xfs_efd_item_ops = { + .flags = XFS_ITEM_RELEASE_WHEN_COMMITTED, + .iop_size = xfs_efd_item_size, + .iop_format = xfs_efd_item_format, + .iop_release = xfs_efd_item_release, +}; + /* - * Since pinning has no meaning for an efd item, unpinning does - * not either. + * Allocate an "extent free done" log item that will hold nextents worth of + * extents. The caller must use all nextents extents, because we are not + * flexible about this at all. */ -STATIC void -xfs_efd_item_unpin( - struct xfs_log_item *lip, - int remove) +static struct xfs_efd_log_item * +xfs_trans_get_efd( + struct xfs_trans *tp, + struct xfs_efi_log_item *efip, + unsigned int nextents) { + struct xfs_efd_log_item *efdp; + + ASSERT(nextents > 0); + + if (nextents > XFS_EFD_MAX_FAST_EXTENTS) { + efdp = kmem_zalloc(sizeof(struct xfs_efd_log_item) + + (nextents - 1) * sizeof(struct xfs_extent), + KM_SLEEP); + } else { + efdp = kmem_zone_zalloc(xfs_efd_zone, KM_SLEEP); + } + + xfs_log_item_init(tp->t_mountp, &efdp->efd_item, XFS_LI_EFD, + &xfs_efd_item_ops); + efdp->efd_efip = efip; + efdp->efd_format.efd_nextents = nextents; + efdp->efd_format.efd_efi_id = efip->efi_format.efi_id; + + xfs_trans_add_item(tp, &efdp->efd_item); + return efdp; } /* - * There isn't much you can do to push on an efd item. It is simply stuck - * waiting for the log to be flushed to disk. + * Free an extent and log it to the EFD. Note that the transaction is marked + * dirty regardless of whether the extent free succeeds or fails to support the + * EFI/EFD lifecycle rules. */ -STATIC uint -xfs_efd_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) +static int +xfs_trans_free_extent( + struct xfs_trans *tp, + struct xfs_efd_log_item *efdp, + xfs_fsblock_t start_block, + xfs_extlen_t ext_len, + const struct xfs_owner_info *oinfo, + bool skip_discard) { - return XFS_ITEM_PINNED; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_extent *extp; + uint next_extent; + xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, start_block); + xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, + start_block); + int error; + + trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, ext_len); + + error = __xfs_free_extent(tp, start_block, ext_len, + oinfo, XFS_AG_RESV_NONE, skip_discard); + /* + * Mark the transaction dirty, even on error. This ensures the + * transaction is aborted, which: + * + * 1.) releases the EFI and frees the EFD + * 2.) shuts down the filesystem + */ + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags); + + next_extent = efdp->efd_next_extent; + ASSERT(next_extent < efdp->efd_format.efd_nextents); + extp = &(efdp->efd_format.efd_extents[next_extent]); + extp->ext_start = start_block; + extp->ext_len = ext_len; + efdp->efd_next_extent++; + + return error; } -/* - * The EFD is either committed or aborted if the transaction is cancelled. If - * the transaction is cancelled, drop our reference to the EFI and free the EFD. - */ -STATIC void -xfs_efd_item_unlock( - struct xfs_log_item *lip) +/* Sort bmap items by AG. */ +static int +xfs_extent_free_diff_items( + void *priv, + struct list_head *a, + struct list_head *b) { - struct xfs_efd_log_item *efdp = EFD_ITEM(lip); + struct xfs_mount *mp = priv; + struct xfs_extent_free_item *ra; + struct xfs_extent_free_item *rb; + + ra = container_of(a, struct xfs_extent_free_item, xefi_list); + rb = container_of(b, struct xfs_extent_free_item, xefi_list); + return XFS_FSB_TO_AGNO(mp, ra->xefi_startblock) - + XFS_FSB_TO_AGNO(mp, rb->xefi_startblock); +} - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) { - xfs_efi_release(efdp->efd_efip); - xfs_efd_item_free(efdp); - } +/* Get an EFI. */ +STATIC void * +xfs_extent_free_create_intent( + struct xfs_trans *tp, + unsigned int count) +{ + struct xfs_efi_log_item *efip; + + ASSERT(tp != NULL); + ASSERT(count > 0); + + efip = xfs_efi_init(tp->t_mountp, count); + ASSERT(efip != NULL); + + /* + * Get a log_item_desc to point at the new item. + */ + xfs_trans_add_item(tp, &efip->efi_item); + return efip; } -/* - * When the efd item is committed to disk, all we need to do is delete our - * reference to our partner efi item and then free ourselves. Since we're - * freeing ourselves we must return -1 to keep the transaction code from further - * referencing this item. - */ -STATIC xfs_lsn_t -xfs_efd_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +/* Log a free extent to the intent item. */ +STATIC void +xfs_extent_free_log_item( + struct xfs_trans *tp, + void *intent, + struct list_head *item) { - struct xfs_efd_log_item *efdp = EFD_ITEM(lip); + struct xfs_efi_log_item *efip = intent; + struct xfs_extent_free_item *free; + uint next_extent; + struct xfs_extent *extp; + + free = container_of(item, struct xfs_extent_free_item, xefi_list); + + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags); /* - * Drop the EFI reference regardless of whether the EFD has been - * aborted. Once the EFD transaction is constructed, it is the sole - * responsibility of the EFD to release the EFI (even if the EFI is - * aborted due to log I/O error). + * atomic_inc_return gives us the value after the increment; + * we want to use it as an array index so we need to subtract 1 from + * it. */ - xfs_efi_release(efdp->efd_efip); - xfs_efd_item_free(efdp); + next_extent = atomic_inc_return(&efip->efi_next_extent) - 1; + ASSERT(next_extent < efip->efi_format.efi_nextents); + extp = &efip->efi_format.efi_extents[next_extent]; + extp->ext_start = free->xefi_startblock; + extp->ext_len = free->xefi_blockcount; +} - return (xfs_lsn_t)-1; +/* Get an EFD so we can process all the free extents. */ +STATIC void * +xfs_extent_free_create_done( + struct xfs_trans *tp, + void *intent, + unsigned int count) +{ + return xfs_trans_get_efd(tp, intent, count); } -/* - * The EFD dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ +/* Process a free extent. */ +STATIC int +xfs_extent_free_finish_item( + struct xfs_trans *tp, + struct list_head *item, + void *done_item, + void **state) +{ + struct xfs_extent_free_item *free; + int error; + + free = container_of(item, struct xfs_extent_free_item, xefi_list); + error = xfs_trans_free_extent(tp, done_item, + free->xefi_startblock, + free->xefi_blockcount, + &free->xefi_oinfo, free->xefi_skip_discard); + kmem_free(free); + return error; +} + +/* Abort all pending EFIs. */ STATIC void -xfs_efd_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +xfs_extent_free_abort_intent( + void *intent) { + xfs_efi_release(intent); } -/* - * This is the ops vector shared by all efd log items. - */ -static const struct xfs_item_ops xfs_efd_item_ops = { - .iop_size = xfs_efd_item_size, - .iop_format = xfs_efd_item_format, - .iop_pin = xfs_efd_item_pin, - .iop_unpin = xfs_efd_item_unpin, - .iop_unlock = xfs_efd_item_unlock, - .iop_committed = xfs_efd_item_committed, - .iop_push = xfs_efd_item_push, - .iop_committing = xfs_efd_item_committing +/* Cancel a free extent. */ +STATIC void +xfs_extent_free_cancel_item( + struct list_head *item) +{ + struct xfs_extent_free_item *free; + + free = container_of(item, struct xfs_extent_free_item, xefi_list); + kmem_free(free); +} + +const struct xfs_defer_op_type xfs_extent_free_defer_type = { + .max_items = XFS_EFI_MAX_FAST_EXTENTS, + .diff_items = xfs_extent_free_diff_items, + .create_intent = xfs_extent_free_create_intent, + .abort_intent = xfs_extent_free_abort_intent, + .log_item = xfs_extent_free_log_item, + .create_done = xfs_extent_free_create_done, + .finish_item = xfs_extent_free_finish_item, + .cancel_item = xfs_extent_free_cancel_item, }; /* - * Allocate and initialize an efd item with the given number of extents. + * AGFL blocks are accounted differently in the reserve pools and are not + * inserted into the busy extent list. */ -struct xfs_efd_log_item * -xfs_efd_init( - struct xfs_mount *mp, - struct xfs_efi_log_item *efip, - uint nextents) - +STATIC int +xfs_agfl_free_finish_item( + struct xfs_trans *tp, + struct list_head *item, + void *done_item, + void **state) { - struct xfs_efd_log_item *efdp; - uint size; + struct xfs_mount *mp = tp->t_mountp; + struct xfs_efd_log_item *efdp = done_item; + struct xfs_extent_free_item *free; + struct xfs_extent *extp; + struct xfs_buf *agbp; + int error; + xfs_agnumber_t agno; + xfs_agblock_t agbno; + uint next_extent; + + free = container_of(item, struct xfs_extent_free_item, xefi_list); + ASSERT(free->xefi_blockcount == 1); + agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock); + agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock); + + trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount); + + error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); + if (!error) + error = xfs_free_agfl_block(tp, agno, agbno, agbp, + &free->xefi_oinfo); - ASSERT(nextents > 0); - if (nextents > XFS_EFD_MAX_FAST_EXTENTS) { - size = (uint)(sizeof(xfs_efd_log_item_t) + - ((nextents - 1) * sizeof(xfs_extent_t))); - efdp = kmem_zalloc(size, KM_SLEEP); - } else { - efdp = kmem_zone_zalloc(xfs_efd_zone, KM_SLEEP); - } + /* + * Mark the transaction dirty, even on error. This ensures the + * transaction is aborted, which: + * + * 1.) releases the EFI and frees the EFD + * 2.) shuts down the filesystem + */ + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags); - xfs_log_item_init(mp, &efdp->efd_item, XFS_LI_EFD, &xfs_efd_item_ops); - efdp->efd_efip = efip; - efdp->efd_format.efd_nextents = nextents; - efdp->efd_format.efd_efi_id = efip->efi_format.efi_id; + next_extent = efdp->efd_next_extent; + ASSERT(next_extent < efdp->efd_format.efd_nextents); + extp = &(efdp->efd_format.efd_extents[next_extent]); + extp->ext_start = free->xefi_startblock; + extp->ext_len = free->xefi_blockcount; + efdp->efd_next_extent++; - return efdp; + kmem_free(free); + return error; } +/* sub-type with special handling for AGFL deferred frees */ +const struct xfs_defer_op_type xfs_agfl_free_defer_type = { + .max_items = XFS_EFI_MAX_FAST_EXTENTS, + .diff_items = xfs_extent_free_diff_items, + .create_intent = xfs_extent_free_create_intent, + .abort_intent = xfs_extent_free_abort_intent, + .log_item = xfs_extent_free_log_item, + .create_done = xfs_extent_free_create_done, + .finish_item = xfs_agfl_free_finish_item, + .cancel_item = xfs_extent_free_cancel_item, +}; + /* * Process an extent free intent item that was recovered from * the log. We need to free the extents that it describes. diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h index 2a6a895ca73e..16aaab06d4ec 100644 --- a/fs/xfs/xfs_extfree_item.h +++ b/fs/xfs/xfs_extfree_item.h @@ -51,7 +51,7 @@ struct kmem_zone; * AIL, so at this point both the EFI and EFD are freed. */ typedef struct xfs_efi_log_item { - xfs_log_item_t efi_item; + struct xfs_log_item efi_item; atomic_t efi_refcount; atomic_t efi_next_extent; unsigned long efi_flags; /* misc flags */ @@ -64,7 +64,7 @@ typedef struct xfs_efi_log_item { * have been freed. */ typedef struct xfs_efd_log_item { - xfs_log_item_t efd_item; + struct xfs_log_item efd_item; xfs_efi_log_item_t *efd_efip; uint efd_next_extent; xfs_efd_log_format_t efd_format; @@ -79,8 +79,6 @@ extern struct kmem_zone *xfs_efi_zone; extern struct kmem_zone *xfs_efd_zone; xfs_efi_log_item_t *xfs_efi_init(struct xfs_mount *, uint); -xfs_efd_log_item_t *xfs_efd_init(struct xfs_mount *, xfs_efi_log_item_t *, - uint); int xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt); void xfs_efi_item_free(xfs_efi_log_item_t *); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 76748255f843..e93bacbd49ae 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -10,14 +10,11 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_inode_item.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" -#include "xfs_error.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_ioctl.h" @@ -28,9 +25,7 @@ #include "xfs_iomap.h" #include "xfs_reflink.h" -#include <linux/dcache.h> #include <linux/falloc.h> -#include <linux/pagevec.h> #include <linux/backing-dev.h> #include <linux/mman.h> @@ -367,20 +362,7 @@ restart: * lock above. Eventually we should look into a way to avoid * the pointless lock roundtrip. */ - if (likely(!(file->f_mode & FMODE_NOCMTIME))) { - error = file_update_time(file); - if (error) - return error; - } - - /* - * If we're writing the file then make sure to clear the setuid and - * setgid bits if the process is not being run by root. This keeps - * people from modifying setuid and setgid binaries. - */ - if (!IS_NOSEC(inode)) - return file_remove_privs(file); - return 0; + return file_modified(file); } static int @@ -392,6 +374,7 @@ xfs_dio_write_end_io( struct inode *inode = file_inode(iocb->ki_filp); struct xfs_inode *ip = XFS_I(inode); loff_t offset = iocb->ki_pos; + unsigned int nofs_flag; int error = 0; trace_xfs_end_io_direct_write(ip, offset, size); @@ -408,10 +391,17 @@ xfs_dio_write_end_io( */ XFS_STATS_ADD(ip->i_mount, xs_write_bytes, size); + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + if (flags & IOMAP_DIO_COW) { error = xfs_reflink_end_cow(ip, offset, size); if (error) - return error; + goto out; } /* @@ -420,8 +410,10 @@ xfs_dio_write_end_io( * earlier allows a racing dio read to find unwritten extents before * they are converted. */ - if (flags & IOMAP_DIO_UNWRITTEN) - return xfs_iomap_write_unwritten(ip, offset, size, true); + if (flags & IOMAP_DIO_UNWRITTEN) { + error = xfs_iomap_write_unwritten(ip, offset, size, true); + goto out; + } /* * We need to update the in-core inode size here so that we don't end up @@ -443,6 +435,8 @@ xfs_dio_write_end_io( spin_unlock(&ip->i_flags_lock); } +out: + memalloc_nofs_restore(nofs_flag); return error; } diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c index 182501373af2..574a7a8b4736 100644 --- a/fs/xfs/xfs_filestream.c +++ b/fs/xfs/xfs_filestream.c @@ -5,22 +5,19 @@ * All Rights Reserved. */ #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" #include "xfs_alloc.h" #include "xfs_mru_cache.h" -#include "xfs_filestream.h" #include "xfs_trace.h" #include "xfs_ag_resv.h" #include "xfs_trans.h" -#include "xfs_shared.h" struct xfs_fstrm_item { struct xfs_mru_cache_elem mru; diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 3d76a9e35870..5a8f9641562a 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -9,16 +9,12 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_error.h" #include "xfs_btree.h" #include "xfs_rmap_btree.h" #include "xfs_trace.h" -#include "xfs_log.h" #include "xfs_rmap.h" #include "xfs_alloc.h" #include "xfs_bit.h" diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 3d0e0570e3aa..3e61d0cc23f8 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -11,15 +11,11 @@ #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_trans.h" #include "xfs_error.h" -#include "xfs_btree.h" #include "xfs_alloc.h" #include "xfs_fsops.h" #include "xfs_trans_space.h" -#include "xfs_rtalloc.h" -#include "xfs_trace.h" #include "xfs_log.h" #include "xfs_ag.h" #include "xfs_ag_resv.h" @@ -251,9 +247,9 @@ xfs_growfs_data( if (mp->m_sb.sb_imax_pct) { uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct; do_div(icount, 100); - mp->m_maxicount = XFS_FSB_TO_INO(mp, icount); + M_IGEO(mp)->maxicount = XFS_FSB_TO_INO(mp, icount); } else - mp->m_maxicount = 0; + M_IGEO(mp)->maxicount = 0; /* Update secondary superblocks now the physical grow has completed */ error = xfs_update_secondary_sbs(mp); diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c index d0d377384120..fa55ab8b8d80 100644 --- a/fs/xfs/xfs_globals.c +++ b/fs/xfs/xfs_globals.c @@ -4,7 +4,6 @@ * All Rights Reserved. */ #include "xfs.h" -#include "xfs_sysctl.h" /* * Tunable XFS parameters. xfs_params is required even when CONFIG_SYSCTL=n, @@ -41,4 +40,7 @@ struct xfs_globals xfs_globals = { #else .bug_on_assert = false, /* assert failures WARN() */ #endif +#ifdef DEBUG + .pwork_threads = -1, /* automatic thread detection */ +#endif }; diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index 4c4929f9e7bf..8e0cb05a7142 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -9,12 +9,8 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trace.h" #include "xfs_health.h" @@ -373,7 +369,7 @@ static const struct ioctl_sick_map ino_map[] = { void xfs_bulkstat_health( struct xfs_inode *ip, - struct xfs_bstat *bs) + struct xfs_bulkstat *bs) { const struct ioctl_sick_map *m; unsigned int sick; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index a76b27565a18..0b0fd10a36d4 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -5,13 +5,13 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" -#include "xfs_error.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_inode_item.h" @@ -23,8 +23,6 @@ #include "xfs_dquot.h" #include "xfs_reflink.h" -#include <linux/kthread.h> -#include <linux/freezer.h> #include <linux/iversion.h> /* diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c index 8381d34cb102..d99a0a3e5f40 100644 --- a/fs/xfs/xfs_icreate_item.c +++ b/fs/xfs/xfs_icreate_item.c @@ -6,14 +6,9 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" -#include "xfs_format.h" #include "xfs_log_format.h" -#include "xfs_trans_resv.h" -#include "xfs_bit.h" -#include "xfs_mount.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" -#include "xfs_error.h" #include "xfs_icreate_item.h" #include "xfs_log.h" @@ -56,80 +51,18 @@ xfs_icreate_item_format( sizeof(struct xfs_icreate_log)); } - -/* Pinning has no meaning for the create item, so just return. */ STATIC void -xfs_icreate_item_pin( +xfs_icreate_item_release( struct xfs_log_item *lip) { + kmem_zone_free(xfs_icreate_zone, ICR_ITEM(lip)); } - -/* pinning has no meaning for the create item, so just return. */ -STATIC void -xfs_icreate_item_unpin( - struct xfs_log_item *lip, - int remove) -{ -} - -STATIC void -xfs_icreate_item_unlock( - struct xfs_log_item *lip) -{ - struct xfs_icreate_item *icp = ICR_ITEM(lip); - - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) - kmem_zone_free(xfs_icreate_zone, icp); - return; -} - -/* - * Because we have ordered buffers being tracked in the AIL for the inode - * creation, we don't need the create item after this. Hence we can free - * the log item and return -1 to tell the caller we're done with the item. - */ -STATIC xfs_lsn_t -xfs_icreate_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ - struct xfs_icreate_item *icp = ICR_ITEM(lip); - - kmem_zone_free(xfs_icreate_zone, icp); - return (xfs_lsn_t)-1; -} - -/* item can never get into the AIL */ -STATIC uint -xfs_icreate_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) -{ - ASSERT(0); - return XFS_ITEM_SUCCESS; -} - -/* Ordered buffers do the dependency tracking here, so this does nothing. */ -STATIC void -xfs_icreate_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ -} - -/* - * This is the ops vector shared by all buf log items. - */ static const struct xfs_item_ops xfs_icreate_item_ops = { + .flags = XFS_ITEM_RELEASE_WHEN_COMMITTED, .iop_size = xfs_icreate_item_size, .iop_format = xfs_icreate_item_format, - .iop_pin = xfs_icreate_item_pin, - .iop_unpin = xfs_icreate_item_unpin, - .iop_push = xfs_icreate_item_push, - .iop_unlock = xfs_icreate_item_unlock, - .iop_committed = xfs_icreate_item_committed, - .iop_committing = xfs_icreate_item_committing, + .iop_release = xfs_icreate_item_release, }; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 71d216cf6f87..6467d5e1df2d 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3,7 +3,6 @@ * Copyright (c) 2000-2006 Silicon Graphics, Inc. * All Rights Reserved. */ -#include <linux/log2.h> #include <linux/iversion.h> #include "xfs.h" @@ -16,10 +15,7 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_inode.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" -#include "xfs_attr_sf.h" #include "xfs_attr.h" #include "xfs_trans_space.h" #include "xfs_trans.h" @@ -32,7 +28,6 @@ #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_filestream.h" -#include "xfs_cksum.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_symlink.h" @@ -40,7 +35,6 @@ #include "xfs_log.h" #include "xfs_bmap_btree.h" #include "xfs_reflink.h" -#include "xfs_dir2_priv.h" kmem_zone_t *xfs_inode_zone; @@ -441,12 +435,12 @@ xfs_lock_inumorder(int lock_mode, int subclass) */ static void xfs_lock_inodes( - xfs_inode_t **ips, - int inodes, - uint lock_mode) + struct xfs_inode **ips, + int inodes, + uint lock_mode) { - int attempts = 0, i, j, try_lock; - xfs_log_item_t *lp; + int attempts = 0, i, j, try_lock; + struct xfs_log_item *lp; /* * Currently supports between 2 and 5 inodes with exclusive locking. We @@ -485,7 +479,7 @@ again: */ if (!try_lock) { for (j = (i - 1); j >= 0 && !try_lock; j--) { - lp = (xfs_log_item_t *)ips[j]->i_itemp; + lp = &ips[j]->i_itemp->ili_item; if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) try_lock++; } @@ -551,7 +545,7 @@ xfs_lock_two_inodes( struct xfs_inode *temp; uint mode_temp; int attempts = 0; - xfs_log_item_t *lp; + struct xfs_log_item *lp; ASSERT(hweight32(ip0_mode) == 1); ASSERT(hweight32(ip1_mode) == 1); @@ -585,7 +579,7 @@ xfs_lock_two_inodes( * the second lock. If we can't get it, we must release the first one * and try again. */ - lp = (xfs_log_item_t *)ip0->i_itemp; + lp = &ip0->i_itemp->ili_item; if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) { if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) { xfs_iunlock(ip0, ip0_mode); @@ -2537,13 +2531,14 @@ xfs_ifree_cluster( xfs_inode_log_item_t *iip; struct xfs_log_item *lip; struct xfs_perag *pag; + struct xfs_ino_geometry *igeo = M_IGEO(mp); xfs_ino_t inum; inum = xic->first_ino; pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum)); - nbufs = mp->m_ialloc_blks / mp->m_blocks_per_cluster; + nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster; - for (j = 0; j < nbufs; j++, inum += mp->m_inodes_per_cluster) { + for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) { /* * The allocation bitmap tells us which inodes of the chunk were * physically allocated. Skip the cluster if an inode falls into @@ -2551,7 +2546,7 @@ xfs_ifree_cluster( */ ioffset = inum - xic->first_ino; if ((xic->alloc & XFS_INOBT_MASK(ioffset)) == 0) { - ASSERT(ioffset % mp->m_inodes_per_cluster == 0); + ASSERT(ioffset % igeo->inodes_per_cluster == 0); continue; } @@ -2567,7 +2562,7 @@ xfs_ifree_cluster( * to mark all the active inodes on the buffer stale. */ bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * mp->m_blocks_per_cluster, + mp->m_bsize * igeo->blocks_per_cluster, XBF_UNMAPPED); if (!bp) @@ -2614,7 +2609,7 @@ xfs_ifree_cluster( * transaction stale above, which means there is no point in * even trying to lock them. */ - for (i = 0; i < mp->m_inodes_per_cluster; i++) { + for (i = 0; i < igeo->inodes_per_cluster; i++) { retry: rcu_read_lock(); ip = radix_tree_lookup(&pag->pag_ici_root, @@ -3472,28 +3467,27 @@ xfs_iflush_cluster( struct xfs_mount *mp = ip->i_mount; struct xfs_perag *pag; unsigned long first_index, mask; - unsigned long inodes_per_cluster; int cilist_size; struct xfs_inode **cilist; struct xfs_inode *cip; + struct xfs_ino_geometry *igeo = M_IGEO(mp); int nr_found; int clcount = 0; int i; pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); - inodes_per_cluster = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog; - cilist_size = inodes_per_cluster * sizeof(xfs_inode_t *); + cilist_size = igeo->inodes_per_cluster * sizeof(struct xfs_inode *); cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS); if (!cilist) goto out_put; - mask = ~(((mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog)) - 1); + mask = ~(igeo->inodes_per_cluster - 1); first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask; rcu_read_lock(); /* really need a gang lookup range call here */ nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist, - first_index, inodes_per_cluster); + first_index, igeo->inodes_per_cluster); if (nr_found == 0) goto out_free; diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index fa1c4fe2ffbf..c9a502eed204 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -5,6 +5,7 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" @@ -12,7 +13,6 @@ #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_inode_item.h" -#include "xfs_error.h" #include "xfs_trace.h" #include "xfs_trans_priv.h" #include "xfs_buf_item.h" @@ -565,7 +565,7 @@ out_unlock: * Unlock the inode associated with the inode log item. */ STATIC void -xfs_inode_item_unlock( +xfs_inode_item_release( struct xfs_log_item *lip) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); @@ -621,23 +621,21 @@ xfs_inode_item_committed( STATIC void xfs_inode_item_committing( struct xfs_log_item *lip, - xfs_lsn_t lsn) + xfs_lsn_t commit_lsn) { - INODE_ITEM(lip)->ili_last_lsn = lsn; + INODE_ITEM(lip)->ili_last_lsn = commit_lsn; + return xfs_inode_item_release(lip); } -/* - * This is the ops vector shared by all buf log items. - */ static const struct xfs_item_ops xfs_inode_item_ops = { .iop_size = xfs_inode_item_size, .iop_format = xfs_inode_item_format, .iop_pin = xfs_inode_item_pin, .iop_unpin = xfs_inode_item_unpin, - .iop_unlock = xfs_inode_item_unlock, + .iop_release = xfs_inode_item_release, .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, - .iop_committing = xfs_inode_item_committing, + .iop_committing = xfs_inode_item_committing, .iop_error = xfs_inode_item_error }; diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index 27081eba220c..07a60e74c39c 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -14,7 +14,7 @@ struct xfs_inode; struct xfs_mount; typedef struct xfs_inode_log_item { - xfs_log_item_t ili_item; /* common portion */ + struct xfs_log_item ili_item; /* common portion */ struct xfs_inode *ili_inode; /* inode ptr */ xfs_lsn_t ili_flush_lsn; /* lsn at last flush */ xfs_lsn_t ili_last_lsn; /* lsn at last transaction */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index d7dfc13f30f5..6f7848cd5527 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -11,9 +11,8 @@ #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" -#include "xfs_ioctl.h" -#include "xfs_alloc.h" #include "xfs_rtalloc.h" +#include "xfs_iwalk.h" #include "xfs_itable.h" #include "xfs_error.h" #include "xfs_attr.h" @@ -25,7 +24,6 @@ #include "xfs_export.h" #include "xfs_trace.h" #include "xfs_icache.h" -#include "xfs_symlink.h" #include "xfs_trans.h" #include "xfs_acl.h" #include "xfs_btree.h" @@ -36,14 +34,8 @@ #include "xfs_ag.h" #include "xfs_health.h" -#include <linux/capability.h> -#include <linux/cred.h> -#include <linux/dcache.h> #include <linux/mount.h> #include <linux/namei.h> -#include <linux/pagemap.h> -#include <linux/slab.h> -#include <linux/exportfs.h> /* * xfs_find_handle maps from userspace xfs_fsop_handlereq structure to @@ -721,16 +713,45 @@ out_unlock: return error; } +/* Return 0 on success or positive error */ +int +xfs_fsbulkstat_one_fmt( + struct xfs_ibulk *breq, + const struct xfs_bulkstat *bstat) +{ + struct xfs_bstat bs1; + + xfs_bulkstat_to_bstat(breq->mp, &bs1, bstat); + if (copy_to_user(breq->ubuffer, &bs1, sizeof(bs1))) + return -EFAULT; + return xfs_ibulk_advance(breq, sizeof(struct xfs_bstat)); +} + +int +xfs_fsinumbers_fmt( + struct xfs_ibulk *breq, + const struct xfs_inumbers *igrp) +{ + struct xfs_inogrp ig1; + + xfs_inumbers_to_inogrp(&ig1, igrp); + if (copy_to_user(breq->ubuffer, &ig1, sizeof(struct xfs_inogrp))) + return -EFAULT; + return xfs_ibulk_advance(breq, sizeof(struct xfs_inogrp)); +} + STATIC int -xfs_ioc_bulkstat( +xfs_ioc_fsbulkstat( xfs_mount_t *mp, unsigned int cmd, void __user *arg) { - xfs_fsop_bulkreq_t bulkreq; - int count; /* # of records returned */ - xfs_ino_t inlast; /* last inode number */ - int done; + struct xfs_fsop_bulkreq bulkreq; + struct xfs_ibulk breq = { + .mp = mp, + .ocount = 0, + }; + xfs_ino_t lastino; int error; /* done = 1 if there are more stats to get and if bulkstat */ @@ -742,41 +763,243 @@ xfs_ioc_bulkstat( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - if (copy_from_user(&bulkreq, arg, sizeof(xfs_fsop_bulkreq_t))) + if (copy_from_user(&bulkreq, arg, sizeof(struct xfs_fsop_bulkreq))) return -EFAULT; - if (copy_from_user(&inlast, bulkreq.lastip, sizeof(__s64))) + if (copy_from_user(&lastino, bulkreq.lastip, sizeof(__s64))) return -EFAULT; - if ((count = bulkreq.icount) <= 0) + if (bulkreq.icount <= 0) return -EINVAL; if (bulkreq.ubuffer == NULL) return -EINVAL; - if (cmd == XFS_IOC_FSINUMBERS) - error = xfs_inumbers(mp, &inlast, &count, - bulkreq.ubuffer, xfs_inumbers_fmt); - else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE) - error = xfs_bulkstat_one(mp, inlast, bulkreq.ubuffer, - sizeof(xfs_bstat_t), NULL, &done); - else /* XFS_IOC_FSBULKSTAT */ - error = xfs_bulkstat(mp, &inlast, &count, xfs_bulkstat_one, - sizeof(xfs_bstat_t), bulkreq.ubuffer, - &done); + breq.ubuffer = bulkreq.ubuffer; + breq.icount = bulkreq.icount; + + /* + * FSBULKSTAT_SINGLE expects that *lastip contains the inode number + * that we want to stat. However, FSINUMBERS and FSBULKSTAT expect + * that *lastip contains either zero or the number of the last inode to + * be examined by the previous call and return results starting with + * the next inode after that. The new bulk request back end functions + * take the inode to start with, so we have to compute the startino + * parameter from lastino to maintain correct function. lastino == 0 + * is a special case because it has traditionally meant "first inode + * in filesystem". + */ + if (cmd == XFS_IOC_FSINUMBERS) { + breq.startino = lastino ? lastino + 1 : 0; + error = xfs_inumbers(&breq, xfs_fsinumbers_fmt); + lastino = breq.startino - 1; + } else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE) { + breq.startino = lastino; + breq.icount = 1; + error = xfs_bulkstat_one(&breq, xfs_fsbulkstat_one_fmt); + } else { /* XFS_IOC_FSBULKSTAT */ + breq.startino = lastino ? lastino + 1 : 0; + error = xfs_bulkstat(&breq, xfs_fsbulkstat_one_fmt); + lastino = breq.startino - 1; + } if (error) return error; - if (bulkreq.ocount != NULL) { - if (copy_to_user(bulkreq.lastip, &inlast, - sizeof(xfs_ino_t))) - return -EFAULT; + if (bulkreq.lastip != NULL && + copy_to_user(bulkreq.lastip, &lastino, sizeof(xfs_ino_t))) + return -EFAULT; - if (copy_to_user(bulkreq.ocount, &count, sizeof(count))) - return -EFAULT; + if (bulkreq.ocount != NULL && + copy_to_user(bulkreq.ocount, &breq.ocount, sizeof(__s32))) + return -EFAULT; + + return 0; +} + +/* Return 0 on success or positive error */ +static int +xfs_bulkstat_fmt( + struct xfs_ibulk *breq, + const struct xfs_bulkstat *bstat) +{ + if (copy_to_user(breq->ubuffer, bstat, sizeof(struct xfs_bulkstat))) + return -EFAULT; + return xfs_ibulk_advance(breq, sizeof(struct xfs_bulkstat)); +} + +/* + * Check the incoming bulk request @hdr from userspace and initialize the + * internal @breq bulk request appropriately. Returns 0 if the bulk request + * should proceed; XFS_ITER_ABORT if there's nothing to do; or the usual + * negative error code. + */ +static int +xfs_bulk_ireq_setup( + struct xfs_mount *mp, + struct xfs_bulk_ireq *hdr, + struct xfs_ibulk *breq, + void __user *ubuffer) +{ + if (hdr->icount == 0 || + (hdr->flags & ~XFS_BULK_IREQ_FLAGS_ALL) || + memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved))) + return -EINVAL; + + breq->startino = hdr->ino; + breq->ubuffer = ubuffer; + breq->icount = hdr->icount; + breq->ocount = 0; + breq->flags = 0; + + /* + * The @ino parameter is a special value, so we must look it up here. + * We're not allowed to have IREQ_AGNO, and we only return one inode + * worth of data. + */ + if (hdr->flags & XFS_BULK_IREQ_SPECIAL) { + if (hdr->flags & XFS_BULK_IREQ_AGNO) + return -EINVAL; + + switch (hdr->ino) { + case XFS_BULK_IREQ_SPECIAL_ROOT: + hdr->ino = mp->m_sb.sb_rootino; + break; + default: + return -EINVAL; + } + breq->icount = 1; } + /* + * The IREQ_AGNO flag means that we only want results from a given AG. + * If @hdr->ino is zero, we start iterating in that AG. If @hdr->ino is + * beyond the specified AG then we return no results. + */ + if (hdr->flags & XFS_BULK_IREQ_AGNO) { + if (hdr->agno >= mp->m_sb.sb_agcount) + return -EINVAL; + + if (breq->startino == 0) + breq->startino = XFS_AGINO_TO_INO(mp, hdr->agno, 0); + else if (XFS_INO_TO_AGNO(mp, breq->startino) < hdr->agno) + return -EINVAL; + + breq->flags |= XFS_IBULK_SAME_AG; + + /* Asking for an inode past the end of the AG? We're done! */ + if (XFS_INO_TO_AGNO(mp, breq->startino) > hdr->agno) + return XFS_ITER_ABORT; + } else if (hdr->agno) + return -EINVAL; + + /* Asking for an inode past the end of the FS? We're done! */ + if (XFS_INO_TO_AGNO(mp, breq->startino) >= mp->m_sb.sb_agcount) + return XFS_ITER_ABORT; + + return 0; +} + +/* + * Update the userspace bulk request @hdr to reflect the end state of the + * internal bulk request @breq. + */ +static void +xfs_bulk_ireq_teardown( + struct xfs_bulk_ireq *hdr, + struct xfs_ibulk *breq) +{ + hdr->ino = breq->startino; + hdr->ocount = breq->ocount; +} + +/* Handle the v5 bulkstat ioctl. */ +STATIC int +xfs_ioc_bulkstat( + struct xfs_mount *mp, + unsigned int cmd, + struct xfs_bulkstat_req __user *arg) +{ + struct xfs_bulk_ireq hdr; + struct xfs_ibulk breq = { + .mp = mp, + }; + int error; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr))) + return -EFAULT; + + error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->bulkstat); + if (error == XFS_ITER_ABORT) + goto out_teardown; + if (error < 0) + return error; + + error = xfs_bulkstat(&breq, xfs_bulkstat_fmt); + if (error) + return error; + +out_teardown: + xfs_bulk_ireq_teardown(&hdr, &breq); + if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr))) + return -EFAULT; + + return 0; +} + +STATIC int +xfs_inumbers_fmt( + struct xfs_ibulk *breq, + const struct xfs_inumbers *igrp) +{ + if (copy_to_user(breq->ubuffer, igrp, sizeof(struct xfs_inumbers))) + return -EFAULT; + return xfs_ibulk_advance(breq, sizeof(struct xfs_inumbers)); +} + +/* Handle the v5 inumbers ioctl. */ +STATIC int +xfs_ioc_inumbers( + struct xfs_mount *mp, + unsigned int cmd, + struct xfs_inumbers_req __user *arg) +{ + struct xfs_bulk_ireq hdr; + struct xfs_ibulk breq = { + .mp = mp, + }; + int error; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + if (copy_from_user(&hdr, &arg->hdr, sizeof(hdr))) + return -EFAULT; + + error = xfs_bulk_ireq_setup(mp, &hdr, &breq, arg->inumbers); + if (error == XFS_ITER_ABORT) + goto out_teardown; + if (error < 0) + return error; + + error = xfs_inumbers(&breq, xfs_inumbers_fmt); + if (error) + return error; + +out_teardown: + xfs_bulk_ireq_teardown(&hdr, &breq); + if (copy_to_user(&arg->hdr, &hdr, sizeof(hdr))) + return -EFAULT; + return 0; } @@ -879,37 +1102,44 @@ xfs_di2lxflags( return flags; } -STATIC int -xfs_ioc_fsgetxattr( - xfs_inode_t *ip, - int attr, - void __user *arg) +static void +xfs_fill_fsxattr( + struct xfs_inode *ip, + bool attr, + struct fsxattr *fa) { - struct fsxattr fa; - - memset(&fa, 0, sizeof(struct fsxattr)); - - xfs_ilock(ip, XFS_ILOCK_SHARED); - fa.fsx_xflags = xfs_ip2xflags(ip); - fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog; - fa.fsx_cowextsize = ip->i_d.di_cowextsize << + simple_fill_fsxattr(fa, xfs_ip2xflags(ip)); + fa->fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog; + fa->fsx_cowextsize = ip->i_d.di_cowextsize << ip->i_mount->m_sb.sb_blocklog; - fa.fsx_projid = xfs_get_projid(ip); + fa->fsx_projid = xfs_get_projid(ip); if (attr) { if (ip->i_afp) { if (ip->i_afp->if_flags & XFS_IFEXTENTS) - fa.fsx_nextents = xfs_iext_count(ip->i_afp); + fa->fsx_nextents = xfs_iext_count(ip->i_afp); else - fa.fsx_nextents = ip->i_d.di_anextents; + fa->fsx_nextents = ip->i_d.di_anextents; } else - fa.fsx_nextents = 0; + fa->fsx_nextents = 0; } else { if (ip->i_df.if_flags & XFS_IFEXTENTS) - fa.fsx_nextents = xfs_iext_count(&ip->i_df); + fa->fsx_nextents = xfs_iext_count(&ip->i_df); else - fa.fsx_nextents = ip->i_d.di_nextents; + fa->fsx_nextents = ip->i_d.di_nextents; } +} + +STATIC int +xfs_ioc_fsgetxattr( + xfs_inode_t *ip, + int attr, + void __user *arg) +{ + struct fsxattr fa; + + xfs_ilock(ip, XFS_ILOCK_SHARED); + xfs_fill_fsxattr(ip, attr, &fa); xfs_iunlock(ip, XFS_ILOCK_SHARED); if (copy_to_user(arg, &fa, sizeof(fa))) @@ -1035,15 +1265,6 @@ xfs_ioctl_setattr_xflags( if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip)) return -EINVAL; - /* - * Can't modify an immutable/append-only file unless - * we have appropriate permission. - */ - if (((ip->i_d.di_flags & (XFS_DIFLAG_IMMUTABLE | XFS_DIFLAG_APPEND)) || - (fa->fsx_xflags & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND))) && - !capable(CAP_LINUX_IMMUTABLE)) - return -EPERM; - /* diflags2 only valid for v3 inodes. */ di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); if (di_flags2 && ip->i_d.di_version < 3) @@ -1202,39 +1423,31 @@ xfs_ioctl_setattr_check_extsize( struct fsxattr *fa) { struct xfs_mount *mp = ip->i_mount; - - if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(VFS_I(ip)->i_mode)) - return -EINVAL; - - if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && - !S_ISDIR(VFS_I(ip)->i_mode)) - return -EINVAL; + xfs_extlen_t size; + xfs_fsblock_t extsize_fsb; if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents && ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) return -EINVAL; - if (fa->fsx_extsize != 0) { - xfs_extlen_t size; - xfs_fsblock_t extsize_fsb; - - extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); - if (extsize_fsb > MAXEXTLEN) - return -EINVAL; + if (fa->fsx_extsize == 0) + return 0; - if (XFS_IS_REALTIME_INODE(ip) || - (fa->fsx_xflags & FS_XFLAG_REALTIME)) { - size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; - } else { - size = mp->m_sb.sb_blocksize; - if (extsize_fsb > mp->m_sb.sb_agblocks / 2) - return -EINVAL; - } + extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize); + if (extsize_fsb > MAXEXTLEN) + return -EINVAL; - if (fa->fsx_extsize % size) + if (XFS_IS_REALTIME_INODE(ip) || + (fa->fsx_xflags & FS_XFLAG_REALTIME)) { + size = mp->m_sb.sb_rextsize << mp->m_sb.sb_blocklog; + } else { + size = mp->m_sb.sb_blocksize; + if (extsize_fsb > mp->m_sb.sb_agblocks / 2) return -EINVAL; - } else - fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); + } + + if (fa->fsx_extsize % size) + return -EINVAL; return 0; } @@ -1260,6 +1473,8 @@ xfs_ioctl_setattr_check_cowextsize( struct fsxattr *fa) { struct xfs_mount *mp = ip->i_mount; + xfs_extlen_t size; + xfs_fsblock_t cowextsize_fsb; if (!