diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/9p/v9fs.c | 29 | ||||
-rw-r--r-- | fs/Kconfig | 5 | ||||
-rw-r--r-- | fs/Makefile | 1 | ||||
-rw-r--r-- | fs/aio.c | 18 | ||||
-rw-r--r-- | fs/autofs/Kconfig | 20 | ||||
-rw-r--r-- | fs/autofs/Makefile | 7 | ||||
-rw-r--r-- | fs/autofs/autofs_i.h (renamed from fs/autofs4/autofs_i.h) | 92 | ||||
-rw-r--r-- | fs/autofs/dev-ioctl.c (renamed from fs/autofs4/dev-ioctl.c) | 31 | ||||
-rw-r--r-- | fs/autofs/expire.c (renamed from fs/autofs4/expire.c) | 133 | ||||
-rw-r--r-- | fs/autofs/init.c (renamed from fs/autofs4/init.c) | 12 | ||||
-rw-r--r-- | fs/autofs/inode.c (renamed from fs/autofs4/inode.c) | 54 | ||||
-rw-r--r-- | fs/autofs/root.c (renamed from fs/autofs4/root.c) | 277 | ||||
-rw-r--r-- | fs/autofs/symlink.c (renamed from fs/autofs4/symlink.c) | 16 | ||||
-rw-r--r-- | fs/autofs/waitq.c (renamed from fs/autofs4/waitq.c) | 59 | ||||
-rw-r--r-- | fs/autofs4/Kconfig | 46 | ||||
-rw-r--r-- | fs/autofs4/Makefile | 4 | ||||
-rw-r--r-- | fs/binfmt_misc.c | 12 | ||||
-rw-r--r-- | fs/block_dev.c | 2 | ||||
-rw-r--r-- | fs/cifs/cifsacl.h | 14 | ||||
-rw-r--r-- | fs/cifs/cifsencrypt.c | 17 | ||||
-rw-r--r-- | fs/cifs/cifsfs.c | 22 | ||||
-rw-r--r-- | fs/cifs/cifsglob.h | 6 | ||||
-rw-r--r-- | fs/cifs/cifsproto.h | 7 | ||||
-rw-r--r-- | fs/cifs/connect.c | 32 | ||||
-rw-r--r-- | fs/cifs/link.c | 6 | ||||
-rw-r--r-- | fs/cifs/misc.c | 17 | ||||
-rw-r--r-- | fs/cifs/smb2file.c | 3 | ||||
-rw-r--r-- | fs/cifs/smb2inode.c | 3 | ||||
-rw-r--r-- | fs/cifs/smb2misc.c | 4 | ||||
-rw-r--r-- | fs/cifs/smb2ops.c | 73 | ||||
-rw-r--r-- | fs/cifs/smb2pdu.c | 24 | ||||
-rw-r--r-- | fs/cifs/smb2proto.h | 2 | ||||
-rw-r--r-- | fs/cifs/smb2transport.c | 12 | ||||
-rw-r--r-- | fs/cifs/smbdirect.c | 121 | ||||
-rw-r--r-- | fs/cifs/smbdirect.h | 2 | ||||
-rw-r--r-- | fs/cifs/transport.c | 34 | ||||
-rw-r--r-- | fs/compat.c | 72 | ||||
-rw-r--r-- | fs/compat_ioctl.c | 2 | ||||
-rw-r--r-- | fs/dax.c | 214 | ||||
-rw-r--r-- | fs/exec.c | 1 | ||||
-rw-r--r-- | fs/fcntl.c | 2 | ||||
-rw-r--r-- | fs/hpfs/hpfs_fn.h | 3 | ||||
-rw-r--r-- | fs/iomap.c | 1 | ||||
-rw-r--r-- | fs/ocfs2/dlmglue.c | 119 | ||||
-rw-r--r-- | fs/ocfs2/dlmglue.h | 1 | ||||
-rw-r--r-- | fs/ocfs2/file.c | 10 | ||||
-rw-r--r-- | fs/ocfs2/file.h | 2 | ||||
-rw-r--r-- | fs/ocfs2/ioctl.c | 2 | ||||
-rw-r--r-- | fs/ocfs2/mmap.c | 44 | ||||
-rw-r--r-- | fs/ocfs2/namei.c | 3 | ||||
-rw-r--r-- | fs/ocfs2/ocfs2_fs.h | 8 | ||||
-rw-r--r-- | fs/proc/array.c | 2 | ||||
-rw-r--r-- | fs/proc/base.c | 265 | ||||
-rw-r--r-- | fs/proc/fd.c | 2 | ||||
-rw-r--r-- | fs/proc/internal.h | 2 | ||||
-rw-r--r-- | fs/proc/page.c | 2 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 26 | ||||
-rw-r--r-- | fs/ubifs/file.c | 11 | ||||
-rw-r--r-- | fs/ubifs/gc.c | 2 | ||||
-rw-r--r-- | fs/ubifs/journal.c | 5 | ||||
-rw-r--r-- | fs/ubifs/log.c | 6 | ||||
-rw-r--r-- | fs/ubifs/lpt_commit.c | 2 | ||||
-rw-r--r-- | fs/ubifs/replay.c | 5 | ||||
-rw-r--r-- | fs/ubifs/ubifs.h | 2 | ||||
-rw-r--r-- | fs/ubifs/xattr.c | 2 | ||||
-rw-r--r-- | fs/userfaultfd.c | 22 | ||||
-rw-r--r-- | fs/xfs/xfs_file.c | 72 | ||||
-rw-r--r-- | fs/xfs/xfs_inode.h | 16 | ||||
-rw-r--r-- | fs/xfs/xfs_ioctl.c | 8 | ||||
-rw-r--r-- | fs/xfs/xfs_iops.c | 16 | ||||
-rw-r--r-- | fs/xfs/xfs_pnfs.c | 15 | ||||
-rw-r--r-- | fs/xfs/xfs_pnfs.h | 5 |
72 files changed, 1241 insertions, 948 deletions
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index e622f0f10502..0429c8ee58f1 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -210,12 +210,12 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; - continue; - } - v9ses->debug = option; + } else { + v9ses->debug = option; #ifdef CONFIG_NET_9P_DEBUG - p9_debug_level = option; + p9_debug_level = option; #endif + } break; case Opt_dfltuid: @@ -231,7 +231,6 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) p9_debug(P9_DEBUG_ERROR, "uid field, but not a uid?\n"); ret = -EINVAL; - continue; } break; case Opt_dfltgid: @@ -247,7 +246,6 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) p9_debug(P9_DEBUG_ERROR, "gid field, but not a gid?\n"); ret = -EINVAL; - continue; } break; case Opt_afid: @@ -256,9 +254,9 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; - continue; + } else { + v9ses->afid = option; } - v9ses->afid = option; break; case Opt_uname: kfree(v9ses->uname); @@ -306,13 +304,12 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) "problem allocating copy of cache arg\n"); goto free_and_return; } - ret = get_cache_mode(s); - if (ret == -EINVAL) { - kfree(s); - goto free_and_return; - } + r = get_cache_mode(s); + if (r < 0) + ret = r; + else + v9ses->cache = r; - v9ses->cache = ret; kfree(s); break; @@ -341,14 +338,12 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts) pr_info("Unknown access argument %s\n", s); kfree(s); - goto free_and_return; + continue; } v9ses->uid = make_kuid(current_user_ns(), uid); if (!uid_valid(v9ses->uid)) { ret = -EINVAL; pr_info("Uknown uid %s\n", s); - kfree(s); - goto free_and_return; } } diff --git a/fs/Kconfig b/fs/Kconfig index ac4ac908f001..ab2d96d1abee 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -38,6 +38,7 @@ config FS_DAX bool "Direct Access (DAX) support" depends on MMU depends on !(ARM || MIPS || SPARC) + select DEV_PAGEMAP_OPS if (ZONE_DEVICE && !FS_DAX_LIMITED) select FS_IOMAP select DAX help @@ -108,6 +109,7 @@ source "fs/notify/Kconfig" source "fs/quota/Kconfig" +source "fs/autofs/Kconfig" source "fs/autofs4/Kconfig" source "fs/fuse/Kconfig" source "fs/overlayfs/Kconfig" @@ -203,6 +205,9 @@ config HUGETLBFS config HUGETLB_PAGE def_bool HUGETLBFS +config MEMFD_CREATE + def_bool TMPFS || HUGETLBFS + config ARCH_HAS_GIGANTIC_PAGE bool diff --git a/fs/Makefile b/fs/Makefile index c9375fd2c8c4..2e005525cc19 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -102,6 +102,7 @@ obj-$(CONFIG_AFFS_FS) += affs/ obj-$(CONFIG_ROMFS_FS) += romfs/ obj-$(CONFIG_QNX4FS_FS) += qnx4/ obj-$(CONFIG_QNX6FS_FS) += qnx6/ +obj-$(CONFIG_AUTOFS_FS) += autofs/ obj-$(CONFIG_AUTOFS4_FS) += autofs4/ obj-$(CONFIG_ADFS_FS) += adfs/ obj-$(CONFIG_FUSE_FS) += fuse/ @@ -1434,7 +1434,23 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb) req->ki_flags = iocb_flags(req->ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; - req->ki_hint = file_write_hint(req->ki_filp); + req->ki_hint = ki_hint_validate(file_write_hint(req->ki_filp)); + if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { + /* + * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then + * aio_reqprio is interpreted as an I/O scheduling + * class and priority. + */ + ret = ioprio_check_cap(iocb->aio_reqprio); + if (ret) { + pr_debug("aio ioprio check cap error: %d\n", ret); + return ret; + } + + req->ki_ioprio = iocb->aio_reqprio; + } else + req->ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); + ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); if (unlikely(ret)) fput(req->ki_filp); diff --git a/fs/autofs/Kconfig b/fs/autofs/Kconfig new file mode 100644 index 000000000000..6a2064eb3b27 --- /dev/null +++ b/fs/autofs/Kconfig @@ -0,0 +1,20 @@ +config AUTOFS_FS + tristate "Kernel automounter support (supports v3, v4 and v5)" + default n + help + The automounter is a tool to automatically mount remote file systems + on demand. This implementation is partially kernel-based to reduce + overhead in the already-mounted case; this is unlike the BSD + automounter (amd), which is a pure user space daemon. + + To use the automounter you need the user-space tools from + <https://www.kernel.org/pub/linux/daemons/autofs/>; you also want + to answer Y to "NFS file system support", below. + + To compile this support as a module, choose M here: the module will be + called autofs. + + If you are not a part of a fairly large, distributed network or + don't have a laptop which needs to dynamically reconfigure to the + local network, you probably do not need an automounter, and can say + N here. diff --git a/fs/autofs/Makefile b/fs/autofs/Makefile new file mode 100644 index 000000000000..43fedde15c26 --- /dev/null +++ b/fs/autofs/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the linux autofs-filesystem routines. +# + +obj-$(CONFIG_AUTOFS_FS) += autofs.o + +autofs-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o diff --git a/fs/autofs4/autofs_i.h b/fs/autofs/autofs_i.h index 4737615f0eaa..9400a9f6318a 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs/autofs_i.h @@ -9,7 +9,7 @@ /* Internal header file for autofs */ -#include <linux/auto_fs4.h> +#include <linux/auto_fs.h> #include <linux/auto_dev-ioctl.h> #include <linux/kernel.h> @@ -25,7 +25,7 @@ #include <linux/spinlock.h> #include <linux/list.h> #include <linux/completion.h> -#include <asm/current.h> +#include <linux/file.h> /* This is the range of ioctl() numbers we claim as ours */ #define AUTOFS_IOC_FIRST AUTOFS_IOC_READY @@ -122,44 +122,44 @@ struct autofs_sb_info { struct rcu_head rcu; }; -static inline struct autofs_sb_info *autofs4_sbi(struct super_block *sb) +static inline struct autofs_sb_info *autofs_sbi(struct super_block *sb) { return (struct autofs_sb_info *)(sb->s_fs_info); } -static inline struct autofs_info *autofs4_dentry_ino(struct dentry *dentry) +static inline struct autofs_info *autofs_dentry_ino(struct dentry *dentry) { return (struct autofs_info *)(dentry->d_fsdata); } -/* autofs4_oz_mode(): do we see the man behind the curtain? (The +/* autofs_oz_mode(): do we see the man behind the curtain? (The * processes which do manipulations for us in user space sees the raw * filesystem without "magic".) */ -static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) +static inline int autofs_oz_mode(struct autofs_sb_info *sbi) { return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp; } -struct inode *autofs4_get_inode(struct super_block *, umode_t); -void autofs4_free_ino(struct autofs_info *); +struct inode *autofs_get_inode(struct super_block *, umode_t); +void autofs_free_ino(struct autofs_info *); /* Expiration */ -int is_autofs4_dentry(struct dentry *); -int autofs4_expire_wait(const struct path *path, int rcu_walk); -int autofs4_expire_run(struct super_block *, struct vfsmount *, - struct autofs_sb_info *, - struct autofs_packet_expire __user *); -int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, - struct autofs_sb_info *sbi, int when); -int autofs4_expire_multi(struct super_block *, struct vfsmount *, - struct autofs_sb_info *, int __user *); -struct dentry *autofs4_expire_direct(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, int how); -struct dentry *autofs4_expire_indirect(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, int how); +int is_autofs_dentry(struct dentry *); +int autofs_expire_wait(const struct path *path, int rcu_walk); +int autofs_expire_run(struct super_block *, struct vfsmount *, + struct autofs_sb_info *, + struct autofs_packet_expire __user *); +int autofs_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int when); +int autofs_expire_multi(struct super_block *, struct vfsmount *, + struct autofs_sb_info *, int __user *); +struct dentry *autofs_expire_direct(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, int how); +struct dentry *autofs_expire_indirect(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, int how); /* Device node initialization */ @@ -168,11 +168,11 @@ void autofs_dev_ioctl_exit(void); /* Operations structures */ -extern const struct inode_operations autofs4_symlink_inode_operations; -extern const struct inode_operations autofs4_dir_inode_operations; -extern const struct file_operations autofs4_dir_operations; -extern const struct file_operations autofs4_root_operations; -extern const struct dentry_operations autofs4_dentry_operations; +extern const struct inode_operations autofs_symlink_inode_operations; +extern const struct inode_operations autofs_dir_inode_operations; +extern const struct file_operations autofs_dir_operations; +extern const struct file_operations autofs_root_operations; +extern const struct dentry_operations autofs_dentry_operations; /* VFS automount flags management functions */ static inline void __managed_dentry_set_managed(struct dentry *dentry) @@ -201,9 +201,9 @@ static inline void managed_dentry_clear_managed(struct dentry *dentry) /* Initializing function */ -int autofs4_fill_super(struct super_block *, void *, int); -struct autofs_info *autofs4_new_ino(struct autofs_sb_info *); -void autofs4_clean_ino(struct autofs_info *); +int autofs_fill_super(struct super_block *, void *, int); +struct autofs_info *autofs_new_ino(struct autofs_sb_info *); +void autofs_clean_ino(struct autofs_info *); static inline int autofs_prepare_pipe(struct file *pipe) { @@ -218,25 +218,25 @@ static inline int autofs_prepare_pipe(struct file *pipe) /* Queue management functions */ -int autofs4_wait(struct autofs_sb_info *, +int autofs_wait(struct autofs_sb_info *, const struct path *, enum autofs_notify); -int autofs4_wait_release(struct autofs_sb_info *, autofs_wqt_t, int); -void autofs4_catatonic_mode(struct autofs_sb_info *); +int autofs_wait_release(struct autofs_sb_info *, autofs_wqt_t, int); +void autofs_catatonic_mode(struct autofs_sb_info *); -static inline u32 autofs4_get_dev(struct autofs_sb_info *sbi) +static inline u32 autofs_get_dev(struct autofs_sb_info *sbi) { return new_encode_dev(sbi->sb->s_dev); } -static inline u64 autofs4_get_ino(struct autofs_sb_info *sbi) +static inline u64 autofs_get_ino(struct autofs_sb_info *sbi) { return d_inode(sbi->sb->s_root)->i_ino; } -static inline void __autofs4_add_expiring(struct dentry *dentry) +static inline void __autofs_add_expiring(struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); if (ino) { if (list_empty(&ino->expiring)) @@ -244,10 +244,10 @@ static inline void __autofs4_add_expiring(struct dentry *dentry) } } -static inline void autofs4_add_expiring(struct dentry *dentry) +static inline void autofs_add_expiring(struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); if (ino) { spin_lock(&sbi->lookup_lock); @@ -257,10 +257,10 @@ static inline void autofs4_add_expiring(struct dentry *dentry) } } -static inline void autofs4_del_expiring(struct dentry *dentry) +static inline void autofs_del_expiring(struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); if (ino) { spin_lock(&sbi->lookup_lock); @@ -270,4 +270,4 @@ static inline void autofs4_del_expiring(struct dentry *dentry) } } -void autofs4_kill_sb(struct super_block *); +void autofs_kill_sb(struct super_block *); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs/dev-ioctl.c index 26f6b4f41ce6..ea4ca1445ab7 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs/dev-ioctl.c @@ -7,23 +7,10 @@ * option, any later version, incorporated herein by reference. */ -#include <linux/module.h> -#include <linux/vmalloc.h> #include <linux/miscdevice.h> -#include <linux/init.h> -#include <linux/wait.h> -#include <linux/namei.h> -#include <linux/fcntl.h> -#include <linux/file.h> -#include <linux/fdtable.h> -#include <linux/sched.h> -#include <linux/cred.h> #include <linux/compat.h> #include <linux/syscalls.h> #include <linux/magic.h> -#include <linux/dcache.h> -#include <linux/uaccess.h> -#include <linux/slab.h> #include "autofs_i.h" @@ -166,7 +153,7 @@ static struct autofs_sb_info *autofs_dev_ioctl_sbi(struct file *f) if (f) { inode = file_inode(f); - sbi = autofs4_sbi(inode->i_sb); + sbi = autofs_sbi(inode->i_sb); } return sbi; } @@ -236,7 +223,7 @@ static int test_by_dev(const struct path *path, void *p) static int test_by_type(const struct path *path, void *p) { - struct autofs_info *ino = autofs4_dentry_ino(path->dentry); + struct autofs_info *ino = autofs_dentry_ino(path->dentry); return ino && ino->sbi->type & *(unsigned *)p; } @@ -324,7 +311,7 @@ static int autofs_dev_ioctl_ready(struct file *fp, autofs_wqt_t token; token = (autofs_wqt_t) param->ready.token; - return autofs4_wait_release(sbi, token, 0); + return autofs_wait_release(sbi, token, 0); } /* @@ -340,7 +327,7 @@ static int autofs_dev_ioctl_fail(struct file *fp, token = (autofs_wqt_t) param->fail.token; status = param->fail.status < 0 ? param->fail.status : -ENOENT; - return autofs4_wait_release(sbi, token, status); + return autofs_wait_release(sbi, token, status); } /* @@ -412,7 +399,7 @@ static int autofs_dev_ioctl_catatonic(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { - autofs4_catatonic_mode(sbi); + autofs_catatonic_mode(sbi); return 0; } @@ -459,10 +446,10 @@ static int autofs_dev_ioctl_requester(struct file *fp, if (err) goto out; - ino = autofs4_dentry_ino(path.dentry); + ino = autofs_dentry_ino(path.dentry); if (ino) { err = 0; - autofs4_expire_wait(&path, 0); + autofs_expire_wait(&path, 0); spin_lock(&sbi->fs_lock); param->requester.uid = from_kuid_munged(current_user_ns(), ino->uid); @@ -489,7 +476,7 @@ static int autofs_dev_ioctl_expire(struct file *fp, how = param->expire.how; mnt = fp->f_path.mnt; - return autofs4_do_expire_multi(sbi->sb, mnt, sbi, how); + return autofs_do_expire_multi(sbi->sb, mnt, sbi, how); } /* Check if autofs mount point is in use */ @@ -686,7 +673,7 @@ static int _autofs_dev_ioctl(unsigned int command, * Admin needs to be able to set the mount catatonic in * order to be able to perform the re-open. */ - if (!autofs4_oz_mode(sbi) && + if (!autofs_oz_mode(sbi) && cmd != AUTOFS_DEV_IOCTL_CATATONIC_CMD) { err = -EACCES; fput(fp); diff --git a/fs/autofs4/expire.c b/fs/autofs/expire.c index 57725d4a8c59..b332d3f6e730 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs/expire.c @@ -13,10 +13,10 @@ static unsigned long now; /* Check if a dentry can be expired */ -static inline int autofs4_can_expire(struct dentry *dentry, - unsigned long timeout, int do_now) +static inline int autofs_can_expire(struct dentry *dentry, + unsigned long timeout, int do_now) { - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_info *ino = autofs_dentry_ino(dentry); /* dentry in the process of being deleted */ if (ino == NULL) @@ -31,7 +31,7 @@ static inline int autofs4_can_expire(struct dentry *dentry, } /* Check a mount point for busyness */ -static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry) +static int autofs_mount_busy(struct vfsmount *mnt, struct dentry *dentry) { struct dentry *top = dentry; struct path path = {.mnt = mnt, .dentry = dentry}; @@ -44,8 +44,8 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry) if (!follow_down_one(&path)) goto done; - if (is_autofs4_dentry(path.dentry)) { - struct autofs_sb_info *sbi = autofs4_sbi(path.dentry->d_sb); + if (is_autofs_dentry(path.dentry)) { + struct autofs_sb_info *sbi = autofs_sbi(path.dentry->d_sb); /* This is an autofs submount, we can't expire it */ if (autofs_type_indirect(sbi->type)) @@ -56,7 +56,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry) if (!may_umount_tree(path.mnt)) { struct autofs_info *ino; - ino = autofs4_dentry_ino(top); + ino = autofs_dentry_ino(top); ino->last_used = jiffies; goto done; } @@ -74,7 +74,7 @@ done: static struct dentry *get_next_positive_subdir(struct dentry *prev, struct dentry *root) { - struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(root->d_sb); struct list_head *next; struct dentry *q; @@ -121,7 +121,7 @@ cont: static struct dentry *get_next_positive_dentry(struct dentry *prev, struct dentry *root) { - struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(root->d_sb); struct list_head *next; struct dentry *p, *ret; @@ -184,10 +184,10 @@ again: * The tree is not busy iff no mountpoints are busy and there are no * autofs submounts. */ -static int autofs4_direct_busy(struct vfsmount *mnt, - struct dentry *top, - unsigned long timeout, - int do_now) +static int autofs_direct_busy(struct vfsmount *mnt, + struct dentry *top, + unsigned long timeout, + int do_now) { pr_debug("top %p %pd\n", top, top); @@ -195,14 +195,14 @@ static int autofs4_direct_busy(struct vfsmount *mnt, if (!may_umount_tree(mnt)) { struct autofs_info *ino; - ino = autofs4_dentry_ino(top); + ino = autofs_dentry_ino(top); if (ino) ino->last_used = jiffies; return 1; } /* Timeout of a direct mount is determined by its top dentry */ - if (!autofs4_can_expire(top, timeout, do_now)) + if (!autofs_can_expire(top, timeout, do_now)) return 1; return 0; @@ -212,12 +212,12 @@ static int autofs4_direct_busy(struct vfsmount *mnt, * Check a directory tree of mount points for busyness * The tree is not busy iff no mountpoints are busy */ -static int autofs4_tree_busy(struct vfsmount *mnt, - struct dentry *top, - unsigned long timeout, - int do_now) +static int autofs_tree_busy(struct vfsmount *mnt, + struct dentry *top, + unsigned long timeout, + int do_now) { - struct autofs_info *top_ino = autofs4_dentry_ino(top); + struct autofs_info *top_ino = autofs_dentry_ino(top); struct dentry *p; pr_debug("top %p %pd\n", top, top); @@ -237,13 +237,13 @@ static int autofs4_tree_busy(struct vfsmount *mnt, * If the fs is busy update the expiry counter. */ if (d_mountpoint(p)) { - if (autofs4_mount_busy(mnt, p)) { + if (autofs_mount_busy(mnt, p)) { top_ino->last_used = jiffies; dput(p); return 1; } } else { - struct autofs_info *ino = autofs4_dentry_ino(p); + struct autofs_info *ino = autofs_dentry_ino(p); unsigned int ino_count = atomic_read(&ino->count); /* allow for dget above and top is already dgot */ @@ -261,16 +261,16 @@ static int autofs4_tree_busy(struct vfsmount *mnt, } /* Timeout of a tree mount is ultimately determined by its top dentry */ - if (!autofs4_can_expire(top, timeout, do_now)) + if (!autofs_can_expire(top, timeout, do_now)) return 1; return 0; } -static struct dentry *autofs4_check_leaves(struct vfsmount *mnt, - struct dentry *parent, - unsigned long timeout, - int do_now) +static struct dentry *autofs_check_leaves(struct vfsmount *mnt, + struct dentry *parent, + unsigned long timeout, + int do_now) { struct dentry *p; @@ -282,11 +282,11 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt, if (d_mountpoint(p)) { /* Can we umount this guy */ - if (autofs4_mount_busy(mnt, p)) + if (autofs_mount_busy(mnt, p)) continue; /* Can we expire this guy */ - if (autofs4_can_expire(p, timeout, do_now)) + if (autofs_can_expire(p, timeout, do_now)) return