(fa->fsx_xflags & FS_XFLAG_COWEXTSIZE)) return 0; @@ -1268,25 +1483,19 @@ xfs_ioctl_setattr_check_cowextsize( ip->i_d.di_version != 3) return -EINVAL; - if (!S_ISREG(VFS_I(ip)->i_mode) && !S_ISDIR(VFS_I(ip)->i_mode)) - return -EINVAL; - - if (fa->fsx_cowextsize != 0) { - xfs_extlen_t size; - xfs_fsblock_t cowextsize_fsb; + if (fa->fsx_cowextsize == 0) + return 0; - cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize); - if (cowextsize_fsb > MAXEXTLEN) - return -EINVAL; + cowextsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_cowextsize); + if (cowextsize_fsb > MAXEXTLEN) + return -EINVAL; - size = mp->m_sb.sb_blocksize; - if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2) - return -EINVAL; + size = mp->m_sb.sb_blocksize; + if (cowextsize_fsb > mp->m_sb.sb_agblocks / 2) + return -EINVAL; - if (fa->fsx_cowextsize % size) - return -EINVAL; - } else - fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; + if (fa->fsx_cowextsize % size) + return -EINVAL; return 0; } @@ -1300,21 +1509,6 @@ xfs_ioctl_setattr_check_projid( if (fa->fsx_projid > (uint16_t)-1 && !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb)) return -EINVAL; - - /* - * Project Quota ID state is only allowed to change from within the init - * namespace. Enforce that restriction only if we are trying to change - * the quota ID state. Everything else is allowed in user namespaces. - */ - if (current_user_ns() == &init_user_ns) - return 0; - - if (xfs_get_projid(ip) != fa->fsx_projid) - return -EINVAL; - if ((fa->fsx_xflags & FS_XFLAG_PROJINHERIT) != - (ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)) - return -EINVAL; - return 0; } @@ -1323,6 +1517,7 @@ xfs_ioctl_setattr( xfs_inode_t *ip, struct fsxattr *fa) { + struct fsxattr old_fa; struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; struct xfs_dquot *udqp = NULL; @@ -1370,7 +1565,6 @@ xfs_ioctl_setattr( goto error_free_dquots; } - if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp) && xfs_get_projid(ip) != fa->fsx_projid) { code = xfs_qm_vop_chown_reserve(tp, ip, udqp, NULL, pdqp, @@ -1379,6 +1573,11 @@ xfs_ioctl_setattr( goto error_trans_cancel; } + xfs_fill_fsxattr(ip, false, &old_fa); + code = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, fa); + if (code) + goto error_trans_cancel; + code = xfs_ioctl_setattr_check_extsize(ip, fa); if (code) goto error_trans_cancel; @@ -1489,6 +1688,7 @@ xfs_ioc_setxflags( { struct xfs_trans *tp; struct fsxattr fa; + struct fsxattr old_fa; unsigned int flags; int join_flags = 0; int error; @@ -1524,6 +1724,13 @@ xfs_ioc_setxflags( goto out_drop_write; } + xfs_fill_fsxattr(ip, false, &old_fa); + error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, &fa); + if (error) { + xfs_trans_cancel(tp); + goto out_drop_write; + } + error = xfs_ioctl_setattr_xflags(tp, ip, &fa); if (error) { xfs_trans_cancel(tp); @@ -1942,7 +2149,12 @@ xfs_file_ioctl( case XFS_IOC_FSBULKSTAT_SINGLE: case XFS_IOC_FSBULKSTAT: case XFS_IOC_FSINUMBERS: + return xfs_ioc_fsbulkstat(mp, cmd, arg); + + case XFS_IOC_BULKSTAT: return xfs_ioc_bulkstat(mp, cmd, arg); + case XFS_IOC_INUMBERS: + return xfs_ioc_inumbers(mp, cmd, arg); case XFS_IOC_FSGEOMETRY_V1: return xfs_ioc_fsgeometry(mp, arg, 3); diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h index 4b17f67c888a..654c0bb1bcf8 100644 --- a/fs/xfs/xfs_ioctl.h +++ b/fs/xfs/xfs_ioctl.h @@ -77,4 +77,12 @@ xfs_set_dmattrs( uint evmask, uint16_t state); +struct xfs_ibulk; +struct xfs_bstat; +struct xfs_inogrp; + +int xfs_fsbulkstat_one_fmt(struct xfs_ibulk *breq, + const struct xfs_bulkstat *bstat); +int xfs_fsinumbers_fmt(struct xfs_ibulk *breq, const struct xfs_inumbers *igrp); + #endif diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index 614fc6886d24..7fcf7569743f 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -3,23 +3,19 @@ * Copyright (c) 2004-2005 Silicon Graphics, Inc. * All Rights Reserved. */ -#include <linux/compat.h> -#include <linux/ioctl.h> #include <linux/mount.h> -#include <linux/slab.h> -#include <linux/uaccess.h> #include <linux/fsmap.h> #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" +#include "xfs_iwalk.h" #include "xfs_itable.h" -#include "xfs_error.h" #include "xfs_fsops.h" -#include "xfs_alloc.h" #include "xfs_rtalloc.h" #include "xfs_attr.h" #include "xfs_ioctl.h" @@ -84,27 +80,26 @@ xfs_compat_growfs_rt_copyin( } STATIC int -xfs_inumbers_fmt_compat( - void __user *ubuffer, - const struct xfs_inogrp *buffer, - long count, - long *written) +xfs_fsinumbers_fmt_compat( + struct xfs_ibulk *breq, + const struct xfs_inumbers *ig) { - compat_xfs_inogrp_t __user *p32 = ubuffer; - long i; + struct compat_xfs_inogrp __user *p32 = breq->ubuffer; + struct xfs_inogrp ig1; + struct xfs_inogrp *igrp = &ig1; - for (i = 0; i < count; i++) { - if (put_user(buffer[i].xi_startino, &p32[i].xi_startino) || - put_user(buffer[i].xi_alloccount, &p32[i].xi_alloccount) || - put_user(buffer[i].xi_allocmask, &p32[i].xi_allocmask)) - return -EFAULT; - } - *written = count * sizeof(*p32); - return 0; + xfs_inumbers_to_inogrp(&ig1, ig); + + if (put_user(igrp->xi_startino, &p32->xi_startino) || + put_user(igrp->xi_alloccount, &p32->xi_alloccount) || + put_user(igrp->xi_allocmask, &p32->xi_allocmask)) + return -EFAULT; + + return xfs_ibulk_advance(breq, sizeof(struct compat_xfs_inogrp)); } #else -#define xfs_inumbers_fmt_compat xfs_inumbers_fmt +#define xfs_fsinumbers_fmt_compat xfs_fsinumbers_fmt #endif /* BROKEN_X86_ALIGNMENT */ STATIC int @@ -121,11 +116,14 @@ xfs_ioctl32_bstime_copyin( return 0; } -/* xfs_bstat_t has differing alignment on intel, & bstime_t sizes everywhere */ +/* + * struct xfs_bstat has differing alignment on intel, & bstime_t sizes + * everywhere + */ STATIC int xfs_ioctl32_bstat_copyin( - xfs_bstat_t *bstat, - compat_xfs_bstat_t __user *bstat32) + struct xfs_bstat *bstat, + struct compat_xfs_bstat __user *bstat32) { if (get_user(bstat->bs_ino, &bstat32->bs_ino) || get_user(bstat->bs_mode, &bstat32->bs_mode) || @@ -171,16 +169,15 @@ xfs_bstime_store_compat( /* Return 0 on success or positive error (to xfs_bulkstat()) */ STATIC int -xfs_bulkstat_one_fmt_compat( - void __user *ubuffer, - int ubsize, - int *ubused, - const xfs_bstat_t *buffer) +xfs_fsbulkstat_one_fmt_compat( + struct xfs_ibulk *breq, + const struct xfs_bulkstat *bstat) { - compat_xfs_bstat_t __user *p32 = ubuffer; + struct compat_xfs_bstat __user *p32 = breq->ubuffer; + struct xfs_bstat bs1; + struct xfs_bstat *buffer = &bs1; - if (ubsize < sizeof(*p32)) - return -ENOMEM; + xfs_bulkstat_to_bstat(breq->mp, &bs1, bstat); if (put_user(buffer->bs_ino, &p32->bs_ino) || put_user(buffer->bs_mode, &p32->bs_mode) || @@ -205,37 +202,24 @@ xfs_bulkstat_one_fmt_compat( put_user(buffer->bs_dmstate, &p32->bs_dmstate) || put_user(buffer->bs_aextents, &p32->bs_aextents)) return -EFAULT; - if (ubused) - *ubused = sizeof(*p32); - return 0; -} -STATIC int -xfs_bulkstat_one_compat( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode number to get data for */ - void __user *buffer, /* buffer to place output in */ - int ubsize, /* size of buffer */ - int *ubused, /* bytes used by me */ - int *stat) /* BULKSTAT_RV_... */ -{ - return xfs_bulkstat_one_int(mp, ino, buffer, ubsize, - xfs_bulkstat_one_fmt_compat, - ubused, stat); + return xfs_ibulk_advance(breq, sizeof(struct compat_xfs_bstat)); } /* copied from xfs_ioctl.c */ STATIC int -xfs_compat_ioc_bulkstat( +xfs_compat_ioc_fsbulkstat( xfs_mount_t *mp, unsigned int cmd, - compat_xfs_fsop_bulkreq_t __user *p32) + struct compat_xfs_fsop_bulkreq __user *p32) { u32 addr; - xfs_fsop_bulkreq_t bulkreq; - int count; /* # of records returned */ - xfs_ino_t inlast; /* last inode number */ - int done; + struct xfs_fsop_bulkreq bulkreq; + struct xfs_ibulk breq = { + .mp = mp, + .ocount = 0, + }; + xfs_ino_t lastino; int error; /* @@ -244,9 +228,8 @@ xfs_compat_ioc_bulkstat( * to userpace memory via bulkreq.ubuffer. Normally the compat * functions and structure size are the correct ones to use ... */ - inumbers_fmt_pf inumbers_func = xfs_inumbers_fmt_compat; - bulkstat_one_pf bs_one_func = xfs_bulkstat_one_compat; - size_t bs_one_size = sizeof(struct compat_xfs_bstat); + inumbers_fmt_pf inumbers_func = xfs_fsinumbers_fmt_compat; + bulkstat_one_fmt_pf bs_one_func = xfs_fsbulkstat_one_fmt_compat; #ifdef CONFIG_X86_X32 if (in_x32_syscall()) { @@ -258,9 +241,8 @@ xfs_compat_ioc_bulkstat( * the data written out in compat layout will not match what * x32 userspace expects. */ - inumbers_func = xfs_inumbers_fmt; - bs_one_func = xfs_bulkstat_one; - bs_one_size = sizeof(struct xfs_bstat); + inumbers_func = xfs_fsinumbers_fmt; + bs_one_func = xfs_fsbulkstat_one_fmt; } #endif @@ -284,40 +266,55 @@ xfs_compat_ioc_bulkstat( return -EFAULT; bulkreq.ocount = compat_ptr(addr); - if (copy_from_user(&inlast, bulkreq.lastip, sizeof(__s64))) + if (copy_from_user(&lastino, bulkreq.lastip, sizeof(__s64))) return -EFAULT; - if ((count = bulkreq.icount) <= 0) + if (bulkreq.icount <= 0) return -EINVAL; if (bulkreq.ubuffer == NULL) return -EINVAL; + breq.ubuffer = bulkreq.ubuffer; + breq.icount = bulkreq.icount; + + /* + * FSBULKSTAT_SINGLE expects that *lastip contains the inode number + * that we want to stat. However, FSINUMBERS and FSBULKSTAT expect + * that *lastip contains either zero or the number of the last inode to + * be examined by the previous call and return results starting with + * the next inode after that. The new bulk request back end functions + * take the inode to start with, so we have to compute the startino + * parameter from lastino to maintain correct function. lastino == 0 + * is a special case because it has traditionally meant "first inode + * in filesystem". + */ if (cmd == XFS_IOC_FSINUMBERS_32) { - error = xfs_inumbers(mp, &inlast, &count, - bulkreq.ubuffer, inumbers_func); + breq.startino = lastino ? lastino + 1 : 0; + error = xfs_inumbers(&breq, inumbers_func); + lastino = breq.startino - 1; } else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE_32) { - int res; - - error = bs_one_func(mp, inlast, bulkreq.ubuffer, - bs_one_size, NULL, &res); + breq.startino = lastino; + breq.icount = 1; + error = xfs_bulkstat_one(&breq, bs_one_func); + lastino = breq.startino; } else if (cmd == XFS_IOC_FSBULKSTAT_32) { - error = xfs_bulkstat(mp, &inlast, &count, - bs_one_func, bs_one_size, - bulkreq.ubuffer, &done); - } else + breq.startino = lastino ? lastino + 1 : 0; + error = xfs_bulkstat(&breq, bs_one_func); + lastino = breq.startino - 1; + } else { error = -EINVAL; + } if (error) return error; - if (bulkreq.ocount != NULL) { - if (copy_to_user(bulkreq.lastip, &inlast, - sizeof(xfs_ino_t))) - return -EFAULT; + if (bulkreq.lastip != NULL && + copy_to_user(bulkreq.lastip, &lastino, sizeof(xfs_ino_t))) + return -EFAULT; - if (copy_to_user(bulkreq.ocount, &count, sizeof(count))) - return -EFAULT; - } + if (bulkreq.ocount != NULL && + copy_to_user(bulkreq.ocount, &breq.ocount, sizeof(__s32))) + return -EFAULT; return 0; } @@ -577,6 +574,8 @@ xfs_file_compat_ioctl( case XFS_IOC_ERROR_CLEARALL: case FS_IOC_GETFSMAP: case XFS_IOC_SCRUB_METADATA: + case XFS_IOC_BULKSTAT: + case XFS_IOC_INUMBERS: return xfs_file_ioctl(filp, cmd, p); #if !defined(BROKEN_X86_ALIGNMENT) || defined(CONFIG_X86_X32) /* @@ -674,7 +673,7 @@ xfs_file_compat_ioctl( case XFS_IOC_FSBULKSTAT_32: case XFS_IOC_FSBULKSTAT_SINGLE_32: case XFS_IOC_FSINUMBERS_32: - return xfs_compat_ioc_bulkstat(mp, cmd, arg); + return xfs_compat_ioc_fsbulkstat(mp, cmd, arg); case XFS_IOC_FD_TO_HANDLE_32: case XFS_IOC_PATH_TO_HANDLE_32: case XFS_IOC_PATH_TO_FSHANDLE_32: { diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h index d28fa824284a..7985344d3aa6 100644 --- a/fs/xfs/xfs_ioctl32.h +++ b/fs/xfs/xfs_ioctl32.h @@ -36,7 +36,7 @@ typedef struct compat_xfs_bstime { __s32 tv_nsec; /* and nanoseconds */ } compat_xfs_bstime_t; -typedef struct compat_xfs_bstat { +struct compat_xfs_bstat { __u64 bs_ino; /* inode number */ __u16 bs_mode; /* type and mode */ __u16 bs_nlink; /* number of links */ @@ -61,14 +61,14 @@ typedef struct compat_xfs_bstat { __u32 bs_dmevmask; /* DMIG event mask */ __u16 bs_dmstate; /* DMIG state info */ __u16 bs_aextents; /* attribute number of extents */ -} __compat_packed compat_xfs_bstat_t; +} __compat_packed; -typedef struct compat_xfs_fsop_bulkreq { +struct compat_xfs_fsop_bulkreq { compat_uptr_t lastip; /* last inode # pointer */ __s32 icount; /* count of entries in buffer */ compat_uptr_t ubuffer; /* user buffer for inode desc. */ compat_uptr_t ocount; /* output count pointer */ -} compat_xfs_fsop_bulkreq_t; +}; #define XFS_IOC_FSBULKSTAT_32 \ _IOWR('X', 101, struct compat_xfs_fsop_bulkreq) @@ -106,7 +106,7 @@ typedef struct compat_xfs_swapext { xfs_off_t sx_offset; /* offset into file */ xfs_off_t sx_length; /* leng from offset */ char sx_pad[16]; /* pad space, unused */ - compat_xfs_bstat_t sx_stat; /* stat of target b4 copy */ + struct compat_xfs_bstat sx_stat; /* stat of target b4 copy */ } __compat_packed compat_xfs_swapext_t; #define XFS_IOC_SWAPEXT_32 _IOWR('X', 109, struct compat_xfs_swapext) @@ -201,11 +201,11 @@ typedef struct compat_xfs_fsop_geom_v1 { #define XFS_IOC_FSGEOMETRY_V1_32 \ _IOR('X', 100, struct compat_xfs_fsop_geom_v1) -typedef struct compat_xfs_inogrp { +struct compat_xfs_inogrp { __u64 xi_startino; /* starting inode number */ __s32 xi_alloccount; /* # bits set in allocmask */ __u64 xi_allocmask; /* mask of allocated inodes */ -} __attribute__((packed)) compat_xfs_inogrp_t; +} __attribute__((packed)); /* These growfs input structures have padding on the end, so must translate */ typedef struct compat_xfs_growfs_data { diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 63d323916bba..3a4310d7cb59 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -4,7 +4,6 @@ * Copyright (c) 2016-2018 Christoph Hellwig. * All Rights Reserved. */ -#include <linux/iomap.h> #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" @@ -12,7 +11,6 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_bmap_btree.h" @@ -25,7 +23,6 @@ #include "xfs_inode_item.h" #include "xfs_iomap.h" #include "xfs_trace.h" -#include "xfs_icache.h" #include "xfs_quota.h" #include "xfs_dquot_item.h" #include "xfs_dquot.h" @@ -779,7 +776,7 @@ xfs_iomap_write_unwritten( * complete here and might deadlock on the iolock. */ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, - XFS_TRANS_RESERVE | XFS_TRANS_NOFS, &tp); + XFS_TRANS_RESERVE, &tp); if (error) return error; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 74047bd0c1ae..ff3c1fae5357 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -10,30 +10,20 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_da_format.h" #include "xfs_inode.h" -#include "xfs_bmap.h" -#include "xfs_bmap_util.h" #include "xfs_acl.h" #include "xfs_quota.h" -#include "xfs_error.h" #include "xfs_attr.h" #include "xfs_trans.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_symlink.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" -#include "xfs_trans_space.h" #include "xfs_iomap.h" -#include "xfs_defer.h" -#include <linux/capability.h> #include <linux/xattr.h> #include <linux/posix_acl.h> #include <linux/security.h> -#include <linux/iomap.h> -#include <linux/slab.h> #include <linux/iversion.h> /* diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index 1e1a0af1dd34..a8a06bb78ea8 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -14,46 +14,66 @@ #include "xfs_btree.h" #include "xfs_ialloc.h" #include "xfs_ialloc_btree.h" +#include "xfs_iwalk.h" #include "xfs_itable.h" #include "xfs_error.h" -#include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_health.h" /* - * Return stat information for one inode. - * Return 0 if ok, else errno. + * Bulk Stat + * ========= + * + * Use the inode walking functions to fill out struct xfs_bulkstat for every + * allocated inode, then pass the stat information to some externally provided + * iteration function. */ -int + +struct xfs_bstat_chunk { + bulkstat_one_fmt_pf formatter; + struct xfs_ibulk *breq; + struct xfs_bulkstat *buf; +}; + +/* + * Fill out the bulkstat info for a single inode and report it somewhere. + * + * bc->breq->lastino is effectively the inode cursor as we walk through the + * filesystem. Therefore, we update it any time we need to move the cursor + * forward, regardless of whether or not we're sending any bstat information + * back to userspace. If the inode is internal metadata or, has been freed + * out from under us, we just simply keep going. + * + * However, if any other type of error happens we want to stop right where we + * are so that userspace will call back with exact number of the bad inode and + * we can send back an error code. + * + * Note that if the formatter tells us there's no space left in the buffer we + * move the cursor forward and abort the walk. + */ +STATIC int xfs_bulkstat_one_int( - struct xfs_mount *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode to get data for */ - void __user *buffer, /* buffer to place output in */ - int ubsize, /* size of buffer */ - bulkstat_one_fmt_pf formatter, /* formatter, copy to user */ - int *ubused, /* bytes used by me */ - int *stat) /* BULKSTAT_RV_... */ + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_ino_t ino, + struct xfs_bstat_chunk *bc) { struct xfs_icdinode *dic; /* dinode core info pointer */ struct xfs_inode *ip; /* incore inode pointer */ struct inode *inode; - struct xfs_bstat *buf; /* return buffer */ - int error = 0; /* error value */ + struct xfs_bulkstat *buf = bc->buf; + int error = -EINVAL; - *stat = BULKSTAT_RV_NOTHING; + if (xfs_internal_inum(mp, ino)) + goto out_advance; - if (!buffer || xfs_internal_inum(mp, ino)) - return -EINVAL; - - buf = kmem_zalloc(sizeof(*buf), KM_SLEEP | KM_MAYFAIL); - if (!buf) - return -ENOMEM; - - error = xfs_iget(mp, NULL, ino, + error = xfs_iget(mp, tp, ino, (XFS_IGET_DONTCACHE | XFS_IGET_UNTRUSTED), XFS_ILOCK_SHARED, &ip); + if (error == -ENOENT || error == -EINVAL) + goto out_advance; if (error) - goto out_free; + goto out; ASSERT(ip != NULL); ASSERT(ip->i_imap.im_blkno != 0); @@ -64,37 +84,35 @@ xfs_bulkstat_one_int( /* xfs_iget returns the following without needing * further change. */ - buf->bs_projid_lo = dic->di_projid_lo; - buf->bs_projid_hi = dic->di_projid_hi; + buf->bs_projectid = xfs_get_projid(ip); buf->bs_ino = ino; buf->bs_uid = dic->di_uid; buf->bs_gid = dic->di_gid; buf->bs_size = dic->di_size; buf->bs_nlink = inode->i_nlink; - buf->bs_atime.tv_sec = inode->i_atime.tv_sec; - buf->bs_atime.tv_nsec = inode->i_atime.tv_nsec; - buf->bs_mtime.tv_sec = inode->i_mtime.tv_sec; - buf->bs_mtime.tv_nsec = inode->i_mtime.tv_nsec; - buf->bs_ctime.tv_sec = inode->i_ctime.tv_sec; - buf->bs_ctime.tv_nsec = inode->i_ctime.tv_nsec; + buf->bs_atime = inode->i_atime.tv_sec; + buf->bs_atime_nsec = inode->i_atime.tv_nsec; + buf->bs_mtime = inode->i_mtime.tv_sec; + buf->bs_mtime_nsec = inode->i_mtime.tv_nsec; + buf->bs_ctime = inode->i_ctime.tv_sec; + buf->bs_ctime_nsec = inode->i_ctime.tv_nsec; + buf->bs_btime = dic->di_crtime.t_sec; + buf->bs_btime_nsec = dic->di_crtime.t_nsec; buf->bs_gen = inode->i_generation; buf->bs_mode = inode->i_mode; buf->bs_xflags = xfs_ip2xflags(ip); - buf->bs_extsize = dic->di_extsize << mp->m_sb.sb_blocklog; + buf->bs_extsize_blks = dic->di_extsize; buf->bs_extents = dic->di_nextents; - memset(buf->bs_pad, 0, sizeof(buf->bs_pad)); xfs_bulkstat_health(ip, buf); - buf->bs_dmevmask = dic->di_dmevmask; - buf->bs_dmstate = dic->di_dmstate; buf->bs_aextents = dic->di_anextents; buf->bs_forkoff = XFS_IFORK_BOFF(ip); + buf->bs_version = XFS_BULKSTAT_VERSION_V5; if (dic->di_version == 3) { if (dic->di_flags2 & XFS_DIFLAG2_COWEXTSIZE) - buf->bs_cowextsize = dic->di_cowextsize << - mp->m_sb.sb_blocklog; + buf->bs_cowextsize_blks = dic->di_cowextsize; } switch (dic->di_format) { @@ -118,385 +136,121 @@ xfs_bulkstat_one_int( xfs_iunlock(ip, XFS_ILOCK_SHARED); xfs_irele(ip); - error = formatter(buffer, ubsize, ubused, buf); - if (!error) - *stat = BULKSTAT_RV_DIDONE; + error = bc->formatter(bc->breq, buf); + if (error == XFS_IBULK_ABORT) + goto out_advance; + if (error) + goto out; - out_free: - kmem_free(buf); +out_advance: + /* + * Advance the cursor to the inode that comes after the one we just + * looked at. We want the caller to move along if the bulkstat + * information was copied successfully; if we tried to grab the inode + * but it's no longer allocated; or if it's internal metadata. + */ + bc->breq->startino = ino + 1; +out: return error; } -/* Return 0 on success or positive error */ -STATIC int -xfs_bulkstat_one_fmt( - void __user *ubuffer, - int ubsize, - int *ubused, - const xfs_bstat_t *buffer) -{ - if (ubsize < sizeof(*buffer)) - return -ENOMEM; - if (copy_to_user(ubuffer, buffer, sizeof(*buffer))) - return -EFAULT; - if (ubused) - *ubused = sizeof(*buffer); - return 0; -} - +/* Bulkstat a single inode. */ int xfs_bulkstat_one( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode number to get data for */ - void __user *buffer, /* buffer to place output in */ - int ubsize, /* size of buffer */ - int *ubused, /* bytes used by me */ - int *stat) /* BULKSTAT_RV_... */ + struct xfs_ibulk *breq, + bulkstat_one_fmt_pf formatter) { - return xfs_bulkstat_one_int(mp, ino, buffer, ubsize, - xfs_bulkstat_one_fmt, ubused, stat); -} + struct xfs_bstat_chunk bc = { + .formatter = formatter, + .breq = breq, + }; + int error; -/* - * Loop over all clusters in a chunk for a given incore inode allocation btree - * record. Do a readahead if there are any allocated inodes in that cluster. - */ -STATIC void -xfs_bulkstat_ichunk_ra( - struct xfs_mount *mp, - xfs_agnumber_t agno, - struct xfs_inobt_rec_incore *irec) -{ - xfs_agblock_t agbno; - struct blk_plug plug; - int i; /* inode chunk index */ - - agbno = XFS_AGINO_TO_AGBNO(mp, irec->ir_startino); - - blk_start_plug(&plug); - for (i = 0; i < XFS_INODES_PER_CHUNK; - i += mp->m_inodes_per_cluster, agbno += mp->m_blocks_per_cluster) { - if (xfs_inobt_maskn(i, mp->m_inodes_per_cluster) & - ~irec->ir_free) { - xfs_btree_reada_bufs(mp, agno, agbno, - mp->m_blocks_per_cluster, - &xfs_inode_buf_ops); - } - } - blk_finish_plug(&plug); -} + ASSERT(breq->icount == 1); -/* - * Lookup the inode chunk that the given inode lives in and then get the record - * if we found the chunk. If the inode was not the last in the chunk and there - * are some left allocated, update the data for the pointed-to record as well as - * return the count of grabbed inodes. - */ -STATIC int -xfs_bulkstat_grab_ichunk( - struct xfs_btree_cur *cur, /* btree cursor */ - xfs_agino_t agino, /* starting inode of chunk */ - int *icount,/* return # of inodes grabbed */ - struct xfs_inobt_rec_incore *irec) /* btree record */ -{ - int idx; /* index into inode chunk */ - int stat; - int error = 0; - - /* Lookup the inode chunk that this inode lives in */ - error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &stat); - if (error) - return error; - if (!stat) { - *icount = 0; - return error; - } + bc.buf = kmem_zalloc(sizeof(struct xfs_bulkstat), + KM_SLEEP | KM_MAYFAIL); + if (!bc.buf) + return -ENOMEM; - /* Get the record, should always work */ - error = xfs_inobt_get_rec(cur, irec, &stat); - if (error) - return error; - XFS_WANT_CORRUPTED_RETURN(cur->bc_mp, stat == 1); + error = xfs_bulkstat_one_int(breq->mp, NULL, breq->startino, &bc); - /* Check if the record contains the inode in request */ - if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino) { - *icount = 0; - return 0; - } + kmem_free(bc.buf); - idx = agino - irec->ir_startino + 1; - if (idx < XFS_INODES_PER_CHUNK && - (xfs_inobt_maskn(idx, XFS_INODES_PER_CHUNK - idx) & ~irec->ir_free)) { - int i; - - /* We got a right chunk with some left inodes allocated at it. - * Grab the chunk record. Mark all the uninteresting inodes - * free -- because they're before our start point. - */ - for (i = 0; i < idx; i++) { - if (XFS_INOBT_MASK(i) & ~irec->ir_free) - irec->ir_freecount++; - } - - irec->ir_free |= xfs_inobt_maskn(0, idx); - *icount = irec->ir_count - irec->ir_freecount; - } + /* + * If we reported one inode to userspace then we abort because we hit + * the end of the buffer. Don't leak that back to userspace. + */ + if (error == XFS_IWALK_ABORT) + error = 0; - return 0; + return error; } -#define XFS_BULKSTAT_UBLEFT(ubleft) ((ubleft) >= statstruct_size) - -struct xfs_bulkstat_agichunk { - char __user **ac_ubuffer;/* pointer into user's buffer */ - int ac_ubleft; /* bytes left in user's buffer */ - int ac_ubelem; /* spaces used in user's buffer */ -}; - -/* - * Process inodes in chunk with a pointer to a formatter function - * that will iget the inode and fill in the appropriate structure. - */ static int -xfs_bulkstat_ag_ichunk( - struct xfs_mount *mp, - xfs_agnumber_t agno, - struct xfs_inobt_rec_incore *irbp, - bulkstat_one_pf formatter, - size_t statstruct_size, - struct xfs_bulkstat_agichunk *acp, - xfs_agino_t *last_agino) +xfs_bulkstat_iwalk( + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_ino_t ino, + void *data) { - char __user **ubufp = acp->ac_ubuffer; - int chunkidx; - int error = 0; - xfs_agino_t agino = irbp->ir_startino; - - for (chunkidx = 0; chunkidx < XFS_INODES_PER_CHUNK; - chunkidx++, agino++) { - int fmterror; - int ubused; - - /* inode won't fit in buffer, we are done */ - if (acp->ac_ubleft < statstruct_size) - break; - - /* Skip if this inode is free */ - if (XFS_INOBT_MASK(chunkidx) & irbp->ir_free) - continue; - - /* Get the inode and fill in a single buffer */ - ubused = statstruct_size; - error = formatter(mp, XFS_AGINO_TO_INO(mp, agno, agino), - *ubufp, acp->ac_ubleft, &ubused, &fmterror); - - if (fmterror == BULKSTAT_RV_GIVEUP || - (error && error != -ENOENT && error != -EINVAL)) { - acp->ac_ubleft = 0; - ASSERT(error); - break; - } - - /* be careful not to leak error if at end of chunk */ - if (fmterror == BULKSTAT_RV_NOTHING || error) { - error = 0; - continue; - } - - *ubufp += ubused; - acp->ac_ubleft -= ubused; - acp->ac_ubelem++; - } - - /* - * Post-update *last_agino. At this point, agino will always point one - * inode past the last inode we processed successfully. Hence we - * substract that inode when setting the *last_agino cursor so that we - * return the correct cookie to userspace. On the next bulkstat call, - * the inode under the lastino cookie will be skipped as we have already - * processed it here. - */ - *last_agino = agino - 1; + int error; + error = xfs_bulkstat_one_int(mp, tp, ino, data); + /* bulkstat just skips over missing inodes */ + if (error == -ENOENT || error == -EINVAL) + return 0; return error; } /* - * Return stat information in bulk (by-inode) for the filesystem. + * Check the incoming lastino parameter. + * + * We allow any inode value that could map to physical space inside the + * filesystem because if there are no inodes there, bulkstat moves on to the + * next chunk. In other words, the magic agino value of zero takes us to the + * first chunk in the AG, and an agino value past the end of the AG takes us to + * the first chunk in the next AG. + * + * Therefore we can end early if the requested inode is beyond the end of the + * filesystem or doesn't map properly. */ -int /* error status */ -xfs_bulkstat( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t *lastinop, /* last inode returned */ - int *ubcountp, /* size of buffer/count returned */ - bulkstat_one_pf formatter, /* func that'd fill a single buf */ - size_t statstruct_size, /* sizeof struct filling */ - char __user *ubuffer, /* buffer with inode stats */ - int *done) /* 1 if there are more stats to get */ +static inline bool +xfs_bulkstat_already_done( + struct xfs_mount *mp, + xfs_ino_t startino) { - xfs_buf_t *agbp; /* agi header buffer */ - xfs_agino_t agino; /* inode # in allocation group */ - xfs_agnumber_t agno; /* allocation group number */ - xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */ - xfs_inobt_rec_incore_t *irbuf; /* start of irec buffer */ - int nirbuf; /* size of irbuf */ - int ubcount; /* size of user's buffer */ - struct xfs_bulkstat_agichunk ac; - int error = 0; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); + xfs_agino_t agino = XFS_INO_TO_AGINO(mp, startino); - /* - * Get the last inode value, see if there's nothing to do. - */ - agno = XFS_INO_TO_AGNO(mp, *lastinop); - agino = XFS_INO_TO_AGINO(mp, *lastinop); - if (agno >= mp->m_sb.sb_agcount || - *lastinop != XFS_AGINO_TO_INO(mp, agno, agino)) { - *done = 1; - *ubcountp = 0; - return 0; - } + return agno >= mp->m_sb.sb_agcount || + startino != XFS_AGINO_TO_INO(mp, agno, agino); +} - ubcount = *ubcountp; /* statstruct's */ - ac.ac_ubuffer = &ubuffer; - ac.ac_ubleft = ubcount * statstruct_size; /* bytes */; - ac.ac_ubelem = 0; +/* Return stat information in bulk (by-inode) for the filesystem. */ +int +xfs_bulkstat( + struct xfs_ibulk *breq, + bulkstat_one_fmt_pf formatter) +{ + struct xfs_bstat_chunk bc = { + .formatter = formatter, + .breq = breq, + }; + int error; - *ubcountp = 0; - *done = 0; + if (xfs_bulkstat_already_done(breq->mp, breq->startino)) + return 0; - irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP); - if (!irbuf) + bc.buf = kmem_zalloc(sizeof(struct xfs_bulkstat), + KM_SLEEP | KM_MAYFAIL); + if (!bc.buf) return -ENOMEM; - nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf); - /* - * Loop over the allocation groups, starting from the last - * inode returned; 0 means start of the allocation group. - */ - while (agno < mp->m_sb.sb_agcount) { - struct xfs_inobt_rec_incore *irbp = irbuf; - struct xfs_inobt_rec_incore *irbufend = irbuf + nirbuf; - bool end_of_ag = false; - int icount = 0; - int stat; - - error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp); - if (error) - break; - /* - * Allocate and initialize a btree cursor for ialloc btree. - */ - cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, - XFS_BTNUM_INO); - if (agino > 0) { - /* - * In the middle of an allocation group, we need to get - * the remainder of the chunk we're in. - */ - struct xfs_inobt_rec_incore r; - - error = xfs_bulkstat_grab_ichunk(cur, agino, &icount, &r); - if (error) - goto del_cursor; - if (icount) { - irbp->ir_startino = r.ir_startino; - irbp->ir_holemask = r.ir_holemask; - irbp->ir_count = r.ir_count; - irbp->ir_freecount = r.ir_freecount; - irbp->ir_free = r.ir_free; - irbp++; - } - /* Increment to the next record */ - error = xfs_btree_increment(cur, 0, &stat); - } else { - /* Start of ag. Lookup the first inode chunk */ - error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &stat); - } - if (error || stat == 0) { - end_of_ag = true; - goto del_cursor; - } - - /* - * Loop through inode btree records in this ag, - * until we run out of inodes or space in the buffer. - */ - while (irbp < irbufend && icount < ubcount) { - struct xfs_inobt_rec_incore r; - - error = xfs_inobt_get_rec(cur, &r, &stat); - if (error || stat == 0) { - end_of_ag = true; - goto del_cursor; - } - - /* - * If this chunk has any allocated inodes, save it. - * Also start read-ahead now for this chunk. - */ - if (r.ir_freecount < r.ir_count) { - xfs_bulkstat_ichunk_ra(mp, agno, &r); - irbp->ir_startino = r.ir_startino; - irbp->ir_holemask = r.ir_holemask; - irbp->ir_count = r.ir_count; - irbp->ir_freecount = r.ir_freecount; - irbp->ir_free = r.ir_free; - irbp++; - icount += r.ir_count - r.ir_freecount; - } - error = xfs_btree_increment(cur, 0, &stat); - if (error || stat == 0) { - end_of_ag = true; - goto del_cursor; - } - cond_resched(); - } - - /* - * Drop the btree buffers and the agi buffer as we can't hold any - * of the locks these represent when calling iget. If there is a - * pending error, then we are done. - */ -del_cursor: - xfs_btree_del_cursor(cur, error); - xfs_buf_relse(agbp); - if (error) - break; - /* - * Now format all the good inodes into the user's buffer. The - * call to xfs_bulkstat_ag_ichunk() sets up the agino pointer - * for the next loop iteration. - */ - irbufend = irbp; - for (irbp = irbuf; - irbp < irbufend && ac.ac_ubleft >= statstruct_size; - irbp++) { - error = xfs_bulkstat_ag_ichunk(mp, agno, irbp, - formatter, statstruct_size, &ac, - &agino); - if (error) - break; - - cond_resched(); - } - - /* - * If we've run out of space or had a formatting error, we - * are now done - */ - if (ac.ac_ubleft < statstruct_size || error) - break; - - if (end_of_ag) { - agno++; - agino = 0; - } - } - /* - * Done, we're either out of filesystem or space to put the data. - */ - kmem_free(irbuf); - *ubcountp = ac.ac_ubelem; + error = xfs_iwalk(breq->mp, NULL, breq->startino, breq->flags, + xfs_bulkstat_iwalk, breq->icount, &bc); + + kmem_free(bc.buf); /* * We found some inodes, so clear the error status and return them. @@ -505,135 +259,136 @@ del_cursor: * triggered again and propagated to userspace as there will be no * formatted inodes in the buffer. */ - if (ac.ac_ubelem) + if (breq->ocount > 0) error = 0; - /* - * If we ran out of filesystem, lastino will point off the end of - * the filesystem so the next call will return immediately. - */ - *lastinop = XFS_AGINO_TO_INO(mp, agno, agino); - if (agno >= mp->m_sb.sb_agcount) - *done = 1; - return error; } -int -xfs_inumbers_fmt( - void __user *ubuffer, /* buffer to write to */ - const struct xfs_inogrp *buffer, /* buffer to read from */ - long count, /* # of elements to read */ - long *written) /* # of bytes written */ +/* Convert bulkstat (v5) to bstat (v1). */ +void +xfs_bulkstat_to_bstat( + struct xfs_mount *mp, + struct xfs_bstat *bs1, + const struct xfs_bulkstat *bstat) { - if (copy_to_user(ubuffer, buffer, count * sizeof(*buffer))) - return -EFAULT; - *written = count * sizeof(*buffer); - return 0; + memset(bs1, 0, sizeof(struct xfs_bstat)); + bs1->bs_ino = bstat->bs_ino; + bs1->bs_mode = bstat->bs_mode; + bs1->bs_nlink = bstat->bs_nlink; + bs1->bs_uid = bstat->bs_uid; + bs1->bs_gid = bstat->bs_gid; + bs1->bs_rdev = bstat->bs_rdev; + bs1->bs_blksize = bstat->bs_blksize; + bs1->bs_size = bstat->bs_size; + bs1->bs_atime.tv_sec = bstat->bs_atime; + bs1->bs_mtime.tv_sec = bstat->bs_mtime; + bs1->bs_ctime.tv_sec = bstat->bs_ctime; + bs1->bs_atime.tv_nsec = bstat->bs_atime_nsec; + bs1->bs_mtime.tv_nsec = bstat->bs_mtime_nsec; + bs1->bs_ctime.tv_nsec = bstat->bs_ctime_nsec; + bs1->bs_blocks = bstat->bs_blocks; + bs1->bs_xflags = bstat->bs_xflags; + bs1->bs_extsize = XFS_FSB_TO_B(mp, bstat->bs_extsize_blks); + bs1->bs_extents = bstat->bs_extents; + bs1->bs_gen = bstat->bs_gen; + bs1->bs_projid_lo = bstat->bs_projectid & 0xFFFF; + bs1->bs_forkoff = bstat->bs_forkoff; + bs1->bs_projid_hi = bstat->bs_projectid >> 16; + bs1->bs_sick = bstat->bs_sick; + bs1->bs_checked = bstat->bs_checked; + bs1->bs_cowextsize = XFS_FSB_TO_B(mp, bstat->bs_cowextsize_blks); + bs1->bs_dmevmask = 0; + bs1->bs_dmstate = 0; + bs1->bs_aextents = bstat->bs_aextents; +} + +struct xfs_inumbers_chunk { + inumbers_fmt_pf formatter; + struct xfs_ibulk *breq; +}; + +/* + * INUMBERS + * ======== + * This is how we export inode btree records to userspace, so that XFS tools + * can figure out where inodes are allocated. + */ + +/* + * Format the inode group structure and report it somewhere. + * + * Similar to xfs_bulkstat_one_int, lastino is the inode cursor as we walk + * through the filesystem so we move it forward unless there was a runtime + * error. If the formatter tells us the buffer is now full we also move the + * cursor forward and abort the walk. + */ +STATIC int +xfs_inumbers_walk( + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_agnumber_t agno, + const struct xfs_inobt_rec_incore *irec, + void *data) +{ + struct xfs_inumbers inogrp = { + .xi_startino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino), + .xi_alloccount = irec->ir_count - irec->ir_freecount, + .xi_allocmask = ~irec->ir_free, + .xi_version = XFS_INUMBERS_VERSION_V5, + }; + struct xfs_inumbers_chunk *ic = data; + int error; + + error = ic->formatter(ic->breq, &inogrp); + if (error && error != XFS_IBULK_ABORT) + return error; + + ic->breq->startino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino) + + XFS_INODES_PER_CHUNK; + return error; } /* * Return inode number table for the filesystem. */ -int /* error status */ +int xfs_inumbers( - struct xfs_mount *mp,/* mount point for filesystem */ - xfs_ino_t *lastino,/* last inode returned */ - int *count,/* size of buffer/count returned */ - void __user *ubuffer,/* buffer with inode descriptions */ + struct xfs_ibulk *breq, inumbers_fmt_pf formatter) { - xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, *lastino); - xfs_agino_t agino = XFS_INO_TO_AGINO(mp, *lastino); - struct xfs_btree_cur *cur = NULL; - struct xfs_buf *agbp = NULL; - struct xfs_inogrp *buffer; - int bcount; - int left = *count; - int bufidx = 0; + struct xfs_inumbers_chunk ic = { + .formatter = formatter, + .breq = breq, + }; int error = 0; - *count = 0; - if (agno >= mp->m_sb.sb_agcount || - *lastino != XFS_AGINO_TO_INO(mp, agno, agino)) - return error; + if (xfs_bulkstat_already_done(breq->mp, breq->startino)) + return 0; - bcount = min(left, (int)(PAGE_SIZE / sizeof(*buffer))); - buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP); - do { - struct xfs_inobt_rec_incore r; - int stat; - - if (!agbp) { - error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp); - if (error) - break; - - cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, - XFS_BTNUM_INO); - error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_GE, - &stat); - if (error) - break; - if (!stat) - goto next_ag; - } - - error = xfs_inobt_get_rec(cur, &r, &stat); - if (error) - break; - if (!stat) - goto next_ag; - - agino = r.ir_startino + XFS_INODES_PER_CHUNK - 1; - buffer[bufidx].xi_startino = - XFS_AGINO_TO_INO(mp, agno, r.ir_startino); - buffer[bufidx].xi_alloccount = r.ir_count - r.ir_freecount; - buffer[bufidx].xi_allocmask = ~r.ir_free; - if (++bufidx == bcount) { - long written; - - error = formatter(ubuffer, buffer, bufidx, &written); - if (error) - break; - ubuffer += written; - *count += bufidx; - bufidx = 0; - } - if (!--left) - break; - - error = xfs_btree_increment(cur, 0, &stat); - if (error) - break; - if (stat) - continue; - -next_ag: - xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); - cur = NULL; - xfs_buf_relse(agbp); - agbp = NULL; - agino = 0; - agno++; - } while (agno < mp->m_sb.sb_agcount); - - if (!error) { - if (bufidx) { - long written; - - error = formatter(ubuffer, buffer, bufidx, &written); - if (!error) - *count += bufidx; - } - *lastino = XFS_AGINO_TO_INO(mp, agno, agino); - } + error = xfs_inobt_walk(breq->mp, NULL, breq->startino, breq->flags, + xfs_inumbers_walk, breq->icount, &ic); - kmem_free(buffer); - if (cur) - xfs_btree_del_cursor(cur, error); - if (agbp) - xfs_buf_relse(agbp); + /* + * We found some inode groups, so clear the error status and return + * them. The lastino pointer will point directly at the inode that + * triggered any error that occurred, so on the next call the error + * will be triggered again and propagated to userspace as there will be + * no formatted inode groups in the buffer. + */ + if (breq->ocount > 0) + error = 0; return error; } + +/* Convert an inumbers (v5) struct to a inogrp (v1) struct. */ +void +xfs_inumbers_to_inogrp( + struct xfs_inogrp *ig1, + const struct xfs_inumbers *ig) +{ + ig1->xi_startino = ig->xi_startino; + ig1->xi_alloccount = ig->xi_alloccount; + ig1->xi_allocmask = ig->xi_allocmask; +} diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h index 8a822285b671..e90c1fc5b981 100644 --- a/fs/xfs/xfs_itable.h +++ b/fs/xfs/xfs_itable.h @@ -5,83 +5,55 @@ #ifndef __XFS_ITABLE_H__ #define __XFS_ITABLE_H__ -/* - * xfs_bulkstat() is used to fill in xfs_bstat structures as well as dm_stat - * structures (by the dmi library). This is a pointer to a formatter function - * that will iget the inode and fill in the appropriate structure. - * see xfs_bulkstat_one() and xfs_dm_bulkstat_one() in dmapi_xfs.c - */ -typedef int (*bulkstat_one_pf)(struct xfs_mount *mp, - xfs_ino_t ino, - void __user *buffer, - int ubsize, - int *ubused, - int *stat); +/* In-memory representation of a userspace request for batch inode data. */ +struct xfs_ibulk { + struct xfs_mount *mp; + void __user *ubuffer; /* user output buffer */ + xfs_ino_t startino; /* start with this inode */ + unsigned int icount; /* number of elements in ubuffer */ + unsigned int ocount; /* number of records returned */ + unsigned int flags; /* see XFS_IBULK_FLAG_* */ +}; + +/* Only iterate within the same AG as startino */ +#define XFS_IBULK_SAME_AG (XFS_IWALK_SAME_AG) + +/* Return value that means we want to abort the walk. */ +#define XFS_IBULK_ABORT (XFS_IWALK_ABORT) /* - * Values for stat return value. + * Advance the user buffer pointer by one record of the given size. If the + * buffer is now full, return the appropriate error code. */ -#define BULKSTAT_RV_NOTHING 0 -#define BULKSTAT_RV_DIDONE 1 -#define BULKSTAT_RV_GIVEUP 2 +static inline int +xfs_ibulk_advance( + struct xfs_ibulk *breq, + size_t bytes) +{ + char __user *b = breq->ubuffer; + + breq->ubuffer = b + bytes; + breq->ocount++; + return breq->ocount == breq->icount ? XFS_IBULK_ABORT : 0; +} /* * Return stat information in bulk (by-inode) for the filesystem. */ -int /* error status */ -xfs_bulkstat( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t *lastino, /* last inode returned */ - int *count, /* size of buffer/count returned */ - bulkstat_one_pf formatter, /* func that'd fill a single buf */ - size_t statstruct_size,/* sizeof struct that we're filling */ - char __user *ubuffer,/* buffer with inode stats */ - int *done); /* 1 if there are more stats to get */ - -typedef int (*bulkstat_one_fmt_pf)( /* used size in bytes or negative error */ - void __user *ubuffer, /* buffer to write to */ - int ubsize, /* remaining user buffer sz */ - int *ubused, /* bytes used by formatter */ - const xfs_bstat_t *buffer); /* buffer to read from */ - -int -xfs_bulkstat_one_int( - xfs_mount_t *mp, - xfs_ino_t ino, - void __user *buffer, - int ubsize, - bulkstat_one_fmt_pf formatter, - int *ubused, - int *stat); -int -xfs_bulkstat_one( - xfs_mount_t *mp, - xfs_ino_t ino, - void __user *buffer, - int ubsize, - int *ubused, - int *stat); +typedef int (*bulkstat_one_fmt_pf)(struct xfs_ibulk *breq, + const struct xfs_bulkstat *bstat); -typedef int (*inumbers_fmt_pf)( - void __user *ubuffer, /* buffer to write to */ - const xfs_inogrp_t *buffer, /* buffer to read from */ - long count, /* # of elements to read */ - long *written); /* # of bytes written */ +int xfs_bulkstat_one(struct xfs_ibulk *breq, bulkstat_one_fmt_pf formatter); +int xfs_bulkstat(struct xfs_ibulk *breq, bulkstat_one_fmt_pf formatter); +void xfs_bulkstat_to_bstat(struct xfs_mount *mp, struct xfs_bstat *bs1, + const struct xfs_bulkstat *bstat); -int -xfs_inumbers_fmt( - void __user *ubuffer, /* buffer to write to */ - const xfs_inogrp_t *buffer, /* buffer to read from */ - long count, /* # of elements to read */ - long *written); /* # of bytes written */ +typedef int (*inumbers_fmt_pf)(struct xfs_ibulk *breq, + const struct xfs_inumbers *igrp); -int /* error status */ -xfs_inumbers( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t *last, /* last inode returned */ - int *count, /* size of buffer/count returned */ - void __user *buffer, /* buffer with inode info */ - inumbers_fmt_pf formatter); +int xfs_inumbers(struct xfs_ibulk *breq, inumbers_fmt_pf formatter); +void xfs_inumbers_to_inogrp(struct xfs_inogrp *ig1, + const struct xfs_inumbers *ig); #endif /* __XFS_ITABLE_H__ */ diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c new file mode 100644 index 000000000000..8c7d727149ea --- /dev/null +++ b/fs/xfs/xfs_iwalk.c @@ -0,0 +1,720 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_inode.h" +#include "xfs_btree.h" +#include "xfs_ialloc.h" +#include "xfs_ialloc_btree.h" +#include "xfs_iwalk.h" +#include "xfs_error.h" +#include "xfs_trace.h" +#include "xfs_icache.h" +#include "xfs_health.h" +#include "xfs_trans.h" +#include "xfs_pwork.h" + +/* + * Walking Inodes in the Filesystem + * ================================ + * + * This iterator function walks a subset of filesystem inodes in increasing + * order from @startino until there are no more inodes. For each allocated + * inode it finds, it calls a walk function with the relevant inode number and + * a pointer to caller-provided data. The walk function can return the usual + * negative error code to stop the iteration; 0 to continue the iteration; or + * XFS_IWALK_ABORT to stop the iteration. This return value is returned to the + * caller. + * + * Internally, we allow the walk function to do anything, which means that we + * cannot maintain the inobt cursor or our lock on the AGI buffer. We + * therefore cache the inobt records in kernel memory and only call the walk + * function when our memory buffer is full. @nr_recs is the number of records + * that we've cached, and @sz_recs is the size of our cache. + * + * It is the responsibility of the walk function to ensure it accesses + * allocated inodes, as the inobt records may be stale by the time they are + * acted upon. + */ + +struct xfs_iwalk_ag { + /* parallel work control data; will be null if single threaded */ + struct xfs_pwork pwork; + + struct xfs_mount *mp; + struct xfs_trans *tp; + + /* Where do we start the traversal? */ + xfs_ino_t startino; + + /* Array of inobt records we cache. */ + struct xfs_inobt_rec_incore *recs; + + /* Number of entries allocated for the @recs array. */ + unsigned int sz_recs; + + /* Number of entries in the @recs array that are in use. */ + unsigned int nr_recs; + + /* Inode walk function and data pointer. */ + xfs_iwalk_fn iwalk_fn; + xfs_inobt_walk_fn inobt_walk_fn; + void *data; + + /* + * Make it look like the inodes up to startino are free so that + * bulkstat can start its inode iteration at the correct place without + * needing to special case everywhere. + */ + unsigned int trim_start:1; + + /* Skip empty inobt records? */ + unsigned int skip_empty:1; +}; + +/* + * Loop over all clusters in a chunk for a given incore inode allocation btree + * record. Do a readahead if there are any allocated inodes in that cluster. + */ +STATIC void +xfs_iwalk_ichunk_ra( + struct xfs_mount *mp, + xfs_agnumber_t agno, + struct xfs_inobt_rec_incore *irec) +{ + struct xfs_ino_geometry *igeo = M_IGEO(mp); + xfs_agblock_t agbno; + struct blk_plug plug; + int i; /* inode chunk index */ + + agbno = XFS_AGINO_TO_AGBNO(mp, irec->ir_startino); + + blk_start_plug(&plug); + for (i = 0; i < XFS_INODES_PER_CHUNK; i += igeo->inodes_per_cluster) { + xfs_inofree_t imask; + + imask = xfs_inobt_maskn(i, igeo->inodes_per_cluster); + if (imask & ~irec->ir_free) { + xfs_btree_reada_bufs(mp, agno, agbno, + igeo->blocks_per_cluster, + &xfs_inode_buf_ops); + } + agbno += igeo->blocks_per_cluster; + } + blk_finish_plug(&plug); +} + +/* + * Set the bits in @irec's free mask that correspond to the inodes before + * @agino so that we skip them. This is how we restart an inode walk that was + * interrupted in the middle of an inode record. + */ +STATIC void +xfs_iwalk_adjust_start( + xfs_agino_t agino, /* starting inode of chunk */ + struct xfs_inobt_rec_incore *irec) /* btree record */ +{ + int idx; /* index into inode chunk */ + int i; + + idx = agino - irec->ir_startino; + + /* + * We got a right chunk with some left inodes allocated at it. Grab + * the chunk record. Mark all the uninteresting inodes free because + * they're before our start point. + */ + for (i = 0; i < idx; i++) { + if (XFS_INOBT_MASK(i) & ~irec->ir_free) + irec->ir_freecount++; + } + + irec->ir_free |= xfs_inobt_maskn(0, idx); +} + +/* Allocate memory for a walk. */ +STATIC int +xfs_iwalk_alloc( + struct xfs_iwalk_ag *iwag) +{ + size_t size; + + ASSERT(iwag->recs == NULL); + iwag->nr_recs = 0; + + /* Allocate a prefetch buffer for inobt records. */ + size = iwag->sz_recs * sizeof(struct xfs_inobt_rec_incore); + iwag->recs = kmem_alloc(size, KM_MAYFAIL); + if (iwag->recs == NULL) + return -ENOMEM; + + return 0; +} + +/* Free memory we allocated for a walk. */ +STATIC void +xfs_iwalk_free( + struct xfs_iwalk_ag *iwag) +{ + kmem_free(iwag->recs); + iwag->recs = NULL; +} + +/* For each inuse inode in each cached inobt record, call our function. */ +STATIC int +xfs_iwalk_ag_recs( + struct xfs_iwalk_ag *iwag) +{ + struct xfs_mount *mp = iwag->mp; + struct xfs_trans *tp = iwag->tp; + xfs_ino_t ino; + unsigned int i, j; + xfs_agnumber_t agno; + int error; + + agno = XFS_INO_TO_AGNO(mp, iwag->startino); + for (i = 0; i < iwag->nr_recs; i++) { + struct xfs_inobt_rec_incore *irec = &iwag->recs[i]; + + trace_xfs_iwalk_ag_rec(mp, agno, irec); + + if (xfs_pwork_want_abort(&iwag->pwork)) + return 0; + + if (iwag->inobt_walk_fn) { + error = iwag->inobt_walk_fn(mp, tp, agno, irec, + iwag->data); + if (error) + return error; + } + + if (!iwag->iwalk_fn) + continue; + + for (j = 0; j < XFS_INODES_PER_CHUNK; j++) { + if (xfs_pwork_want_abort(&iwag->pwork)) + return 0; + + /* Skip if this inode is free */ + if (XFS_INOBT_MASK(j) & irec->ir_free) + continue; + + /* Otherwise call our function. */ + ino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino + j); + error = iwag->iwalk_fn(mp, tp, ino, iwag->data); + if (error) + return error; + } + } + + return 0; +} + +/* Delete cursor and let go of AGI. */ +static inline void +xfs_iwalk_del_inobt( + struct xfs_trans *tp, + struct xfs_btree_cur **curpp, + struct xfs_buf **agi_bpp, + int error) +{ + if (*curpp) { + xfs_btree_del_cursor(*curpp, error); + *curpp = NULL; + } + if (*agi_bpp) { + xfs_trans_brelse(tp, *agi_bpp); + *agi_bpp = NULL; + } +} + +/* + * Set ourselves up for walking inobt records starting from a given point in + * the filesystem. + * + * If caller passed in a nonzero start inode number, load the record from the + * inobt and make the record look like all the inodes before agino are free so + * that we skip them, and then move the cursor to the next inobt record. This + * is how we support starting an iwalk in the middle of an inode chunk. + * + * If the caller passed in a start number of zero, move the cursor to the first + * inobt record. + * + * The caller is responsible for cleaning up the cursor and buffer pointer + * regardless of the error status. + */ +STATIC int +xfs_iwalk_ag_start( + struct xfs_iwalk_ag *iwag, + xfs_agnumber_t agno, + xfs_agino_t agino, + struct xfs_btree_cur **curpp, + struct xfs_buf **agi_bpp, + int *has_more) +{ + struct xfs_mount *mp = iwag->mp; + struct xfs_trans *tp = iwag->tp; + struct xfs_inobt_rec_incore *irec; + int error; + + /* Set up a fresh cursor and empty the inobt cache. */ + iwag->nr_recs = 0; + error = xfs_inobt_cur(mp, tp, agno, XFS_BTNUM_INO, curpp, agi_bpp); + if (error) + return error; + + /* Starting at the beginning of the AG? That's easy! */ + if (agino == 0) + return xfs_inobt_lookup(*curpp, 0, XFS_LOOKUP_GE, has_more); + + /* + * Otherwise, we have to grab the inobt record where we left off, stuff + * the record into our cache, and then see if there are more records. + * We require a lookup cache of at least two elements so that the + * caller doesn't have to deal with tearing down the cursor to walk the + * records. + */ + error = xfs_inobt_lookup(*curpp, agino, XFS_LOOKUP_LE, has_more); + if (error) + return error; + + /* + * If the LE lookup at @agino yields no records, jump ahead to the + * inobt cursor increment to see if there are more records to process. + */ + if (!*has_more) + goto out_advance; + + /* Get the record, should always work */ + irec = &iwag->recs[iwag->nr_recs]; + error = xfs_inobt_get_rec(*curpp, irec, has_more); + if (error) + return error; + XFS_WANT_CORRUPTED_RETURN(mp, *has_more == 1); + + /* + * If the LE lookup yielded an inobt record before the cursor position, + * skip it and see if there's another one after it. + */ + if (irec->ir_startino + XFS_INODES_PER_CHUNK <= agino) + goto out_advance; + + /* + * If agino fell in the middle of the inode record, make it look like + * the inodes up to agino are free so that we don't return them again. + */ + if (iwag->trim_start) + xfs_iwalk_adjust_start(agino, irec); + + /* + * The prefetch calculation is supposed to give us a large enough inobt + * record cache that grab_ichunk can stage a partial first record and + * the loop body can cache a record without having to check for cache + * space until after it reads an inobt record. + */ + iwag->nr_recs++; + ASSERT(iwag->nr_recs < iwag->sz_recs); + +out_advance: + return xfs_btree_increment(*curpp, 0, has_more); +} + +/* + * The inobt record cache is full, so preserve the inobt cursor state and + * run callbacks on the cached inobt records. When we're done, restore the + * cursor state to wherever the cursor would have been had the cache not been + * full (and therefore we could've just incremented the cursor) if *@has_more + * is true. On exit, *@has_more will indicate whether or not the caller should + * try for more inode records. + */ +STATIC int +xfs_iwalk_run_callbacks( + struct xfs_iwalk_ag *iwag, + xfs_agnumber_t agno, + struct xfs_btree_cur **curpp, + struct xfs_buf **agi_bpp, + int *has_more) +{ + struct xfs_mount *mp = iwag->mp; + struct xfs_trans *tp = iwag->tp; + struct xfs_inobt_rec_incore *irec; + xfs_agino_t restart; + int error; + + ASSERT(iwag->nr_recs > 0); + + /* Delete cursor but remember the last record we cached... */ + xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0); + irec = &iwag->recs[iwag->nr_recs - 1]; + restart = irec->ir_startino + XFS_INODES_PER_CHUNK - 1; + + error = xfs_iwalk_ag_recs(iwag); + if (error) + return error; + + /* ...empty the cache... */ + iwag->nr_recs = 0; + + if (!has_more) + return 0; + + /* ...and recreate the cursor just past where we left off. */ + error = xfs_inobt_cur(mp, tp, agno, XFS_BTNUM_INO, curpp, agi_bpp); + if (error) + return error; + + return xfs_inobt_lookup(*curpp, restart, XFS_LOOKUP_GE, has_more); +} + +/* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */ +STATIC int +xfs_iwalk_ag( + struct xfs_iwalk_ag *iwag) +{ + struct xfs_mount *mp = iwag->mp; + struct xfs_trans *tp = iwag->tp; + struct xfs_buf *agi_bp = NULL; + struct xfs_btree_cur *cur = NULL; + xfs_agnumber_t agno; + xfs_agino_t agino; + int has_more; + int error = 0; + + /* Set up our cursor at the right place in the inode btree. */ + agno = XFS_INO_TO_AGNO(mp, iwag->startino); + agino = XFS_INO_TO_AGINO(mp, iwag->startino); + error = xfs_iwalk_ag_start(iwag, agno, agino, &cur, &agi_bp, &has_more); + + while (!error && has_more) { + struct xfs_inobt_rec_incore *irec; + + cond_resched(); + if (xfs_pwork_want_abort(&iwag->pwork)) + goto out; + + /* Fetch the inobt record. */ + irec = &iwag->recs[iwag->nr_recs]; + error = xfs_inobt_get_rec(cur, irec, &has_more); + if (error || !has_more) + break; + + /* No allocated inodes in this chunk; skip it. */ + if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) { + error = xfs_btree_increment(cur, 0, &has_more); + if (error) + break; + continue; + } + + /* + * Start readahead for this inode chunk in anticipation of + * walking the inodes. + */ + if (iwag->iwalk_fn) + xfs_iwalk_ichunk_ra(mp, agno, irec); + + /* + * If there's space in the buffer for more records, increment + * the btree cursor and grab more. + */ + if (++iwag->nr_recs < iwag->sz_recs) { + error = xfs_btree_increment(cur, 0, &has_more); + if (error || !has_more) + break; + continue; + } + + /* + * Otherwise, we need to save cursor state and run the callback + * function on the cached records. The run_callbacks function + * is supposed to return a cursor pointing to the record where + * we would be if we had been able to increment like above. + */ + ASSERT(has_more); + error = xfs_iwalk_run_callbacks(iwag, agno, &cur, &agi_bp, + &has_more); + } + + if (iwag->nr_recs == 0 || error) + goto out; + + /* Walk the unprocessed records in the cache. */ + error = xfs_iwalk_run_callbacks(iwag, agno, &cur, &agi_bp, &has_more); + +out: + xfs_iwalk_del_inobt(tp, &cur, &agi_bp, error); + return error; +} + +/* + * We experimentally determined that the reduction in ioctl call overhead + * diminishes when userspace asks for more than 2048 inodes, so we'll cap + * prefetch at this point. + */ +#define IWALK_MAX_INODE_PREFETCH (2048U) + +/* + * Given the number of inodes to prefetch, set the number of inobt records that + * we cache in memory, which controls the number of inodes we try to read + * ahead. Set the maximum if @inodes == 0. + */ +static inline unsigned int +xfs_iwalk_prefetch( + unsigned int inodes) +{ + unsigned int inobt_records; + + /* + * If the caller didn't tell us the number of inodes they wanted, + * assume the maximum prefetch possible for best performance. + * Otherwise, cap prefetch at that maximum so that we don't start an + * absurd amount of prefetch. + */ + if (inodes == 0) + inodes = IWALK_MAX_INODE_PREFETCH; + inodes = min(inodes, IWALK_MAX_INODE_PREFETCH); + + /* Round the inode count up to a full chunk. */ + inodes = round_up(inodes, XFS_INODES_PER_CHUNK); + + /* + * In order to convert the number of inodes to prefetch into an + * estimate of the number of inobt records to cache, we require a + * conversion factor that reflects our expectations of the average + * loading factor of an inode chunk. Based on data gathered, most + * (but not all) filesystems manage to keep the inode chunks totally + * full, so we'll underestimate slightly so that our readahead will + * still deliver the performance we want on aging filesystems: + * + * inobt = inodes / (INODES_PER_CHUNK * (4 / 5)); + * + * The funny math is to avoid integer division. + */ + inobt_records = (inodes * 5) / (4 * XFS_INODES_PER_CHUNK); + + /* + * Allocate enough space to prefetch at least two inobt records so that + * we can cache both the record where the iwalk started and the next + * record. This simplifies the AG inode walk loop setup code. + */ + return max(inobt_records, 2U); +} + +/* + * Walk all inodes in the filesystem starting from @startino. The @iwalk_fn + * will be called for each allocated inode, being passed the inode's number and + * @data. @max_prefetch controls how many inobt records' worth of inodes we + * try to readahead. + */ +int +xfs_iwalk( + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_ino_t startino, + unsigned int flags, + xfs_iwalk_fn iwalk_fn, + unsigned int inode_records, + void *data) +{ + struct xfs_iwalk_ag iwag = { + .mp = mp, + .tp = tp, + .iwalk_fn = iwalk_fn, + .data = data, + .startino = startino, + .sz_recs = xfs_iwalk_prefetch(inode_records), + .trim_start = 1, + .skip_empty = 1, + .pwork = XFS_PWORK_SINGLE_THREADED, + }; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); + int error; + + ASSERT(agno < mp->m_sb.sb_agcount); + ASSERT(!(flags & ~XFS_IWALK_FLAGS_ALL)); + + error = xfs_iwalk_alloc(&iwag); + if (error) + return error; + + for (; agno < mp->m_sb.sb_agcount; agno++) { + error = xfs_iwalk_ag(&iwag); + if (error) + break; + iwag.startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); + if (flags & XFS_INOBT_WALK_SAME_AG) + break; + } + + xfs_iwalk_free(&iwag); + return error; +} + +/* Run per-thread iwalk work. */ +static int +xfs_iwalk_ag_work( + struct xfs_mount *mp, + struct xfs_pwork *pwork) +{ + struct xfs_iwalk_ag *iwag; + int error = 0; + + iwag = container_of(pwork, struct xfs_iwalk_ag, pwork); + if (xfs_pwork_want_abort(pwork)) + goto out; + + error = xfs_iwalk_alloc(iwag); + if (error) + goto out; + + error = xfs_iwalk_ag(iwag); + xfs_iwalk_free(iwag); +out: + kmem_free(iwag); + return error; +} + +/* + * Walk all the inodes in the filesystem using multiple threads to process each + * AG. + */ +int +xfs_iwalk_threaded( + struct xfs_mount *mp, + xfs_ino_t startino, + unsigned int flags, + xfs_iwalk_fn iwalk_fn, + unsigned int inode_records, + bool polled, + void *data) +{ + 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); + if (error) + return error; + + for (; agno < mp->m_sb.sb_agcount; agno++) { + struct xfs_iwalk_ag *iwag; + + if (xfs_pwork_ctl_want_abort(&pctl)) + break; + + iwag = kmem_zalloc(sizeof(struct xfs_iwalk_ag), KM_SLEEP); + iwag->mp = mp; + iwag->iwalk_fn = iwalk_fn; + iwag->data = data; + iwag->startino = startino; + iwag->sz_recs = xfs_iwalk_prefetch(inode_records); + xfs_pwork_queue(&pctl, &iwag->pwork); + startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); + if (flags & XFS_INOBT_WALK_SAME_AG) + break; + } + + if (polled) + xfs_pwork_poll(&pctl); + return xfs_pwork_destroy(&pctl); +} + +/* + * Allow callers to cache up to a page's worth of inobt records. This reflects + * the existing inumbers prefetching behavior. Since the inobt walk does not + * itself do anything with the inobt records, we can set a fairly high limit + * here. + */ +#define MAX_INOBT_WALK_PREFETCH \ + (PAGE_SIZE / sizeof(struct xfs_inobt_rec_incore)) + +/* + * Given the number of records that the user wanted, set the number of inobt + * records that we buffer in memory. Set the maximum if @inobt_records == 0. + */ +static inline unsigned int +xfs_inobt_walk_prefetch( + unsigned int inobt_records) +{ + /* + * If the caller didn't tell us the number of inobt records they + * wanted, assume the maximum prefetch possible for best performance. + */ + if (inobt_records == 0) + inobt_records = MAX_INOBT_WALK_PREFETCH; + + /* + * Allocate enough space to prefetch at least two inobt records so that + * we can cache both the record where the iwalk started and the next + * record. This simplifies the AG inode walk loop setup code. + */ + inobt_records = max(inobt_records, 2U); + + /* + * Cap prefetch at that maximum so that we don't use an absurd amount + * of memory. + */ + return min_t(unsigned int, inobt_records, MAX_INOBT_WALK_PREFETCH); +} + +/* + * Walk all inode btree records in the filesystem starting from @startino. The + * @inobt_walk_fn will be called for each btree record, being passed the incore + * record and @data. @max_prefetch controls how many inobt records we try to + * cache ahead of time. + */ +int +xfs_inobt_walk( + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_ino_t startino, + unsigned int flags, + xfs_inobt_walk_fn inobt_walk_fn, + unsigned int inobt_records, + void *data) +{ + struct xfs_iwalk_ag iwag = { + .mp = mp, + .tp = tp, + .inobt_walk_fn = inobt_walk_fn, + .data = data, + .startino = startino, + .sz_recs = xfs_inobt_walk_prefetch(inobt_records), + .pwork = XFS_PWORK_SINGLE_THREADED, + }; + xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); + int error; + + ASSERT(agno < mp->m_sb.sb_agcount); + ASSERT(!(flags & ~XFS_INOBT_WALK_FLAGS_ALL)); + + error = xfs_iwalk_alloc(&iwag); + if (error) + return error; + + for (; agno < mp->m_sb.sb_agcount; agno++) { + error = xfs_iwalk_ag(&iwag); + if (error) + break; + iwag.startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); + if (flags & XFS_INOBT_WALK_SAME_AG) + break; + } + + xfs_iwalk_free(&iwag); + return error; +} diff --git a/fs/xfs/xfs_iwalk.h b/fs/xfs/xfs_iwalk.h new file mode 100644 index 000000000000..6c960e10ed4d --- /dev/null +++ b/fs/xfs/xfs_iwalk.