p; } } @@ -294,10 +294,10 @@ static struct dentry *autofs4_check_leaves(struct vfsmount *mnt, } /* Check if we can expire a direct mount (possibly a tree) */ -struct dentry *autofs4_expire_direct(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, - int how) +struct dentry *autofs_expire_direct(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, + int how) { unsigned long timeout; struct dentry *root = dget(sb->s_root); @@ -310,9 +310,9 @@ struct dentry *autofs4_expire_direct(struct super_block *sb, now = jiffies; timeout = sbi->exp_timeout; - if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { + if (!autofs_direct_busy(mnt, root, timeout, do_now)) { spin_lock(&sbi->fs_lock); - ino = autofs4_dentry_ino(root); + ino = autofs_dentry_ino(root); /* No point expiring a pending mount */ if (ino->flags & AUTOFS_INF_PENDING) { spin_unlock(&sbi->fs_lock); @@ -321,7 +321,7 @@ struct dentry *autofs4_expire_direct(struct super_block *sb, ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); - if (!autofs4_direct_busy(mnt, root, timeout, do_now)) { + if (!autofs_direct_busy(mnt, root, timeout, do_now)) { spin_lock(&sbi->fs_lock); ino->flags |= AUTOFS_INF_EXPIRING; init_completion(&ino->expire_complete); @@ -350,7 +350,7 @@ static struct dentry *should_expire(struct dentry *dentry, { int do_now = how & AUTOFS_EXP_IMMEDIATE; int exp_leaves = how & AUTOFS_EXP_LEAVES; - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_info *ino = autofs_dentry_ino(dentry); unsigned int ino_count; /* No point expiring a pending mount */ @@ -367,11 +367,11 @@ static struct dentry *should_expire(struct dentry *dentry, pr_debug("checking mountpoint %p %pd\n", dentry, dentry); /* Can we umount this guy */ - if (autofs4_mount_busy(mnt, dentry)) + if (autofs_mount_busy(mnt, dentry)) return NULL; /* Can we expire this guy */ - if (autofs4_can_expire(dentry, timeout, do_now)) + if (autofs_can_expire(dentry, timeout, do_now)) return dentry; return NULL; } @@ -382,7 +382,7 @@ static struct dentry *should_expire(struct dentry *dentry, * A symlink can't be "busy" in the usual sense so * just check last used for expire timeout. */ - if (autofs4_can_expire(dentry, timeout, do_now)) + if (autofs_can_expire(dentry, timeout, do_now)) return dentry; return NULL; } @@ -397,7 +397,7 @@ static struct dentry *should_expire(struct dentry *dentry, if (d_count(dentry) > ino_count) return NULL; - if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) + if (!autofs_tree_busy(mnt, dentry, timeout, do_now)) return dentry; /* * Case 3: pseudo direct mount, expire individual leaves @@ -411,7 +411,7 @@ static struct dentry *should_expire(struct dentry *dentry, if (d_count(dentry) > ino_count) return NULL; - expired = autofs4_check_leaves(mnt, dentry, timeout, do_now); + expired = autofs_check_leaves(mnt, dentry, timeout, do_now); if (expired) { if (expired == dentry) dput(dentry); @@ -427,10 +427,10 @@ static struct dentry *should_expire(struct dentry *dentry, * - it is unused by any user process * - it has been unused for exp_timeout time */ -struct dentry *autofs4_expire_indirect(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, - int how) +struct dentry *autofs_expire_indirect(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, + int how) { unsigned long timeout; struct dentry *root = sb->s_root; @@ -450,7 +450,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, int flags = how; spin_lock(&sbi->fs_lock); - ino = autofs4_dentry_ino(dentry); + ino = autofs_dentry_ino(dentry); if (ino->flags & AUTOFS_INF_WANT_EXPIRE) { spin_unlock(&sbi->fs_lock); continue; @@ -462,7 +462,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, continue; spin_lock(&sbi->fs_lock); - ino = autofs4_dentry_ino(expired); + ino = autofs_dentry_ino(expired); ino->flags |= AUTOFS_INF_WANT_EXPIRE; spin_unlock(&sbi->fs_lock); synchronize_rcu(); @@ -498,11 +498,11 @@ found: return expired; } -int autofs4_expire_wait(const struct path *path, int rcu_walk) +int autofs_expire_wait(const struct path *path, int rcu_walk) { struct dentry *dentry = path->dentry; - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); int status; int state; @@ -529,7 +529,7 @@ retry: pr_debug("waiting for expire %p name=%pd\n", dentry, dentry); - status = autofs4_wait(sbi, path, NFY_NONE); + status = autofs_wait(sbi, path, NFY_NONE); wait_for_completion(&ino->expire_complete); pr_debug("expire done status=%d\n", status); @@ -545,10 +545,10 @@ retry: } /* Perform an expiry operation */ -int autofs4_expire_run(struct super_block *sb, - struct vfsmount *mnt, - struct autofs_sb_info *sbi, - struct autofs_packet_expire __user *pkt_p) +int autofs_expire_run(struct super_block *sb, + struct vfsmount *mnt, + struct autofs_sb_info *sbi, + struct autofs_packet_expire __user *pkt_p) { struct autofs_packet_expire pkt; struct autofs_info *ino; @@ -560,7 +560,7 @@ int autofs4_expire_run(struct super_block *sb, pkt.hdr.proto_version = sbi->version; pkt.hdr.type = autofs_ptype_expire; - dentry = autofs4_expire_indirect(sb, mnt, sbi, 0); + dentry = autofs_expire_indirect(sb, mnt, sbi, 0); if (!dentry) return -EAGAIN; @@ -573,7 +573,7 @@ int autofs4_expire_run(struct super_block *sb, ret = -EFAULT; spin_lock(&sbi->fs_lock); - ino = autofs4_dentry_ino(dentry); + ino = autofs_dentry_ino(dentry); /* avoid rapid-fire expire attempts if expiry fails */ ino->last_used = now; ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE); @@ -583,25 +583,25 @@ int autofs4_expire_run(struct super_block *sb, return ret; } -int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, - struct autofs_sb_info *sbi, int when) +int autofs_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, + struct autofs_sb_info *sbi, int when) { struct dentry *dentry; int ret = -EAGAIN; if (autofs_type_trigger(sbi->type)) - dentry = autofs4_expire_direct(sb, mnt, sbi, when); + dentry = autofs_expire_direct(sb, mnt, sbi, when); else - dentry = autofs4_expire_indirect(sb, mnt, sbi, when); + dentry = autofs_expire_indirect(sb, mnt, sbi, when); if (dentry) { - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_info *ino = autofs_dentry_ino(dentry); const struct path path = { .mnt = mnt, .dentry = dentry }; /* This is synchronous because it makes the daemon a * little easier */ - ret = autofs4_wait(sbi, &path, NFY_EXPIRE); + ret = autofs_wait(sbi, &path, NFY_EXPIRE); spin_lock(&sbi->fs_lock); /* avoid rapid-fire expire attempts if expiry fails */ @@ -619,7 +619,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt, * Call repeatedly until it returns -EAGAIN, meaning there's nothing * more to be done. */ -int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt, +int autofs_expire_multi(struct super_block *sb, struct vfsmount *mnt, struct autofs_sb_info *sbi, int __user *arg) { int do_now = 0; @@ -627,6 +627,5 @@ int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt, if (arg && get_user(do_now, arg)) return -EFAULT; - return autofs4_do_expire_multi(sb, mnt, sbi, do_now); + return autofs_do_expire_multi(sb, mnt, sbi, do_now); } - diff --git a/fs/autofs4/init.c b/fs/autofs/init.c index 8cf0e63389ae..16fb61315843 100644 --- a/fs/autofs4/init.c +++ b/fs/autofs/init.c @@ -13,18 +13,18 @@ static struct dentry *autofs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - return mount_nodev(fs_type, flags, data, autofs4_fill_super); + return mount_nodev(fs_type, flags, data, autofs_fill_super); } static struct file_system_type autofs_fs_type = { .owner = THIS_MODULE, .name = "autofs", .mount = autofs_mount, - .kill_sb = autofs4_kill_sb, + .kill_sb = autofs_kill_sb, }; MODULE_ALIAS_FS("autofs"); -static int __init init_autofs4_fs(void) +static int __init init_autofs_fs(void) { int err; @@ -37,12 +37,12 @@ static int __init init_autofs4_fs(void) return err; } -static void __exit exit_autofs4_fs(void) +static void __exit exit_autofs_fs(void) { autofs_dev_ioctl_exit(); unregister_filesystem(&autofs_fs_type); } -module_init(init_autofs4_fs) -module_exit(exit_autofs4_fs) +module_init(init_autofs_fs) +module_exit(exit_autofs_fs) MODULE_LICENSE("GPL"); diff --git a/fs/autofs4/inode.c b/fs/autofs/inode.c index 09e7d68dff02..b51980fc274e 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs/inode.c @@ -7,18 +7,14 @@ * option, any later version, incorporated herein by reference. */ -#include <linux/kernel.h> -#include <linux/slab.h> -#include <linux/file.h> #include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/parser.h> -#include <linux/bitops.h> #include <linux/magic.h> + #include "autofs_i.h" -#include <linux/module.h> -struct autofs_info *autofs4_new_ino(struct autofs_sb_info *sbi) +struct autofs_info *autofs_new_ino(struct autofs_sb_info *sbi) { struct autofs_info *ino; @@ -32,21 +28,21 @@ struct autofs_info *autofs4_new_ino(struct autofs_sb_info *sbi) return ino; } -void autofs4_clean_ino(struct autofs_info *ino) +void autofs_clean_ino(struct autofs_info *ino) { ino->uid = GLOBAL_ROOT_UID; ino->gid = GLOBAL_ROOT_GID; ino->last_used = jiffies; } -void autofs4_free_ino(struct autofs_info *ino) +void autofs_free_ino(struct autofs_info *ino) { kfree(ino); } -void autofs4_kill_sb(struct super_block *sb) +void autofs_kill_sb(struct super_block *sb) { - struct autofs_sb_info *sbi = autofs4_sbi(sb); + struct autofs_sb_info *sbi = autofs_sbi(sb); /* * In the event of a failure in get_sb_nodev the superblock @@ -56,7 +52,7 @@ void autofs4_kill_sb(struct super_block *sb) */ if (sbi) { /* Free wait queues, close pipe */ - autofs4_catatonic_mode(sbi); + autofs_catatonic_mode(sbi); put_pid(sbi->oz_pgrp); } @@ -66,9 +62,9 @@ void autofs4_kill_sb(struct super_block *sb) kfree_rcu(sbi, rcu); } -static int autofs4_show_options(struct seq_file *m, struct dentry *root) +static int autofs_show_options(struct seq_file *m, struct dentry *root) { - struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(root->d_sb); struct inode *root_inode = d_inode(root->d_sb->s_root); if (!sbi) @@ -101,16 +97,16 @@ static int autofs4_show_options(struct seq_file *m, struct dentry *root) return 0; } -static void autofs4_evict_inode(struct inode *inode) +static void autofs_evict_inode(struct inode *inode) { clear_inode(inode); kfree(inode->i_private); } -static const struct super_operations autofs4_sops = { +static const struct super_operations autofs_sops = { .statfs = simple_statfs, - .show_options = autofs4_show_options, - .evict_inode = autofs4_evict_inode, + .show_options = autofs_show_options, + .evict_inode = autofs_evict_inode, }; enum {Opt_err, Opt_fd, Opt_uid, Opt_gid, Opt_pgrp, Opt_minproto, Opt_maxproto, @@ -206,7 +202,7 @@ static int parse_options(char *options, int *pipefd, kuid_t *uid, kgid_t *gid, return (*pipefd < 0); } -int autofs4_fill_super(struct super_block *s, void *data, int silent) +int autofs_fill_super(struct super_block *s, void *data, int silent) { struct inode *root_inode; struct dentry *root; @@ -246,19 +242,19 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) s->s_blocksize = 1024; s->s_blocksize_bits = 10; s->s_magic = AUTOFS_SUPER_MAGIC; - s->s_op = &autofs4_sops; - s->s_d_op = &autofs4_dentry_operations; + s->s_op = &autofs_sops; + s->s_d_op = &autofs_dentry_operations; s->s_time_gran = 1; /* * Get the root inode and dentry, but defer checking for errors. */ - ino = autofs4_new_ino(sbi); + ino = autofs_new_ino(sbi); if (!ino) { ret = -ENOMEM; goto fail_free; } - root_inode = autofs4_get_inode(s, S_IFDIR | 0755); + root_inode = autofs_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); if (!root) goto fail_ino; @@ -305,8 +301,8 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) if (autofs_type_trigger(sbi->type)) __managed_dentry_set_managed(root); - root_inode->i_fop = &autofs4_root_operations; - root_inode->i_op = &autofs4_dir_inode_operations; + root_inode->i_fop = &autofs_root_operations; + root_inode->i_op = &autofs_dir_inode_operations; pr_debug("pipe fd = %d, pgrp = %u\n", pipefd, pid_nr(sbi->oz_pgrp)); pipe = fget(pipefd); @@ -340,14 +336,14 @@ fail_dput: dput(root); goto fail_free; fail_ino: - autofs4_free_ino(ino); + autofs_free_ino(ino); fail_free: kfree(sbi); s->s_fs_info = NULL; return ret; } -struct inode *autofs4_get_inode(struct super_block *sb, umode_t mode) +struct inode *autofs_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); @@ -364,10 +360,10 @@ struct inode *autofs4_get_inode(struct super_block *sb, umode_t mode) if (S_ISDIR(mode)) { set_nlink(inode, 2); - inode->i_op = &autofs4_dir_inode_operations; - inode->i_fop = &autofs4_dir_operations; + inode->i_op = &autofs_dir_inode_operations; + inode->i_fop = &autofs_dir_operations; } else if (S_ISLNK(mode)) { - inode->i_op = &autofs4_symlink_inode_operations; + inode->i_op = &autofs_symlink_inode_operations; } else WARN_ON(1); diff --git a/fs/autofs4/root.c b/fs/autofs/root.c index b12e37f27530..a3d414150578 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs/root.c @@ -9,72 +9,66 @@ */ #include <linux/capability.h> -#include <linux/errno.h> -#include <linux/stat.h> -#include <linux/slab.h> -#include <linux/param.h> -#include <linux/time.h> #include <linux/compat.h> -#include <linux/mutex.h> #include "autofs_i.h" -static int autofs4_dir_symlink(struct inode *, struct dentry *, const char *); -static int autofs4_dir_unlink(struct inode *, struct dentry *); -static int autofs4_dir_rmdir(struct inode *, struct dentry *); -static int autofs4_dir_mkdir(struct inode *, struct dentry *, umode_t); -static long autofs4_root_ioctl(struct file *, unsigned int, unsigned long); +static int autofs_dir_symlink(struct inode *, struct dentry *, const char *); +static int autofs_dir_unlink(struct inode *, struct dentry *); +static int autofs_dir_rmdir(struct inode *, struct dentry *); +static int autofs_dir_mkdir(struct inode *, struct dentry *, umode_t); +static long autofs_root_ioctl(struct file *, unsigned int, unsigned long); #ifdef CONFIG_COMPAT -static long autofs4_root_compat_ioctl(struct file *, - unsigned int, unsigned long); +static long autofs_root_compat_ioctl(struct file *, + unsigned int, unsigned long); #endif -static int autofs4_dir_open(struct inode *inode, struct file *file); -static struct dentry *autofs4_lookup(struct inode *, - struct dentry *, unsigned int); -static struct vfsmount *autofs4_d_automount(struct path *); -static int autofs4_d_manage(const struct path *, bool); -static void autofs4_dentry_release(struct dentry *); - -const struct file_operations autofs4_root_operations = { +static int autofs_dir_open(struct inode *inode, struct file *file); +static struct dentry *autofs_lookup(struct inode *, + struct dentry *, unsigned int); +static struct vfsmount *autofs_d_automount(struct path *); +static int autofs_d_manage(const struct path *, bool); +static void autofs_dentry_release(struct dentry *); + +const struct file_operations autofs_root_operations = { .open = dcache_dir_open, .release = dcache_dir_close, .read = generic_read_dir, .iterate_shared = dcache_readdir, .llseek = dcache_dir_lseek, - .unlocked_ioctl = autofs4_root_ioctl, + .unlocked_ioctl = autofs_root_ioctl, #ifdef CONFIG_COMPAT - .compat_ioctl = autofs4_root_compat_ioctl, + .compat_ioctl = autofs_root_compat_ioctl, #endif }; -const struct file_operations autofs4_dir_operations = { - .open = autofs4_dir_open, +const struct file_operations autofs_dir_operations = { + .open = autofs_dir_open, .release = dcache_dir_close, .read = generic_read_dir, .iterate_shared = dcache_readdir, .llseek = dcache_dir_lseek, }; -const struct inode_operations autofs4_dir_inode_operations = { - .lookup = autofs4_lookup, - .unlink = autofs4_dir_unlink, - .symlink = autofs4_dir_symlink, - .mkdir = autofs4_dir_mkdir, - .rmdir = autofs4_dir_rmdir, +const struct inode_operations autofs_dir_inode_operations = { + .lookup = autofs_lookup, + .unlink = autofs_dir_unlink, + .symlink = autofs_dir_symlink, + .mkdir = autofs_dir_mkdir, + .rmdir = autofs_dir_rmdir, }; -const struct dentry_operations autofs4_dentry_operations = { - .d_automount = autofs4_d_automount, - .d_manage = autofs4_d_manage, - .d_release = autofs4_dentry_release, +const struct dentry_operations autofs_dentry_operations = { + .d_automount = autofs_d_automount, + .d_manage = autofs_d_manage, + .d_release = autofs_dentry_release, }; -static void autofs4_add_active(struct dentry *dentry) +static void autofs_add_active(struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino; - ino = autofs4_dentry_ino(dentry); + ino = autofs_dentry_ino(dentry); if (ino) { spin_lock(&sbi->lookup_lock); if (!ino->active_count) { @@ -86,12 +80,12 @@ static void autofs4_add_active(struct dentry *dentry) } } -static void autofs4_del_active(struct dentry *dentry) +static void autofs_del_active(struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct autofs_info *ino; - ino = autofs4_dentry_ino(dentry); + ino = autofs_dentry_ino(dentry); if (ino) { spin_lock(&sbi->lookup_lock); ino->active_count--; @@ -103,14 +97,14 @@ static void autofs4_del_active(struct dentry *dentry) } } -static int autofs4_dir_open(struct inode *inode, struct file *file) +static int autofs_dir_open(struct inode *inode, struct file *file) { struct dentry *dentry = file->f_path.dentry; - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); pr_debug("file=%p dentry=%p %pd\n", file, dentry, dentry); - if (autofs4_oz_mode(sbi)) + if (autofs_oz_mode(sbi)) goto out; /* @@ -133,10 +127,10 @@ out: return dcache_dir_open(inode, file); } -static void autofs4_dentry_release(struct dentry *de) +static void autofs_dentry_release(struct dentry *de) { - struct autofs_info *ino = autofs4_dentry_ino(de); - struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb); + struct autofs_info *ino = autofs_dentry_ino(de); + struct autofs_sb_info *sbi = autofs_sbi(de->d_sb); pr_debug("releasing %p\n", de); @@ -152,12 +146,12 @@ static void autofs4_dentry_release(struct dentry *de) spin_unlock(&sbi->lookup_lock); } - autofs4_free_ino(ino); + autofs_free_ino(ino); } -static struct dentry *autofs4_lookup_active(struct dentry *dentry) +static struct dentry *autofs_lookup_active(struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct dentry *parent = dentry->d_parent; const struct qstr *name = &dentry->d_name; unsigned int len = name->len; @@ -209,10 +203,10 @@ next: return NULL; } -static struct dentry *autofs4_lookup_expiring(struct dentry *dentry, - bool rcu_walk) +static struct dentry *autofs_lookup_expiring(struct dentry *dentry, + bool rcu_walk) { - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); struct dentry *parent = dentry->d_parent; const struct qstr *name = &dentry->d_name; unsigned int len = name->len; @@ -269,17 +263,17 @@ next: return NULL; } -static int autofs4_mount_wait(const struct path *path, bool rcu_walk) +static int autofs_mount_wait(const struct path *path, bool rcu_walk) { - struct autofs_sb_info *sbi = autofs4_sbi(path->dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(path->dentry); + struct autofs_sb_info *sbi = autofs_sbi(path->dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(path->dentry); int status = 0; if (ino->flags & AUTOFS_INF_PENDING) { if (rcu_walk) return -ECHILD; pr_debug("waiting for mount name=%pd\n", path->dentry); - status = autofs4_wait(sbi, path, NFY_MOUNT); + status = autofs_wait(sbi, path, NFY_MOUNT); pr_debug("mount wait done status=%d\n", status); } ino->last_used = jiffies; @@ -291,11 +285,11 @@ static int do_expire_wait(const struct path *path, bool rcu_walk) struct dentry *dentry = path->dentry; struct dentry *expiring; - expiring = autofs4_lookup_expiring(dentry, rcu_walk); + expiring = autofs_lookup_expiring(dentry, rcu_walk); if (IS_ERR(expiring)) return PTR_ERR(expiring); if (!expiring) - return autofs4_expire_wait(path, rcu_walk); + return autofs_expire_wait(path, rcu_walk); else { const struct path this = { .mnt = path->mnt, .dentry = expiring }; /* @@ -303,17 +297,17 @@ static int do_expire_wait(const struct path *path, bool rcu_walk) * be quite complete, but the directory has been removed * so it must have been successful, just wait for it. */ - autofs4_expire_wait(&this, 0); - autofs4_del_expiring(expiring); + autofs_expire_wait(&this, 0); + autofs_del_expiring(expiring); dput(expiring); } return 0; } -static struct dentry *autofs4_mountpoint_changed(struct path *path) +static struct dentry *autofs_mountpoint_changed(struct path *path) { struct dentry *dentry = path->dentry; - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); /* * If this is an indirect mount the dentry could have gone away @@ -327,7 +321,7 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path) new = d_lookup(parent, &dentry->d_name); if (!new) return NULL; - ino = autofs4_dentry_ino(new); + ino = autofs_dentry_ino(new); ino->last_used = jiffies; dput(path->dentry); path->dentry = new; @@ -335,17 +329,17 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path) return path->dentry; } -static struct vfsmount *autofs4_d_automount(struct path *path) +static struct vfsmount *autofs_d_automount(struct path *path) { struct dentry *dentry = path->dentry; - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); int status; pr_debug("dentry=%p %pd\n", dentry, dentry); /* The daemon never triggers a mount. */ - if (autofs4_oz_mode(sbi)) + if (autofs_oz_mode(sbi)) return NULL; /* @@ -364,7 +358,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path) spin_lock(&sbi->fs_lock); if (ino->flags & AUTOFS_INF_PENDING) { spin_unlock(&sbi->fs_lock); - status = autofs4_mount_wait(path, 0); + status = autofs_mount_wait(path, 0); if (status) return ERR_PTR(status); goto done; @@ -405,7 +399,7 @@ static struct vfsmount *autofs4_d_automount(struct path *path) } ino->flags |= AUTOFS_INF_PENDING; spin_unlock(&sbi->fs_lock); - status = autofs4_mount_wait(path, 0); + status = autofs_mount_wait(path, 0); spin_lock(&sbi->fs_lock); ino->flags &= ~AUTOFS_INF_PENDING; if (status) { @@ -416,24 +410,24 @@ static struct vfsmount *autofs4_d_automount(struct path *path) spin_unlock(&sbi->fs_lock); done: /* Mount succeeded, check if we ended up with a new dentry */ - dentry = autofs4_mountpoint_changed(path); + dentry = autofs_mountpoint_changed(path); if (!dentry) return ERR_PTR(-ENOENT); return NULL; } -static int autofs4_d_manage(const struct path *path, bool rcu_walk) +static int autofs_d_manage(const struct path *path, bool rcu_walk) { struct dentry *dentry = path->dentry; - struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dentry->d_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); int status; pr_debug("dentry=%p %pd\n", dentry, dentry); /* The daemon never waits. */ - if (autofs4_oz_mode(sbi)) { + if (autofs_oz_mode(sbi)) { if (!path_is_mountpoint(path)) return -EISDIR; return 0; @@ -447,7 +441,7 @@ static int autofs4_d_manage(const struct path *path, bool rcu_walk) * This dentry may be under construction so wait on mount * completion. */ - status = autofs4_mount_wait(path, rcu_walk); + status = autofs_mount_wait(path, rcu_walk); if (status) return status; @@ -500,8 +494,8 @@ static int autofs4_d_manage(const struct path *path, bool rcu_walk) } /* Lookups in the root directory */ -static struct dentry *autofs4_lookup(struct inode *dir, - struct dentry *dentry, unsigned int flags) +static struct dentry *autofs_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) { struct autofs_sb_info *sbi; struct autofs_info *ino; @@ -513,13 +507,13 @@ static struct dentry *autofs4_lookup(struct inode *dir, if (dentry->d_name.len > NAME_MAX) return ERR_PTR(-ENAMETOOLONG); - sbi = autofs4_sbi(dir->i_sb); + sbi = autofs_sbi(dir->i_sb); pr_debug("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n", current->pid, task_pgrp_nr(current), sbi->catatonic, - autofs4_oz_mode(sbi)); + autofs_oz_mode(sbi)); - active = autofs4_lookup_active(dentry); + active = autofs_lookup_active(dentry); if (active) return active; else { @@ -529,7 +523,7 @@ static struct dentry *autofs4_lookup(struct inode *dir, * can return fail immediately. The daemon however does need * to create directories within the file system. */ - if (!autofs4_oz_mode(sbi) && !IS_ROOT(dentry->d_parent)) + if (!autofs_oz_mode(sbi) && !IS_ROOT(dentry->d_parent)) return ERR_PTR(-ENOENT); /* Mark entries in the root as mount triggers */ @@ -537,24 +531,24 @@ static struct dentry *autofs4_lookup(struct inode *dir, autofs_type_indirect(sbi->type)) __managed_dentry_set_managed(dentry); - ino = autofs4_new_ino(sbi); + ino = autofs_new_ino(sbi); if (!ino) return ERR_PTR(-ENOMEM); dentry->d_fsdata = ino; ino->dentry = dentry; - autofs4_add_active(dentry); + autofs_add_active(dentry); } return NULL; } -static int autofs4_dir_symlink(struct inode *dir, +static int autofs_dir_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { - struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; struct inode *inode; size_t size = strlen(symname); @@ -562,14 +556,14 @@ static int autofs4_dir_symlink(struct inode *dir, pr_debug("%s <- %pd\n", symname, dentry); - if (!autofs4_oz_mode(sbi)) + if (!autofs_oz_mode(sbi)) return -EACCES; BUG_ON(!ino); - autofs4_clean_ino(ino); + autofs_clean_ino(ino); - autofs4_del_active(dentry); + autofs_del_active(dentry); cp = kmalloc(size + 1, GFP_KERNEL); if (!cp) @@ -577,7 +571,7 @@ static int autofs4_dir_symlink(struct inode *dir, strcpy(cp, symname); - inode = autofs4_get_inode(dir->i_sb, S_IFLNK | 0555); + inode = autofs_get_inode(dir->i_sb, S_IFLNK | 0555); if (!inode) { kfree(cp); return -ENOMEM; @@ -588,7 +582,7 @@ static int autofs4_dir_symlink(struct inode *dir, dget(dentry); atomic_inc(&ino->count); - p_ino = autofs4_dentry_ino(dentry->d_parent); + p_ino = autofs_dentry_ino(dentry->d_parent); if (p_ino && !IS_ROOT(dentry)) atomic_inc(&p_ino->count); @@ -610,20 +604,20 @@ static int autofs4_dir_symlink(struct inode *dir, * If a process is blocked on the dentry waiting for the expire to finish, * it will invalidate the dentry and try to mount with a new one. * - * Also see autofs4_dir_rmdir().. + * Also see autofs_dir_rmdir().. */ -static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) +static int autofs_dir_unlink(struct inode *dir, struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; /* This allows root to remove symlinks */ - if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) + if (!autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) return -EPERM; if (atomic_dec_and_test(&ino->count)) { - p_ino = autofs4_dentry_ino(dentry->d_parent); + p_ino = autofs_dentry_ino(dentry->d_parent); if (p_ino && !IS_ROOT(dentry)) atomic_dec(&p_ino->count); } @@ -635,7 +629,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry) dir->i_mtime = current_time(dir); spin_lock(&sbi->lookup_lock); - __autofs4_add_expiring(dentry); + __autofs_add_expiring(dentry); d_drop(dentry); spin_unlock(&sbi->lookup_lock); @@ -692,15 +686,15 @@ static void autofs_clear_leaf_automount_flags(struct dentry *dentry) managed_dentry_set_managed(parent); } -static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) +static int autofs_dir_rmdir(struct inode *dir, struct dentry *dentry) { - struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; pr_debug("dentry %p, removing %pd\n", dentry, dentry); - if (!autofs4_oz_mode(sbi)) + if (!autofs_oz_mode(sbi)) return -EACCES; spin_lock(&sbi->lookup_lock); @@ -708,7 +702,7 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) spin_unlock(&sbi->lookup_lock); return -ENOTEMPTY; } - __autofs4_add_expiring(dentry); + __autofs_add_expiring(dentry); d_drop(dentry); spin_unlock(&sbi->lookup_lock); @@ -716,7 +710,7 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) autofs_clear_leaf_automount_flags(dentry); if (atomic_dec_and_test(&ino->count)) { - p_ino = autofs4_dentry_ino(dentry->d_parent); + p_ino = autofs_dentry_ino(dentry->d_parent); if (p_ino && dentry->d_parent != dentry) atomic_dec(&p_ino->count); } @@ -730,26 +724,26 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry) return 0; } -static int autofs4_dir_mkdir(struct inode *dir, - struct dentry *dentry, umode_t mode) +static int autofs_dir_mkdir(struct inode *dir, + struct dentry *dentry, umode_t mode) { - struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb); - struct autofs_info *ino = autofs4_dentry_ino(dentry); + struct autofs_sb_info *sbi = autofs_sbi(dir->i_sb); + struct autofs_info *ino = autofs_dentry_ino(dentry); struct autofs_info *p_ino; struct inode *inode; - if (!autofs4_oz_mode(sbi)) + if (!autofs_oz_mode(sbi)) return -EACCES; pr_debug("dentry %p, creating %pd\n", dentry, dentry); BUG_ON(!ino); - autofs4_clean_ino(ino); + autofs_clean_ino(ino); - autofs4_del_active(dentry); + autofs_del_active(dentry); - inode = autofs4_get_inode(dir->i_sb, S_IFDIR | mode); + inode = autofs_get_inode(dir->i_sb, S_IFDIR | mode); if (!inode) return -ENOMEM; d_add(dentry, inode); @@ -759,7 +753,7 @@ static int autofs4_dir_mkdir(struct inode *dir, dget(dentry); atomic_inc(&ino->count); - p_ino = autofs4_dentry_ino(dentry->d_parent); + p_ino = autofs_dentry_ino(dentry->d_parent); if (p_ino && !IS_ROOT(dentry)) atomic_inc(&p_ino->count); inc_nlink(dir); @@ -770,7 +764,7 @@ static int autofs4_dir_mkdir(struct inode *dir, /* Get/set timeout ioctl() operation */ #ifdef CONFIG_COMPAT -static inline int autofs4_compat_get_set_timeout(struct autofs_sb_info *sbi, +static inline int autofs_compat_get_set_timeout(struct autofs_sb_info *sbi, compat_ulong_t __user *p) { unsigned long ntimeout; @@ -795,7 +789,7 @@ error: } #endif -static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi, +static inline int autofs_get_set_timeout(struct autofs_sb_info *sbi, unsigned long __user *p) { unsigned long ntimeout; @@ -820,14 +814,14 @@ error: } /* Return protocol version */ -static inline int autofs4_get_protover(struct autofs_sb_info *sbi, +static inline int autofs_get_protover(struct autofs_sb_info *sbi, int __user *p) { return put_user(sbi->version, p); } /* Return protocol sub version */ -static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, +static inline int autofs_get_protosubver(struct autofs_sb_info *sbi, int __user *p) { return put_user(sbi->sub_version, p); @@ -836,7 +830,7 @@ static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, /* * Tells the daemon whether it can umount the autofs mount. */ -static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p) +static inline int autofs_ask_umount(struct vfsmount *mnt, int __user *p) { int status = 0; @@ -850,14 +844,14 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p) return status; } -/* Identify autofs4_dentries - this is so we can tell if there's +/* Identify autofs_dentries - this is so we can tell if there's * an extra dentry refcount or not. We only hold a refcount on the * dentry if its non-negative (ie, d_inode != NULL) */ -int is_autofs4_dentry(struct dentry *dentry) +int is_autofs_dentry(struct dentry *dentry) { return dentry && d_really_is_positive(dentry) && - dentry->d_op == &autofs4_dentry_operations && + dentry->d_op == &autofs_dentry_operations && dentry->d_fsdata != NULL; } @@ -865,10 +859,10 @@ int is_autofs4_dentry(struct dentry *dentry) * ioctl()'s on the root directory is the chief method for the daemon to * generate kernel reactions */ -static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp, +static int autofs_root_ioctl_unlocked(struct inode *inode, struct file *filp, unsigned int cmd, unsigned long arg) { - struct autofs_sb_info *sbi = autofs4_sbi(inode->i_sb); + struct autofs_sb_info *sbi = autofs_sbi(inode->i_sb); void __user *p = (void __user *)arg; pr_debug("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n", @@ -878,64 +872,63 @@ static int autofs4_root_ioctl_unlocked(struct inode *inode, struct file *filp, _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT) return -ENOTTY; - if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) + if (!autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) return -EPERM; switch (cmd) { case AUTOFS_IOC_READY: /* Wait queue: go ahead and retry */ - return autofs4_wait_release(sbi, (autofs_wqt_t) arg, 0); + return autofs_wait_release(sbi, (autofs_wqt_t) arg, 0); case AUTOFS_IOC_FAIL: /* Wait queue: fail with ENOENT */ - return autofs4_wait_release(sbi, (autofs_wqt_t) arg, -ENOENT); + return autofs_wait_release(sbi, (autofs_wqt_t) arg, -ENOENT); case AUTOFS_IOC_CATATONIC: /* Enter catatonic mode (daemon shutdown) */ - autofs4_catatonic_mode(sbi); + autofs_catatonic_mode(sbi); return 0; case AUTOFS_IOC_PROTOVER: /* Get protocol version */ - return autofs4_get_protover(sbi, p); + return autofs_get_protover(sbi, p); case AUTOFS_IOC_PROTOSUBVER: /* Get protocol sub version */ - return autofs4_get_protosubver(sbi, p); + return autofs_get_protosubver(sbi, p); case AUTOFS_IOC_SETTIMEOUT: - return autofs4_get_set_timeout(sbi, p); + return autofs_get_set_timeout(sbi, p); #ifdef CONFIG_COMPAT case AUTOFS_IOC_SETTIMEOUT32: - return autofs4_compat_get_set_timeout(sbi, p); + return autofs_compat_get_set_timeout(sbi, p); #endif case AUTOFS_IOC_ASKUMOUNT: - return autofs4_ask_umount(filp->f_path.mnt, p); + return autofs_ask_umount(filp->f_path.mnt, p); /* return a single thing to expire */ case AUTOFS_IOC_EXPIRE: - return autofs4_expire_run(inode->i_sb, - filp->f_path.mnt, sbi, p); + return