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#ifndef __XFS_IWALK_H__ +#define __XFS_IWALK_H__ + +/* Walk all inodes in the filesystem starting from @startino. */ +typedef int (*xfs_iwalk_fn)(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_ino_t ino, void *data); +/* Return values for xfs_iwalk_fn. */ +#define XFS_IWALK_CONTINUE (XFS_ITER_CONTINUE) +#define XFS_IWALK_ABORT (XFS_ITER_ABORT) + +int xfs_iwalk(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t startino, + unsigned int flags, xfs_iwalk_fn iwalk_fn, + unsigned int inode_records, void *data); +int xfs_iwalk_threaded(struct xfs_mount *mp, xfs_ino_t startino, + unsigned int flags, xfs_iwalk_fn iwalk_fn, + unsigned int inode_records, bool poll, void *data); + +/* Only iterate inodes within the same AG as @startino. */ +#define XFS_IWALK_SAME_AG (0x1) + +#define XFS_IWALK_FLAGS_ALL (XFS_IWALK_SAME_AG) + +/* Walk all inode btree records in the filesystem starting from @startino. */ +typedef int (*xfs_inobt_walk_fn)(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_agnumber_t agno, + const struct xfs_inobt_rec_incore *irec, + void *data); +/* Return value (for xfs_inobt_walk_fn) that aborts the walk immediately. */ +#define XFS_INOBT_WALK_ABORT (XFS_IWALK_ABORT) + +int xfs_inobt_walk(struct xfs_mount *mp, struct xfs_trans *tp, + xfs_ino_t startino, unsigned int flags, + xfs_inobt_walk_fn inobt_walk_fn, unsigned int inobt_records, + void *data); + +/* Only iterate inobt records within the same AG as @startino. */ +#define XFS_INOBT_WALK_SAME_AG (XFS_IWALK_SAME_AG) + +#define XFS_INOBT_WALK_FLAGS_ALL (XFS_INOBT_WALK_SAME_AG) + +#endif /* __XFS_IWALK_H__ */ diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index edbd5a210df2..ca15105681ca 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -110,8 +110,6 @@ typedef __u32 xfs_nlink_t; #define current_restore_flags_nested(sp, f) \ (current->flags = ((current->flags & ~(f)) | (*(sp) & (f)))) -#define spinlock_destroy(lock) - #define NBBY 8 /* number of bits per byte */ /* @@ -221,6 +219,9 @@ static inline uint64_t howmany_64(uint64_t x, uint32_t y) return x; } +int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, + char *data, unsigned int op); + #define ASSERT_ALWAYS(expr) \ (likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__)) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 457ced3ee3e1..00e9f5c388d3 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -16,11 +16,7 @@ #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" -#include "xfs_log_recover.h" -#include "xfs_inode.h" #include "xfs_trace.h" -#include "xfs_fsops.h" -#include "xfs_cksum.h" #include "xfs_sysfs.h" #include "xfs_sb.h" #include "xfs_health.h" @@ -45,21 +41,14 @@ STATIC int xlog_space_left( struct xlog *log, atomic64_t *head); -STATIC int -xlog_sync( - struct xlog *log, - struct xlog_in_core *iclog); STATIC void xlog_dealloc_log( struct xlog *log); /* local state machine functions */ -STATIC void xlog_state_done_syncing(xlog_in_core_t *iclog, int); -STATIC void -xlog_state_do_callback( - struct xlog *log, - int aborted, - struct xlog_in_core *iclog); +STATIC void xlog_state_done_syncing( + struct xlog_in_core *iclog, + bool aborted); STATIC int xlog_state_get_iclog_space( struct xlog *log, @@ -107,8 +96,7 @@ STATIC void xlog_verify_iclog( struct xlog *log, struct xlog_in_core *iclog, - int count, - bool syncing); + int count); STATIC void xlog_verify_tail_lsn( struct xlog *log, @@ -117,7 +105,7 @@ xlog_verify_tail_lsn( #else #define xlog_verify_dest_ptr(a,b) #define xlog_verify_grant_tail(a) -#define xlog_verify_iclog(a,b,c,d) +#define xlog_verify_iclog(a,b,c) #define xlog_verify_tail_lsn(a,b,c) #endif @@ -541,32 +529,6 @@ xfs_log_done( return lsn; } -/* - * Attaches a new iclog I/O completion callback routine during - * transaction commit. If the log is in error state, a non-zero - * return code is handed back and the caller is responsible for - * executing the callback at an appropriate time. - */ -int -xfs_log_notify( - struct xlog_in_core *iclog, - xfs_log_callback_t *cb) -{ - int abortflg; - - spin_lock(&iclog->ic_callback_lock); - abortflg = (iclog->ic_state & XLOG_STATE_IOERROR); - if (!abortflg) { - ASSERT_ALWAYS((iclog->ic_state == XLOG_STATE_ACTIVE) || - (iclog->ic_state == XLOG_STATE_WANT_SYNC)); - cb->cb_next = NULL; - *(iclog->ic_callback_tail) = cb; - iclog->ic_callback_tail = &(cb->cb_next); - } - spin_unlock(&iclog->ic_callback_lock); - return abortflg; -} - int xfs_log_release_iclog( struct xfs_mount *mp, @@ -807,16 +769,12 @@ xfs_log_mount_finish( * The mount has failed. Cancel the recovery if it hasn't completed and destroy * the log. */ -int +void xfs_log_mount_cancel( struct xfs_mount *mp) { - int error; - - error = xlog_recover_cancel(mp->m_log); + xlog_recover_cancel(mp->m_log); xfs_log_unmount(mp); - - return error; } /* @@ -932,7 +890,7 @@ xfs_log_unmount_write(xfs_mount_t *mp) * 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_mp->m_logdev_targp)) { + xfs_readonly_buftarg(log->l_targ)) { ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); return 0; } @@ -1244,53 +1202,49 @@ xlog_space_left( } -/* - * Log function which is called when an io completes. - * - * The log manager needs its own routine, in order to control what - * happens with the buffer after the write completes. - */ static void -xlog_iodone(xfs_buf_t *bp) +xlog_ioend_work( + struct work_struct *work) { - struct xlog_in_core *iclog = bp->b_log_item; - struct xlog *l = iclog->ic_log; - int aborted = 0; + struct xlog_in_core *iclog = + container_of(work, struct xlog_in_core, ic_end_io_work); + struct xlog *log = iclog->ic_log; + bool aborted = false; + int error; + + error = blk_status_to_errno(iclog->ic_bio.bi_status); +#ifdef DEBUG + /* treat writes with injected CRC errors as failed */ + if (iclog->ic_fail_crc) + error = -EIO; +#endif /* - * Race to shutdown the filesystem if we see an error or the iclog is in - * IOABORT state. The IOABORT state is only set in DEBUG mode to inject - * CRC errors into log recovery. + * Race to shutdown the filesystem if we see an error. */ - if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR) || - iclog->ic_state & XLOG_STATE_IOABORT) { - if (iclog->ic_state & XLOG_STATE_IOABORT) - iclog->ic_state &= ~XLOG_STATE_IOABORT; - - xfs_buf_ioerror_alert(bp, __func__); - xfs_buf_stale(bp); - xfs_force_shutdown(l->l_mp, SHUTDOWN_LOG_IO_ERROR); + if (XFS_TEST_ERROR(error, log->l_mp, XFS_ERRTAG_IODONE_IOERR)) { + xfs_alert(log->l_mp, "log I/O error %d", error); + xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR); /* * This flag will be propagated to the trans-committed * callback routines to let them know that the log-commit * didn't succeed. */ - aborted = XFS_LI_ABORTED; + aborted = true; } else if (iclog->ic_state & XLOG_STATE_IOERROR) { - aborted = XFS_LI_ABORTED; + aborted = true; } - /* log I/O is always issued ASYNC */ - ASSERT(bp->b_flags & XBF_ASYNC); xlog_state_done_syncing(iclog, aborted); + bio_uninit(&iclog->ic_bio); /* - * drop the buffer lock now that we are done. Nothing references - * the buffer after this, so an unmount waiting on this lock can now - * tear it down safely. As such, it is unsafe to reference the buffer - * (bp) after the unlock as we could race with it being freed. + * Drop the lock to signal that we are done. Nothing references the + * iclog after this, so an unmount waiting on this lock can now tear it + * down safely. As such, it is unsafe to reference the iclog after the + * unlock as we could race with it being freed. */ - xfs_buf_unlock(bp); + up(&iclog->ic_sema); } /* @@ -1301,65 +1255,26 @@ xlog_iodone(xfs_buf_t *bp) * If the filesystem blocksize is too large, we may need to choose a * larger size since the directory code currently logs entire blocks. */ - STATIC void xlog_get_iclog_buffer_size( struct xfs_mount *mp, struct xlog *log) { - int size; - int xhdrs; - if (mp->m_logbufs <= 0) - log->l_iclog_bufs = XLOG_MAX_ICLOGS; - else - log->l_iclog_bufs = mp->m_logbufs; + mp->m_logbufs = XLOG_MAX_ICLOGS; + if (mp->m_logbsize <= 0) + mp->m_logbsize = XLOG_BIG_RECORD_BSIZE; + + log->l_iclog_bufs = mp->m_logbufs; + log->l_iclog_size = mp->m_logbsize; /* - * Buffer size passed in from mount system call. + * # headers = size / 32k - one header holds cycles from 32k of data. */ - if (mp->m_logbsize > 0) { - size = log->l_iclog_size = mp->m_logbsize; - log->l_iclog_size_log = 0; - while (size != 1) { - log->l_iclog_size_log++; - size >>= 1; - } - - if (xfs_sb_version_haslogv2(&mp->m_sb)) { - /* # headers = size / 32k - * one header holds cycles from 32k of data - */ - - xhdrs = mp->m_logbsize / XLOG_HEADER_CYCLE_SIZE; - if (mp->m_logbsize % XLOG_HEADER_CYCLE_SIZE) - xhdrs++; - log->l_iclog_hsize = xhdrs << BBSHIFT; - log->l_iclog_heads = xhdrs; - } else { - ASSERT(mp->m_logbsize <= XLOG_BIG_RECORD_BSIZE); - log->l_iclog_hsize = BBSIZE; - log->l_iclog_heads = 1; - } - goto done; - } - - /* All machines use 32kB buffers by default. */ - log->l_iclog_size = XLOG_BIG_RECORD_BSIZE; - log->l_iclog_size_log = XLOG_BIG_RECORD_BSHIFT; - - /* the default log size is 16k or 32k which is one header sector */ - log->l_iclog_hsize = BBSIZE; - log->l_iclog_heads = 1; - -done: - /* are we being asked to make the sizes selected above visible? */ - if (mp->m_logbufs == 0) - mp->m_logbufs = log->l_iclog_bufs; - if (mp->m_logbsize == 0) - mp->m_logbsize = log->l_iclog_size; -} /* xlog_get_iclog_buffer_size */ - + log->l_iclog_heads = + DIV_ROUND_UP(mp->m_logbsize, XLOG_HEADER_CYCLE_SIZE); + log->l_iclog_hsize = log->l_iclog_heads << BBSHIFT; +} void xfs_log_work_queue( @@ -1422,7 +1337,6 @@ xlog_alloc_log( xlog_rec_header_t *head; xlog_in_core_t **iclogp; xlog_in_core_t *iclog, *prev_iclog=NULL; - xfs_buf_t *bp; int i; int error = -ENOMEM; uint log2_size = 0; @@ -1480,30 +1394,6 @@ xlog_alloc_log( xlog_get_iclog_buffer_size(mp, log); - /* - * Use a NULL block for the extra log buffer used during splits so that - * it will trigger errors if we ever try to do IO on it without first - * having set it up properly. - */ - error = -ENOMEM; - bp = xfs_buf_alloc(mp->m_logdev_targp, XFS_BUF_DADDR_NULL, - BTOBB(log->l_iclog_size), XBF_NO_IOACCT); - if (!bp) - goto out_free_log; - - /* - * The iclogbuf buffer locks are held over IO but we are not going to do - * IO yet. Hence unlock the buffer so that the log IO path can grab it - * when appropriately. - */ - ASSERT(xfs_buf_islocked(bp)); - xfs_buf_unlock(bp); - - /* use high priority wq for log I/O completion */ - bp->b_ioend_wq = mp->m_log_workqueue; - bp->b_iodone = xlog_iodone; - log->l_xbuf = bp; - spin_lock_init(&log->l_icloglock); init_waitqueue_head(&log->l_flush_wait); @@ -1516,29 +1406,22 @@ xlog_alloc_log( * xlog_in_core_t in xfs_log_priv.h for details. */ ASSERT(log->l_iclog_size >= 4096); - for (i=0; i < log->l_iclog_bufs; i++) { - *iclogp = kmem_zalloc(sizeof(xlog_in_core_t), KM_MAYFAIL); - if (!*iclogp) + for (i = 0; i < log->l_iclog_bufs; i++) { + size_t bvec_size = howmany(log->l_iclog_size, PAGE_SIZE) * + sizeof(struct bio_vec); + + iclog = kmem_zalloc(sizeof(*iclog) + bvec_size, KM_MAYFAIL); + if (!iclog) goto out_free_iclog; - iclog = *iclogp; + *iclogp = iclog; iclog->ic_prev = prev_iclog; prev_iclog = iclog; - bp = xfs_buf_get_uncached(mp->m_logdev_targp, - BTOBB(log->l_iclog_size), - XBF_NO_IOACCT); - if (!bp) + iclog->ic_data = kmem_alloc_large(log->l_iclog_size, + KM_MAYFAIL); + if (!iclog->ic_data) goto out_free_iclog; - - ASSERT(xfs_buf_islocked(bp)); - xfs_buf_unlock(bp); - - /* use high priority wq for log I/O completion */ - bp->b_ioend_wq = mp->m_log_workqueue; - bp->b_iodone = xlog_iodone; - iclog->ic_bp = bp; - iclog->ic_data = bp->b_addr; #ifdef DEBUG log->l_iclog_bak[i] = &iclog->ic_header; #endif @@ -1552,36 +1435,43 @@ xlog_alloc_log( head->h_fmt = cpu_to_be32(XLOG_FMT); memcpy(&head->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(uuid_t)); - iclog->ic_size = BBTOB(bp->b_length) - log->l_iclog_hsize; + iclog->ic_size = log->l_iclog_size - log->l_iclog_hsize; iclog->ic_state = XLOG_STATE_ACTIVE; iclog->ic_log = log; atomic_set(&iclog->ic_refcnt, 0); spin_lock_init(&iclog->ic_callback_lock); - iclog->ic_callback_tail = &(iclog->ic_callback); + INIT_LIST_HEAD(&iclog->ic_callbacks); iclog->ic_datap = (char *)iclog->ic_data + log->l_iclog_hsize; init_waitqueue_head(&iclog->ic_force_wait); init_waitqueue_head(&iclog->ic_write_wait); + INIT_WORK(&iclog->ic_end_io_work, xlog_ioend_work); + sema_init(&iclog->ic_sema, 1); iclogp = &iclog->ic_next; } *iclogp = log->l_iclog; /* complete ring */ 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_fsname); + if (!log->l_ioend_workqueue) + goto out_free_iclog; + error = xlog_cil_init(log); if (error) - goto out_free_iclog; + goto out_destroy_workqueue; return log; +out_destroy_workqueue: + destroy_workqueue(log->l_ioend_workqueue); out_free_iclog: for (iclog = log->l_iclog; iclog; iclog = prev_iclog) { prev_iclog = iclog->ic_next; - if (iclog->ic_bp) - xfs_buf_free(iclog->ic_bp); + kmem_free(iclog->ic_data); kmem_free(iclog); } - spinlock_destroy(&log->l_icloglock); - xfs_buf_free(log->l_xbuf); out_free_log: kmem_free(log); out: @@ -1766,42 +1656,155 @@ xlog_cksum( return xfs_end_cksum(crc); } -/* - * The bdstrat callback function for log bufs. This gives us a central - * place to trap bufs in case we get hit by a log I/O error and need to - * shutdown. Actually, in practice, even when we didn't get a log error, - * we transition the iclogs to IOERROR state *after* flushing all existing - * iclogs to disk. This is because we don't want anymore new transactions to be - * started or completed afterwards. - * - * We lock the iclogbufs here so that we can serialise against IO completion - * during unmount. We might be processing a shutdown triggered during unmount, - * and that can occur asynchronously to the unmount thread, and hence we need to - * ensure that completes before tearing down the iclogbufs. Hence we need to - * hold the buffer lock across the log IO to acheive that. - */ -STATIC int -xlog_bdstrat( - struct xfs_buf *bp) +static void +xlog_bio_end_io( + struct bio *bio) { - struct xlog_in_core *iclog = bp->b_log_item; + struct xlog_in_core *iclog = bio->bi_private; - xfs_buf_lock(bp); - if (iclog->ic_state & XLOG_STATE_IOERROR) { - xfs_buf_ioerror(bp, -EIO); - xfs_buf_stale(bp); - xfs_buf_ioend(bp); + queue_work(iclog->ic_log->l_ioend_workqueue, + &iclog->ic_end_io_work); +} + +static void +xlog_map_iclog_data( + struct bio *bio, + void *data, + size_t count) +{ + do { + struct page *page = kmem_to_page(data); + unsigned int off = offset_in_page(data); + size_t len = min_t(size_t, count, PAGE_SIZE - off); + + WARN_ON_ONCE(bio_add_page(bio, page, len, off) != len); + + data += len; + count -= len; + } while (count); +} + +STATIC void +xlog_write_iclog( + struct xlog *log, + struct xlog_in_core *iclog, + uint64_t bno, + unsigned int count, + bool need_flush) +{ + ASSERT(bno < log->l_logBBsize); + + /* + * We lock the iclogbufs here so that we can serialise against I/O + * completion during unmount. We might be processing a shutdown + * triggered during unmount, and that can occur asynchronously to the + * unmount thread, and hence we need to ensure that completes before + * tearing down the iclogbufs. Hence we need to hold the buffer lock + * across the log IO to archieve that. + */ + down(&iclog->ic_sema); + if (unlikely(iclog->ic_state & XLOG_STATE_IOERROR)) { /* * It would seem logical to return EIO here, but we rely on * the log state machine to propagate I/O errors instead of - * doing it here. Similarly, IO completion will unlock the - * buffer, so we don't do it here. + * doing it here. We kick of the state machine and unlock + * the buffer manually, the code needs to be kept in sync + * with the I/O completion path. */ - return 0; + xlog_state_done_syncing(iclog, XFS_LI_ABORTED); + up(&iclog->ic_sema); + return; } - xfs_buf_submit(bp); - return 0; + iclog->ic_io_size = count; + + bio_init(&iclog->ic_bio, iclog->ic_bvec, howmany(count, PAGE_SIZE)); + bio_set_dev(&iclog->ic_bio, log->l_targ->bt_bdev); + iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart + bno; + iclog->ic_bio.bi_end_io = xlog_bio_end_io; + iclog->ic_bio.bi_private = iclog; + iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_FUA; + if (need_flush) + iclog->ic_bio.bi_opf |= REQ_PREFLUSH; + + xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, iclog->ic_io_size); + if (is_vmalloc_addr(iclog->ic_data)) + flush_kernel_vmap_range(iclog->ic_data, iclog->ic_io_size); + + /* + * If this log buffer would straddle the end of the log we will have + * to split it up into two bios, so that we can continue at the start. + */ + if (bno + BTOBB(count) > log->l_logBBsize) { + struct bio *split; + + split = bio_split(&iclog->ic_bio, log->l_logBBsize - bno, + GFP_NOIO, &fs_bio_set); + bio_chain(split, &iclog->ic_bio); + submit_bio(split); + + /* restart at logical offset zero for the remainder */ + iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart; + } + + submit_bio(&iclog->ic_bio); +} + +/* + * We need to bump cycle number for the part of the iclog that is + * written to the start of the log. Watch out for the header magic + * number case, though. + */ +static void +xlog_split_iclog( + struct xlog *log, + void *data, + uint64_t bno, + unsigned int count) +{ + unsigned int split_offset = BBTOB(log->l_logBBsize - bno); + unsigned int i; + + for (i = split_offset; i < count; i += BBSIZE) { + uint32_t cycle = get_unaligned_be32(data + i); + + if (++cycle == XLOG_HEADER_MAGIC_NUM) + cycle++; + put_unaligned_be32(cycle, data + i); + } +} + +static int +xlog_calc_iclog_size( + struct xlog *log, + struct xlog_in_core *iclog, + uint32_t *roundoff) +{ + uint32_t count_init, count; + bool use_lsunit; + + use_lsunit = xfs_sb_version_haslogv2(&log->l_mp->m_sb) && + log->l_mp->m_sb.sb_logsunit > 1; + + /* Add for LR header */ + count_init = log->l_iclog_hsize + iclog->ic_offset; + + /* Round out the log write size */ + if (use_lsunit) { + /* we have a v2 stripe unit to use */ + count = XLOG_LSUNITTOB(log, XLOG_BTOLSUNIT(log, count_init)); + } else { + count = BBTOB(BTOBB(count_init)); + } + + ASSERT(count >= count_init); + *roundoff = count - count_init; + + if (use_lsunit) + ASSERT(*roundoff < log->l_mp->m_sb.sb_logsunit); + else + ASSERT(*roundoff < BBTOB(1)); + return count; } /* @@ -1824,46 +1827,23 @@ xlog_bdstrat( * log will require grabbing the lock though. * * The entire log manager uses a logical block numbering scheme. Only - * log_sync (and then only bwrite()) know about the fact that the log may - * not start with block zero on a given device. The log block start offset - * is added immediately before calling bwrite(). + * xlog_write_iclog knows about the fact that the log may not start with + * block zero on a given device. */ - -STATIC int +STATIC void xlog_sync( struct xlog *log, struct xlog_in_core *iclog) { - xfs_buf_t *bp; - int i; - uint count; /* byte count of bwrite */ - uint count_init; /* initial count before roundup */ - int roundoff; /* roundoff to BB or stripe */ - int split = 0; /* split write into two regions */ - int error; - int v2 = xfs_sb_version_haslogv2(&log->l_mp->m_sb); - int size; + unsigned int count; /* byte count of bwrite */ + unsigned int roundoff; /* roundoff to BB or stripe */ + uint64_t bno; + unsigned int size; + bool need_flush = true, split = false; - XFS_STATS_INC(log->l_mp, xs_log_writes); ASSERT(atomic_read(&iclog->ic_refcnt) == 0); - /* Add for LR header */ - count_init = log->l_iclog_hsize + iclog->ic_offset; - - /* Round out the log write size */ - if (v2 && log->l_mp->m_sb.sb_logsunit > 1) { - /* we have a v2 stripe unit to use */ - count = XLOG_LSUNITTOB(log, XLOG_BTOLSUNIT(log, count_init)); - } else { - count = BBTOB(BTOBB(count_init)); - } - roundoff = count - count_init; - ASSERT(roundoff >= 0); - ASSERT((v2 && log->l_mp->m_sb.sb_logsunit > 1 && - roundoff < log->l_mp->m_sb.sb_logsunit) - || - (log->l_mp->m_sb.sb_logsunit <= 1 && - roundoff < BBTOB(1))); + count = xlog_calc_iclog_size(log, iclog, &roundoff); /* move grant heads by roundoff in sync */ xlog_grant_add_space(log, &log->l_reserve_head.grant, roundoff); @@ -1874,41 +1854,19 @@ xlog_sync( /* real byte length */ size = iclog->ic_offset; - if (v2) + if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) size += roundoff; iclog->ic_header.h_len = cpu_to_be32(size); - bp = iclog->ic_bp; - XFS_BUF_SET_ADDR(bp, BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn))); - + XFS_STATS_INC(log->l_mp, xs_log_writes); XFS_STATS_ADD(log->l_mp, xs_log_blocks, BTOBB(count)); - /* Do we need to split this write into 2 parts? */ - if (XFS_BUF_ADDR(bp) + BTOBB(count) > log->l_logBBsize) { - char *dptr; - - split = count - (BBTOB(log->l_logBBsize - XFS_BUF_ADDR(bp))); - count = BBTOB(log->l_logBBsize - XFS_BUF_ADDR(bp)); - iclog->ic_bwritecnt = 2; + bno = BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn)); - /* - * Bump the cycle numbers at the start of each block in the - * part of the iclog that ends up in the buffer that gets - * written to the start of the log. - * - * Watch out for the header magic number case, though. - */ - dptr = (char *)&iclog->ic_header + count; - for (i = 0; i < split; i += BBSIZE) { - uint32_t cycle = be32_to_cpu(*(__be32 *)dptr); - if (++cycle == XLOG_HEADER_MAGIC_NUM) - cycle++; - *(__be32 *)dptr = cpu_to_be32(cycle); - - dptr += BBSIZE; - } - } else { - iclog->ic_bwritecnt = 1; + /* Do we need to split this write into 2 parts? */ + if (bno + BTOBB(count) > log->l_logBBsize) { + xlog_split_iclog(log, &iclog->ic_header, bno, count); + split = true; } /* calculcate the checksum */ @@ -1921,18 +1879,15 @@ xlog_sync( * write on I/O completion and shutdown the fs. The subsequent mount * detects the bad CRC and attempts to recover. */ +#ifdef DEBUG if (XFS_TEST_ERROR(false, log->l_mp, XFS_ERRTAG_LOG_BAD_CRC)) { iclog->ic_header.h_crc &= cpu_to_le32(0xAAAAAAAA); - iclog->ic_state |= XLOG_STATE_IOABORT; + iclog->ic_fail_crc = true; xfs_warn(log->l_mp, "Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.", be64_to_cpu(iclog->ic_header.h_lsn)); } - - bp->b_io_length = BTOBB(count); - bp->b_log_item = iclog; - bp->b_flags &= ~XBF_FLUSH; - bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE | XBF_FUA); +#endif /* * Flush the data device before flushing the log to make sure all meta @@ -1942,50 +1897,14 @@ xlog_sync( * synchronously here; for an internal log we can simply use the block * layer state machine for preflushes. */ - if (log->l_mp->m_logdev_targp != log->l_mp->m_ddev_targp) + if (log->l_targ != log->l_mp->m_ddev_targp || split) { xfs_blkdev_issue_flush(log->l_mp->m_ddev_targp); - else - bp->b_flags |= XBF_FLUSH; - - ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1); - ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize); - - xlog_verify_iclog(log, iclog, count, true); - - /* account for log which doesn't start at block #0 */ - XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart); - - /* - * Don't call xfs_bwrite here. We do log-syncs even when the filesystem - * is shutting down. - */ - error = xlog_bdstrat(bp); - if (error) { - xfs_buf_ioerror_alert(bp, "xlog_sync"); - return error; + need_flush = false; } - if (split) { - bp = iclog->ic_log->l_xbuf; - XFS_BUF_SET_ADDR(bp, 0); /* logical 0 */ - xfs_buf_associate_memory(bp, - (char *)&iclog->ic_header + count, split); - bp->b_log_item = iclog; - bp->b_flags &= ~XBF_FLUSH; - bp->b_flags |= (XBF_ASYNC | XBF_SYNCIO | XBF_WRITE | XBF_FUA); - - ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1); - ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize); - - /* account for internal log which doesn't start at block #0 */ - XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart); - error = xlog_bdstrat(bp); - if (error) { - xfs_buf_ioerror_alert(bp, "xlog_sync (split)"); - return error; - } - } - return 0; -} /* xlog_sync */ + + xlog_verify_iclog(log, iclog, count); + xlog_write_iclog(log, iclog, bno, count, need_flush); +} /* * Deallocate a log structure @@ -2005,31 +1924,21 @@ xlog_dealloc_log( */ iclog = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++) { - xfs_buf_lock(iclog->ic_bp); - xfs_buf_unlock(iclog->ic_bp); + down(&iclog->ic_sema); + up(&iclog->ic_sema); iclog = iclog->ic_next; } - /* - * Always need to ensure that the extra buffer does not point to memory - * owned by another log buffer before we free it. Also, cycle the lock - * first to ensure we've completed IO on it. - */ - xfs_buf_lock(log->l_xbuf); - xfs_buf_unlock(log->l_xbuf); - xfs_buf_set_empty(log->l_xbuf, BTOBB(log->l_iclog_size)); - xfs_buf_free(log->l_xbuf); - iclog = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++) { - xfs_buf_free(iclog->ic_bp); next_iclog = iclog->ic_next; + kmem_free(iclog->ic_data); kmem_free(iclog); iclog = next_iclog; } - spinlock_destroy(&log->l_icloglock); log->l_mp->m_log = NULL; + destroy_workqueue(log->l_ioend_workqueue); kmem_free(log); } /* xlog_dealloc_log */ @@ -2069,7 +1978,7 @@ xlog_print_tic_res( /* match with XLOG_REG_TYPE_* in xfs_log.h */ #define REG_TYPE_STR(type, str) [XLOG_REG_TYPE_##type] = str - static char *res_type_str[XLOG_REG_TYPE_MAX + 1] = { + static char *res_type_str[] = { REG_TYPE_STR(BFORMAT, "bformat"), REG_TYPE_STR(BCHUNK, "bchunk"), REG_TYPE_STR(EFI_FORMAT, "efi_format"), @@ -2089,8 +1998,15 @@ xlog_print_tic_res( REG_TYPE_STR(UNMOUNT, "unmount"), REG_TYPE_STR(COMMIT, "commit"), REG_TYPE_STR(TRANSHDR, "trans header"), - REG_TYPE_STR(ICREATE, "inode create") + REG_TYPE_STR(ICREATE, "inode create"), + REG_TYPE_STR(RUI_FORMAT, "rui_format"), + REG_TYPE_STR(RUD_FORMAT, "rud_format"), + REG_TYPE_STR(CUI_FORMAT, "cui_format"), + REG_TYPE_STR(CUD_FORMAT, "cud_format"), + REG_TYPE_STR(BUI_FORMAT, "bui_format"), + REG_TYPE_STR(BUD_FORMAT, "bud_format"), }; + BUILD_BUG_ON(ARRAY_SIZE(res_type_str) != XLOG_REG_TYPE_MAX + 1); #undef REG_TYPE_STR xfs_warn(mp, "ticket reservation summary:"); @@ -2603,7 +2519,7 @@ xlog_state_clean_log( if (iclog->ic_state == XLOG_STATE_DIRTY) { iclog->ic_state = XLOG_STATE_ACTIVE; iclog->ic_offset = 0; - ASSERT(iclog->ic_callback == NULL); + ASSERT(list_empty_careful(&iclog->ic_callbacks)); /* * If the number of ops in this iclog indicate it just * contains the dummy transaction, we can @@ -2673,37 +2589,32 @@ xlog_state_clean_log( STATIC xfs_lsn_t xlog_get_lowest_lsn( - struct xlog *log) + struct xlog *log) { - xlog_in_core_t *lsn_log; - xfs_lsn_t lowest_lsn, lsn; + struct xlog_in_core *iclog = log->l_iclog; + xfs_lsn_t lowest_lsn = 0, lsn; - lsn_log = log->l_iclog; - lowest_lsn = 0; do { - if (!(lsn_log->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_DIRTY))) { - lsn = be64_to_cpu(lsn_log->ic_header.h_lsn); - if ((lsn && !lowest_lsn) || - (XFS_LSN_CMP(lsn, lowest_lsn) < 0)) { + if (iclog->ic_state & (XLOG_STATE_ACTIVE | XLOG_STATE_DIRTY)) + continue; + + lsn = be64_to_cpu(iclog->ic_header.h_lsn); + if ((lsn && !lowest_lsn) || XFS_LSN_CMP(lsn, lowest_lsn) < 0) lowest_lsn = lsn; - } - } - lsn_log = lsn_log->ic_next; - } while (lsn_log != log->l_iclog); + } while ((iclog = iclog->ic_next) != log->l_iclog); + return lowest_lsn; } - STATIC void xlog_state_do_callback( struct xlog *log, - int aborted, + bool aborted, struct xlog_in_core *ciclog) { xlog_in_core_t *iclog; xlog_in_core_t *first_iclog; /* used to know when we've * processed all iclogs once */ - xfs_log_callback_t *cb, *cb_next; int flushcnt = 0; xfs_lsn_t lowest_lsn; int ioerrors; /* counter: iclogs with errors */ @@ -2814,7 +2725,7 @@ xlog_state_do_callback( */ ASSERT(XFS_LSN_CMP(atomic64_read(&log->l_last_sync_lsn), be64_to_cpu(iclog->ic_header.h_lsn)) <= 0); - if (iclog->ic_callback) + if (!list_empty_careful(&iclog->ic_callbacks)) atomic64_set(&log->l_last_sync_lsn, be64_to_cpu(iclog->ic_header.h_lsn)); @@ -2831,26 +2742,20 @@ xlog_state_do_callback( * callbacks being added. */ spin_lock(&iclog->ic_callback_lock); - cb = iclog->ic_callback; - while (cb) { - iclog->ic_callback_tail = &(iclog->ic_callback); - iclog->ic_callback = NULL; - spin_unlock(&iclog->ic_callback_lock); + while (!list_empty(&iclog->ic_callbacks)) { + LIST_HEAD(tmp); - /* perform callbacks in the order given */ - for (; cb; cb = cb_next) { - cb_next = cb->cb_next; - cb->cb_func(cb->cb_arg, aborted); - } + list_splice_init(&iclog->ic_callbacks, &tmp); + + spin_unlock(&iclog->ic_callback_lock); + xlog_cil_process_committed(&tmp, aborted); spin_lock(&iclog->ic_callback_lock); - cb = iclog->ic_callback; } loopdidcallbacks++; funcdidcallbacks++; spin_lock(&log->l_icloglock); - ASSERT(iclog->ic_callback == NULL); spin_unlock(&iclog->ic_callback_lock); if (!(iclog->ic_state & XLOG_STATE_IOERROR)) iclog->ic_state = XLOG_STATE_DIRTY; @@ -2936,18 +2841,16 @@ xlog_state_do_callback( */ STATIC void xlog_state_done_syncing( - xlog_in_core_t *iclog, - int aborted) + struct xlog_in_core *iclog, + bool aborted) { - struct xlog *log = iclog->ic_log; + struct xlog *log = iclog->ic_log; spin_lock(&log->l_icloglock); ASSERT(iclog->ic_state == XLOG_STATE_SYNCING || iclog->ic_state == XLOG_STATE_IOERROR); ASSERT(atomic_read(&iclog->ic_refcnt) == 0); - ASSERT(iclog->ic_bwritecnt == 1 || iclog->ic_bwritecnt == 2); - /* * If we got an error, either on the first buffer, or in the case of @@ -2955,13 +2858,8 @@ xlog_state_done_syncing( * and none should ever be attempted to be written to disk * again. */ - if (iclog->ic_state != XLOG_STATE_IOERROR) { - if (--iclog->ic_bwritecnt == 1) { - spin_unlock(&log->l_icloglock); - return; - } + if (iclog->ic_state != XLOG_STATE_IOERROR) iclog->ic_state = XLOG_STATE_DONE_SYNC; - } /* * Someone could be sleeping prior to writing out the next @@ -3230,7 +3128,7 @@ xlog_state_release_iclog( * flags after this point. */ if (sync) - return xlog_sync(log, iclog); + xlog_sync(log, iclog); return 0; } /* xlog_state_release_iclog */ @@ -3821,8 +3719,7 @@ STATIC void xlog_verify_iclog( struct xlog *log, struct xlog_in_core *iclog, - int count, - bool syncing) + int count) { xlog_op_header_t *ophead; xlog_in_core_t *icptr; @@ -3866,7 +3763,7 @@ xlog_verify_iclog( /* clientid is only 1 byte */ p = &ophead->oh_clientid; field_offset = p - base_ptr; - if (!syncing || (field_offset & 0x1ff)) { + if (field_offset & 0x1ff) { clientid = ophead->oh_clientid; } else { idx = BTOBBT((char *)&ophead->oh_clientid - iclog->ic_datap); @@ -3889,7 +3786,7 @@ xlog_verify_iclog( /* check length */ p = &ophead->oh_len; field_offset = p - base_ptr; - if (!syncing || (field_offset & 0x1ff)) { + if (field_offset & 0x1ff) { op_len = be32_to_cpu(ophead->oh_len); } else { idx = BTOBBT((uintptr_t)&ophead->oh_len - @@ -4026,7 +3923,7 @@ xfs_log_force_umount( * avoid races. */ wake_up_all(&log->l_cilp->xc_commit_wait); - xlog_state_do_callback(log, XFS_LI_ABORTED, NULL); + xlog_state_do_callback(log, true, NULL); #ifdef XFSERRORDEBUG { diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 73a64bf32f6f..84e06805160f 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -6,6 +6,8 @@ #ifndef __XFS_LOG_H__ #define __XFS_LOG_H__ +struct xfs_cil_ctx; + struct xfs_log_vec { struct xfs_log_vec *lv_next; /* next lv in build list */ int lv_niovecs; /* number of iovecs in lv */ @@ -72,16 +74,6 @@ xlog_copy_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp, } /* - * Structure used to pass callback function and the function's argument - * to the log manager. - */ -typedef struct xfs_log_callback { - struct xfs_log_callback *cb_next; - void (*cb_func)(void *, int); - void *cb_arg; -} xfs_log_callback_t; - -/* * By comparing each component, we don't have to worry about extra * endian issues in treating two 32 bit numbers as one 64 bit number */ @@ -125,12 +117,10 @@ int xfs_log_mount(struct xfs_mount *mp, xfs_daddr_t start_block, int num_bblocks); int xfs_log_mount_finish(struct xfs_mount *mp); -int xfs_log_mount_cancel(struct xfs_mount *); +void xfs_log_mount_cancel(struct xfs_mount *); xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp); xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp); void xfs_log_space_wake(struct xfs_mount *mp); -int xfs_log_notify(struct xlog_in_core *iclog, - struct xfs_log_callback *callback_entry); int xfs_log_release_iclog(struct xfs_mount *mp, struct xlog_in_core *iclog); int xfs_log_reserve(struct xfs_mount *mp, @@ -148,6 +138,7 @@ void xfs_log_ticket_put(struct xlog_ticket *ticket); void xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp, xfs_lsn_t *commit_lsn, bool regrant); +void xlog_cil_process_committed(struct list_head *list, bool aborted); bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip); void xfs_log_work_queue(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index 5e595948bc5a..fa5602d0fd7f 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -10,10 +10,7 @@ #include "xfs_shared.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_error.h" -#include "xfs_alloc.h" #include "xfs_extent_busy.h" -#include "xfs_discard.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" @@ -246,7 +243,8 @@ xfs_cil_prepare_item( * shadow buffer, so update the the pointer to it appropriately. */ if (!old_lv) { - lv->lv_item->li_ops->iop_pin(lv->lv_item); + if (lv->lv_item->li_ops->iop_pin) + lv->lv_item->li_ops->iop_pin(lv->lv_item); lv->lv_item->li_lv_shadow = NULL; } else if (old_lv != lv) { ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED); @@ -576,10 +574,9 @@ xlog_discard_busy_extents( */ static void xlog_cil_committed( - void *args, - int abort) + struct xfs_cil_ctx *ctx, + bool abort) { - struct xfs_cil_ctx *ctx = args; struct xfs_mount *mp = ctx->cil->xc_log->l_mp; /* @@ -614,6 +611,20 @@ xlog_cil_committed( kmem_free(ctx); } +void +xlog_cil_process_committed( + struct list_head *list, + bool aborted) +{ + struct xfs_cil_ctx *ctx; + + while ((ctx = list_first_entry_or_null(list, + struct xfs_cil_ctx, iclog_entry))) { + list_del(&ctx->iclog_entry); + xlog_cil_committed(ctx, aborted); + } +} + /* * Push the Committed Item List to the log. If @push_seq flag is zero, then it * is a background flush and so we can chose to ignore it. Otherwise, if the @@ -835,12 +846,15 @@ restart: if (commit_lsn == -1) goto out_abort; - /* attach all the transactions w/ busy extents to iclog */ - ctx->log_cb.cb_func = xlog_cil_committed; - ctx->log_cb.cb_arg = ctx; - error = xfs_log_notify(commit_iclog, &ctx->log_cb); - if (error) + spin_lock(&commit_iclog->ic_callback_lock); + if (commit_iclog->ic_state & XLOG_STATE_IOERROR) { + spin_unlock(&commit_iclog->ic_callback_lock); goto out_abort; + } + ASSERT_ALWAYS(commit_iclog->ic_state == XLOG_STATE_ACTIVE || + commit_iclog->ic_state == XLOG_STATE_WANT_SYNC); + list_add_tail(&ctx->iclog_entry, &commit_iclog->ic_callbacks); + spin_unlock(&commit_iclog->ic_callback_lock); /* * now the checkpoint commit is complete and we've attached the @@ -864,7 +878,7 @@ out_skip: out_abort_free_ticket: xfs_log_ticket_put(tic); out_abort: - xlog_cil_committed(ctx, XFS_LI_ABORTED); + xlog_cil_committed(ctx, true); return -EIO; } @@ -984,6 +998,7 @@ xfs_log_commit_cil( { struct xlog *log = mp->m_log; struct xfs_cil *cil = log->l_cilp; + struct xfs_log_item *lip, *next; xfs_lsn_t xc_commit_lsn; /* @@ -1008,7 +1023,7 @@ xfs_log_commit_cil( /* * Once all the items of the transaction have been copied to the CIL, - * the items can be unlocked and freed. + * the items can be unlocked and possibly freed. * * This needs to be done before we drop the CIL context lock because we * have to update state in the log items and unlock them before they go @@ -1017,8 +1032,12 @@ xfs_log_commit_cil( * the log items. This affects (at least) processing of stale buffers, * inodes and EFIs. */ - xfs_trans_free_items(tp, xc_commit_lsn, false); - + trace_xfs_trans_commit_items(tp, _RET_IP_); + list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { + xfs_trans_del_item(lip); + if (lip->li_ops->iop_committing) + lip->li_ops->iop_committing(lip, xc_commit_lsn); + } xlog_cil_push_background(log); up_read(&cil->xc_ctx_lock); diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index b5f82cb36202..b880c23cb6e4 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -10,7 +10,6 @@ struct xfs_buf; struct xlog; struct xlog_ticket; struct xfs_mount; -struct xfs_log_callback; /* * Flags for log structure @@ -50,7 +49,6 @@ static inline uint xlog_get_client_id(__be32 i) #define XLOG_STATE_CALLBACK 0x0020 /* Callback functions now */ #define XLOG_STATE_DIRTY 0x0040 /* Dirty IC log, not ready for ACTIVE status*/ #define XLOG_STATE_IOERROR 0x0080 /* IO error happened in sync'ing log */ -#define XLOG_STATE_IOABORT 0x0100 /* force abort on I/O completion (debug) */ #define XLOG_STATE_ALL 0x7FFF /* All possible valid flags */ #define XLOG_STATE_NOTUSED 0x8000 /* This IC log not being used */ @@ -179,11 +177,10 @@ typedef struct xlog_ticket { * the iclog. * - ic_forcewait is used to implement synchronous forcing of the iclog to disk. * - ic_next is the pointer to the next iclog in the ring. - * - ic_bp is a pointer to the buffer used to write this incore log to disk. * - ic_log is a pointer back to the global log structure. - * - ic_callback is a linked list of callback function/argument pairs to be - * called after an iclog finishes writing. - * - ic_size is the full size of the header plus data. + * - ic_size is the full size of the log buffer, minus the cycle headers. + * - ic_io_size is the size of the currently pending log buffer write, which + * might be smaller than ic_size * - ic_offset is the current number of bytes written to in this iclog. * - ic_refcnt is bumped when someone is writing to the log. * - ic_state is the state of the iclog. @@ -193,7 +190,7 @@ typedef struct xlog_ticket { * structure cacheline aligned. The following fields can be contended on * by independent processes: * - * - ic_callback_* + * - ic_callbacks * - ic_refcnt * - fields protected by the global l_icloglock * @@ -206,23 +203,28 @@ typedef struct xlog_in_core { wait_queue_head_t ic_write_wait; struct xlog_in_core *ic_next; struct xlog_in_core *ic_prev; - struct xfs_buf *ic_bp; struct xlog *ic_log; - int ic_size; - int ic_offset; - int ic_bwritecnt; + u32 ic_size; + u32 ic_io_size; + u32 ic_offset; unsigned short ic_state; char *ic_datap; /* pointer to iclog data */ /* Callback structures need their own cacheline */ spinlock_t ic_callback_lock ____cacheline_aligned_in_smp; - struct xfs_log_callback *ic_callback; - struct xfs_log_callback **ic_callback_tail; + struct list_head ic_callbacks; /* reference counts need their own cacheline */ atomic_t ic_refcnt ____cacheline_aligned_in_smp; xlog_in_core_2_t *ic_data; #define ic_header ic_data->hic_header +#ifdef DEBUG + bool ic_fail_crc : 1; +#endif + struct semaphore ic_sema; + struct work_struct ic_end_io_work; + struct bio ic_bio; + struct bio_vec ic_bvec[]; } xlog_in_core_t; /* @@ -243,7 +245,7 @@ struct xfs_cil_ctx { int space_used; /* aggregate size of regions */ struct list_head busy_extents; /* busy extents in chkpt */ struct xfs_log_vec *lv_chain; /* logvecs being pushed */ - struct xfs_log_callback log_cb; /* completion callback hook. */ + struct list_head iclog_entry; struct list_head committing; /* ctx committing list */ struct work_struct discard_endio_work; }; @@ -350,9 +352,8 @@ struct xlog { struct xfs_mount *l_mp; /* mount point */ struct xfs_ail *l_ailp; /* AIL log is working with */ struct xfs_cil *l_cilp; /* CIL log is working with */ - struct xfs_buf *l_xbuf; /* extra buffer for log - * wrapping */ struct xfs_buftarg *l_targ; /* buftarg of log */ + struct workqueue_struct *l_ioend_workqueue; /* for I/O completions */ struct delayed_work l_work; /* background flush work */ uint l_flags; uint l_quotaoffs_flag; /* XFS_DQ_*, for QUOTAOFFs */ @@ -361,7 +362,6 @@ struct xlog { int l_iclog_heads; /* # of iclog header sectors */ uint l_sectBBsize; /* sector size in BBs (2^n) */ int l_iclog_size; /* size of log in bytes */ - int l_iclog_size_log; /* log power size of log */ int l_iclog_bufs; /* number of iclog buffers */ xfs_daddr_t l_logBBstart; /* start block of log */ int l_logsize; /* size of log in bytes */ @@ -418,7 +418,7 @@ xlog_recover( extern int xlog_recover_finish( struct xlog *log); -extern int +extern void xlog_recover_cancel(struct xlog *); extern __le32 xlog_cksum(struct xlog *log, struct xlog_rec_header *rhead, diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 9329f5adbfbe..13d1d3e95b88 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -13,8 +13,6 @@ #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_log.h" @@ -26,7 +24,6 @@ #include "xfs_alloc.h" #include "xfs_ialloc.h" #include "xfs_quota.h" -#include "xfs_cksum.h" #include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_bmap_btree.h" @@ -79,7 +76,7 @@ struct xfs_buf_cancel { * are valid, false otherwise. */ static inline bool -xlog_verify_bp( +xlog_verify_bno( struct xlog *log, xfs_daddr_t blk_no, int bbcount) @@ -92,22 +89,19 @@ xlog_verify_bp( } /* - * Allocate a buffer to hold log data. The buffer needs to be able - * to map to a range of nbblks basic blocks at any valid (basic - * block) offset within the log. + * Allocate a buffer to hold log data. The buffer needs to be able to map to + * a range of nbblks basic blocks at any valid offset within the log. */ -STATIC xfs_buf_t * -xlog_get_bp( +static char * +xlog_alloc_buffer( struct xlog *log, int nbblks) { - struct xfs_buf *bp; - /* * Pass log block 0 since we don't have an addr yet, buffer will be * verified on read. */ - if (!xlog_verify_bp(log, 0, nbblks)) { + if (!xlog_verify_bno(log, 0, nbblks)) { xfs_warn(log->l_mp, "Invalid block length (0x%x) for buffer", nbblks); XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_HIGH, log->l_mp); @@ -115,69 +109,48 @@ xlog_get_bp( } /* - * We do log I/O in units of log sectors (a power-of-2 - * multiple of the basic block size), so we round up the - * requested size to accommodate the basic blocks required - * for complete log sectors. + * We do log I/O in units of log sectors (a power-of-2 multiple of the + * basic block size), so we round up the requested size to accommodate + * the basic blocks required for complete log sectors. * - * In addition, the buffer may be used for a non-sector- - * aligned block offset, in which case an I/O of the - * requested size could extend beyond the end of the - * buffer. If the requested size is only 1 basic block it - * will never straddle a sector boundary, so this won't be - * an issue. Nor will this be a problem if the log I/O is - * done in basic blocks (sector size 1). But otherwise we - * extend the buffer by one extra log sector to ensure - * there's space to accommodate this possibility. + * In addition, the buffer may be used for a non-sector-aligned block + * offset, in which case an I/O of the requested size could extend + * beyond the end of the buffer. If the requested size is only 1 basic + * block it will never straddle a sector boundary, so this won't be an + * issue. Nor will this be a problem if the log I/O is done in basic + * blocks (sector size 1). But otherwise we extend the buffer by one + * extra log sector to ensure there's space to accommodate this + * possibility. */ if (nbblks > 1 && log->l_sectBBsize > 1) nbblks += log->l_sectBBsize; nbblks = round_up(nbblks, log->l_sectBBsize); - - bp = xfs_buf_get_uncached(log->l_mp->m_logdev_targp, nbblks, 0); - if (bp) - xfs_buf_unlock(bp); - return bp; -} - -STATIC void -xlog_put_bp( - xfs_buf_t *bp) -{ - xfs_buf_free(bp); + return kmem_alloc_large(BBTOB(nbblks), KM_MAYFAIL); } /* * Return the address of the start of the given block number's data * in a log buffer. The buffer covers a log sector-aligned region. */ -STATIC char * +static inline unsigned int xlog_align( struct xlog *log, - xfs_daddr_t blk_no, - int nbblks, - struct xfs_buf *bp) + xfs_daddr_t blk_no) { - xfs_daddr_t offset = blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1); - - ASSERT(offset + nbblks <= bp->b_length); - return bp->b_addr + BBTOB(offset); + return BBTOB(blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1)); } - -/* - * nbblks should be uint, but oh well. Just want to catch that 32-bit length. - */ -STATIC int -xlog_bread_noalign( - struct xlog *log, - xfs_daddr_t blk_no, - int nbblks, - struct xfs_buf *bp) +static int +xlog_do_io( + struct xlog *log, + xfs_daddr_t blk_no, + unsigned int nbblks, + char *data, + unsigned int op) { - int error; + int error; - if (!xlog_verify_bp(log, blk_no, nbblks)) { + if (!xlog_verify_bno(log, blk_no, nbblks)) { xfs_warn(log->l_mp, "Invalid log block/length (0x%llx, 0x%x) for buffer", blk_no, nbblks); @@ -187,107 +160,53 @@ xlog_bread_noalign( blk_no = round_down(blk_no, log->l_sectBBsize); nbblks = round_up(nbblks, log->l_sectBBsize); - ASSERT(nbblks > 0); - ASSERT(nbblks <= bp->b_length); - - XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no); - bp->b_flags |= XBF_READ; - bp->b_io_length = nbblks; - bp->b_error = 0; - error = xfs_buf_submit(bp); - if (error && !XFS_FORCED_SHUTDOWN(log->l_mp)) - xfs_buf_ioerror_alert(bp, __func__); + error = xfs_rw_bdev(log->l_targ->bt_bdev, log->l_logBBstart + blk_no, + BBTOB(nbblks), data, op); + if (error && !XFS_FORCED_SHUTDOWN(log->l_mp)) { + xfs_alert(log->l_mp, + "log recovery %s I/O error at daddr 0x%llx len %d error %d", + op == REQ_OP_WRITE ? "write" : "read", + blk_no, nbblks, error); + } return error; } STATIC int -xlog_bread( +xlog_bread_noalign( struct xlog *log, xfs_daddr_t blk_no, int nbblks, - struct xfs_buf *bp, - char **offset) + char *data) { - int error; - - error = xlog_bread_noalign(log, blk_no, nbblks, bp); - if (error) - return error; - - *offset = xlog_align(log, blk_no, nbblks, bp); - return 0; + return xlog_do_io(log, blk_no, nbblks, data, REQ_OP_READ); } -/* - * Read at an offset into the buffer. Returns with the buffer in it's original - * state regardless of the result of the read. - */ STATIC int -xlog_bread_offset( +xlog_bread( struct xlog *log, - xfs_daddr_t blk_no, /* block to read from */ - int nbblks, /* blocks to read */ - struct xfs_buf *bp, - char *offset) + xfs_daddr_t blk_no, + int nbblks, + char *data, + char **offset) { - char *orig_offset = bp->b_addr; - int orig_len = BBTOB(bp->b_length); - int error, error2; - - error = xfs_buf_associate_memory(bp, offset, BBTOB(nbblks)); - if (error) - return error; - - error = xlog_bread_noalign(log, blk_no, nbblks, bp); + int error; - /* must reset buffer pointer even on error */ - error2 = xfs_buf_associate_memory(bp, orig_offset, orig_len); - if (error) - return error; - return error2; + error = xlog_do_io(log, blk_no, nbblks, data, REQ_OP_READ); + if (!error) + *offset = data + xlog_align(log, blk_no); + return error; } -/* - * Write out the buffer at the given block for the given number of blocks. - * The buffer is kept locked across the write and is returned locked. - * This can only be used for synchronous log writes. - */ STATIC int xlog_bwrite( struct xlog *log, xfs_daddr_t blk_no, int nbblks, - struct xfs_buf *bp) + char *data) { - int error; - - if (!xlog_verify_bp(log, blk_no, nbblks)) { - xfs_warn(log->l_mp, - "Invalid log block/length (0x%llx, 0x%x) for buffer", - blk_no, nbblks); - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_HIGH, log->l_mp); - return -EFSCORRUPTED; - } - - blk_no = round_down(blk_no, log->l_sectBBsize); - nbblks = round_up(nbblks, log->l_sectBBsize); - - ASSERT(nbblks > 0); - ASSERT(nbblks <= bp->b_length); - - XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no); - xfs_buf_hold(bp); - xfs_buf_lock(bp); - bp->b_io_length = nbblks; - bp->b_error = 0; - - error = xfs_bwrite(bp); - if (error) - xfs_buf_ioerror_alert(bp, __func__); - xfs_buf_relse(bp); - return error; + return xlog_do_io(log, blk_no, nbblks, data, REQ_OP_WRITE); } #ifdef DEBUG @@ -377,10 +296,9 @@ xlog_recover_iodone( * We're not going to bother about retrying * this during recovery. One strike! */ - if (!XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) { + if (!XFS_FORCED_SHUTDOWN(bp->b_mount)) { xfs_buf_ioerror_alert(bp, __func__); - xfs_force_shutdown(bp->b_target->bt_mount, - SHUTDOWN_META_IO_ERROR); + xfs_force_shutdown(bp->b_mount, SHUTDOWN_META_IO_ERROR); } } @@ -405,7 +323,7 @@ xlog_recover_iodone( STATIC int xlog_find_cycle_start( struct xlog *log, - struct xfs_buf *bp, + char *buffer, xfs_daddr_t first_blk, xfs_daddr_t *last_blk, uint cycle) @@ -419,7 +337,7 @@ xlog_find_cycle_start( end_blk = *last_blk; mid_blk = BLK_AVG(first_blk, end_blk); while (mid_blk != first_blk && mid_blk != end_blk) { - error = xlog_bread(log, mid_blk, 1, bp, &offset); + error = xlog_bread(log, mid_blk, 1, buffer, &offset); if (error) return error; mid_cycle = xlog_get_cycle(offset); @@ -455,7 +373,7 @@ xlog_find_verify_cycle( { xfs_daddr_t i, j; uint cycle; - xfs_buf_t *bp; + char *buffer; xfs_daddr_t bufblks; char *buf = NULL; int error = 0; @@ -469,7 +387,7 @@ xlog_find_verify_cycle( bufblks = 1 << ffs(nbblks); while (bufblks > log->l_logBBsize) bufblks >>= 1; - while (!(bp = xlog_get_bp(log, bufblks))) { + while (!(buffer = xlog_alloc_buffer(log, bufblks))) { bufblks >>= 1; if (bufblks < log->l_sectBBsize) return -ENOMEM; @@ -480,7 +398,7 @@ xlog_find_verify_cycle( bcount = min(bufblks, (start_blk + nbblks - i)); - error = xlog_bread(log, i, bcount, bp, &buf); + error = xlog_bread(log, i, bcount, buffer, &buf); if (error) goto out; @@ -498,7 +416,7 @@ xlog_find_verify_cycle( *new_blk = -1; out: - xlog_put_bp(bp); + kmem_free(buffer); return error; } @@ -522,7 +440,7 @@ xlog_find_verify_log_record( int extra_bblks) { xfs_daddr_t i; - xfs_buf_t *bp; + char *buffer; char *offset = NULL; xlog_rec_header_t *head = NULL; int error = 0; @@ -532,12 +450,14 @@ xlog_find_verify_log_record( ASSERT(start_blk != 0 || *last_blk != start_blk); - if (!(bp = xlog_get_bp(log, num_blks))) { - if (!(bp = xlog_get_bp(log, 1))) + buffer = xlog_alloc_buffer(log, num_blks); + if (!buffer) { + buffer = xlog_alloc_buffer(log, 1); + if (!buffer) return -ENOMEM; smallmem = 1; } else { - error = xlog_bread(log, start_blk, num_blks, bp, &offset); + error = xlog_bread(log, start_blk, num_blks, buffer, &offset); if (error) goto out; offset += ((num_blks - 1) << BBSHIFT); @@ -554,7 +474,7 @@ xlog_find_verify_log_record( } if (smallmem) { - error = xlog_bread(log, i, 1, bp, &offset); + error = xlog_bread(log, i, 1, buffer, &offset); if (error) goto out; } @@ -607,7 +527,7 @@ xlog_find_verify_log_record( *last_blk = i; out: - xlog_put_bp(bp); + kmem_free(buffer); return error; } @@ -629,7 +549,7 @@ xlog_find_head( struct xlog *log, xfs_daddr_t *return_head_blk) { - xfs_buf_t *bp; + char *buffer; char *offset; xfs_daddr_t new_blk, first_blk, start_blk, last_blk, head_blk; int num_scan_bblks; @@ -659,20 +579,20 @@ xlog_find_head( } first_blk = 0; /* get cycle # of 1st block */ - bp = xlog_get_bp(log, 1); - if (!bp) + buffer = xlog_alloc_buffer(log, 1); + if (!buffer) return -ENOMEM; - error = xlog_bread(log, 0, 1, bp, &offset); + error = xlog_bread(log, 0, 1, buffer, &offset); if (error) - goto bp_err; + goto out_free_buffer; first_half_cycle = xlog_get_cycle(offset); last_blk = head_blk = log_bbnum - 1; /* get cycle # of last block */ - error = xlog_bread(log, last_blk, 1, bp, &offset); + error = xlog_bread(log, last_blk, 1, buffer, &offset); if (error) - goto bp_err; + goto out_free_buffer; last_half_cycle = xlog_get_cycle(offset); ASSERT(last_half_cycle != 0); @@ -740,9 +660,10 @@ xlog_find_head( * ^ we want to locate this spot */ stop_on_cycle = last_half_cycle; - if ((error = xlog_find_cycle_start(log, bp, first_blk, - &head_blk, last_half_cycle))) - goto bp_err; + error = xlog_find_cycle_start(log, buffer, first_blk, &head_blk, + last_half_cycle); + if (error) + goto out_free_buffer; } /* @@ -762,7 +683,7 @@ xlog_find_head( if ((error = xlog_find_verify_cycle(log, start_blk, num_scan_bblks, stop_on_cycle, &new_blk))) - goto bp_err; + goto out_free_buffer; if (new_blk != -1) head_blk = new_blk; } else { /* need to read 2 parts of log */ @@ -799,7 +720,7 @@ xlog_find_head( if ((error = xlog_find_verify_cycle(log, start_blk, num_scan_bblks - (int)head_blk, (stop_on_cycle - 1), &new_blk))) - goto bp_err; + goto out_free_buffer; if (new_blk != -1) { head_blk = new_blk; goto validate_head; @@ -815,7 +736,7 @@ xlog_find_head( if ((error = xlog_find_verify_cycle(log, start_blk, (int)head_blk, stop_on_cycle, &new_blk))) - goto bp_err; + goto out_free_buffer; if (new_blk != -1) head_blk = new_blk; } @@ -834,13 +755,13 @@ validate_head: if (error == 1) error = -EIO; if (error) - goto bp_err; + goto out_free_buffer; } else { start_blk = 0; ASSERT(head_blk <= INT_MAX); error = xlog_find_verify_log_record(log, start_blk, &head_blk, 0); if (error < 0) - goto bp_err; + goto out_free_buffer; if (error == 1) { /* We hit the beginning of the log during our search */ start_blk = log_bbnum - (num_scan_bblks - head_blk); @@ -853,14 +774,14 @@ validate_head: if (error == 1) error = -EIO; if (error) - goto bp_err; + goto out_free_buffer; if (new_blk != log_bbnum) head_blk = new_blk; } else if (error) - goto bp_err; + goto out_free_buffer; } - xlog_put_bp(bp); + kmem_free(buffer); if (head_blk == log_bbnum) *return_head_blk = 0; else @@ -873,9 +794,8 @@ validate_head: */ return 0; - bp_err: - xlog_put_bp(bp); - +out_free_buffer: + kmem_free(buffer); if (error) xfs_warn(log->l_mp, "failed to find log head"); return error; @@ -895,7 +815,7 @@ xlog_rseek_logrec_hdr( xfs_daddr_t head_blk, xfs_daddr_t tail_blk, int count, - struct xfs_buf *bp, + char *buffer, xfs_daddr_t *rblk, struct xlog_rec_header **rhead, bool *wrapped) @@ -914,7 +834,7 @@ xlog_rseek_logrec_hdr( */ end_blk = head_blk > tail_blk ? tail_blk : 0; for (i = (int) head_blk - 1; i >= end_blk; i--) { - error = xlog_bread(log, i, 1, bp, &offset); + error = xlog_bread(log, i, 1, buffer, &offset); if (error) goto out_error; @@ -933,7 +853,7 @@ xlog_rseek_logrec_hdr( */ if (tail_blk >= head_blk && found != count) { for (i = log->l_logBBsize - 1; i >= (int) tail_blk; i--) { - error = xlog_bread(log, i, 1, bp, &offset); + error = xlog_bread(log, i, 1, buffer, &offset); if (error) goto out_error; @@ -969,7 +889,7 @@ xlog_seek_logrec_hdr( xfs_daddr_t head_blk, xfs_daddr_t tail_blk, int count, - struct xfs_buf *bp, + char *buffer, xfs_daddr_t *rblk, struct xlog_rec_header **rhead, bool *wrapped) @@ -988,7 +908,7 @@ xlog_seek_logrec_hdr( */ end_blk = head_blk > tail_blk ? head_blk : log->l_logBBsize - 1; for (i = (int) tail_blk; i <= end_blk; i++) { - error = xlog_bread(log, i, 1, bp, &offset); + error = xlog_bread(log, i, 1, buffer, &offset); if (error) goto out_error; @@ -1006,7 +926,7 @@ xlog_seek_logrec_hdr( */ if (tail_blk > head_blk && found != count) { for (i = 0; i < (int) head_blk; i++) { - error = xlog_bread(log, i, 1, bp, &offset); + error = xlog_bread(log, i, 1, buffer, &offset); if (error) goto out_error; @@ -1069,22 +989,22 @@ xlog_verify_tail( int hsize) { struct xlog_rec_header *thead; - struct xfs_buf *bp; + char *buffer; xfs_daddr_t first_bad; int error = 0; bool wrapped; xfs_daddr_t tmp_tail; xfs_daddr_t orig_tail = *tail_blk; - bp = xlog_get_bp(log, 1); - if (!bp) + buffer = xlog_alloc_buffer(log, 1); + if (!buffer) return -ENOMEM; /* * Make sure the tail points to a record (returns positive count on * success). */ - error = xlog_seek_logrec_hdr(log, head_blk, *tail_blk, 1, bp, + error = xlog_seek_logrec_hdr(log, head_blk, *tail_blk, 1, buffer, &tmp_tail, &thead, &wrapped); if (error < 0) goto out; @@ -1113,8 +1033,8 @@ xlog_verify_tail( break; /* skip to the next record; returns positive count on success */ - error = xlog_seek_logrec_hdr(log, head_blk, first_bad, 2, bp, - &tmp_tail, &thead, &wrapped); + error = xlog_seek_logrec_hdr(log, head_blk, first_bad, 2, + buffer, &tmp_tail, &thead, &wrapped); if (error < 0) goto out; @@ -1129,7 +1049,7 @@ xlog_verify_tail( "Tail block (0x%llx) overwrite detected. Updated to 0x%llx", orig_tail, *tail_blk); out: - xlog_put_bp(bp); + kmem_free(buffer); return error; } @@ -1151,13 +1071,13 @@ xlog_verify_head( struct xlog *log, xfs_daddr_t *head_blk, /* in/out: unverified head */ xfs_daddr_t *tail_blk, /* out: tail block */ - struct xfs_buf *bp, + char *buffer, xfs_daddr_t *rhead_blk, /* start blk of last record */ struct xlog_rec_header **rhead, /* ptr to last record */ bool *wrapped) /* last rec. wraps phys. log */ { struct xlog_rec_header *tmp_rhead; - struct xfs_buf *tmp_bp; + char *tmp_buffer; xfs_daddr_t first_bad; xfs_daddr_t tmp_rhead_blk; int found; @@ -1168,15 +1088,15 @@ xlog_verify_head( * Check the head of the log for torn writes. Search backwards from the * head until we hit the tail or the maximum number of log record I/Os * that could have been in flight at one time. Use a temporary buffer so - * we don't trash the rhead/bp pointers from the caller. + * we don't trash the rhead/buffer pointers from the caller. */ - tmp_bp = xlog_get_bp(log, 1); - if (!tmp_bp) + tmp_buffer = xlog_alloc_buffer(log, 1); + if (!tmp_buffer) return -ENOMEM; error = xlog_rseek_logrec_hdr(log, *head_blk, *tail_blk, - XLOG_MAX_ICLOGS, tmp_bp, &tmp_rhead_blk, - &tmp_rhead, &tmp_wrapped); - xlog_put_bp(tmp_bp); + XLOG_MAX_ICLOGS, tmp_buffer, + &tmp_rhead_blk, &tmp_rhead, &tmp_wrapped); + kmem_free(tmp_buffer); if (error < 0) return error; @@ -1205,8 +1125,8 @@ xlog_verify_head( * (i.e., the records with invalid CRC) if the cycle number * matches the the current cycle. */ - found = xlog_rseek_logrec_hdr(log, first_bad, *tail_blk, 1, bp, - rhead_blk, rhead, wrapped); + found = xlog_rseek_logrec_hdr(log, first_bad, *tail_blk, 1, + buffer, rhead_blk, rhead, wrapped); if (found < 0) return found; if (found == 0) /* XXX: right thing to do here? */ @@ -1266,7 +1186,7 @@ xlog_check_unmount_rec( xfs_daddr_t *tail_blk, struct xlog_rec_header *rhead, xfs_daddr_t rhead_blk, - struct xfs_buf *bp, + char *buffer, bool *clean) { struct xlog_op_header *op_head; @@ -1309,7 +1229,7 @@ xlog_check_unmount_rec( if (*head_blk == after_umount_blk && be32_to_cpu(rhead->h_num_logops) == 1) { umount_data_blk = xlog_wrap_logbno(log, rhead_blk + hblks); - error = xlog_bread(log, umount_data_blk, 1, bp, &offset); + error = xlog_bread(log, umount_data_blk, 1, buffer, &offset); if (error) return error; @@ -1388,7 +1308,7 @@ xlog_find_tail( { xlog_rec_header_t *rhead; char *offset = NULL; - xfs_buf_t *bp; + char *buffer; int error; xfs_daddr_t rhead_blk; xfs_lsn_t tail_lsn; @@ -1402,11 +1322,11 @@ xlog_find_tail( return error; ASSERT(*head_blk < INT_MAX); - bp = xlog_get_bp(log, 1); - if (!bp) + buffer = xlog_alloc_buffer(log, 1); + if (!buffer) return -ENOMEM; if (*head_blk == 0) { /* special case */ - error = xlog_bread(log, 0, 1, bp, &offset); + error = xlog_bread(log, 0, 1, buffer, &offset); if (error) goto done; @@ -1422,7 +1342,7 @@ xlog_find_tail( * block. This wraps all the way back around to the head so something is * seriously wrong if we can't find it. */ - error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, bp, + error = xlog_rseek_logrec_hdr(log, *head_blk, *head_blk, 1, buffer, &rhead_blk, &rhead, &wrapped); if (error < 0) return error; @@ -1443,7 +1363,7 @@ xlog_find_tail( * state to determine whether recovery is necessary. */ error = xlog_check_unmount_rec(log, head_blk, tail_blk, rhead, - rhead_blk, bp, &clean); + rhead_blk, buffer, &clean); if (error) goto done; @@ -1460,7 +1380,7 @@ xlog_find_tail( if (!clean) { xfs_daddr_t orig_head = *head_blk; - error = xlog_verify_head(log, head_blk, tail_blk, bp, + error = xlog_verify_head(log, head_blk, tail_blk, buffer, &rhead_blk, &rhead, &wrapped); if (error) goto done; @@ -1471,7 +1391,7 @@ xlog_find_tail( wrapped); tail_lsn = atomic64_read(&log->l_tail_lsn); error = xlog_check_unmount_rec(log, head_blk, tail_blk, - rhead, rhead_blk, bp, + rhead, rhead_blk, buffer, &clean); if (error) goto done; @@ -1505,11 +1425,11 @@ xlog_find_tail( * But... if the -device- itself is readonly, just skip this. * We can't recover this device anyway, so it won't matter. */ - if (!xfs_readonly_buftarg(log->l_mp->m_logdev_targp)) + if (!xfs_readonly_buftarg(log->l_targ)) error = xlog_clear_stale_blocks(log, tail_lsn); done: - xlog_put_bp(bp); + kmem_free(buffer); if (error) xfs_warn(log->l_mp, "failed to locate log tail"); @@ -1537,7 +1457,7 @@ xlog_find_zeroed( struct xlog *log, xfs_daddr_t *blk_no) { - xfs_buf_t *bp; + char *buffer; char *offset; uint first_cycle, last_cycle; xfs_daddr_t new_blk, last_blk, start_blk; @@ -1547,35 +1467,36 @@ xlog_find_zeroed( *blk_no = 0; /* check totally zeroed log */ - bp = xlog_get_bp(log, 1); - if (!bp) + buffer = xlog_alloc_buffer(log, 1); + if (!buffer) return -ENOMEM; - error = xlog_bread(log, 0, 1, bp, &offset); + error = xlog_bread(log, 0, 1, buffer, &offset); if (error) - goto bp_err; + goto out_free_buffer; first_cycle = xlog_get_cycle(offset); if (first_cycle == 0) { /* completely zeroed log */ *blk_no = 0; - xlog_put_bp(bp); + kmem_free(buffer); return 1; } /* check partially zeroed log */ - error = xlog_bread(log, log_bbnum-1, 1, bp, &offset); + error = xlog_bread(log, log_bbnum-1, 1, buffer, &offset); if (error) - goto bp_err; + goto out_free_buffer; last_cycle = xlog_get_cycle(offset); if (last_cycle != 0) { /* log completely written to */ - xlog_put_bp(bp); + kmem_free(buffer); return 0; } /* we have a partially zeroed log */ last_blk = log_bbnum-1; - if ((error = xlog_find_cycle_start(log, bp, 0, &last_blk, 0))) - goto bp_err; + error = xlog_find_cycle_start(log, buffer, 0, &last_blk, 0); + if (error) + goto out_free_buffer; /* * Validate the answer. Because there is no way to guarantee that @@ -1598,7 +1519,7 @@ xlog_find_zeroed( */ if ((error = xlog_find_verify_cycle(log, start_blk, (int)num_scan_bblks, 0, &new_blk))) - goto bp_err; + goto out_free_buffer; if (new_blk != -1) last_blk = new_blk; @@ -1610,11 +1531,11 @@ xlog_find_zeroed( if (error == 1) error = -EIO; if (error) - goto bp_err; + goto out_free_buffer; *blk_no = last_blk; -bp_err: - xlog_put_bp(bp); +out_free_buffer: + kmem_free(buffer); if (error) return error; return 1; @@ -1657,7 +1578,7 @@ xlog_write_log_records( int tail_block) { char *offset; - xfs_buf_t *bp; + char *buffer; int balign, ealign; int sectbb = log->l_sectBBsize; int end_block = start_block + blocks; @@ -1674,7 +1595,7 @@ xlog_write_log_records( bufblks = 1 << ffs(blocks); while (bufblks > log->l_logBBsize) bufblks >>= 1; - while (!(bp = xlog_get_bp(log, bufblks))) { + while (!(buffer = xlog_alloc_buffer(log, bufblks))) { bufblks >>= 1; if (bufblks < sectbb) return -ENOMEM; @@ -1686,9 +1607,9 @@ xlog_write_log_records( */ balign = round_down(start_block, sectbb); if (balign != start_block) { - error = xlog_bread_noalign(log, start_block, 1, bp); + error = xlog_bread_noalign(log, start_block, 1, buffer); if (error) - goto out_put_bp; + goto out_free_buffer; j = start_block - balign; } @@ -1705,29 +1626,28 @@ xlog_write_log_records( */ ealign = round_down(end_block, sectbb); if (j == 0 && (start_block + endcount > ealign)) { - offset = bp->b_addr + BBTOB(ealign - start_block); - error = xlog_bread_offset(log, ealign, sectbb, - bp, offset); + error = xlog_bread_noalign(log, ealign, sectbb, + buffer + BBTOB(ealign - start_block)); if (error) break; } - offset = xlog_align(log, start_block, endcount, bp); + offset = buffer + xlog_align(log, start_block); for (; j < endcount; j++) { xlog_add_record(log, offset, cycle, i+j, tail_cycle, tail_block); offset += BBSIZE; } - error = xlog_bwrite(log, start_block, endcount, bp); + error = xlog_bwrite(log, start_block, endcount, buffer); if (error) break; start_block += endcount; j = 0; } - out_put_bp: - xlog_put_bp(bp); +out_free_buffer: + kmem_free(buffer); return error; } @@ -2162,7 +2082,7 @@ xlog_recover_do_inode_buffer( if (xfs_sb_version_hascrc(&mp->m_sb)) bp->b_ops = &xfs_inode_buf_ops; - inodes_per_buf = BBTOB(bp->b_io_length) >> mp->m_sb.sb_inodelog; + inodes_per_buf = BBTOB(bp->b_length) >> mp->m_sb.sb_inodelog; for (i = 0; i < inodes_per_buf; i++) { next_unlinked_offset = (i * mp->m_sb.sb_inodesize) + offsetof(xfs_dinode_t, di_next_unlinked); @@ -2204,8 +2124,7 @@ xlog_recover_do_inode_buffer( ASSERT(item->ri_buf[item_index].i_addr != NULL); ASSERT((item->ri_buf[item_index].i_len % XFS_BLF_CHUNK) == 0); - ASSERT((reg_buf_offset + reg_buf_bytes) <= - BBTOB(bp->b_io_length)); + ASSERT((reg_buf_offset + reg_buf_bytes) <= BBTOB(bp->b_length)); /* * The current logged region contains a copy of the @@ -2670,7 +2589,7 @@ xlog_recover_do_reg_buffer( ASSERT(nbits > 0); ASSERT(item->ri_buf[i].i_addr != NULL); ASSERT(item->ri_buf[i].i_len % XFS_BLF_CHUNK == 0); - ASSERT(BBTOB(bp->b_io_length) >= + ASSERT(BBTOB(bp->b_length) >= ((uint)bit << XFS_BLF_SHIFT) + (nbits << XFS_BLF_SHIFT)); /* @@ -2882,23 +2801,22 @@ xlog_recover_buffer_pass2( * * Also make sure that only inode buffers with good sizes stay in * the buffer cache. The kernel moves inodes in buffers of 1 block - * or mp->m_inode_cluster_size bytes, whichever is bigger. The inode + * or inode_cluster_size bytes, whichever is bigger. The inode * buffers in the log can be a different size if the log was generated * by an older kernel using unclustered inode buffers or a newer kernel * running with a different inode cluster size. Regardless, if the - * the inode buffer size isn't max(blocksize, mp->m_inode_cluster_size) - * for *our* value of mp->m_inode_cluster_size, then we need to keep + * the inode buffer size isn't max(blocksize, inode_cluster_size) + * for *our* value of inode_cluster_size, then we need to keep * the buffer out of the buffer cache so that the buffer won't * overlap with future reads of those inodes. */ if (XFS_DINODE_MAGIC == be16_to_cpu(*((__be16 *)xfs_buf_offset(bp, 0))) && - (BBTOB(bp->b_io_length) != max(log->l_mp->m_sb.sb_blocksize, - (uint32_t)log->l_mp->m_inode_cluster_size))) { + (BBTOB(bp->b_length) != M_IGEO(log->l_mp)->inode_cluster_size)) { xfs_buf_stale(bp); error = xfs_bwrite(bp); } else { - ASSERT(bp->b_target->bt_mount == mp); + ASSERT(bp->b_mount == mp); bp->b_iodone = xlog_recover_iodone; xfs_buf_delwri_queue(bp, buffer_list); } @@ -3260,7 +3178,7 @@ out_owner_change: /* re-generate the checksum. */ xfs_dinode_calc_crc(log->l_mp, dip); - ASSERT(bp->b_target->bt_mount == mp); + ASSERT(bp->b_mount == mp); bp->b_iodone = xlog_recover_iodone; xfs_buf_delwri_queue(bp, buffer_list); @@ -3399,7 +3317,7 @@ xlog_recover_dquot_pass2( } ASSERT(dq_f->qlf_size == 2); - ASSERT(bp->b_target->bt_mount == mp); + ASSERT(bp->b_mount == mp); bp->b_iodone = xlog_recover_iodone; xfs_buf_delwri_queue(bp, buffer_list); @@ -3463,7 +3381,7 @@ xlog_recover_efd_pass2( { xfs_efd_log_format_t *efd_formatp; xfs_efi_log_item_t *efip = NULL; - xfs_log_item_t *lip; + struct xfs_log_item *lip; uint64_t efi_id; struct xfs_ail_cursor cur; struct xfs_ail *ailp = log->l_ailp; @@ -3849,6 +3767,7 @@ xlog_recover_do_icreate_pass2( { struct xfs_mount *mp = log->l_mp; struct xfs_icreate_log *icl; + struct xfs_ino_geometry *igeo = M_IGEO(mp); xfs_agnumber_t agno; xfs_agblock_t agbno; unsigned int count; @@ -3898,10 +3817,10 @@ xlog_recover_do_icreate_pass2( /* * The inode chunk is either full or sparse and we only support - * m_ialloc_min_blks sized sparse allocations at this time. + * m_ino_geo.ialloc_min_blks sized sparse allocations at this time. */ - if (length != mp->m_ialloc_blks && - length != mp->m_ialloc_min_blks) { + if (length != igeo->ialloc_blks && + length != igeo->ialloc_min_blks) { xfs_warn(log->l_mp, "%s: unsupported chunk length", __FUNCTION__); return -EINVAL; @@ -3921,13 +3840,13 @@ xlog_recover_do_icreate_pass2( * buffers for cancellation so we don't overwrite anything written after * a cancellation. */ - bb_per_cluster = XFS_FSB_TO_BB(mp, mp->m_blocks_per_cluster); - nbufs = length / mp->m_blocks_per_cluster; + bb_per_cluster = XFS_FSB_TO_BB(mp, igeo->blocks_per_cluster); + nbufs = length / igeo->blocks_per_cluster; for (i = 0, cancel_count = 0; i < nbufs; i++) { xfs_daddr_t daddr; daddr = XFS_AGB_TO_DADDR(mp, agno, - agbno + i * mp->m_blocks_per_cluster); + agbno + i * igeo->blocks_per_cluster); if (xlog_check_buffer_cancelled(log, daddr, bb_per_cluster, 0)) cancel_count++; } @@ -4956,12 +4875,11 @@ out: * A cancel occurs when the mount has failed and we're bailing out. * Release all pending log intent items so they don't pin the AIL. */ -STATIC int +STATIC void xlog_recover_cancel_intents( struct xlog *log) { struct xfs_log_item *lip; - int error = 0; struct xfs_ail_cursor cur; struct xfs_ail *ailp; @@ -5001,7 +4919,6 @@ xlog_recover_cancel_intents( xfs_trans_ail_cursor_done(&cur); spin_unlock(&ailp->ail_lock); - return error; } /* @@ -5307,7 +5224,7 @@ xlog_do_recovery_pass( xfs_daddr_t blk_no, rblk_no; xfs_daddr_t rhead_blk; char *offset; - xfs_buf_t *hbp, *dbp; + char *hbp, *dbp; int error = 0, h_size, h_len; int error2 = 0; int bblks, split_bblks; @@ -5332,7 +5249,7 @@ xlog_do_recovery_pass( * iclog header and extract the header size from it. Get a * new hbp that is the correct size. */ - hbp = xlog_get_bp(log, 1); + hbp = xlog_alloc_buffer(log, 1); if (!hbp) return -ENOMEM; @@ -5374,23 +5291,23 @@ xlog_do_recovery_pass( hblks = h_size / XLOG_HEADER_CYCLE_SIZE; if (h_size % XLOG_HEADER_CYCLE_SIZE) hblks++; - xlog_put_bp(hbp); - hbp = xlog_get_bp(log, hblks); + kmem_free(hbp); + hbp = xlog_alloc_buffer(log, hblks); } else { hblks = 1; } } else { ASSERT(log->l_sectBBsize == 1); hblks = 1; - hbp = xlog_get_bp(log, 1); + hbp = xlog_alloc_buffer(log, 1); h_size = XLOG_BIG_RECORD_BSIZE; } if (!hbp) return -ENOMEM; - dbp = xlog_get_bp(log, BTOBB(h_size)); + dbp = xlog_alloc_buffer(log, BTOBB(h_size)); if (!dbp) { - xlog_put_bp(hbp); + kmem_free(hbp); return -ENOMEM; } @@ -5405,7 +5322,7 @@ xlog_do_recovery_pass( /* * Check for header wrapping around physical end-of-log */ - offset = hbp->b_addr; + offset = hbp; split_hblks = 0; wrapped_hblks = 0; if (blk_no + hblks <= log->l_logBBsize) { @@ -5441,8 +5358,8 @@ xlog_do_recovery_pass( * - order is important. */ wrapped_hblks = hblks - split_hblks; - error = xlog_bread_offset(log, 0, - wrapped_hblks, hbp, + error = xlog_bread_noalign(log, 0, + wrapped_hblks, offset + BBTOB(split_hblks)); if (error) goto bread_err2; @@ -5473,7 +5390,7 @@ xlog_do_recovery_pass( } else { /* This log record is split across the * physical end of log */ - offset = dbp->b_addr; + offset = dbp; split_bblks = 0; if (blk_no != log->l_logBBsize) { /* some data is before the physical @@ -5502,8 +5419,8 @@ xlog_do_recovery_pass( * _first_, then the log start (LR header end) * - order is important. */ - error = xlog_bread_offset(log, 0, - bblks - split_bblks, dbp, + error = xlog_bread_noalign(log, 0, + bblks - split_bblks, offset + BBTOB(split_bblks)); if (error) goto bread_err2; @@ -5551,9 +5468,9 @@ xlog_do_recovery_pass( } bread_err2: - xlog_put_bp(dbp); + kmem_free(dbp); bread_err1: - xlog_put_bp(hbp); + kmem_free(hbp); /* * Submit buffers that have been added from the last record processed, @@ -5687,7 +5604,7 @@ xlog_do_recover( * Now that we've finished replaying all buffer and inode * updates, re-read in the superblock and reverify it. */ - bp = xfs_getsb(mp, 0); + bp = xfs_getsb(mp); bp->b_flags &= ~(XBF_DONE | XBF_ASYNC); ASSERT(!