autofs_expire_run(inode->i_sb, filp->f_path.mnt, sbi, p); /* same as above, but can send multiple expires through pipe */ case AUTOFS_IOC_EXPIRE_MULTI: - return autofs4_expire_multi(inode->i_sb, - filp->f_path.mnt, sbi, p); + return autofs_expire_multi(inode->i_sb, + filp->f_path.mnt, sbi, p); default: return -EINVAL; } } -static long autofs4_root_ioctl(struct file *filp, +static long autofs_root_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); - return autofs4_root_ioctl_unlocked(inode, filp, cmd, arg); + return autofs_root_ioctl_unlocked(inode, filp, cmd, arg); } #ifdef CONFIG_COMPAT -static long autofs4_root_compat_ioctl(struct file *filp, +static long autofs_root_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); int ret; if (cmd == AUTOFS_IOC_READY || cmd == AUTOFS_IOC_FAIL) - ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, arg); + ret = autofs_root_ioctl_unlocked(inode, filp, cmd, arg); else - ret = autofs4_root_ioctl_unlocked(inode, filp, cmd, + ret = autofs_root_ioctl_unlocked(inode, filp, cmd, (unsigned long) compat_ptr(arg)); return ret; diff --git a/fs/autofs4/symlink.c b/fs/autofs/symlink.c index ab0b4285a202..aad3902c0cc1 100644 --- a/fs/autofs4/symlink.c +++ b/fs/autofs/symlink.c @@ -8,22 +8,22 @@ #include "autofs_i.h" -static const char *autofs4_get_link(struct dentry *dentry, - struct inode *inode, - struct delayed_call *done) +static const char *autofs_get_link(struct dentry *dentry, + struct inode *inode, + struct delayed_call *done) { struct autofs_sb_info *sbi; struct autofs_info *ino; if (!dentry) return ERR_PTR(-ECHILD); - sbi = autofs4_sbi(dentry->d_sb); - ino = autofs4_dentry_ino(dentry); - if (ino && !autofs4_oz_mode(sbi)) + sbi = autofs_sbi(dentry->d_sb); + ino = autofs_dentry_ino(dentry); + if (ino && !autofs_oz_mode(sbi)) ino->last_used = jiffies; return d_inode(dentry)->i_private; } -const struct inode_operations autofs4_symlink_inode_operations = { - .get_link = autofs4_get_link +const struct inode_operations autofs_symlink_inode_operations = { + .get_link = autofs_get_link }; diff --git a/fs/autofs4/waitq.c b/fs/autofs/waitq.c index be9c3dc048ab..f6385c6ef0a5 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs/waitq.c @@ -7,19 +7,15 @@ * option, any later version, incorporated herein by reference. */ -#include <linux/slab.h> -#include <linux/time.h> -#include <linux/signal.h> #include <linux/sched/signal.h> -#include <linux/file.h> #include "autofs_i.h" /* We make this a static variable rather than a part of the superblock; it * is better if we don't reassign numbers easily even across filesystems */ -static autofs_wqt_t autofs4_next_wait_queue = 1; +static autofs_wqt_t autofs_next_wait_queue = 1; -void autofs4_catatonic_mode(struct autofs_sb_info *sbi) +void autofs_catatonic_mode(struct autofs_sb_info *sbi) { struct autofs_wait_queue *wq, *nwq; @@ -49,8 +45,8 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi) mutex_unlock(&sbi->wq_mutex); } -static int autofs4_write(struct autofs_sb_info *sbi, - struct file *file, const void *addr, int bytes) +static int autofs_write(struct autofs_sb_info *sbi, + struct file *file, const void *addr, int bytes) { unsigned long sigpipe, flags; const char *data = (const char *)addr; @@ -82,7 +78,7 @@ static int autofs4_write(struct autofs_sb_info *sbi, return bytes == 0 ? 0 : wr < 0 ? wr : -EIO; } -static void autofs4_notify_daemon(struct autofs_sb_info *sbi, +static void autofs_notify_daemon(struct autofs_sb_info *sbi, struct autofs_wait_queue *wq, int type) { @@ -167,23 +163,23 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, mutex_unlock(&sbi->wq_mutex); - switch (ret = autofs4_write(sbi, pipe, &pkt, pktsz)) { + switch (ret = autofs_write(sbi, pipe, &pkt, pktsz)) { case 0: break; case -ENOMEM: case -ERESTARTSYS: /* Just fail this one */ - autofs4_wait_release(sbi, wq->wait_queue_token, ret); + autofs_wait_release(sbi, wq->wait_queue_token, ret); break; default: - autofs4_catatonic_mode(sbi); + autofs_catatonic_mode(sbi); break; } fput(pipe); } -static int autofs4_getpath(struct autofs_sb_info *sbi, - struct dentry *dentry, char **name) +static int autofs_getpath(struct autofs_sb_info *sbi, + struct dentry *dentry, char *name) { struct dentry *root = sbi->sb->s_root; struct dentry *tmp; @@ -193,7 +189,7 @@ static int autofs4_getpath(struct autofs_sb_info *sbi, unsigned seq; rename_retry: - buf = *name; + buf = name; len = 0; seq = read_seqbegin(&rename_lock); @@ -228,7 +224,7 @@ rename_retry: } static struct autofs_wait_queue * -autofs4_find_wait(struct autofs_sb_info *sbi, const struct qstr *qstr) +autofs_find_wait(struct autofs_sb_info *sbi, const struct qstr *qstr) { struct autofs_wait_queue *wq; @@ -263,7 +259,7 @@ static int validate_request(struct autofs_wait_queue **wait, return -ENOENT; /* Wait in progress, continue; */ - wq = autofs4_find_wait(sbi, qstr); + wq = autofs_find_wait(sbi, qstr); if (wq) { *wait = wq; return 1; @@ -272,7 +268,7 @@ static int validate_request(struct autofs_wait_queue **wait, *wait = NULL; /* If we don't yet have any info this is a new request */ - ino = autofs4_dentry_ino(dentry); + ino = autofs_dentry_ino(dentry); if (!ino) return 1; @@ -297,7 +293,7 @@ static int validate_request(struct autofs_wait_queue **wait, if (sbi->catatonic) return -ENOENT; - wq = autofs4_find_wait(sbi, qstr); + wq = autofs_find_wait(sbi, qstr); if (wq) { *wait = wq; return 1; @@ -351,7 +347,7 @@ static int validate_request(struct autofs_wait_queue **wait, return 1; } -int autofs4_wait(struct autofs_sb_info *sbi, +int autofs_wait(struct autofs_sb_info *sbi, const struct path *path, enum autofs_notify notify) { struct dentry *dentry = path->dentry; @@ -399,7 +395,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, if (IS_ROOT(dentry) && autofs_type_trigger(sbi->type)) qstr.len = sprintf(name, "%p", dentry); else { - qstr.len = autofs4_getpath(sbi, dentry, &name); + qstr.len = autofs_getpath(sbi, dentry, name); if (!qstr.len) { kfree(name); return -ENOENT; @@ -430,15 +426,15 @@ int autofs4_wait(struct autofs_sb_info *sbi, return -ENOMEM; } - wq->wait_queue_token = autofs4_next_wait_queue; - if (++autofs4_next_wait_queue == 0) - autofs4_next_wait_queue = 1; + wq->wait_queue_token = autofs_next_wait_queue; + if (++autofs_next_wait_queue == 0) + autofs_next_wait_queue = 1; wq->next = sbi->queues; sbi->queues = wq; init_waitqueue_head(&wq->queue); memcpy(&wq->name, &qstr, sizeof(struct qstr)); - wq->dev = autofs4_get_dev(sbi); - wq->ino = autofs4_get_ino(sbi); + wq->dev = autofs_get_dev(sbi); + wq->ino = autofs_get_ino(sbi); wq->uid = current_uid(); wq->gid = current_gid(); wq->pid = pid; @@ -467,9 +463,9 @@ int autofs4_wait(struct autofs_sb_info *sbi, wq->name.name, notify); /* - * autofs4_notify_daemon() may block; it will unlock ->wq_mutex + * autofs_notify_daemon() may block; it will unlock ->wq_mutex */ - autofs4_notify_daemon(sbi, wq, type); + autofs_notify_daemon(sbi, wq, type); } else { wq->wait_ctr++; pr_debug("existing wait id = 0x%08lx, name = %.*s, nfy=%d\n", @@ -500,12 +496,12 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *de = NULL; /* direct mount or browsable map */ - ino = autofs4_dentry_ino(dentry); + ino = autofs_dentry_ino(dentry); if (!ino) { /* If not lookup actual dentry used */ de = d_lookup(dentry->d_parent, &dentry->d_name); if (de) - ino = autofs4_dentry_ino(de); + ino = autofs_dentry_ino(de); } /* Set mount requester */ @@ -530,7 +526,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, } -int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_token, int status) +int autofs_wait_release(struct autofs_sb_info *sbi, + autofs_wqt_t wait_queue_token, int status) { struct autofs_wait_queue *wq, **wql; diff --git a/fs/autofs4/Kconfig b/fs/autofs4/Kconfig index 44727bf18297..99fda4d6da25 100644 --- a/fs/autofs4/Kconfig +++ b/fs/autofs4/Kconfig @@ -1,5 +1,7 @@ config AUTOFS4_FS - tristate "Kernel automounter version 4 support (also supports v3)" + tristate "Kernel automounter version 4 support (also supports v3 and v5)" + default n + depends on AUTOFS_FS = n help The automounter is a tool to automatically mount remote file systems on demand. This implementation is partially kernel-based to reduce @@ -7,14 +9,38 @@ config AUTOFS4_FS automounter (amd), which is a pure user space daemon. To use the automounter you need the user-space tools from - <https://www.kernel.org/pub/linux/daemons/autofs/v4/>; you also - want to answer Y to "NFS file system support", below. + <https://www.kernel.org/pub/linux/daemons/autofs/>; you also want + to answer Y to "NFS file system support", below. - To compile this support as a module, choose M here: the module will be - called autofs4. You will need to add "alias autofs autofs4" to your - modules configuration file. + This module is in the process of being renamed from autofs4 to + autofs. Since autofs is now the only module that provides the + autofs file system the module is not version 4 specific. - If you are not a part of a fairly large, distributed network or - don't have a laptop which needs to dynamically reconfigure to the - local network, you probably do not need an automounter, and can say - N here. + The autofs4 module is now built from the source located in + fs/autofs. The autofs4 directory and its configuration entry + will be removed two kernel versions from the inclusion of this + change. + + Changes that will need to be made should be limited to: + - source include statments should be changed from autofs_fs4.h to + autofs_fs.h since these two header files have been merged. + - user space scripts that manually load autofs4.ko should be + changed to load autofs.ko. But since the module directory name + and the module name are the same as the file system name there + is no need to manually load module. + - any "alias autofs autofs4" will need to be removed. + - due to the autofs4 module directory name not being the same as + its file system name autoloading didn't work properly. Because + of this kernel configurations would often build the module into + the kernel. This may have resulted in selinux policies that will + prevent the autofs module from autoloading and will need to be + updated. + + Please configure AUTOFS_FS instead of AUTOFS4_FS from now on. + + NOTE: Since the modules autofs and autofs4 use the same file system + type name of "autofs" only one can be built. The "depends" + above will result in AUTOFS4_FS not appearing in .config for + any setting of AUTOFS_FS other than n and AUTOFS4_FS will + appear under the AUTOFS_FS entry otherwise which is intended + to draw attention to the module rename change. diff --git a/fs/autofs4/Makefile b/fs/autofs4/Makefile index a811c1f7d9ab..417dd726d9ef 100644 --- a/fs/autofs4/Makefile +++ b/fs/autofs4/Makefile @@ -4,4 +4,6 @@ obj-$(CONFIG_AUTOFS4_FS) += autofs4.o -autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o +autofs4-objs := ../autofs/init.o ../autofs/inode.o ../autofs/root.o \ + ../autofs/symlink.o ../autofs/waitq.o ../autofs/expire.o \ + ../autofs/dev-ioctl.o diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index