(bp->b_flags & XBF_WRITE)); bp->b_flags |= XBF_READ; @@ -5860,16 +5777,12 @@ xlog_recover_finish( return 0; } -int +void xlog_recover_cancel( struct xlog *log) { - int error = 0; - if (log->l_flags & XLOG_RECOVERY_NEEDED) - error = xlog_recover_cancel_intents(log); - - return error; + xlog_recover_cancel_intents(log); } #if defined(DEBUG) diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index 6b736ea58d35..9804efe525a9 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -6,8 +6,8 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_error.h" +#include "xfs_shared.h" #include "xfs_format.h" -#include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 6b2bfe81dc51..322da6909290 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -12,9 +12,6 @@ #include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_dir2.h" #include "xfs_ialloc.h" @@ -27,7 +24,6 @@ #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_fsops.h" -#include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_sysfs.h" #include "xfs_rmap_btree.h" @@ -430,30 +426,6 @@ xfs_update_alignment(xfs_mount_t *mp) } /* - * Set the maximum inode count for this filesystem - */ -STATIC void -xfs_set_maxicount(xfs_mount_t *mp) -{ - xfs_sb_t *sbp = &(mp->m_sb); - uint64_t icount; - - if (sbp->sb_imax_pct) { - /* - * Make sure the maximum inode count is a multiple - * of the units we allocate inodes in. - */ - icount = sbp->sb_dblocks * sbp->sb_imax_pct; - do_div(icount, 100); - do_div(icount, mp->m_ialloc_blks); - mp->m_maxicount = (icount * mp->m_ialloc_blks) << - sbp->sb_inopblog; - } else { - mp->m_maxicount = 0; - } -} - -/* * Set the default minimum read and write sizes unless * already specified in a mount option. * We use smaller I/O sizes when the file system @@ -509,29 +481,6 @@ xfs_set_low_space_thresholds( } } - -/* - * Set whether we're using inode alignment. - */ -STATIC void -xfs_set_inoalignment(xfs_mount_t *mp) -{ - if (xfs_sb_version_hasalign(&mp->m_sb) && - mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp)) - mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1; - else - mp->m_inoalign_mask = 0; - /* - * If we are using stripe alignment, check whether - * the stripe unit is a multiple of the inode alignment - */ - if (mp->m_dalign && mp->m_inoalign_mask && - !(mp->m_dalign & mp->m_inoalign_mask)) - mp->m_sinoalign = mp->m_dalign; - else - mp->m_sinoalign = 0; -} - /* * Check that the data (and log if separate) is an ok size. */ @@ -683,6 +632,7 @@ xfs_mountfs( { struct xfs_sb *sbp = &(mp->m_sb); struct xfs_inode *rip; + struct xfs_ino_geometry *igeo = M_IGEO(mp); uint64_t resblks; uint quotamount = 0; uint quotaflags = 0; @@ -749,12 +699,10 @@ xfs_mountfs( xfs_alloc_compute_maxlevels(mp); xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK); xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK); - xfs_ialloc_compute_maxlevels(mp); + xfs_ialloc_setup_geometry(mp); xfs_rmapbt_compute_maxlevels(mp); xfs_refcountbt_compute_maxlevels(mp); - xfs_set_maxicount(mp); - /* enable fail_at_unmount as default */ mp->m_fail_unmount = true; @@ -788,50 +736,22 @@ xfs_mountfs( xfs_set_low_space_thresholds(mp); /* - * Set the inode cluster size. - * This may still be overridden by the file system - * block size if it is larger than the chosen cluster size. - * - * For v5 filesystems, scale the cluster size with the inode size to - * keep a constant ratio of inode per cluster buffer, but only if mkfs - * has set the inode alignment value appropriately for larger cluster - * sizes. - */ - mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE; - if (xfs_sb_version_hascrc(&mp->m_sb)) { - int new_size = mp->m_inode_cluster_size; - - new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE; - if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size)) - mp->m_inode_cluster_size = new_size; - } - mp->m_blocks_per_cluster = xfs_icluster_size_fsb(mp); - mp->m_inodes_per_cluster = XFS_FSB_TO_INO(mp, mp->m_blocks_per_cluster); - mp->m_cluster_align = xfs_ialloc_cluster_alignment(mp); - mp->m_cluster_align_inodes = XFS_FSB_TO_INO(mp, mp->m_cluster_align); - - /* * If enabled, sparse inode chunk alignment is expected to match the * cluster size. Full inode chunk alignment must match the chunk size, * but that is checked on sb read verification... */ if (xfs_sb_version_hassparseinodes(&mp->m_sb) && mp->m_sb.sb_spino_align != - XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) { + XFS_B_TO_FSBT(mp, igeo->inode_cluster_size_raw)) { xfs_warn(mp, "Sparse inode block alignment (%u) must match cluster size (%llu).", mp->m_sb.sb_spino_align, - XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)); + XFS_B_TO_FSBT(mp, igeo->inode_cluster_size_raw)); error = -EINVAL; goto out_remove_uuid; } /* - * Set inode alignment fields - */ - xfs_set_inoalignment(mp); - - /* * Check that the data (and log if separate) is an ok size. */ error = xfs_check_sizes(mp); @@ -1385,24 +1305,14 @@ xfs_mod_frextents( * xfs_getsb() is called to obtain the buffer for the superblock. * The buffer is returned locked and read in from disk. * The buffer should be released with a call to xfs_brelse(). - * - * If the flags parameter is BUF_TRYLOCK, then we'll only return - * the superblock buffer if it can be locked without sleeping. - * If it can't then we'll return NULL. */ struct xfs_buf * xfs_getsb( - struct xfs_mount *mp, - int flags) + struct xfs_mount *mp) { struct xfs_buf *bp = mp->m_sb_bp; - if (!xfs_buf_trylock(bp)) { - if (flags & XBF_TRYLOCK) - return NULL; - xfs_buf_lock(bp); - } - + xfs_buf_lock(bp); xfs_buf_hold(bp); ASSERT(bp->b_flags & XBF_DONE); return bp; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index c81a5cd7c228..4adb6837439a 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -105,6 +105,7 @@ typedef struct xfs_mount { struct xfs_da_geometry *m_dir_geo; /* directory block geometry */ struct xfs_da_geometry *m_attr_geo; /* attribute block geometry */ struct xlog *m_log; /* log specific stuff */ + struct xfs_ino_geometry m_ino_geo; /* inode geometry */ int m_logbufs; /* number of log buffers */ int m_logbsize; /* size of each log buffer */ uint m_rsumlevels; /* rt summary levels */ @@ -126,12 +127,6 @@ typedef struct xfs_mount { uint8_t m_blkbit_log; /* blocklog + NBBY */ uint8_t m_blkbb_log; /* blocklog - BBSHIFT */ uint8_t m_agno_log; /* log #ag's */ - uint8_t m_agino_log; /* #bits for agino in inum */ - uint m_inode_cluster_size;/* min inode buf size */ - unsigned int m_inodes_per_cluster; - unsigned int m_blocks_per_cluster; - unsigned int m_cluster_align; - unsigned int m_cluster_align_inodes; uint m_blockmask; /* sb_blocksize-1 */ uint m_blockwsize; /* sb_blocksize in words */ uint m_blockwmask; /* blockwsize-1 */ @@ -139,15 +134,12 @@ typedef struct xfs_mount { uint m_alloc_mnr[2]; /* min alloc btree records */ uint m_bmap_dmxr[2]; /* max bmap btree records */ uint m_bmap_dmnr[2]; /* min bmap btree records */ - uint m_inobt_mxr[2]; /* max inobt btree records */ - uint m_inobt_mnr[2]; /* min inobt btree records */ uint m_rmap_mxr[2]; /* max rmap btree records */ uint m_rmap_mnr[2]; /* min rmap btree records */ uint m_refc_mxr[2]; /* max refc btree records */ uint m_refc_mnr[2]; /* min refc btree records */ uint m_ag_maxlevels; /* XFS_AG_MAXLEVELS */ uint m_bm_maxlevels[2]; /* XFS_BM_MAXLEVELS */ - uint m_in_maxlevels; /* max inobt btree levels. */ uint m_rmap_maxlevels; /* max rmap btree levels */ uint m_refc_maxlevels; /* max refcount btree level */ xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */ @@ -159,20 +151,13 @@ typedef struct xfs_mount { int m_fixedfsid[2]; /* unchanged for life of FS */ uint64_t m_flags; /* global mount flags */ bool m_finobt_nores; /* no per-AG finobt resv. */ - int m_ialloc_inos; /* inodes in inode allocation */ - int m_ialloc_blks; /* blocks in inode allocation */ - int m_ialloc_min_blks;/* min blocks in sparse inode - * allocation */ - int m_inoalign_mask;/* mask sb_inoalignmt if used */ uint m_qflags; /* quota status flags */ struct xfs_trans_resv m_resv; /* precomputed res values */ - uint64_t m_maxicount; /* maximum inode count */ uint64_t m_resblks; /* total reserved blocks */ uint64_t m_resblks_avail;/* available reserved blocks */ uint64_t m_resblks_save; /* reserved blks @ remount,ro */ int m_dalign; /* stripe unit */ int m_swidth; /* stripe width */ - int m_sinoalign; /* stripe unit inode alignment */ uint8_t m_sectbb_log; /* sectlog - BBSHIFT */ const struct xfs_nameops *m_dirnameops; /* vector of dir name ops */ const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */ @@ -198,7 +183,6 @@ 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_log_workqueue; struct workqueue_struct *m_eofblocks_workqueue; struct workqueue_struct *m_sync_workqueue; @@ -226,6 +210,8 @@ typedef struct xfs_mount { #endif } xfs_mount_t; +#define M_IGEO(mp) (&(mp)->m_ino_geo) + /* * Flags for m_flags. */ @@ -465,7 +451,7 @@ extern int xfs_mod_fdblocks(struct xfs_mount *mp, int64_t delta, bool reserved); extern int xfs_mod_frextents(struct xfs_mount *mp, int64_t delta); -extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int); +extern struct xfs_buf *xfs_getsb(xfs_mount_t *); extern int xfs_readsb(xfs_mount_t *, int); extern void xfs_freesb(xfs_mount_t *); extern bool xfs_fs_writable(struct xfs_mount *mp, int level); diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index c8ba98fae30a..b6701b4f59a9 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -146,6 +146,11 @@ xfs_check_ondisk_structs(void) XFS_CHECK_OFFSET(struct xfs_dir3_data_hdr, hdr.magic, 0); XFS_CHECK_OFFSET(struct xfs_dir3_free, hdr.hdr.magic, 0); XFS_CHECK_OFFSET(struct xfs_attr3_leafblock, hdr.info.hdr, 0); + + XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat, 192); + XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers, 24); + XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req, 64); } #endif /* __XFS_ONDISK_H */ diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index bde2c9f56a46..0c954cad7449 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -2,23 +2,16 @@ /* * Copyright (c) 2014 Christoph Hellwig. */ -#include <linux/iomap.h> #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_log.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" -#include "xfs_error.h" #include "xfs_iomap.h" -#include "xfs_shared.h" -#include "xfs_bit.h" -#include "xfs_pnfs.h" /* * Ensure that we do not have any outstanding pNFS layouts that can be used by diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c new file mode 100644 index 000000000000..4bcc3e61056c --- /dev/null +++ b/fs/xfs/xfs_pwork.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_shared.h" +#include "xfs_format.h" +#include "xfs_log_format.h" +#include "xfs_trans_resv.h" +#include "xfs_mount.h" +#include "xfs_trace.h" +#include "xfs_sysctl.h" +#include "xfs_pwork.h" +#include <linux/nmi.h> + +/* + * Parallel Work Queue + * =================== + * + * Abstract away the details of running a large and "obviously" parallelizable + * task across multiple CPUs. Callers initialize the pwork control object with + * a desired level of parallelization and a work function. Next, they embed + * struct xfs_pwork in whatever structure they use to pass work context to a + * worker thread and queue that pwork. The work function will be passed the + * pwork item when it is run (from process context) and any returned error will + * be recorded in xfs_pwork_ctl.error. Work functions should check for errors + * and abort if necessary; the non-zeroness of xfs_pwork_ctl.error does not + * stop workqueue item processing. + * + * This is the rough equivalent of the xfsprogs workqueue code, though we can't + * reuse that name here. + */ + +/* Invoke our caller's function. */ +static void +xfs_pwork_work( + struct work_struct *work) +{ + struct xfs_pwork *pwork; + struct xfs_pwork_ctl *pctl; + int error; + + pwork = container_of(work, struct xfs_pwork, work); + pctl = pwork->pctl; + error = pctl->work_fn(pctl->mp, pwork); + if (error && !pctl->error) + pctl->error = error; + if (atomic_dec_and_test(&pctl->nr_work)) + wake_up(&pctl->poll_wait); +} + +/* + * Set up control data for parallel work. @work_fn is the function that will + * be called. @tag will be written into the kernel threads. @nr_threads is + * the level of parallelism desired, or 0 for no limit. + */ +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) +{ +#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, + current->pid); + if (!pctl->wq) + return -ENOMEM; + pctl->work_fn = work_fn; + pctl->error = 0; + pctl->mp = mp; + atomic_set(&pctl->nr_work, 0); + init_waitqueue_head(&pctl->poll_wait); + + return 0; +} + +/* Queue some parallel work. */ +void +xfs_pwork_queue( + struct xfs_pwork_ctl *pctl, + struct xfs_pwork *pwork) +{ + INIT_WORK(&pwork->work, xfs_pwork_work); + pwork->pctl = pctl; + atomic_inc(&pctl->nr_work); + queue_work(pctl->wq, &pwork->work); +} + +/* Wait for the work to finish and tear down the control structure. */ +int +xfs_pwork_destroy( + struct xfs_pwork_ctl *pctl) +{ + destroy_workqueue(pctl->wq); + pctl->wq = NULL; + return pctl->error; +} + +/* + * Wait for the work to finish by polling completion status and touch the soft + * lockup watchdog. This is for callers such as mount which hold locks. + */ +void +xfs_pwork_poll( + struct xfs_pwork_ctl *pctl) +{ + while (wait_event_timeout(pctl->poll_wait, + 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_queue) ? 2 : 1; +} diff --git a/fs/xfs/xfs_pwork.h b/fs/xfs/xfs_pwork.h new file mode 100644 index 000000000000..8133124cf3bb --- /dev/null +++ b/fs/xfs/xfs_pwork.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2019 Oracle. All Rights Reserved. + * Author: Darrick J. Wong <darrick.wong@oracle.com> + */ +#ifndef __XFS_PWORK_H__ +#define __XFS_PWORK_H__ + +struct xfs_pwork; +struct xfs_mount; + +typedef int (*xfs_pwork_work_fn)(struct xfs_mount *mp, struct xfs_pwork *pwork); + +/* + * Parallel work coordination structure. + */ +struct xfs_pwork_ctl { + struct workqueue_struct *wq; + struct xfs_mount *mp; + xfs_pwork_work_fn work_fn; + struct wait_queue_head poll_wait; + atomic_t nr_work; + int error; +}; + +/* + * Embed this parallel work control item inside your own work structure, + * then queue work with it. + */ +struct xfs_pwork { + struct work_struct work; + struct xfs_pwork_ctl *pctl; +}; + +#define XFS_PWORK_SINGLE_THREADED { .pctl = NULL } + +/* Have we been told to abort? */ +static inline bool +xfs_pwork_ctl_want_abort( + struct xfs_pwork_ctl *pctl) +{ + return pctl && pctl->error; +} + +/* Have we been told to abort? */ +static inline bool +xfs_pwork_want_abort( + struct xfs_pwork *pwork) +{ + return xfs_pwork_ctl_want_abort(pwork->pctl); +} + +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); +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 aa6b6db3db0e..5e7a37f0cf84 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -13,19 +13,15 @@ #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" -#include "xfs_ialloc.h" -#include "xfs_itable.h" +#include "xfs_iwalk.h" #include "xfs_quota.h" -#include "xfs_error.h" #include "xfs_bmap.h" -#include "xfs_bmap_btree.h" #include "xfs_bmap_util.h" #include "xfs_trans.h" #include "xfs_trans_space.h" #include "xfs_qm.h" #include "xfs_trace.h" #include "xfs_icache.h" -#include "xfs_cksum.h" /* * The global quota manager. There is only one of these for the entire @@ -1118,17 +1114,15 @@ xfs_qm_quotacheck_dqadjust( /* ARGSUSED */ STATIC int xfs_qm_dqusage_adjust( - xfs_mount_t *mp, /* mount point for filesystem */ - xfs_ino_t ino, /* inode number to get data for */ - void __user *buffer, /* not used */ - int ubsize, /* not used */ - int *ubused, /* not used */ - int *res) /* result code value */ + struct xfs_mount *mp, + struct xfs_trans *tp, + xfs_ino_t ino, + void *data) { - xfs_inode_t *ip; - xfs_qcnt_t nblks; - xfs_filblks_t rtblks = 0; /* total rt blks */ - int error; + struct xfs_inode *ip; + xfs_qcnt_t nblks; + xfs_filblks_t rtblks = 0; /* total rt blks */ + int error; ASSERT(XFS_IS_QUOTA_RUNNING(mp)); @@ -1136,20 +1130,18 @@ xfs_qm_dqusage_adjust( * rootino must have its resources accounted for, not so with the quota * inodes. */ - if (xfs_is_quota_inode(&mp->m_sb, ino)) { - *res = BULKSTAT_RV_NOTHING; - return -EINVAL; - } + if (xfs_is_quota_inode(&mp->m_sb, ino)) + return 0; /* * We don't _need_ to take the ilock EXCL here because quotacheck runs * at mount time and therefore nobody will be racing chown/chproj. */ - error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, 0, &ip); - if (error) { - *res = BULKSTAT_RV_NOTHING; + error = xfs_iget(mp, tp, ino, XFS_IGET_DONTCACHE, 0, &ip); + if (error == -EINVAL || error == -ENOENT) + return 0; + if (error) return error; - } ASSERT(ip->i_delayed_blks == 0); @@ -1157,7 +1149,7 @@ xfs_qm_dqusage_adjust( struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); if (!(ifp->if_flags & XFS_IFEXTENTS)) { - error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK); + error = xfs_iread_extents(tp, ip, XFS_DATA_FORK); if (error) goto error0; } @@ -1200,13 +1192,8 @@ xfs_qm_dqusage_adjust( goto error0; } - xfs_irele(ip); - *res = BULKSTAT_RV_DIDONE; - return 0; - error0: xfs_irele(ip); - *res = BULKSTAT_RV_GIVEUP; return error; } @@ -1270,18 +1257,13 @@ STATIC int xfs_qm_quotacheck( xfs_mount_t *mp) { - int done, count, error, error2; - xfs_ino_t lastino; - size_t structsz; + int error, error2; uint flags; LIST_HEAD (buffer_list); struct xfs_inode *uip = mp->m_quotainfo->qi_uquotaip; struct xfs_inode *gip = mp->m_quotainfo->qi_gquotaip; struct xfs_inode *pip = mp->m_quotainfo->qi_pquotaip; - count = INT_MAX; - structsz = 1; - lastino = 0; flags = 0; ASSERT(uip || gip || pip); @@ -1318,18 +1300,10 @@ xfs_qm_quotacheck( flags |= XFS_PQUOTA_CHKD; } - do { - /* - * Iterate thru all the inodes in the file system, - * adjusting the corresponding dquot counters in core. - */ - error = xfs_bulkstat(mp, &lastino, &count, - xfs_qm_dqusage_adjust, - structsz, NULL, &done); - if (error) - break; - - } while (!done); + error = xfs_iwalk_threaded(mp, 0, 0, xfs_qm_dqusage_adjust, 0, true, + NULL); + if (error) + goto error_return; /* * We've made all the changes that we need to make incore. Flush them diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 3091e4bc04ef..5d72e88598b4 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -5,13 +5,13 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_quota.h" #include "xfs_mount.h" #include "xfs_inode.h" -#include "xfs_error.h" #include "xfs_trans.h" #include "xfs_qm.h" diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index b3190890f096..da7ad0383037 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -4,7 +4,6 @@ * All Rights Reserved. */ -#include <linux/capability.h> #include "xfs.h" #include "xfs_fs.h" @@ -12,17 +11,13 @@ #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" -#include "xfs_bit.h" #include "xfs_sb.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_error.h" #include "xfs_quota.h" #include "xfs_qm.h" -#include "xfs_trace.h" #include "xfs_icache.h" -#include "xfs_defer.h" STATIC int xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint); STATIC int xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *, diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index a7c0c657dfaf..cd6c7210a373 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -4,6 +4,7 @@ * All Rights Reserved. */ #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" @@ -11,10 +12,8 @@ #include "xfs_inode.h" #include "xfs_quota.h" #include "xfs_trans.h" -#include "xfs_trace.h" #include "xfs_icache.h" #include "xfs_qm.h" -#include <linux/quota.h> static void diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index fce38b56b962..d8288aa0670a 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -14,7 +14,6 @@ #include "xfs_defer.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" -#include "xfs_buf_item.h" #include "xfs_refcount_item.h" #include "xfs_log.h" #include "xfs_refcount.h" @@ -95,15 +94,6 @@ xfs_cui_item_format( } /* - * Pinning has no meaning for an cui item, so just return. - */ -STATIC void -xfs_cui_item_pin( - struct xfs_log_item *lip) -{ -} - -/* * The unpin operation is the last place an CUI is manipulated in the log. It is * either inserted in the AIL or aborted in the event of a log I/O error. In * either case, the CUI transaction has been successfully committed to make it @@ -122,71 +112,22 @@ xfs_cui_item_unpin( } /* - * CUI items have no locking or pushing. However, since CUIs are pulled from - * the AIL when their corresponding CUDs are committed to disk, their situation - * is very similar to being pinned. Return XFS_ITEM_PINNED so that the caller - * will eventually flush the log. This should help in getting the CUI out of - * the AIL. - */ -STATIC uint -xfs_cui_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) -{ - return XFS_ITEM_PINNED; -} - -/* * The CUI has been either committed or aborted if the transaction has been * cancelled. If the transaction was cancelled, an CUD isn't going to be * constructed and thus we free the CUI here directly. */ STATIC void -xfs_cui_item_unlock( +xfs_cui_item_release( struct xfs_log_item *lip) { - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) - xfs_cui_release(CUI_ITEM(lip)); + xfs_cui_release(CUI_ITEM(lip)); } -/* - * The CUI is logged only once and cannot be moved in the log, so simply return - * the lsn at which it's been logged. - */ -STATIC xfs_lsn_t -xfs_cui_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ - return lsn; -} - -/* - * The CUI dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ -STATIC void -xfs_cui_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ -} - -/* - * This is the ops vector shared by all cui log items. - */ static const struct xfs_item_ops xfs_cui_item_ops = { .iop_size = xfs_cui_item_size, .iop_format = xfs_cui_item_format, - .iop_pin = xfs_cui_item_pin, .iop_unpin = xfs_cui_item_unpin, - .iop_unlock = xfs_cui_item_unlock, - .iop_committed = xfs_cui_item_committed, - .iop_push = xfs_cui_item_push, - .iop_committing = xfs_cui_item_committing, + .iop_release = xfs_cui_item_release, }; /* @@ -254,126 +195,250 @@ xfs_cud_item_format( } /* - * Pinning has no meaning for an cud item, so just return. + * The CUD is either committed or aborted if the transaction is cancelled. If + * the transaction is cancelled, drop our reference to the CUI and free the + * CUD. */ STATIC void -xfs_cud_item_pin( +xfs_cud_item_release( struct xfs_log_item *lip) { + struct xfs_cud_log_item *cudp = CUD_ITEM(lip); + + xfs_cui_release(cudp->cud_cuip); + kmem_zone_free(xfs_cud_zone, cudp); } -/* - * Since pinning has no meaning for an cud item, unpinning does - * not either. - */ -STATIC void -xfs_cud_item_unpin( - struct xfs_log_item *lip, - int remove) +static const struct xfs_item_ops xfs_cud_item_ops = { + .flags = XFS_ITEM_RELEASE_WHEN_COMMITTED, + .iop_size = xfs_cud_item_size, + .iop_format = xfs_cud_item_format, + .iop_release = xfs_cud_item_release, +}; + +static struct xfs_cud_log_item * +xfs_trans_get_cud( + struct xfs_trans *tp, + struct xfs_cui_log_item *cuip) { + struct xfs_cud_log_item *cudp; + + cudp = kmem_zone_zalloc(xfs_cud_zone, KM_SLEEP); + xfs_log_item_init(tp->t_mountp, &cudp->cud_item, XFS_LI_CUD, + &xfs_cud_item_ops); + cudp->cud_cuip = cuip; + cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id; + + xfs_trans_add_item(tp, &cudp->cud_item); + return cudp; } /* - * There isn't much you can do to push on an cud item. It is simply stuck - * waiting for the log to be flushed to disk. + * Finish an refcount update and log it to the CUD. Note that the + * transaction is marked dirty regardless of whether the refcount + * update succeeds or fails to support the CUI/CUD lifecycle rules. */ -STATIC uint -xfs_cud_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) +static int +xfs_trans_log_finish_refcount_update( + struct xfs_trans *tp, + struct xfs_cud_log_item *cudp, + enum xfs_refcount_intent_type type, + xfs_fsblock_t startblock, + xfs_extlen_t blockcount, + xfs_fsblock_t *new_fsb, + xfs_extlen_t *new_len, + struct xfs_btree_cur **pcur) { - return XFS_ITEM_PINNED; + int error; + + error = xfs_refcount_finish_one(tp, type, startblock, + blockcount, new_fsb, new_len, pcur); + + /* + * Mark the transaction dirty, even on error. This ensures the + * transaction is aborted, which: + * + * 1.) releases the CUI and frees the CUD + * 2.) shuts down the filesystem + */ + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags); + + return error; } -/* - * The CUD is either committed or aborted if the transaction is cancelled. If - * the transaction is cancelled, drop our reference to the CUI and free the - * CUD. - */ -STATIC void -xfs_cud_item_unlock( - struct xfs_log_item *lip) +/* Sort refcount intents by AG. */ +static int +xfs_refcount_update_diff_items( + void *priv, + struct list_head *a, + struct list_head *b) { - struct xfs_cud_log_item *cudp = CUD_ITEM(lip); + struct xfs_mount *mp = priv; + struct xfs_refcount_intent *ra; + struct xfs_refcount_intent *rb; + + ra = container_of(a, struct xfs_refcount_intent, ri_list); + rb = container_of(b, struct xfs_refcount_intent, ri_list); + return XFS_FSB_TO_AGNO(mp, ra->ri_startblock) - + XFS_FSB_TO_AGNO(mp, rb->ri_startblock); +} - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) { - xfs_cui_release(cudp->cud_cuip); - kmem_zone_free(xfs_cud_zone, cudp); +/* Get an CUI. */ +STATIC void * +xfs_refcount_update_create_intent( + struct xfs_trans *tp, + unsigned int count) +{ + struct xfs_cui_log_item *cuip; + + ASSERT(tp != NULL); + ASSERT(count > 0); + + cuip = xfs_cui_init(tp->t_mountp, count); + ASSERT(cuip != NULL); + + /* + * Get a log_item_desc to point at the new item. + */ + xfs_trans_add_item(tp, &cuip->cui_item); + return cuip; +} + +/* Set the phys extent flags for this reverse mapping. */ +static void +xfs_trans_set_refcount_flags( + struct xfs_phys_extent *refc, + enum xfs_refcount_intent_type type) +{ + refc->pe_flags = 0; + switch (type) { + case XFS_REFCOUNT_INCREASE: + case XFS_REFCOUNT_DECREASE: + case XFS_REFCOUNT_ALLOC_COW: + case XFS_REFCOUNT_FREE_COW: + refc->pe_flags |= type; + break; + default: + ASSERT(0); } } -/* - * When the cud item is committed to disk, all we need to do is delete our - * reference to our partner cui item and then free ourselves. Since we're - * freeing ourselves we must return -1 to keep the transaction code from - * further referencing this item. - */ -STATIC xfs_lsn_t -xfs_cud_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +/* Log refcount updates in the intent item. */ +STATIC void +xfs_refcount_update_log_item( + struct xfs_trans *tp, + void *intent, + struct list_head *item) { - struct xfs_cud_log_item *cudp = CUD_ITEM(lip); + struct xfs_cui_log_item *cuip = intent; + struct xfs_refcount_intent *refc; + uint next_extent; + struct xfs_phys_extent *ext; + + refc = container_of(item, struct xfs_refcount_intent, ri_list); + + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags); /* - * Drop the CUI reference regardless of whether the CUD has been - * aborted. Once the CUD transaction is constructed, it is the sole - * responsibility of the CUD to release the CUI (even if the CUI is - * aborted due to log I/O error). + * atomic_inc_return gives us the value after the increment; + * we want to use it as an array index so we need to subtract 1 from + * it. */ - xfs_cui_release(cudp->cud_cuip); - kmem_zone_free(xfs_cud_zone, cudp); + next_extent = atomic_inc_return(&cuip->cui_next_extent) - 1; + ASSERT(next_extent < cuip->cui_format.cui_nextents); + ext = &cuip->cui_format.cui_extents[next_extent]; + ext->pe_startblock = refc->ri_startblock; + ext->pe_len = refc->ri_blockcount; + xfs_trans_set_refcount_flags(ext, refc->ri_type); +} - return (xfs_lsn_t)-1; +/* Get an CUD so we can process all the deferred refcount updates. */ +STATIC void * +xfs_refcount_update_create_done( + struct xfs_trans *tp, + void *intent, + unsigned int count) +{ + return xfs_trans_get_cud(tp, intent); } -/* - * The CUD dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ -STATIC void -xfs_cud_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +/* Process a deferred refcount update. */ +STATIC int +xfs_refcount_update_finish_item( + struct xfs_trans *tp, + struct list_head *item, + void *done_item, + void **state) { + struct xfs_refcount_intent *refc; + xfs_fsblock_t new_fsb; + xfs_extlen_t new_aglen; + int error; + + refc = container_of(item, struct xfs_refcount_intent, ri_list); + error = xfs_trans_log_finish_refcount_update(tp, done_item, + refc->ri_type, + refc->ri_startblock, + refc->ri_blockcount, + &new_fsb, &new_aglen, + (struct xfs_btree_cur **)state); + /* Did we run out of reservation? Requeue what we didn't finish. */ + if (!error && new_aglen > 0) { + ASSERT(refc->ri_type == XFS_REFCOUNT_INCREASE || + refc->ri_type == XFS_REFCOUNT_DECREASE); + refc->ri_startblock = new_fsb; + refc->ri_blockcount = new_aglen; + return -EAGAIN; + } + kmem_free(refc); + return error; } -/* - * This is the ops vector shared by all cud log items. - */ -static const struct xfs_item_ops xfs_cud_item_ops = { - .iop_size = xfs_cud_item_size, - .iop_format = xfs_cud_item_format, - .iop_pin = xfs_cud_item_pin, - .iop_unpin = xfs_cud_item_unpin, - .iop_unlock = xfs_cud_item_unlock, - .iop_committed = xfs_cud_item_committed, - .iop_push = xfs_cud_item_push, - .iop_committing = xfs_cud_item_committing, -}; +/* Clean up after processing deferred refcounts. */ +STATIC void +xfs_refcount_update_finish_cleanup( + struct xfs_trans *tp, + void *state, + int error) +{ + struct xfs_btree_cur *rcur = state; -/* - * Allocate and initialize an cud item with the given number of extents. - */ -struct xfs_cud_log_item * -xfs_cud_init( - struct xfs_mount *mp, - struct xfs_cui_log_item *cuip) + xfs_refcount_finish_one_cleanup(tp, rcur, error); +} +/* Abort all pending CUIs. */ +STATIC void +xfs_refcount_update_abort_intent( + void *intent) { - struct xfs_cud_log_item *cudp; + xfs_cui_release(intent); +} - cudp = kmem_zone_zalloc(xfs_cud_zone, KM_SLEEP); - xfs_log_item_init(mp, &cudp->cud_item, XFS_LI_CUD, &xfs_cud_item_ops); - cudp->cud_cuip = cuip; - cudp->cud_format.cud_cui_id = cuip->cui_format.cui_id; +/* Cancel a deferred refcount update. */ +STATIC void +xfs_refcount_update_cancel_item( + struct list_head *item) +{ + struct xfs_refcount_intent *refc; - return cudp; + refc = container_of(item, struct xfs_refcount_intent, ri_list); + kmem_free(refc); } +const struct xfs_defer_op_type xfs_refcount_update_defer_type = { + .max_items = XFS_CUI_MAX_FAST_EXTENTS, + .diff_items = xfs_refcount_update_diff_items, + .create_intent = xfs_refcount_update_create_intent, + .abort_intent = xfs_refcount_update_abort_intent, + .log_item = xfs_refcount_update_log_item, + .create_done = xfs_refcount_update_create_done, + .finish_item = xfs_refcount_update_finish_item, + .finish_cleanup = xfs_refcount_update_finish_cleanup, + .cancel_item = xfs_refcount_update_cancel_item, +}; + /* * Process a refcount update intent item that was recovered from the log. * We need to update the refcountbt. diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h index 3896dcc2368f..e47530f30489 100644 --- a/fs/xfs/xfs_refcount_item.h +++ b/fs/xfs/xfs_refcount_item.h @@ -78,8 +78,6 @@ extern struct kmem_zone *xfs_cui_zone; extern struct kmem_zone *xfs_cud_zone; struct xfs_cui_log_item *xfs_cui_init(struct xfs_mount *, uint); -struct xfs_cud_log_item *xfs_cud_init(struct xfs_mount *, - struct xfs_cui_log_item *); void xfs_cui_item_free(struct xfs_cui_log_item *); void xfs_cui_release(struct xfs_cui_log_item *); int xfs_cui_recover(struct xfs_trans *parent_tp, struct xfs_cui_log_item *cuip); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 680ae7662a78..c4ec7afd1170 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -11,21 +11,12 @@ #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_defer.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" -#include "xfs_inode_item.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" -#include "xfs_error.h" -#include "xfs_dir2.h" -#include "xfs_dir2_priv.h" -#include "xfs_ioctl.h" #include "xfs_trace.h" -#include "xfs_log.h" #include "xfs_icache.h" -#include "xfs_pnfs.h" #include "xfs_btree.h" #include "xfs_refcount_btree.h" #include "xfs_refcount.h" @@ -33,11 +24,9 @@ #include "xfs_trans_space.h" #include "xfs_bit.h" #include "xfs_alloc.h" -#include "xfs_quota_defs.h" #include "xfs_quota.h" #include "xfs_reflink.h" #include "xfs_iomap.h" -#include "xfs_rmap_btree.h" #include "xfs_sb.h" #include "xfs_ag_resv.h" @@ -572,7 +561,7 @@ xfs_reflink_cancel_cow_range( /* Start a rolling transaction to remove the mappings */ error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write, - 0, 0, XFS_TRANS_NOFS, &tp); + 0, 0, 0, &tp); if (error) goto out; @@ -631,7 +620,7 @@ xfs_reflink_end_cow_extent( resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, - XFS_TRANS_RESERVE | XFS_TRANS_NOFS, &tp); + XFS_TRANS_RESERVE, &tp); if (error) return error; diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 127dc9c32a54..77ed557b6127 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -14,7 +14,6 @@ #include "xfs_defer.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" -#include "xfs_buf_item.h" #include "xfs_rmap_item.h" #include "xfs_log.h" #include "xfs_rmap.h" @@ -94,15 +93,6 @@ xfs_rui_item_format( } /* - * Pinning has no meaning for an rui item, so just return. - */ -STATIC void -xfs_rui_item_pin( - struct xfs_log_item *lip) -{ -} - -/* * The unpin operation is the last place an RUI is manipulated in the log. It is * either inserted in the AIL or aborted in the event of a log I/O error. In * either case, the RUI transaction has been successfully committed to make it @@ -121,71 +111,22 @@ xfs_rui_item_unpin( } /* - * RUI items have no locking or pushing. However, since RUIs are pulled from - * the AIL when their corresponding RUDs are committed to disk, their situation - * is very similar to being pinned. Return XFS_ITEM_PINNED so that the caller - * will eventually flush the log. This should help in getting the RUI out of - * the AIL. - */ -STATIC uint -xfs_rui_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) -{ - return XFS_ITEM_PINNED; -} - -/* * The RUI has been either committed or aborted if the transaction has been * cancelled. If the transaction was cancelled, an RUD isn't going to be * constructed and thus we free the RUI here directly. */ STATIC void -xfs_rui_item_unlock( +xfs_rui_item_release( struct xfs_log_item *lip) { - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) - xfs_rui_release(RUI_ITEM(lip)); + xfs_rui_release(RUI_ITEM(lip)); } -/* - * The RUI is logged only once and cannot be moved in the log, so simply return - * the lsn at which it's been logged. - */ -STATIC xfs_lsn_t -xfs_rui_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ - return lsn; -} - -/* - * The RUI dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ -STATIC void -xfs_rui_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) -{ -} - -/* - * This is the ops vector shared by all rui log items. - */ static const struct xfs_item_ops xfs_rui_item_ops = { .iop_size = xfs_rui_item_size, .iop_format = xfs_rui_item_format, - .iop_pin = xfs_rui_item_pin, .iop_unpin = xfs_rui_item_unpin, - .iop_unlock = xfs_rui_item_unlock, - .iop_committed = xfs_rui_item_committed, - .iop_push = xfs_rui_item_push, - .iop_committing = xfs_rui_item_committing, + .iop_release = xfs_rui_item_release, }; /* @@ -275,126 +216,271 @@ xfs_rud_item_format( } /* - * Pinning has no meaning for an rud item, so just return. + * The RUD is either committed or aborted if the transaction is cancelled. If + * the transaction is cancelled, drop our reference to the RUI and free the + * RUD. */ STATIC void -xfs_rud_item_pin( +xfs_rud_item_release( struct xfs_log_item *lip) { + struct xfs_rud_log_item *rudp = RUD_ITEM(lip); + + xfs_rui_release(rudp->rud_ruip); + kmem_zone_free(xfs_rud_zone, rudp); } -/* - * Since pinning has no meaning for an rud item, unpinning does - * not either. - */ -STATIC void -xfs_rud_item_unpin( - struct xfs_log_item *lip, - int remove) +static const struct xfs_item_ops xfs_rud_item_ops = { + .flags = XFS_ITEM_RELEASE_WHEN_COMMITTED, + .iop_size = xfs_rud_item_size, + .iop_format = xfs_rud_item_format, + .iop_release = xfs_rud_item_release, +}; + +static struct xfs_rud_log_item * +xfs_trans_get_rud( + struct xfs_trans *tp, + struct xfs_rui_log_item *ruip) { + struct xfs_rud_log_item *rudp; + + rudp = kmem_zone_zalloc(xfs_rud_zone, KM_SLEEP); + xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD, + &xfs_rud_item_ops); + rudp->rud_ruip = ruip; + rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id; + + xfs_trans_add_item(tp, &rudp->rud_item); + return rudp; } -/* - * There isn't much you can do to push on an rud item. It is simply stuck - * waiting for the log to be flushed to disk. - */ -STATIC uint -xfs_rud_item_push( - struct xfs_log_item *lip, - struct list_head *buffer_list) +/* Set the map extent flags for this reverse mapping. */ +static void +xfs_trans_set_rmap_flags( + struct xfs_map_extent *rmap, + enum xfs_rmap_intent_type type, + int whichfork, + xfs_exntst_t state) { - return XFS_ITEM_PINNED; + rmap->me_flags = 0; + if (state == XFS_EXT_UNWRITTEN) + rmap->me_flags |= XFS_RMAP_EXTENT_UNWRITTEN; + if (whichfork == XFS_ATTR_FORK) + rmap->me_flags |= XFS_RMAP_EXTENT_ATTR_FORK; + switch (type) { + case XFS_RMAP_MAP: + rmap->me_flags |= XFS_RMAP_EXTENT_MAP; + break; + case XFS_RMAP_MAP_SHARED: + rmap->me_flags |= XFS_RMAP_EXTENT_MAP_SHARED; + break; + case XFS_RMAP_UNMAP: + rmap->me_flags |= XFS_RMAP_EXTENT_UNMAP; + break; + case XFS_RMAP_UNMAP_SHARED: + rmap->me_flags |= XFS_RMAP_EXTENT_UNMAP_SHARED; + break; + case XFS_RMAP_CONVERT: + rmap->me_flags |= XFS_RMAP_EXTENT_CONVERT; + break; + case XFS_RMAP_CONVERT_SHARED: + rmap->me_flags |= XFS_RMAP_EXTENT_CONVERT_SHARED; + break; + case XFS_RMAP_ALLOC: + rmap->me_flags |= XFS_RMAP_EXTENT_ALLOC; + break; + case XFS_RMAP_FREE: + rmap->me_flags |= XFS_RMAP_EXTENT_FREE; + break; + default: + ASSERT(0); + } } /* - * The RUD is either committed or aborted if the transaction is cancelled. If - * the transaction is cancelled, drop our reference to the RUI and free the - * RUD. + * Finish an rmap update and log it to the RUD. Note that the transaction is + * marked dirty regardless of whether the rmap update succeeds or fails to + * support the RUI/RUD lifecycle rules. */ -STATIC void -xfs_rud_item_unlock( - struct xfs_log_item *lip) +static int +xfs_trans_log_finish_rmap_update( + struct xfs_trans *tp, + struct xfs_rud_log_item *rudp, + enum xfs_rmap_intent_type type, + uint64_t owner, + int whichfork, + xfs_fileoff_t startoff, + xfs_fsblock_t startblock, + xfs_filblks_t blockcount, + xfs_exntst_t state, + struct xfs_btree_cur **pcur) { - struct xfs_rud_log_item *rudp = RUD_ITEM(lip); + int error; - if (test_bit(XFS_LI_ABORTED, &lip->li_flags)) { - xfs_rui_release(rudp->rud_ruip); - kmem_zone_free(xfs_rud_zone, rudp); - } + error = xfs_rmap_finish_one(tp, type, owner, whichfork, startoff, + startblock, blockcount, state, pcur); + + /* + * Mark the transaction dirty, even on error. This ensures the + * transaction is aborted, which: + * + * 1.) releases the RUI and frees the RUD + * 2.) shuts down the filesystem + */ + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags); + + return error; } -/* - * When the rud item is committed to disk, all we need to do is delete our - * reference to our partner rui item and then free ourselves. Since we're - * freeing ourselves we must return -1 to keep the transaction code from - * further referencing this item. - */ -STATIC xfs_lsn_t -xfs_rud_item_committed( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +/* Sort rmap intents by AG. */ +static int +xfs_rmap_update_diff_items( + void *priv, + struct list_head *a, + struct list_head *b) { - struct xfs_rud_log_item *rudp = RUD_ITEM(lip); + struct xfs_mount *mp = priv; + struct xfs_rmap_intent *ra; + struct xfs_rmap_intent *rb; + + ra = container_of(a, struct xfs_rmap_intent, ri_list); + rb = container_of(b, struct xfs_rmap_intent, ri_list); + return XFS_FSB_TO_AGNO(mp, ra->ri_bmap.br_startblock) - + XFS_FSB_TO_AGNO(mp, rb->ri_bmap.br_startblock); +} + +/* Get an RUI. */ +STATIC void * +xfs_rmap_update_create_intent( + struct xfs_trans *tp, + unsigned int count) +{ + struct xfs_rui_log_item *ruip; + + ASSERT(tp != NULL); + ASSERT(count > 0); + + ruip = xfs_rui_init(tp->t_mountp, count); + ASSERT(ruip != NULL); /* - * Drop the RUI reference regardless of whether the RUD has been - * aborted. Once the RUD transaction is constructed, it is the sole - * responsibility of the RUD to release the RUI (even if the RUI is - * aborted due to log I/O error). + * Get a log_item_desc to point at the new item. */ - xfs_rui_release(rudp->rud_ruip); - kmem_zone_free(xfs_rud_zone, rudp); - - return (xfs_lsn_t)-1; + xfs_trans_add_item(tp, &ruip->rui_item); + return ruip; } -/* - * The RUD dependency tracking op doesn't do squat. It can't because - * it doesn't know where the free extent is coming from. The dependency - * tracking has to be handled by the "enclosing" metadata object. For - * example, for inodes, the inode is locked throughout the extent freeing - * so the dependency should be recorded there. - */ +/* Log rmap updates in the intent item. */ STATIC void -xfs_rud_item_committing( - struct xfs_log_item *lip, - xfs_lsn_t lsn) +xfs_rmap_update_log_item( + struct xfs_trans *tp, + void *intent, + struct list_head *item) { + struct xfs_rui_log_item *ruip = intent; + struct xfs_rmap_intent *rmap; + uint next_extent; + struct xfs_map_extent *map; + + rmap = container_of(item, struct xfs_rmap_intent, ri_list); + + tp->t_flags |= XFS_TRANS_DIRTY; + set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags); + + /* + * atomic_inc_return gives us the value after the increment; + * we want to use it as an array index so we need to subtract 1 from + * it. + */ + next_extent = atomic_inc_return(&ruip->rui_next_extent) - 1; + ASSERT(next_extent < ruip->rui_format.rui_nextents); + map = &ruip->rui_format.rui_extents[next_extent]; + map->me_owner = rmap->ri_owner; + map->me_startblock = rmap->ri_bmap.br_startblock; + map->me_startoff = rmap->ri_bmap.br_startoff; + map->me_len = rmap->ri_bmap.br_blockcount; + xfs_trans_set_rmap_flags(map, rmap->ri_type, rmap->ri_whichfork, + rmap->ri_bmap.br_state); } -/* - * This is the ops vector shared by all rud log items. - */ -static const struct xfs_item_ops xfs_rud_item_ops = { - .iop_size = xfs_rud_item_size, - .iop_format = xfs_rud_item_format, - .iop_pin = xfs_rud_item_pin, - .iop_unpin = xfs_rud_item_unpin, - .iop_unlock = xfs_rud_item_unlock, - .iop_committed = xfs_rud_item_committed, - .iop_push = xfs_rud_item_push, - .iop_committing = xfs_rud_item_committing, -}; +/* Get an RUD so we can process all the deferred rmap updates. */ +STATIC void * +xfs_rmap_update_create_done( + struct xfs_trans *tp, + void *intent, + unsigned int count) +{ + return xfs_trans_get_rud(tp, intent); +} -/* - * Allocate and initialize an rud item with the given number of extents. - */ -struct xfs_rud_log_item * -xfs_rud_init( - struct xfs_mount *mp, - struct xfs_rui_log_item *ruip) +/* Process a deferred rmap update. */ +STATIC int +xfs_rmap_update_finish_item( + struct xfs_trans *tp, + struct list_head *item, + void *done_item, + void **state) +{ + struct xfs_rmap_intent *rmap; + int error; + + rmap = container_of(item, struct xfs_rmap_intent, ri_list); + error = xfs_trans_log_finish_rmap_update(tp, done_item, + rmap->ri_type, + rmap->ri_owner, rmap->ri_whichfork, + rmap->ri_bmap.br_startoff, + rmap->ri_bmap.br_startblock, + rmap->ri_bmap.br_blockcount, + rmap->ri_bmap.br_state, + (struct xfs_btree_cur **)state); + kmem_free(rmap); + return error; +} + +/* Clean up after processing deferred rmaps. */ +STATIC void +xfs_rmap_update_finish_cleanup( + struct xfs_trans *tp, + void *state, + int error) +{ + struct xfs_btree_cur *rcur = state; + + xfs_rmap_finish_one_cleanup(tp, rcur, error); +} +/* Abort all pending RUIs. */ +STATIC void +xfs_rmap_update_abort_intent( + void *intent) { - struct xfs_rud_log_item *rudp; + xfs_rui_release(intent); +} - rudp = kmem_zone_zalloc(xfs_rud_zone, KM_SLEEP); - xfs_log_item_init(mp, &rudp->rud_item, XFS_LI_RUD, &xfs_rud_item_ops); - rudp->rud_ruip = ruip; - rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id; +/* Cancel a deferred rmap update. */ +STATIC void +xfs_rmap_update_cancel_item( + struct list_head *item) +{ + struct xfs_rmap_intent *rmap; - return rudp; + rmap = container_of(item, struct xfs_rmap_intent, ri_list); + kmem_free(rmap); } +const struct xfs_defer_op_type xfs_rmap_update_defer_type = { + .max_items = XFS_RUI_MAX_FAST_EXTENTS, + .diff_items = xfs_rmap_update_diff_items, + .create_intent = xfs_rmap_update_create_intent, + .abort_intent = xfs_rmap_update_abort_intent, + .log_item = xfs_rmap_update_log_item, + .create_done = xfs_rmap_update_create_done, + .finish_item = xfs_rmap_update_finish_item, + .finish_cleanup = xfs_rmap_update_finish_cleanup, + .cancel_item = xfs_rmap_update_cancel_item, +}; + /* * Process an rmap update intent item that was recovered from the log. * We need to update the rmapbt. diff --git a/fs/xfs/xfs_rmap_item.h b/fs/xfs/xfs_rmap_item.h index 7e482baa27f5..8708e4a5aa5c 100644 --- a/fs/xfs/xfs_rmap_item.h +++ b/fs/xfs/xfs_rmap_item.h @@ -78,8 +78,6 @@ extern struct kmem_zone *xfs_rui_zone; extern struct kmem_zone *xfs_rud_zone; struct xfs_rui_log_item *xfs_rui_init(struct xfs_mount *, uint); -struct xfs_rud_log_item *xfs_rud_init(struct xfs_mount *, - struct xfs_rui_log_item *); int xfs_rui_copy_format(struct xfs_log_iovec *buf, struct xfs_rui_log_format *dst_rui_fmt); void xfs_rui_item_free(struct xfs_rui_log_item *); diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index ac0fcdad0c4e..5fa4db3c3e32 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -11,17 +11,11 @@ #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_bmap.h" -#include "xfs_bmap_util.h" #include "xfs_bmap_btree.h" -#include "xfs_alloc.h" -#include "xfs_error.h" #include "xfs_trans.h" #include "xfs_trans_space.h" -#include "xfs_trace.h" -#include "xfs_buf.h" #include "xfs_icache.h" #include "xfs_rtalloc.h" diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index cc509743facd..113883c4f202 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -4,7 +4,6 @@ * All Rights Reserved. */ #include "xfs.h" -#include <linux/proc_fs.h> struct xstats xfsstats; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index a14d11d78bd8..f9450235533c 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -11,18 +11,15 @@ #include "xfs_trans_resv.h" #include "xfs_sb.h" #include "xfs_mount.h" -#include "xfs_da_format.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_bmap.h" #include "xfs_alloc.h" -#include "xfs_error.h" #include "xfs_fsops.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_log.h" #include "xfs_log_priv.h" -#include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_extfree_item.h" #include "xfs_mru_cache.h" @@ -38,18 +35,8 @@ #include "xfs_refcount_item.h" #include "xfs_bmap_item.h" #include "xfs_reflink.h" -#include "xfs_defer.h" -#include <linux/namei.h> -#include <linux/dax.h> -#include <linux/init.h> -#include <linux/slab.h> #include <linux/magic.h> -#include <linux/mount.h> -#include <linux/mempool.h> -#include <linux/writeback.h> -#include <linux/kthread.h> -#include <linux/freezer.h> #include <linux/parser.h> static const struct super_operations xfs_super_operations; @@ -582,7 +569,7 @@ xfs_set_inode_alloc( * Calculate how much should be reserved for inodes to meet * the max inode percentage. Used only for inode32. */ - if (mp->m_maxicount) { + if (M_IGEO(mp)->maxicount) { uint64_t icount; icount = sbp->sb_dblocks * sbp->sb_imax_pct; @@ -840,16 +827,10 @@ xfs_init_mount_workqueues( if (!mp->m_reclaim_workqueue) goto out_destroy_cil; - mp->m_log_workqueue = alloc_workqueue("xfs-log/%s", - WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0, - mp->m_fsname); - if (!mp->m_log_workqueue) - goto out_destroy_reclaim; - mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s", WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname); if (!mp->m_eofblocks_workqueue) - goto out_destroy_log; + goto out_destroy_reclaim; mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0, mp->m_fsname); @@ -860,8 +841,6 @@ xfs_init_mount_workqueues( out_destroy_eofb: destroy_workqueue(mp->m_eofblocks_workqueue); -out_destroy_log: - destroy_workqueue(mp->m_log_workqueue); out_destroy_reclaim: destroy_workqueue(mp->m_reclaim_workqueue); out_destroy_cil: @@ -880,7 +859,6 @@ xfs_destroy_mount_workqueues( { destroy_workqueue(mp->m_sync_workqueue); destroy_workqueue(mp->m_eofblocks_workqueue); - destroy_workqueue(mp->m_log_workqueue); destroy_workqueue(mp->m_reclaim_workqueue); destroy_workqueue(mp->m_cil_workqueue); destroy_workqueue(mp->m_unwritten_workqueue); @@ -1131,10 +1109,10 @@ xfs_fs_statfs( fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree); statp->f_files = min(icount + fakeinos, (uint64_t)XFS_MAXINUMBER); - if (mp->m_maxicount) + if (M_IGEO(mp)->maxicount) statp->f_files = min_t(typeof(statp->f_files), statp->f_files, - mp->m_maxicount); + M_IGEO(mp)->maxicount); /* If sb_icount overshot maxicount, report actual allocation */ statp->f_files = max_t(typeof(statp->f_files), @@ -1685,6 +1663,8 @@ xfs_fs_fill_super( sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits); sb->s_max_links = XFS_MAXLINK; sb->s_time_gran = 1; + sb->s_iflags |= SB_I_CGROUPWB; + set_posix_acl_flag(sb); /* version 5 superblocks support inode version counters. */ diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h index 21cb49a43d7c..763e43d22dee 100644 --- a/fs/xfs/xfs_super.h +++ b/fs/xfs/xfs_super.h @@ -38,6 +38,18 @@ extern void xfs_qm_exit(void); # define XFS_SCRUB_STRING #endif +#ifdef CONFIG_XFS_ONLINE_REPAIR +# define XFS_REPAIR_STRING "repair, " +#else +# define XFS_REPAIR_STRING +#endif + +#ifdef CONFIG_XFS_WARN +# define XFS_WARN_STRING "verbose warnings, " +#else +# define XFS_WARN_STRING +#endif + #ifdef DEBUG # define XFS_DBG_STRING "debug" #else @@ -49,6 +61,8 @@ extern void xfs_qm_exit(void); XFS_SECURITY_STRING \ XFS_REALTIME_STRING \ XFS_SCRUB_STRING \ + XFS_REPAIR_STRING \ + XFS_WARN_STRING \ XFS_DBG_STRING /* DBG must be last */ struct xfs_inode; diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index b2c1177c717f..ed66fd2de327 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -12,23 +12,14 @@ #include "xfs_trans_resv.h" #include "xfs_bit.h" #include "xfs_mount.h" -#include "xfs_da_format.h" -#include "xfs_da_btree.h" -#include "xfs_defer.h" #include "xfs_dir2.h" #include "xfs_inode.h" -#include "xfs_ialloc.h" -#include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_bmap_btree.h" -#include "xfs_bmap_util.h" -#include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_trace.h" -#include "xfs_symlink.h" #include "xfs_trans.h" -#include "xfs_log.h" /* ----- Kernel only functions below ----- */ int diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index 0cc034dfb786..31b3bdbd2eba 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -4,10 +4,7 @@ * All Rights Reserved. */ #include "xfs.h" -#include <linux/sysctl.h> -#include <linux/proc_fs.h> #include "xfs_error.h" -#include "xfs_stats.h" static struct ctl_table_header *xfs_table_header; diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h index ad7f9be13087..8abf4640f1d5 100644 --- a/fs/xfs/xfs_sysctl.h +++ b/fs/xfs/xfs_sysctl.h @@ -82,6 +82,9 @@ enum { extern xfs_param_t xfs_params; struct xfs_globals { +#ifdef DEBUG + int pwork_threads; /* parallel workqueue threads */ +#endif int log_recovery_delay; /* log recovery delay (secs) */ int mount_delay; /* mount setup delay (secs) */ bool bug_on_assert; /* BUG() the kernel on assert failure */ diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index cabda13f3c64..ddd0bf7a4740 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -10,9 +10,7 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_sysfs.h" -#include "xfs_log.h" #include "xfs_log_priv.h" -#include "xfs_stats.h" #include "xfs_mount.h" struct xfs_sysfs_attr { @@ -206,11 +204,51 @@ always_cow_show( } XFS_SYSFS_ATTR_RW(always_cow); +#ifdef DEBUG +/* + * Override how many threads the parallel work queue is allowed to create. + * This has to be a debug-only global (instead of an errortag) because one of + * the main users of parallel workqueues is mount time quotacheck. + */ +STATIC ssize_t +pwork_threads_store( + struct kobject *kobject, + const char *buf, + size_t count) +{ + int ret; + int val; + + ret = kstrtoint(buf, 0, &val); + if (ret) + return ret; + + if (val < -1 || val > num_possible_cpus()) + return -EINVAL; + + xfs_globals.pwork_threads = val; + + return count; +} + +STATIC ssize_t +pwork_threads_show( + struct kobject *kobject, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.pwork_threads); +} +XFS_SYSFS_ATTR_RW(pwork_threads); +#endif /* DEBUG */ + static struct attribute *xfs_dbg_attrs[] = { ATTR_LIST(bug_on_assert), ATTR_LIST(log_recovery_delay), ATTR_LIST(mount_delay), ATTR_LIST(always_cow), +#ifdef DEBUG + ATTR_LIST(pwork_threads), +#endif NULL, }; diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index cb6489c22cad..bc85b89f88ca 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -15,24 +15,16 @@ #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_da_btree.h" -#include "xfs_ialloc.h" -#include "xfs_itable.h" #include "xfs_alloc.h" #include "xfs_bmap.h" #include "xfs_attr.h" -#include "xfs_attr_leaf.h" #include "xfs_trans.h" -#include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_buf_item.h" #include "xfs_quota.h" -#include "xfs_iomap.h" -#include "xfs_aops.h" #include "xfs_dquot_item.h" #include "xfs_dquot.h" #include "xfs_log_recover.h" -#include "xfs_inode_item.h" -#include "xfs_bmap_btree.h" #include "xfs_filestream.h" #include "xfs_fsmap.h" diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 2464ea351f83..8094b1920eef 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -475,7 +475,7 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale); -DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock); +DEFINE_BUF_ITEM_EVENT(xfs_buf_item_release); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push); DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf); @@ -3360,6 +3360,7 @@ DEFINE_TRANS_EVENT(xfs_trans_dup); DEFINE_TRANS_EVENT(xfs_trans_free); DEFINE_TRANS_EVENT(xfs_trans_roll); DEFINE_TRANS_EVENT(xfs_trans_add_item); +DEFINE_TRANS_EVENT(xfs_trans_commit_items); DEFINE_TRANS_EVENT(xfs_trans_free_items); TRACE_EVENT(xfs_iunlink_update_bucket, @@ -3516,6 +3517,64 @@ DEFINE_EVENT(xfs_inode_corrupt_class, name, \ DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_sick); DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_healthy); +TRACE_EVENT(xfs_iwalk_ag, + TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, + xfs_agino_t startino), + TP_ARGS(mp, agno, startino), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(xfs_agino_t, startino) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->agno = agno; + __entry->startino = startino; + ), + TP_printk("dev %d:%d agno %d startino %u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __entry->startino) +) + +TRACE_EVENT(xfs_iwalk_ag_rec, + TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, + struct xfs_inobt_rec_incore *irec), + TP_ARGS(mp, agno, irec), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_agnumber_t, agno) + __field(xfs_agino_t, startino) + __field(uint64_t, freemask) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->agno = agno; + __entry->startino = irec->ir_startino; + __entry->freemask = irec->ir_free; + ), + TP_printk("dev %d:%d agno %d startino %u freemask 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __entry->startino, __entry->freemask) +) + +TRACE_EVENT(xfs_pwork_init, + TP_PROTO(struct xfs_mount *mp, unsigned int nr_threads, pid_t pid), + TP_ARGS(mp, nr_threads, pid), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(unsigned int, nr_threads) + __field(pid_t, pid) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->nr_threads = nr_threads; + __entry->pid = pid; + ), + TP_printk("dev %d:%d nr_threads %u pid %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->nr_threads, __entry->pid) +) + #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 912b42f5fe4a..d42a68d8313b 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -11,7 +11,6 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_inode.h" #include "xfs_extent_busy.h" #include "xfs_quota.h" #include "xfs_trans.h" @@ -264,9 +263,7 @@ xfs_trans_alloc( * GFP_NOFS allocation context so that we avoid lockdep false positives * by doing GFP_KERNEL allocations inside sb_start_intwrite(). */ - tp = kmem_zone_zalloc(xfs_trans_zone, - (flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP); - + tp = kmem_zone_zalloc(xfs_trans_zone, KM_SLEEP); if (!(flags & XFS_TRANS_NO_WRITECOUNT)) sb_start_intwrite(mp->m_super); @@ -452,7 +449,7 @@ xfs_trans_apply_sb_deltas( xfs_buf_t *bp; int whole = 0; - bp = xfs_trans_getsb(tp, tp->t_mountp, 0); + bp = xfs_trans_getsb(tp, tp->t_mountp); sbp = XFS_BUF_TO_SBP(bp); /* @@ -767,10 +764,9 @@ xfs_trans_del_item( } /* Detach and unlock all of the items in a transaction */ -void +static void xfs_trans_free_items( struct xfs_trans *tp, - xfs_lsn_t commit_lsn, bool abort) { struct xfs_log_item *lip, *next; @@ -779,11 +775,10 @@ xfs_trans_free_items( list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) { xfs_trans_del_item(lip); - if (commit_lsn != NULLCOMMITLSN) - lip->li_ops->iop_committing(lip, commit_lsn); if (abort) set_bit(XFS_LI_ABORTED, &lip->li_flags); - lip->li_ops->iop_unlock(lip); + if (lip->li_ops->iop_release) + lip->li_ops->iop_release(lip); } } @@ -804,7 +799,8 @@ xfs_log_item_batch_insert( for (i = 0; i < nr_items; i++) { struct xfs_log_item *lip = log_items[i]; - lip->li_ops->iop_unpin(lip, 0); + if (lip->li_ops->iop_unpin) + lip->li_ops->iop_unpin(lip, 0); } } @@ -815,7 +811,7 @@ xfs_log_item_batch_insert( * * If we are called with the aborted flag set, it is because a log write during * a CIL checkpoint commit has failed. In this case, all the items in the - * checkpoint have already gone through iop_commited and iop_unlock, which + * checkpoint have already gone through iop_committed and iop_committing, which * means that checkpoint commit abort handling is treated exactly the same * as an iclog write error even though we haven't started any IO yet. Hence in * this case all we need to do is iop_committed processing, followed by an @@ -833,7 +829,7 @@ xfs_trans_committed_bulk( struct xfs_ail *ailp, struct xfs_log_vec *log_vector, xfs_lsn_t commit_lsn, - int aborted) + bool aborted) { #define LOG_ITEM_BATCH_SIZE 32 struct xfs_log_item *log_items[LOG_ITEM_BATCH_SIZE]; @@ -852,7 +848,16 @@ xfs_trans_committed_bulk( if (aborted) set_bit(XFS_LI_ABORTED, &lip->li_flags); - item_lsn = lip->li_ops->iop_committed(lip, commit_lsn); + + if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) { + lip->li_ops->iop_release(lip); + continue; + } + + if (lip->li_ops->iop_committed) + item_lsn = lip->li_ops->iop_committed(lip, commit_lsn); + else + item_lsn = commit_lsn; /* item_lsn of -1 means the item needs no further processing */ if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0) @@ -864,7 +869,8 @@ xfs_trans_committed_bulk( */ if (aborted) { ASSERT(XFS_FORCED_SHUTDOWN(ailp->ail_mount)); - lip->li_ops->iop_unpin(lip, 1); + if (lip->li_ops->iop_unpin) + lip->li_ops->iop_unpin(lip, 1); continue; } @@ -882,7 +888,8 @@ xfs_trans_committed_bulk( xfs_trans_ail_update(ailp, lip, item_lsn); else spin_unlock(&ailp->ail_lock); - lip->li_ops->iop_unpin(lip, 0); + if (lip->li_ops->iop_unpin) + lip->li_ops->iop_unpin(lip, 0); continue; } @@ -998,7 +1005,7 @@ out_unreserve: tp->t_ticket = NULL; } current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - xfs_trans_free_items(tp, NULLCOMMITLSN, !!error); + xfs_trans_free_items(tp, !!error); xfs_trans_free(tp); XFS_STATS_INC(mp, xs_trans_empty); @@ -1060,7 +1067,7 @@ xfs_trans_cancel( /* mark this thread as no longer being in a transaction */ current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS); - xfs_trans_free_items(tp, NULLCOMMITLSN, dirty); + xfs_trans_free_items(tp, dirty); xfs_trans_free(tp); } diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index c6e1c5704a8c..64d7f171ebd3 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -27,7 +27,7 @@ struct xfs_cud_log_item; struct xfs_bui_log_item; struct xfs_bud_log_item; -typedef struct xfs_log_item { +struct xfs_log_item { struct list_head li_ail; /* AIL pointers */ struct list_head li_trans; /* transaction list */ xfs_lsn_t li_lsn; /* last on-disk lsn */ @@ -48,7 +48,7 @@ typedef struct xfs_log_item { struct xfs_log_vec *li_lv; /* active log vector */ struct xfs_log_vec *li_lv_shadow; /* standby vector */ xfs_lsn_t li_seq; /* CIL commit seq */ -} xfs_log_item_t; +}; /* * li_flags use the (set/test/clear)_bit atomic interfaces because updates can @@ -67,17 +67,24 @@ typedef struct xfs_log_item { { (1 << XFS_LI_DIRTY), "DIRTY" } struct xfs_item_ops { - void (*iop_size)(xfs_log_item_t *, int *, int *); - void (*iop_format)(xfs_log_item_t *, struct xfs_log_vec *); - void (*iop_pin)(xfs_log_item_t *); - void (*iop_unpin)(xfs_log_item_t *, int remove); + unsigned flags; + void (*iop_size)(struct xfs_log_item *, int *, int *); + void (*iop_format)(struct xfs_log_item *, struct xfs_log_vec *); + void (*iop_pin)(struct xfs_log_item *); + void (*iop_unpin)(struct xfs_log_item *, int remove); uint (*iop_push)(struct xfs_log_item *, struct list_head *); - void (*iop_unlock)(xfs_log_item_t *); - xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); - void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); - void (*iop_error)(xfs_log_item_t *, xfs_buf_t *); + void (*iop_committing)(struct xfs_log_item *, xfs_lsn_t commit_lsn); + void (*iop_release)(struct xfs_log_item *); + xfs_lsn_t (*iop_committed)(struct xfs_log_item *, xfs_lsn_t); + void (*iop_error)(struct xfs_log_item *, xfs_buf_t *); }; +/* + * Release the log item as soon as committed. This is for items just logging + * intents that never need to be written back in place. + */ +#define XFS_ITEM_RELEASE_WHEN_COMMITTED (1 << 0) + void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, int type, const struct xfs_item_ops *ops); @@ -203,7 +210,7 @@ xfs_trans_read_buf( flags, bpp, ops); } -struct xfs_buf *xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int); +struct xfs_buf *xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *); void xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *); void xfs_trans_bjoin(xfs_trans_t *, struct xfs_buf *); @@ -223,14 +230,6 @@ void xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *); bool xfs_trans_buf_is_dirty(struct xfs_buf *bp); void xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint); -struct xfs_efd_log_item *xfs_trans_get_efd(struct xfs_trans *, - struct xfs_efi_log_item *, - uint); -int xfs_trans_free_extent(struct xfs_trans *, - struct xfs_efd_log_item *, xfs_fsblock_t, - xfs_extlen_t, - const struct xfs_owner_info *, - bool); int xfs_trans_commit(struct xfs_trans *); int xfs_trans_roll(struct xfs_trans **); int xfs_trans_roll_inode(struct xfs_trans **, struct xfs_inode *); @@ -245,37 +244,4 @@ void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp, extern kmem_zone_t *xfs_trans_zone; -/* rmap updates */ -enum xfs_rmap_intent_type; - -struct xfs_rud_log_item *xfs_trans_get_rud(struct xfs_trans *tp, - struct xfs_rui_log_item *ruip); -int xfs_trans_log_finish_rmap_update(struct xfs_trans *tp, - struct xfs_rud_log_item *rudp, enum xfs_rmap_intent_type type, - uint64_t owner, int whichfork, xfs_fileoff_t startoff, - xfs_fsblock_t startblock, xfs_filblks_t blockcount, - xfs_exntst_t state, struct xfs_btree_cur **pcur); - -/* refcount updates */ -enum xfs_refcount_intent_type; - -struct xfs_cud_log_item *xfs_trans_get_cud(struct xfs_trans *tp, - struct xfs_cui_log_item *cuip); -int xfs_trans_log_finish_refcount_update(struct xfs_trans *tp, - struct xfs_cud_log_item *cudp, - enum xfs_refcount_intent_type type, xfs_fsblock_t startblock, - xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb, - xfs_extlen_t *new_len, struct xfs_btree_cur **pcur); - -/* mapping updates */ -enum xfs_bmap_intent_type; - -struct xfs_bud_log_item *xfs_trans_get_bud(struct xfs_trans *tp, - struct xfs_bui_log_item *buip); -int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp, - struct xfs_bud_log_item *rudp, enum xfs_bmap_intent_type type, - struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff, - xfs_fsblock_t startblock, xfs_filblks_t *blockcount, - xfs_exntst_t state); - #endif /* __XFS_TRANS_H__ */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index d3a4e89bf4a0..6ccfd75d3c24 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -6,6 +6,7 @@ */ #include "xfs.h" #include "xfs_fs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" @@ -74,29 +75,29 @@ xfs_ail_check( * Return a pointer to the last item in the AIL. If the AIL is empty, then * return NULL. */ -static xfs_log_item_t * +static struct xfs_log_item * xfs_ail_max( struct xfs_ail *ailp) { if (list_empty(&ailp->ail_head)) return NULL; - return list_entry(ailp->ail_head.prev, xfs_log_item_t, li_ail); + return list_entry(ailp->ail_head.prev, struct xfs_log_item, li_ail); } /* * Return a pointer to the item which follows the given item in the AIL. If * the given item is the last item in the list, then return NULL. */ -static xfs_log_item_t * +static struct xfs_log_item * xfs_ail_next( - struct xfs_ail *ailp, - xfs_log_item_t *lip) + struct xfs_ail *ailp, + struct xfs_log_item *lip) { if (lip->li_ail.next == &ailp->ail_head) return NULL; - return list_first_entry(&lip->li_ail, xfs_log_item_t, li_ail); + return list_first_entry(&lip->li_ail, struct xfs_log_item, li_ail); } /* @@ -109,10 +110,10 @@ xfs_ail_next( */ xfs_lsn_t xfs_ail_min_lsn( - struct xfs_ail *ailp) + struct xfs_ail *ailp) { - xfs_lsn_t lsn = 0; - xfs_log_item_t *lip; + xfs_lsn_t lsn = 0; + struct xfs_log_item *lip; spin_lock(&ailp->ail_lock); lip = xfs_ail_min(ailp); @@ -128,10 +129,10 @@ xfs_ail_min_lsn( */ static xfs_lsn_t xfs_ail_max_lsn( - struct xfs_ail *ailp) + struct xfs_ail *ailp) { - xfs_lsn_t lsn = 0; - xfs_log_item_t *lip; + xfs_lsn_t lsn = 0; + struct xfs_log_item *lip; spin_lock(&ailp->ail_lock); lip = xfs_ail_max(ailp); @@ -216,13 +217,13 @@ xfs_trans_ail_cursor_clear( * ascending traversal. Pass a @lsn of zero to initialise the cursor to the * first item in the AIL. Returns NULL if the list is empty. */ -xfs_log_item_t * +struct xfs_log_item * xfs_trans_ail_cursor_first( struct xfs_ail *ailp, struct xfs_ail_cursor *cur, xfs_lsn_t lsn) { - xfs_log_item_t *lip; + struct xfs_log_item *lip; xfs_trans_ail_cursor_init(ailp, cur); @@ -248,7 +249,7 @@ __xfs_trans_ail_cursor_last( struct xfs_ail *ailp, xfs_lsn_t lsn) { - xfs_log_item_t *lip; + struct xfs_log_item *lip; list_for_each_entry_reverse(lip, &ailp->ail_head, li_ail) { if (XFS_LSN_CMP(lip->li_lsn, lsn) <= 0) @@ -327,8 +328,8 @@ xfs_ail_splice( */ static void xfs_ail_delete( - struct xfs_ail *ailp, - xfs_log_item_t *lip) + struct xfs_ail *ailp, + struct xfs_log_item *lip) { xfs_ail_check(ailp, lip); list_del(&lip->li_ail); @@ -347,6 +348,14 @@ xfsaild_push_item( if (XFS_TEST_ERROR(false, ailp->ail_mount, XFS_ERRTAG_LOG_ITEM_PIN)) return XFS_ITEM_PINNED; + /* + * Consider the item pinned if a push callback is not defined so the + * caller will force the log. This should only happen for intent items + * as they are unpinned once the associated done item is committed to + * the on-disk log. + */ + if (!lip->li_ops->iop_push) + return XFS_ITEM_PINNED; return lip->li_ops->iop_push(lip, &ailp->ail_buf_list); } @@ -356,7 +365,7 @@ xfsaild_push( { xfs_mount_t *mp = ailp->ail_mount; struct xfs_ail_cursor cur; - xfs_log_item_t *lip; + struct xfs_log_item *lip; xfs_lsn_t lsn; xfs_lsn_t target; long tout; @@ -611,10 +620,10 @@ xfsaild( */ void xfs_ail_push( - struct xfs_ail *ailp, - xfs_lsn_t threshold_lsn) + struct xfs_ail *ailp, + xfs_lsn_t threshold_lsn) { - xfs_log_item_t *lip; + struct xfs_log_item *lip; lip = xfs_ail_min(ailp); if (!lip || XFS_FORCED_SHUTDOWN(ailp->ail_mount) || @@ -699,7 +708,7 @@ xfs_trans_ail_update_bulk( int nr_items, xfs_lsn_t lsn) __releases(ailp->ail_lock) { - xfs_log_item_t *mlip; + struct xfs_log_item *mlip; int mlip_changed = 0; int i; LIST_HEAD(tmp); diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c deleted file mode 100644 index e1c7d55b32c3..000000000000 --- a/fs/xfs/xfs_trans_bmap.c +++ /dev/null @@ -1,232 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2016 Oracle. All Rights Reserved. - * Author: Darrick J. Wong <darrick.wong@oracle.com> - */ -#include "xfs.h" -#include "xfs_fs.h" -#include "xfs_shared.h" -#include "xfs_format.h" -#include "xfs_log_format.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_trans.h" -#include "xfs_trans_priv.h" -#include "xfs_bmap_item.h" -#include "xfs_alloc.h" -#include "xfs_bmap.h" -#include "xfs_inode.h" - -/* - * This routine is called to allocate a "bmap update done" - * log item. - */ -struct xfs_bud_log_item * -xfs_trans_get_bud( - struct xfs_trans *tp, - struct xfs_bui_log_item *buip) -{ - struct xfs_bud_log_item *budp; - - budp = xfs_bud_init(tp->t_mountp, buip); - xfs_trans_add_item(tp, &budp->bud_item); - return budp; -} - -/* - * Finish an bmap update and log it to the BUD. Note that the - * transaction is marked dirty regardless of whether the bmap update - * succeeds or fails to support the BUI/BUD lifecycle rules. - */ -int -xfs_trans_log_finish_bmap_update( - struct xfs_trans *tp, - struct xfs_bud_log_item *budp, - enum xfs_bmap_intent_type type, - struct xfs_inode *ip, - int whichfork, - xfs_fileoff_t startoff, - xfs_fsblock_t startblock, - xfs_filblks_t *blockcount, - xfs_exntst_t state) -{ - int error; - - error = xfs_bmap_finish_one(tp, ip, type, whichfork, startoff, - startblock, blockcount, state); - - /* - * Mark the transaction dirty, even on error. This ensures the - * transaction is aborted, which: - * - * 1.) releases the BUI and frees the BUD - * 2.) shuts down the filesystem - */ - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &budp->bud_item.li_flags); - - return error; -} - -/* Sort bmap intents by inode. */ -static int -xfs_bmap_update_diff_items( - void *priv, - struct list_head *a, - struct list_head *b) -{ - struct xfs_bmap_intent *ba; - struct xfs_bmap_intent *bb; - - ba = container_of(a, struct xfs_bmap_intent, bi_list); - bb = container_of(b, struct xfs_bmap_intent, bi_list); - return ba->bi_owner->i_ino - bb->bi_owner->i_ino; -} - -/* Get an BUI. */ -STATIC void * -xfs_bmap_update_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_bui_log_item *buip; - - ASSERT(count == XFS_BUI_MAX_FAST_EXTENTS); - ASSERT(tp != NULL); - - buip = xfs_bui_init(tp->t_mountp); - ASSERT(buip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &buip->bui_item); - return buip; -} - -/* Set the map extent flags for this mapping. */ -static void -xfs_trans_set_bmap_flags( - struct xfs_map_extent *bmap, - enum xfs_bmap_intent_type type, - int whichfork, - xfs_exntst_t state) -{ - bmap->me_flags = 0; - switch (type) { - case XFS_BMAP_MAP: - case XFS_BMAP_UNMAP: - bmap->me_flags = type; - break; - default: - ASSERT(0); - } - if (state == XFS_EXT_UNWRITTEN) - bmap->me_flags |= XFS_BMAP_EXTENT_UNWRITTEN; - if (whichfork == XFS_ATTR_FORK) - bmap->me_flags |= XFS_BMAP_EXTENT_ATTR_FORK; -} - -/* Log bmap updates in the intent item. */ -STATIC void -xfs_bmap_update_log_item( - struct xfs_trans *tp, - void *intent, - struct list_head *item) -{ - struct xfs_bui_log_item *buip = intent; - struct xfs_bmap_intent *bmap; - uint next_extent; - struct xfs_map_extent *map; - - bmap = container_of(item, struct xfs_bmap_intent, bi_list); - - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &buip->bui_item.li_flags); - - /* - * atomic_inc_return gives us the value after the increment; - * we want to use it as an array index so we need to subtract 1 from - * it. - */ - next_extent = atomic_inc_return(&buip->bui_next_extent) - 1; - ASSERT(next_extent < buip->bui_format.bui_nextents); - map = &buip->bui_format.bui_extents[next_extent]; - map->me_owner = bmap->bi_owner->i_ino; - map->me_startblock = bmap->bi_bmap.br_startblock; - map->me_startoff = bmap->bi_bmap.br_startoff; - map->me_len = bmap->bi_bmap.br_blockcount; - xfs_trans_set_bmap_flags(map, bmap->bi_type, bmap->bi_whichfork, - bmap->bi_bmap.br_state); -} - -/* Get an BUD so we can process all the deferred rmap updates. */ -STATIC void * -xfs_bmap_update_create_done( - struct xfs_trans *tp, - void *intent, - unsigned int count) -{ - return xfs_trans_get_bud(tp, intent); -} - -/* Process a deferred rmap update. */ -STATIC int -xfs_bmap_update_finish_item( - struct xfs_trans *tp, - struct list_head *item, - void *done_item, - void **state) -{ - struct xfs_bmap_intent *bmap; - xfs_filblks_t count; - int error; - - bmap = container_of(item, struct xfs_bmap_intent, bi_list); - count = bmap->bi_bmap.br_blockcount; - error = xfs_trans_log_finish_bmap_update(tp, done_item, - bmap->bi_type, - bmap->bi_owner, bmap->bi_whichfork, - bmap->bi_bmap.br_startoff, - bmap->bi_bmap.br_startblock, - &count, - bmap->bi_bmap.br_state); - if (!error && count > 0) { - ASSERT(bmap->bi_type == XFS_BMAP_UNMAP); - bmap->bi_bmap.br_blockcount = count; - return -EAGAIN; - } - kmem_free(bmap); - return error; -} - -/* Abort all pending BUIs. */ -STATIC void -xfs_bmap_update_abort_intent( - void *intent) -{ - xfs_bui_release(intent); -} - -/* Cancel a deferred rmap update. */ -STATIC void -xfs_bmap_update_cancel_item( - struct list_head *item) -{ - struct xfs_bmap_intent *bmap; - - bmap = container_of(item, struct xfs_bmap_intent, bi_list); - kmem_free(bmap); -} - -const struct xfs_defer_op_type xfs_bmap_update_defer_type = { - .max_items = XFS_BUI_MAX_FAST_EXTENTS, - .diff_items = xfs_bmap_update_diff_items, - .create_intent = xfs_bmap_update_create_intent, - .abort_intent = xfs_bmap_update_abort_intent, - .log_item = xfs_bmap_update_log_item, - .create_done = xfs_bmap_update_create_done, - .finish_item = xfs_bmap_update_finish_item, - .cancel_item = xfs_bmap_update_cancel_item, -}; diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 7d65ebf1e847..b5b3a78ef31c 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -10,11 +10,9 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_trans_priv.h" -#include "xfs_error.h" #include "xfs_trace.h" /* @@ -174,8 +172,7 @@ xfs_trans_get_buf_map( xfs_buf_t * xfs_trans_getsb( xfs_trans_t *tp, - struct xfs_mount *mp, - int flags) + struct xfs_mount *mp) { xfs_buf_t *bp; struct xfs_buf_log_item *bip; @@ -185,7 +182,7 @@ xfs_trans_getsb( * if tp is NULL. */ if (tp == NULL) - return xfs_getsb(mp, flags); + return xfs_getsb(mp); /* * If the superblock buffer already has this transaction @@ -203,7 +200,7 @@ xfs_trans_getsb( return bp; } - bp = xfs_getsb(mp, flags); + bp = xfs_getsb(mp); if (bp == NULL) return NULL; @@ -428,7 +425,7 @@ xfs_trans_brelse( /* * Mark the buffer as not needing to be unlocked when the buf item's - * iop_unlock() routine is called. The buffer must already be locked + * iop_committing() routine is called. The buffer must already be locked * and associated with the given transaction. */ /* ARGSUSED */ diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index cd664a03613f..1027c9ca6eb8 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -11,7 +11,6 @@ #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" -#include "xfs_error.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_quota.h" @@ -29,7 +28,6 @@ xfs_trans_dqjoin( xfs_trans_t *tp, xfs_dquot_t *dqp) { - ASSERT(dqp->q_transp != tp); ASSERT(XFS_DQ_IS_LOCKED(dqp)); ASSERT(dqp->q_logitem.qli_dquot == dqp); @@ -37,15 +35,8 @@ xfs_trans_dqjoin( * Get a log_item_desc to point at the new item. */ xfs_trans_add_item(tp, &dqp->q_logitem.qli_item); - - /* - * Initialize d_transp so we can later determine if this dquot is - * associated with this transaction. - */ - dqp->q_transp = tp; } - /* * This is called to mark the dquot as needing * to be logged when the transaction is committed. The dquot must @@ -61,7 +52,6 @@ xfs_trans_log_dquot( xfs_trans_t *tp, xfs_dquot_t *dqp) { - ASSERT(dqp->q_transp == tp); ASSERT(XFS_DQ_IS_LOCKED(dqp)); tp->t_flags |= XFS_TRANS_DIRTY; @@ -347,7 +337,6 @@ xfs_trans_apply_dquot_deltas( break; ASSERT(XFS_DQ_IS_LOCKED(dqp)); - ASSERT(dqp->q_transp == tp); /* * adjust the actual number of blocks used diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c deleted file mode 100644 index 8ee7a3f8bb20..000000000000 --- a/fs/xfs/xfs_trans_extfree.c +++ /dev/null @@ -1,286 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2000,2005 Silicon Graphics, Inc. - * All Rights Reserved. - */ -#include "xfs.h" -#include "xfs_fs.h" -#include "xfs_shared.h" -#include "xfs_format.h" -#include "xfs_log_format.h" -#include "xfs_trans_resv.h" -#include "xfs_bit.h" -#include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_trans.h" -#include "xfs_trans_priv.h" -#include "xfs_extfree_item.h" -#include "xfs_alloc.h" -#include "xfs_bmap.h" -#include "xfs_trace.h" - -/* - * This routine is called to allocate an "extent free done" - * log item that will hold nextents worth of extents. The - * caller must use all nextents extents, because we are not - * flexible about this at all. - */ -struct xfs_efd_log_item * -xfs_trans_get_efd(struct xfs_trans *tp, - struct xfs_efi_log_item *efip, - uint nextents) -{ - struct xfs_efd_log_item *efdp; - - ASSERT(tp != NULL); - ASSERT(nextents > 0); - - efdp = xfs_efd_init(tp->t_mountp, efip, nextents); - ASSERT(efdp != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &efdp->efd_item); - return efdp; -} - -/* - * Free an extent and log it to the EFD. Note that the transaction is marked - * dirty regardless of whether the extent free succeeds or fails to support the - * EFI/EFD lifecycle rules. - */ -int -xfs_trans_free_extent( - struct xfs_trans *tp, - struct xfs_efd_log_item *efdp, - xfs_fsblock_t start_block, - xfs_extlen_t ext_len, - const struct xfs_owner_info *oinfo, - bool skip_discard) -{ - struct xfs_mount *mp = tp->t_mountp; - struct xfs_extent *extp; - uint next_extent; - xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, start_block); - xfs_agblock_t agbno = XFS_FSB_TO_AGBNO(mp, - start_block); - int error; - - trace_xfs_bmap_free_deferred(tp->t_mountp, agno, 0, agbno, ext_len); - - error = __xfs_free_extent(tp, start_block, ext_len, - oinfo, XFS_AG_RESV_NONE, skip_discard); - /* - * Mark the transaction dirty, even on error. This ensures the - * transaction is aborted, which: - * - * 1.) releases the EFI and frees the EFD - * 2.) shuts down the filesystem - */ - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags); - - next_extent = efdp->efd_next_extent; - ASSERT(next_extent < efdp->efd_format.efd_nextents); - extp = &(efdp->efd_format.efd_extents[next_extent]); - extp->ext_start = start_block; - extp->ext_len = ext_len; - efdp->efd_next_extent++; - - return error; -} - -/* Sort bmap items by AG. */ -static int -xfs_extent_free_diff_items( - void *priv, - struct list_head *a, - struct list_head *b) -{ - struct xfs_mount *mp = priv; - struct xfs_extent_free_item *ra; - struct xfs_extent_free_item *rb; - - ra = container_of(a, struct xfs_extent_free_item, xefi_list); - rb = container_of(b, struct xfs_extent_free_item, xefi_list); - return XFS_FSB_TO_AGNO(mp, ra->xefi_startblock) - - XFS_FSB_TO_AGNO(mp, rb->xefi_startblock); -} - -/* Get an EFI. */ -STATIC void * -xfs_extent_free_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_efi_log_item *efip; - - ASSERT(tp != NULL); - ASSERT(count > 0); - - efip = xfs_efi_init(tp->t_mountp, count); - ASSERT(efip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &efip->efi_item); - return efip; -} - -/* Log a free extent to the intent item. */ -STATIC void -xfs_extent_free_log_item( - struct xfs_trans *tp, - void *intent, - struct list_head *item) -{ - struct xfs_efi_log_item *efip = intent; - struct xfs_extent_free_item *free; - uint next_extent; - struct xfs_extent *extp; - - free = container_of(item, struct xfs_extent_free_item, xefi_list); - - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &efip->efi_item.li_flags); - - /* - * atomic_inc_return gives us the value after the increment; - * we want to use it as an array index so we need to subtract 1 from - * it. - */ - next_extent = atomic_inc_return(&efip->efi_next_extent) - 1; - ASSERT(next_extent < efip->efi_format.efi_nextents); - extp = &efip->efi_format.efi_extents[next_extent]; - extp->ext_start = free->xefi_startblock; - extp->ext_len = free->xefi_blockcount; -} - -/* Get an EFD so we can process all the free extents. */ -STATIC void * -xfs_extent_free_create_done( - struct xfs_trans *tp, - void *intent, - unsigned int count) -{ - return xfs_trans_get_efd(tp, intent, count); -} - -/* Process a free extent. */ -STATIC int -xfs_extent_free_finish_item( - struct xfs_trans *tp, - struct list_head *item, - void *done_item, - void **state) -{ - struct xfs_extent_free_item *free; - int error; - - free = container_of(item, struct xfs_extent_free_item, xefi_list); - error = xfs_trans_free_extent(tp, done_item, - free->xefi_startblock, - free->xefi_blockcount, - &free->xefi_oinfo, free->xefi_skip_discard); - kmem_free(free); - return error; -} - -/* Abort all pending EFIs. */ -STATIC void -xfs_extent_free_abort_intent( - void *intent) -{ - xfs_efi_release(intent); -} - -/* Cancel a free extent. */ -STATIC void -xfs_extent_free_cancel_item( - struct list_head *item) -{ - struct xfs_extent_free_item *free; - - free = container_of(item, struct xfs_extent_free_item, xefi_list); - kmem_free(free); -} - -const struct xfs_defer_op_type xfs_extent_free_defer_type = { - .max_items = XFS_EFI_MAX_FAST_EXTENTS, - .diff_items = xfs_extent_free_diff_items, - .create_intent = xfs_extent_free_create_intent, - .abort_intent = xfs_extent_free_abort_intent, - .log_item = xfs_extent_free_log_item, - .create_done = xfs_extent_free_create_done, - .finish_item = xfs_extent_free_finish_item, - .cancel_item = xfs_extent_free_cancel_item, -}; - -/* - * AGFL blocks are accounted differently in the reserve pools and are not - * inserted into the busy extent list. - */ -STATIC int -xfs_agfl_free_finish_item( - struct xfs_trans *tp, - struct list_head *item, - void *done_item, - void **state) -{ - struct xfs_mount *mp = tp->t_mountp; - struct xfs_efd_log_item *efdp = done_item; - struct xfs_extent_free_item *free; - struct xfs_extent *extp; - struct xfs_buf *agbp; - int error; - xfs_agnumber_t agno; - xfs_agblock_t agbno; - uint next_extent; - - free = container_of(item, struct xfs_extent_free_item, xefi_list); - ASSERT(free->xefi_blockcount == 1); - agno = XFS_FSB_TO_AGNO(mp, free->xefi_startblock); - agbno = XFS_FSB_TO_AGBNO(mp, free->xefi_startblock); - - trace_xfs_agfl_free_deferred(mp, agno, 0, agbno, free->xefi_blockcount); - - error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); - if (!error) - error = xfs_free_agfl_block(tp, agno, agbno, agbp, - &free->xefi_oinfo); - - /* - * Mark the transaction dirty, even on error. This ensures the - * transaction is aborted, which: - * - * 1.) releases the EFI and frees the EFD - * 2.) shuts down the filesystem - */ - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags); - - next_extent = efdp->efd_next_extent; - ASSERT(next_extent < efdp->efd_format.efd_nextents); - extp = &(efdp->efd_format.efd_extents[next_extent]); - extp->ext_start = free->xefi_startblock; - extp->ext_len = free->xefi_blockcount; - efdp->efd_next_extent++; - - kmem_free(free); - return error; -} - - -/* sub-type with special handling for AGFL deferred frees */ -const struct xfs_defer_op_type xfs_agfl_free_defer_type = { - .max_items = XFS_EFI_MAX_FAST_EXTENTS, - .diff_items = xfs_extent_free_diff_items, - .create_intent = xfs_extent_free_create_intent, - .abort_intent = xfs_extent_free_abort_intent, - .log_item = xfs_extent_free_log_item, - .create_done = xfs_extent_free_create_done, - .finish_item = xfs_agfl_free_finish_item, - .cancel_item = xfs_extent_free_cancel_item, -}; diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index 542927321a61..93d14e47269d 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -8,13 +8,10 @@ #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_inode_item.h" -#include "xfs_trace.h" #include <linux/iversion.h> diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 091eae9f4e74..2e073c1c4614 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -16,12 +16,10 @@ struct xfs_log_vec; void xfs_trans_init(struct xfs_mount *); void xfs_trans_add_item(struct xfs_trans *, struct xfs_log_item *); void xfs_trans_del_item(struct xfs_log_item *); -void xfs_trans_free_items(struct xfs_trans *tp, xfs_lsn_t commit_lsn, - bool abort); void xfs_trans_unreserve_and_mod_sb(struct xfs_trans *tp); void xfs_trans_committed_bulk(struct xfs_ail *ailp, struct xfs_log_vec *lv, - xfs_lsn_t commit_lsn, int aborted); + xfs_lsn_t commit_lsn, bool aborted); /* * AIL traversal cursor. * diff --git a/fs/xfs/xfs_trans_refcount.c b/fs/xfs/xfs_trans_refcount.c deleted file mode 100644 index 8d734728dd1b..000000000000 --- a/fs/xfs/xfs_trans_refcount.c +++ /dev/null @@ -1,240 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2016 Oracle. All Rights Reserved. - * Author: Darrick J. Wong <darrick.wong@oracle.com> - */ -#include "xfs.h" -#include "xfs_fs.h" -#include "xfs_shared.h" -#include "xfs_format.h" -#include "xfs_log_format.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_trans.h" -#include "xfs_trans_priv.h" -#include "xfs_refcount_item.h" -#include "xfs_alloc.h" -#include "xfs_refcount.h" - -/* - * This routine is called to allocate a "refcount update done" - * log item. - */ -struct xfs_cud_log_item * -xfs_trans_get_cud( - struct xfs_trans *tp, - struct xfs_cui_log_item *cuip) -{ - struct xfs_cud_log_item *cudp; - - cudp = xfs_cud_init(tp->t_mountp, cuip); - xfs_trans_add_item(tp, &cudp->cud_item); - return cudp; -} - -/* - * Finish an refcount update and log it to the CUD. Note that the - * transaction is marked dirty regardless of whether the refcount - * update succeeds or fails to support the CUI/CUD lifecycle rules. - */ -int -xfs_trans_log_finish_refcount_update( - struct xfs_trans *tp, - struct xfs_cud_log_item *cudp, - enum xfs_refcount_intent_type type, - xfs_fsblock_t startblock, - xfs_extlen_t blockcount, - xfs_fsblock_t *new_fsb, - xfs_extlen_t *new_len, - struct xfs_btree_cur **pcur) -{ - int error; - - error = xfs_refcount_finish_one(tp, type, startblock, - blockcount, new_fsb, new_len, pcur); - - /* - * Mark the transaction dirty, even on error. This ensures the - * transaction is aborted, which: - * - * 1.) releases the CUI and frees the CUD - * 2.) shuts down the filesystem - */ - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &cudp->cud_item.li_flags); - - return error; -} - -/* Sort refcount intents by AG. */ -static int -xfs_refcount_update_diff_items( - void *priv, - struct list_head *a, - struct list_head *b) -{ - struct xfs_mount *mp = priv; - struct xfs_refcount_intent *ra; - struct xfs_refcount_intent *rb; - - ra = container_of(a, struct xfs_refcount_intent, ri_list); - rb = container_of(b, struct xfs_refcount_intent, ri_list); - return XFS_FSB_TO_AGNO(mp, ra->ri_startblock) - - XFS_FSB_TO_AGNO(mp, rb->ri_startblock); -} - -/* Get an CUI. */ -STATIC void * -xfs_refcount_update_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_cui_log_item *cuip; - - ASSERT(tp != NULL); - ASSERT(count > 0); - - cuip = xfs_cui_init(tp->t_mountp, count); - ASSERT(cuip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &cuip->cui_item); - return cuip; -} - -/* Set the phys extent flags for this reverse mapping. */ -static void -xfs_trans_set_refcount_flags( - struct xfs_phys_extent *refc, - enum xfs_refcount_intent_type type) -{ - refc->pe_flags = 0; - switch (type) { - case XFS_REFCOUNT_INCREASE: - case XFS_REFCOUNT_DECREASE: - case XFS_REFCOUNT_ALLOC_COW: - case XFS_REFCOUNT_FREE_COW: - refc->pe_flags |= type; - break; - default: - ASSERT(0); - } -} - -/* Log refcount updates in the intent item. */ -STATIC void -xfs_refcount_update_log_item( - struct xfs_trans *tp, - void *intent, - struct list_head *item) -{ - struct xfs_cui_log_item *cuip = intent; - struct xfs_refcount_intent *refc; - uint next_extent; - struct xfs_phys_extent *ext; - - refc = container_of(item, struct xfs_refcount_intent, ri_list); - - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &cuip->cui_item.li_flags); - - /* - * atomic_inc_return gives us the value after the increment; - * we want to use it as an array index so we need to subtract 1 from - * it. - */ - next_extent = atomic_inc_return(&cuip->cui_next_extent) - 1; - ASSERT(next_extent < cuip->cui_format.cui_nextents); - ext = &cuip->cui_format.cui_extents[next_extent]; - ext->pe_startblock = refc->ri_startblock; - ext->pe_len = refc->ri_blockcount; - xfs_trans_set_refcount_flags(ext, refc->ri_type); -} - -/* Get an CUD so we can process all the deferred refcount updates. */ -STATIC void * -xfs_refcount_update_create_done( - struct xfs_trans *tp, - void *intent, - unsigned int count) -{ - return xfs_trans_get_cud(tp, intent); -} - -/* Process a deferred refcount update. */ -STATIC int -xfs_refcount_update_finish_item( - struct xfs_trans *tp, - struct list_head *item, - void *done_item, - void **state) -{ - struct xfs_refcount_intent *refc; - xfs_fsblock_t new_fsb; - xfs_extlen_t new_aglen; - int error; - - refc = container_of(item, struct xfs_refcount_intent, ri_list); - error = xfs_trans_log_finish_refcount_update(tp, done_item, - refc->ri_type, - refc->ri_startblock, - refc->ri_blockcount, - &new_fsb, &new_aglen, - (struct xfs_btree_cur **)state); - /* Did we run out of reservation? Requeue what we didn't finish. */ - if (!error && new_aglen > 0) { - ASSERT(refc->ri_type == XFS_REFCOUNT_INCREASE || - refc->ri_type == XFS_REFCOUNT_DECREASE); - refc->ri_startblock = new_fsb; - refc->ri_blockcount = new_aglen; - return -EAGAIN; - } - kmem_free(refc); - return error; -} - -/* Clean up after processing deferred refcounts. */ -STATIC void -xfs_refcount_update_finish_cleanup( - struct xfs_trans *tp, - void *state, - int error) -{ - struct xfs_btree_cur *rcur = state; - - xfs_refcount_finish_one_cleanup(tp, rcur, error); -} - -/* Abort all pending CUIs. */ -STATIC void -xfs_refcount_update_abort_intent( - void *intent) -{ - xfs_cui_release(intent); -} - -/* Cancel a deferred refcount update. */ -STATIC void -xfs_refcount_update_cancel_item( - struct list_head *item) -{ - struct xfs_refcount_intent *refc; - - refc = container_of(item, struct xfs_refcount_intent, ri_list); - kmem_free(refc); -} - -const struct xfs_defer_op_type xfs_refcount_update_defer_type = { - .max_items = XFS_CUI_MAX_FAST_EXTENTS, - .diff_items = xfs_refcount_update_diff_items, - .create_intent = xfs_refcount_update_create_intent, - .abort_intent = xfs_refcount_update_abort_intent, - .log_item = xfs_refcount_update_log_item, - .create_done = xfs_refcount_update_create_done, - .finish_item = xfs_refcount_update_finish_item, - .finish_cleanup = xfs_refcount_update_finish_cleanup, - .cancel_item = xfs_refcount_update_cancel_item, -}; diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c deleted file mode 100644 index 5c7936b1be13..000000000000 --- a/fs/xfs/xfs_trans_rmap.c +++ /dev/null @@ -1,257 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * Copyright (C) 2016 Oracle. All Rights Reserved. - * Author: Darrick J. Wong <darrick.wong@oracle.com> - */ -#include "xfs.h" -#include "xfs_fs.h" -#include "xfs_shared.h" -#include "xfs_format.h" -#include "xfs_log_format.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" -#include "xfs_defer.h" -#include "xfs_trans.h" -#include "xfs_trans_priv.h" -#include "xfs_rmap_item.h" -#include "xfs_alloc.h" -#include "xfs_rmap.h" - -/* Set the map extent flags for this reverse mapping. */ -static void -xfs_trans_set_rmap_flags( - struct xfs_map_extent *rmap, - enum xfs_rmap_intent_type type, - int whichfork, - xfs_exntst_t state) -{ - rmap->me_flags = 0; - if (state == XFS_EXT_UNWRITTEN) - rmap->me_flags |= XFS_RMAP_EXTENT_UNWRITTEN; - if (whichfork == XFS_ATTR_FORK) - rmap->me_flags |= XFS_RMAP_EXTENT_ATTR_FORK; - switch (type) { - case XFS_RMAP_MAP: - rmap->me_flags |= XFS_RMAP_EXTENT_MAP; - break; - case XFS_RMAP_MAP_SHARED: - rmap->me_flags |= XFS_RMAP_EXTENT_MAP_SHARED; - break; - case XFS_RMAP_UNMAP: - rmap->me_flags |= XFS_RMAP_EXTENT_UNMAP; - break; - case XFS_RMAP_UNMAP_SHARED: - rmap->me_flags |= XFS_RMAP_EXTENT_UNMAP_SHARED; - break; - case XFS_RMAP_CONVERT: - rmap->me_flags |= XFS_RMAP_EXTENT_CONVERT; - break; - case XFS_RMAP_CONVERT_SHARED: - rmap->me_flags |= XFS_RMAP_EXTENT_CONVERT_SHARED; - break; - case XFS_RMAP_ALLOC: - rmap->me_flags |= XFS_RMAP_EXTENT_ALLOC; - break; - case XFS_RMAP_FREE: - rmap->me_flags |= XFS_RMAP_EXTENT_FREE; - break; - default: - ASSERT(0); - } -} - -struct xfs_rud_log_item * -xfs_trans_get_rud( - struct xfs_trans *tp, - struct xfs_rui_log_item *ruip) -{ - struct xfs_rud_log_item *rudp; - - rudp = xfs_rud_init(tp->t_mountp, ruip); - xfs_trans_add_item(tp, &rudp->rud_item); - return rudp; -} - -/* - * Finish an rmap update and log it to the RUD. Note that the transaction is - * marked dirty regardless of whether the rmap update succeeds or fails to - * support the RUI/RUD lifecycle rules. - */ -int -xfs_trans_log_finish_rmap_update( - struct xfs_trans *tp, - struct xfs_rud_log_item *rudp, - enum xfs_rmap_intent_type type, - uint64_t owner, - int whichfork, - xfs_fileoff_t startoff, - xfs_fsblock_t startblock, - xfs_filblks_t blockcount, - xfs_exntst_t state, - struct xfs_btree_cur **pcur) -{ - int error; - - error = xfs_rmap_finish_one(tp, type, owner, whichfork, startoff, - startblock, blockcount, state, pcur); - - /* - * Mark the transaction dirty, even on error. This ensures the - * transaction is aborted, which: - * - * 1.) releases the RUI and frees the RUD - * 2.) shuts down the filesystem - */ - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags); - - return error; -} - -/* Sort rmap intents by AG. */ -static int -xfs_rmap_update_diff_items( - void *priv, - struct list_head *a, - struct list_head *b) -{ - struct xfs_mount *mp = priv; - struct xfs_rmap_intent *ra; - struct xfs_rmap_intent *rb; - - ra = container_of(a, struct xfs_rmap_intent, ri_list); - rb = container_of(b, struct xfs_rmap_intent, ri_list); - return XFS_FSB_TO_AGNO(mp, ra->ri_bmap.br_startblock) - - XFS_FSB_TO_AGNO(mp, rb->ri_bmap.br_startblock); -} - -/* Get an RUI. */ -STATIC void * -xfs_rmap_update_create_intent( - struct xfs_trans *tp, - unsigned int count) -{ - struct xfs_rui_log_item *ruip; - - ASSERT(tp != NULL); - ASSERT(count > 0); - - ruip = xfs_rui_init(tp->t_mountp, count); - ASSERT(ruip != NULL); - - /* - * Get a log_item_desc to point at the new item. - */ - xfs_trans_add_item(tp, &ruip->rui_item); - return ruip; -} - -/* Log rmap updates in the intent item. */ -STATIC void -xfs_rmap_update_log_item( - struct xfs_trans *tp, - void *intent, - struct list_head *item) -{ - struct xfs_rui_log_item *ruip = intent; - struct xfs_rmap_intent *rmap; - uint next_extent; - struct xfs_map_extent *map; - - rmap = container_of(item, struct xfs_rmap_intent, ri_list); - - tp->t_flags |= XFS_TRANS_DIRTY; - set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags); - - /* - * atomic_inc_return gives us the value after the increment; - * we want to use it as an array index so we need to subtract 1 from - * it. - */ - next_extent = atomic_inc_return(&ruip->rui_next_extent) - 1; - ASSERT(next_extent < ruip->rui_format.rui_nextents); - map = &ruip->rui_format.rui_extents[next_extent]; - map->me_owner = rmap->ri_owner; - map->me_startblock = rmap->ri_bmap.br_startblock; - map->me_startoff = rmap->ri_bmap.br_startoff; - map->me_len = rmap->ri_bmap.br_blockcount; - xfs_trans_set_rmap_flags(map, rmap->ri_type, rmap->ri_whichfork, - rmap->ri_bmap.br_state); -} - -/* Get an RUD so we can process all the deferred rmap updates. */ -STATIC void * -xfs_rmap_update_create_done( - struct xfs_trans *tp, - void *intent, - unsigned int count) -{ - return xfs_trans_get_rud(tp, intent); -} - -/* Process a deferred rmap update. */ -STATIC int -xfs_rmap_update_finish_item( - struct xfs_trans *tp, - struct list_head *item, - void *done_item, - void **state) -{ - struct xfs_rmap_intent *rmap; - int error; - - rmap = container_of(item, struct xfs_rmap_intent, ri_list); - error = xfs_trans_log_finish_rmap_update(tp, done_item, - rmap->ri_type, - rmap->ri_owner, rmap->ri_whichfork, - rmap->ri_bmap.br_startoff, - rmap->ri_bmap.br_startblock, - rmap->ri_bmap.br_blockcount, - rmap->ri_bmap.br_state, - (struct xfs_btree_cur **)state); - kmem_free(rmap); - return error; -} - -/* Clean up after processing deferred rmaps. */ -STATIC void -xfs_rmap_update_finish_cleanup( - struct xfs_trans *tp, - void *state, - int error) -{ - struct xfs_btree_cur *rcur = state; - - xfs_rmap_finish_one_cleanup(tp, rcur, error); -} - -/* Abort all pending RUIs. */ -STATIC void -xfs_rmap_update_abort_intent( - void *intent) -{ - xfs_rui_release(intent); -} - -/* Cancel a deferred rmap update. */ -STATIC void -xfs_rmap_update_cancel_item( - struct list_head *item) -{ - struct xfs_rmap_intent *rmap; - - rmap = container_of(item, struct xfs_rmap_intent, ri_list); - kmem_free(rmap); -} - -const struct xfs_defer_op_type xfs_rmap_update_defer_type = { - .max_items = XFS_RUI_MAX_FAST_EXTENTS, - .diff_items = xfs_rmap_update_diff_items, - .create_intent = xfs_rmap_update_create_intent, - .abort_intent = xfs_rmap_update_abort_intent, - .log_item = xfs_rmap_update_log_item, - .create_done = xfs_rmap_update_create_done, - .finish_item = xfs_rmap_update_finish_item, - .finish_cleanup = xfs_rmap_update_finish_cleanup, - .cancel_item = xfs_rmap_update_cancel_item, -}; diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 9a63016009a1..3123b5aaad2a 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -5,15 +5,12 @@ */ #include "xfs.h" +#include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" -#include "xfs_trans_resv.h" -#include "xfs_mount.h" #include "xfs_da_format.h" #include "xfs_inode.h" #include "xfs_attr.h" -#include "xfs_attr_leaf.h" -#include "xfs_acl.h" #include <linux/posix_acl_xattr.h> #include <linux/xattr.h> |