a41b48f82a70..4de191563261 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -387,8 +387,13 @@ static Node *create_entry(const char __user *buffer, size_t count) s = strchr(p, del); if (!s) goto einval; - *s++ = '\0'; - e->offset = simple_strtoul(p, &p, 10); + *s = '\0'; + if (p != s) { + int r = kstrtoint(p, 10, &e->offset); + if (r != 0 || e->offset < 0) + goto einval; + } + p = s; if (*p++) goto einval; pr_debug("register: offset: %#x\n", e->offset); @@ -428,7 +433,8 @@ static Node *create_entry(const char __user *buffer, size_t count) if (e->mask && string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size) goto einval; - if (e->size + e->offset > BINPRM_BUF_SIZE) + if (e->size > BINPRM_BUF_SIZE || + BINPRM_BUF_SIZE - e->size < e->offset) goto einval; pr_debug("register: magic/mask length: %i\n", e->size); if (USE_DEBUG) { diff --git a/fs/block_dev.c b/fs/block_dev.c index bef6934b6189..05e12aea2404 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -216,6 +216,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, bio.bi_write_hint = iocb->ki_hint; bio.bi_private = current; bio.bi_end_io = blkdev_bio_end_io_simple; + bio.bi_ioprio = iocb->ki_ioprio; ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) @@ -355,6 +356,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio->bi_write_hint = iocb->ki_hint; bio->bi_private = dio; bio->bi_end_io = blkdev_bio_end_io; + bio->bi_ioprio = iocb->ki_ioprio; ret = bio_iov_iter_get_pages(bio, iter); if (unlikely(ret)) { diff --git a/fs/cifs/cifsacl.h b/fs/cifs/cifsacl.h index 4f3884835267..dd95a6fa24bf 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/cifs/cifsacl.h @@ -98,4 +98,18 @@ struct cifs_ace { struct cifs_sid sid; /* ie UUID of user or group who gets these perms */ } __attribute__((packed)); +/* + * Minimum security identifier can be one for system defined Users + * and Groups such as NULL SID and World or Built-in accounts such + * as Administrator and Guest and consists of + * Revision + Num (Sub)Auths + Authority + Domain (one Subauthority) + */ +#define MIN_SID_LEN (1 + 1 + 6 + 4) /* in bytes */ + +/* + * Minimum security descriptor can be one without any SACL and DACL and can + * consist of revision, type, and two sids of minimum size for owner and group + */ +#define MIN_SEC_DESC_LEN (sizeof(struct cifs_ntsd) + (2 * MIN_SID_LEN)) + #endif /* _CIFSACL_H */ diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index a6ef088e057b..937251cc61c0 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -37,6 +37,7 @@ #include <crypto/aead.h> int __cifs_calc_signature(struct smb_rqst *rqst, + int start, struct TCP_Server_Info *server, char *signature, struct shash_desc *shash) { @@ -45,10 +46,7 @@ int __cifs_calc_signature(struct smb_rqst *rqst, struct kvec *iov = rqst->rq_iov; int n_vec = rqst->rq_nvec; - if (n_vec < 2 || iov[0].iov_len != 4) - return -EIO; - - for (i = 1; i < n_vec; i++) { + for (i = start; i < n_vec; i++) { if (iov[i].iov_len == 0) continue; if (iov[i].iov_base == NULL) { @@ -68,11 +66,12 @@ int __cifs_calc_signature(struct smb_rqst *rqst, /* now hash over the rq_pages array */ for (i = 0; i < rqst->rq_npages; i++) { - void *kaddr = kmap(rqst->rq_pages[i]); - size_t len = rqst->rq_pagesz; + void *kaddr; + unsigned int len, offset; + + rqst_page_get_length(rqst, i, &len, &offset); - if (i == rqst->rq_npages - 1) - len = rqst->rq_tailsz; + kaddr = (char *) kmap(rqst->rq_pages[i]) + offset; crypto_shash_update(shash, kaddr, len); @@ -119,7 +118,7 @@ static int cifs_calc_signature(struct smb_rqst *rqst, return rc; } - return __cifs_calc_signature(rqst, server, signature, + return __cifs_calc_signature(rqst, 1, server, signature, &server->secmech.sdescmd5->shash); } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index eb7b6573f322..d5aa7ae917bf 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -698,8 +698,8 @@ static int cifs_set_super(struct super_block *sb, void *data) } static struct dentry * -cifs_do_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +cifs_smb3_do_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, bool is_smb3) { int rc; struct super_block *sb; @@ -710,7 +710,7 @@ cifs_do_mount(struct file_system_type *fs_type, cifs_dbg(FYI, "Devname: %s flags: %d\n", dev_name, flags); - volume_info = cifs_get_volume_info((char *)data, dev_name); + volume_info = cifs_get_volume_info((char *)data, dev_name, is_smb3); if (IS_ERR(volume_info)) return ERR_CAST(volume_info); @@ -790,6 +790,20 @@ out_nls: goto out; } +static struct dentry * +smb3_do_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return cifs_smb3_do_mount(fs_type, flags, dev_name, data, true); +} + +static struct dentry * +cifs_do_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return cifs_smb3_do_mount(fs_type, flags, dev_name, data, false); +} + static ssize_t cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) { @@ -925,7 +939,7 @@ MODULE_ALIAS_FS("cifs"); static struct file_system_type smb3_fs_type = { .owner = THIS_MODULE, .name = "smb3", - .mount = cifs_do_mount, + .mount = smb3_do_mount, .kill_sb = cifs_kill_sb, /* .fs_flags */ }; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 08d1cdd96701..1efa2e65bc1a 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1019,6 +1019,12 @@ tlink_tcon(struct tcon_link *tlink) return tlink->tl_tcon; } +static inline struct tcon_link * +cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb) +{ + return cifs_sb->master_tlink; +} + extern void cifs_put_tlink(struct tcon_link *tlink); static inline struct tcon_link * diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 7933c5f9c076..4e0d183c3d10 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -211,7 +211,7 @@ extern int cifs_setup_cifs_sb(struct smb_vol *pvolume_info, extern int cifs_match_super(struct super_block *, void *); extern void cifs_cleanup_volume_info(struct smb_vol *pvolume_info); extern struct smb_vol *cifs_get_volume_info(char *mount_data, - const char *devname); + const char *devname, bool is_smb3); extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *); extern void cifs_umount(struct cifs_sb_info *); extern void cifs_mark_open_files_invalid(struct cifs_tcon *tcon); @@ -544,7 +544,7 @@ int cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, unsigned int *pbytes_written); -int __cifs_calc_signature(struct smb_rqst *rqst, +int __cifs_calc_signature(struct smb_rqst *rqst, int start, struct TCP_Server_Info *server, char *signature, struct shash_desc *shash); enum securityEnum cifs_select_sectype(struct TCP_Server_Info *, @@ -557,4 +557,7 @@ int cifs_alloc_hash(const char *name, struct crypto_shash **shash, struct sdesc **sdesc); void cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc); +extern void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, + unsigned int *len, unsigned int *offset); + #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index e5a2fe7f0dd4..96645a7d8f27 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -320,7 +320,7 @@ static int generic_ip_connect(struct TCP_Server_Info *server); static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); static void cifs_prune_tlinks(struct work_struct *work); static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, - const char *devname); + const char *devname, bool is_smb3); /* * cifs tcp session reconnection @@ -1166,7 +1166,7 @@ cifs_parse_cache_flavor(char *value, struct smb_vol *vol) } static int -cifs_parse_smb_version(char *value, struct smb_vol *vol) +cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3) { substring_t args[MAX_OPT_ARGS]; @@ -1176,6 +1176,10 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol) cifs_dbg(VFS, "mount with legacy dialect disabled\n"); return 1; } + if (is_smb3) { + cifs_dbg(VFS, "vers=1.0 (cifs) not permitted when mounting with smb3\n"); + return 1; + } vol->ops = &smb1_operations; vol->vals = &smb1_values; break; @@ -1184,6 +1188,10 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol) cifs_dbg(VFS, "mount with legacy dialect disabled\n"); return 1; } + if (is_smb3) { + cifs_dbg(VFS, "vers=2.0 not permitted when mounting with smb3\n"); + return 1; + } vol->ops = &smb20_operations; vol->vals = &smb20_values; break; @@ -1272,7 +1280,7 @@ cifs_parse_devname(const char *devname, struct smb_vol *vol) static int cifs_parse_mount_options(const char *mountdata, const char *devname, - struct smb_vol *vol) + struct smb_vol *vol, bool is_smb3) { char *data, *end; char *mountdata_copy = NULL, *options; @@ -1985,7 +1993,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (string == NULL) goto out_nomem; - if (cifs_parse_smb_version(string, vol) != 0) + if (cifs_parse_smb_version(string, vol, is_smb3) != 0) goto cifs_parse_mount_err; got_version = true; break; @@ -3116,12 +3124,6 @@ cifs_put_tlink(struct tcon_link *tlink) return; } -static inline struct tcon_link * -cifs_sb_master_tlink(struct cifs_sb_info *cifs_sb) -{ - return cifs_sb->master_tlink; -} - static int compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) { @@ -3803,7 +3805,7 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, } else { cleanup_volume_info_contents(volume_info); rc = cifs_setup_volume_info(volume_info, mdata, - fake_devname); + fake_devname, false); } kfree(fake_devname); kfree(cifs_sb->mountdata); @@ -3816,11 +3818,11 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, - const char *devname) + const char *devname, bool is_smb3) { int rc = 0; - if (cifs_parse_mount_options(mount_data, devname, volume_info)) + if (cifs_parse_mount_options(mount_data, devname, volume_info, is_smb3)) return -EINVAL; if (volume_info->nullauth) { @@ -3854,7 +3856,7 @@ cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, } struct smb_vol * -cifs_get_volume_info(char *mount_data, const char *devname) +cifs_get_volume_info(char *mount_data, const char *devname, bool is_smb3) { int rc; struct smb_vol *volume_info; @@ -3863,7 +3865,7 @@ cifs_get_volume_info(char *mount_data, const char *devname) if (!volume_info) return ERR_PTR(-ENOMEM); - rc = cifs_setup_volume_info(volume_info, mount_data, devname); + rc = cifs_setup_volume_info(volume_info, mount_data, devname, is_smb3); if (rc) { cifs_cleanup_volume_info(volume_info); volume_info = ERR_PTR(rc); diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 889a840172eb..de41f96aba49 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -421,7 +421,8 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, return -ENOMEM; } - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, pfile_info, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, pfile_info, NULL, + NULL); if (rc) goto qmf_out_open_fail; @@ -478,7 +479,8 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, + NULL); if (rc) { kfree(utf16_path); return rc; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index aba3fc3058da..f90d4ad6624c 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -905,3 +905,20 @@ cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc) crypto_free_shash(*shash); *shash = NULL; } + +/** + * rqst_page_get_length - obtain the length and offset for a page in smb_rqst + * Input: rqst - a smb_rqst, page - a page index for rqst + * Output: *len - the length for this page, *offset - the offset for this page + */ +void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, + unsigned int *len, unsigned int *offset) +{ + *len = rqst->rq_pagesz; + *offset = (page == 0) ? rqst->rq_offset : 0; + + if (rqst->rq_npages == 1 || page == rqst->rq_npages-1) + *len = rqst->rq_tailsz; + else if (page == 0) + *len = rqst->rq_pagesz - rqst->rq_offset; +} diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 12af5dba742b..788412675723 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -64,7 +64,8 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE); - rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL); + rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL, + NULL); if (rc) goto out; diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index a6e786e39248..d01ad706d7fc 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -71,7 +71,8 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, + NULL); if (rc) { kfree(utf16_path); return rc; diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index cb5728e3d87d..e2bec47c6845 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -453,8 +453,10 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb) start_of_path = from + 1; #ifdef CONFIG_CIFS_SMB311 /* SMB311 POSIX extensions paths do not include leading slash */ - else if (cifs_sb_master_tcon(cifs_sb)->posix_extensions) + else if (cifs_sb_master_tlink(cifs_sb) && + cifs_sb_master_tcon(cifs_sb)->posix_extensions) { start_of_path = from + 1; + } #endif /* 311 */ else start_of_path = from; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 950d0ab2cc61..b15f5957d645 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -348,7 +348,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) oparams.fid = pfid; oparams.reconnect = false; - rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparams, &srch_path, &oplock, NULL, NULL, NULL); if (rc == 0) { memcpy(tcon->prfid, pfid, sizeof(struct cifs_fid)); tcon->valid_root_fid = true; @@ -375,7 +375,8 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) oparms.reconnect = false; if (no_cached_open) - rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, + NULL); else rc = open_shroot(xid, tcon, &fid); @@ -413,7 +414,7 @@ smb2_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon) oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL); if (rc) return; @@ -449,7 +450,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); if (rc) { kfree(utf16_path); return rc; @@ -598,7 +599,7 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); kfree(utf16_path); if (rc) { cifs_dbg(FYI, "open failed rc=%d\n", rc); @@ -677,7 +678,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); kfree(utf16_path); if (rc) { cifs_dbg(FYI, "open failed rc=%d\n", rc); @@ -1261,7 +1262,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); kfree(utf16_path); if (rc) { cifs_dbg(FYI, "open dir failed rc=%d\n", rc); @@ -1361,7 +1362,7 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL); if (rc) return rc; buf->f_type = SMB2_MAGIC_NUMBER; @@ -1515,7 +1516,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_fid fid; struct kvec err_iov = {NULL, 0}; - struct smb2_err_rsp *err_buf; + struct smb2_err_rsp *err_buf = NULL; + int resp_buftype; struct smb2_symlink_err_rsp *symlink; unsigned int sub_len; unsigned int sub_offset; @@ -1535,18 +1537,18 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov); - + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov, + &resp_buftype); if (!rc || !err_iov.iov_base) { - kfree(utf16_path); - return -ENOENT; + rc = -ENOENT; + goto querty_exit; } err_buf = err_iov.iov_base; if (le32_to_cpu(err_buf->ByteCount) < sizeof(struct smb2_symlink_err_rsp) || err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE) { - kfree(utf16_path); - return -ENOENT; + rc = -ENOENT; + goto querty_exit; } /* open must fail on symlink - reset rc */ @@ -1558,25 +1560,28 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, print_offset = le16_to_cpu(symlink->PrintNameOffset); if (err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE + sub_offset + sub_len) { - kfree(utf16_path); - return -ENOENT; + rc = -ENOENT; + goto querty_exit; } if (err_iov.iov_len < SMB2_SYMLINK_STRUCT_SIZE + print_offset + print_len) { - kfree(utf16_path); - return -ENOENT; + rc = -ENOENT; + goto querty_exit; } *target_path = cifs_strndup_from_utf16( (char *)symlink->PathBuffer + sub_offset, sub_len, true, cifs_sb->local_nls); if (!(*target_path)) { - kfree(utf16_path); - return -ENOMEM; + rc = -ENOMEM; + goto querty_exit; } convert_delimiter(*target_path, '/'); cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path); + + querty_exit: + free_rsp_buf(resp_buftype, err_buf); kfree(utf16_path); return rc; } @@ -1649,7 +1654,7 @@ get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); kfree(utf16_path); if (!rc) { rc = SMB2_query_acl(xid, tlink_tcon(tlink), fid.persistent_fid, @@ -1712,7 +1717,7 @@ set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL); + rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); kfree(utf16_path); if (!rc) { rc = SMB2_set_acl(xid, tlink_tcon(tlink), fid.persistent_fid, @@ -2189,9 +2194,10 @@ init_sg(struct smb_rqst *rqst, u8 *sign) smb2_sg_set_buf(&sg[i], rqst->rq_iov[i+1].iov_base, rqst->rq_iov[i+1].iov_len); for (j = 0; i < sg_len - 1; i++, j++) { - unsigned int len = (j < rqst->rq_npages - 1) ? rqst->rq_pagesz - : rqst->rq_tailsz; - sg_set_page(&sg[i], rqst->rq_pages[j], len, 0); + unsigned int len, offset; + + rqst_page_get_length(rqst, j, &len, &offset); + sg_set_page(&sg[i], rqst->rq_pages[j], len, offset); } smb2_sg_set_buf(&sg[sg_len - 1], sign, SMB2_SIGNATURE_SIZE); return sg; @@ -2229,7 +2235,7 @@ static int crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc) { struct smb2_transform_hdr *tr_hdr = - (struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base; + (struct smb2_transform_hdr *)rqst->rq_iov[1].iov_base; unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int rc = 0; struct scatterlist *sg; @@ -2338,6 +2344,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq, return rc; new_rq->rq_pages = pages; + new_rq->rq_offset = old_rq->rq_offset; new_rq->rq_npages = old_rq->rq_npages; new_rq->rq_pagesz = old_rq->rq_pagesz; new_rq->rq_tailsz = old_rq->rq_tailsz; @@ -2379,10 +2386,14 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq, /* copy pages form the old */ for (i = 0; i < npages; i++) { - char *dst = kmap(new_rq->rq_pages[i]); - char *src = kmap(old_rq->rq_pages[i]); - unsigned int len = (i < npages - 1) ? new_rq->rq_pagesz : - new_rq->rq_tailsz; + char *dst, *src; + unsigned int offset, len; + + rqst_page_get_length(new_rq, i, &len, &offset); + + dst = (char *) kmap(new_rq->rq_pages[i]) + offset; + src = (char *) kmap(old_rq->rq_pages[i]) + offset; + memcpy(dst, src, len); kunmap(new_rq->rq_pages[i]); kunmap(old_rq->rq_pages[i]); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 281fbc1dc720..48e2004c75fb 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1889,7 +1889,7 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len, int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, __u8 *oplock, struct smb2_file_all_info *buf, - struct kvec *err_iov) + struct kvec *err_iov, int *buftype) { struct smb2_create_req *req; struct smb2_create_rsp *rsp; @@ -2052,6 +2052,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, cifs_stats_fail_inc(tcon, SMB2_CREATE_HE); if (err_iov && rsp) { *err_iov = rsp_iov; + *buftype = resp_buftype; resp_buftype = CIFS_NO_BUFFER; rsp = NULL; } @@ -2492,8 +2493,7 @@ SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon, return query_info(xid, tcon, persistent_fid, volatile_fid, 0, SMB2_O_INFO_SECURITY, additional_info, - SMB2_MAX_BUFFER_SIZE, - sizeof(struct smb2_file_all_info), data, plen); + SMB2_MAX_BUFFER_SIZE, MIN_SEC_DESC_LEN, data, plen); } int @@ -2721,8 +2721,8 @@ smb2_new_read_req(void **buf, unsigned int *total_len, rdata->mr = smbd_register_mr( server->smbd_conn, rdata->pages, - rdata->nr_pages, rdata->tailsz, - true, need_invalidate); + rdata->nr_pages, rdata->page_offset, + rdata->tailsz, true, need_invalidate); if (!rdata->mr) return -ENOBUFS; @@ -3108,16 +3108,22 @@ smb2_async_writev(struct cifs_writedata *wdata, wdata->mr = smbd_register_mr( server->smbd_conn, wdata->pages, - wdata->nr_pages, wdata->tailsz, - false, need_invalidate); + wdata->nr_pages, wdata->page_offset, + wdata->tailsz, false, need_invalidate); if (!wdata->mr) { rc = -ENOBUFS; goto async_writev_out; } req->Length = 0; req->DataOffset = 0; - req->RemainingBytes = - cpu_to_le32((wdata->nr_pages-1)*PAGE_SIZE + wdata->tailsz); + if (wdata->nr_pages > 1) + req->RemainingBytes = + cpu_to_le32( + (wdata->nr_pages - 1) * wdata->pagesz - + wdata->page_offset + wdata->tailsz + ); + else + req->RemainingBytes = cpu_to_le32(wdata->tailsz); req->Channel = SMB2_CHANNEL_RDMA_V1_INVALIDATE; if (need_invalidate) req->Channel = SMB2_CHANNEL_RDMA_V1; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 908555b1c6b5..c84020057bd8 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -125,7 +125,7 @@ extern int SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon); extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, __u8 *oplock, struct smb2_file_all_info *buf, - struct kvec *err_iov); + struct kvec *err_iov, int *resp_buftype); extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data, u32 indatalen, diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 2c671123a6bf..349d5ccf854c 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -171,7 +171,9 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) unsigned char smb2_signature[SMB2_HMACSHA256_SIZE]; unsigned char *sigptr = smb2_signature; struct kvec *iov = rqst->rq_iov; - struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[1].iov_base; + int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0; + struct smb2_sync_hdr *shdr = + (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base; struct cifs_ses *ses; ses = smb2_find_smb_ses(server, shdr->SessionId); @@ -202,7 +204,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; } - rc = __cifs_calc_signature(rqst, server, sigptr, + rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr, &server->secmech.sdeschmacsha256->shash); if (!rc) @@ -412,7 +414,9 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) unsigned char smb3_signature[SMB2_CMACAES_SIZE]; unsigned char *sigptr = smb3_signature; struct kvec *iov = rqst->rq_iov; - struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[1].iov_base; + int iov_hdr_index = rqst->rq_nvec > 1 ? 1 : 0; + struct smb2_sync_hdr *shdr = + (struct smb2_sync_hdr *)iov[iov_hdr_index].iov_base; struct cifs_ses *ses; ses = smb2_find_smb_ses(server, shdr->SessionId); @@ -443,7 +447,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) return rc; } - rc = __cifs_calc_signature(rqst, server, sigptr, + rc = __cifs_calc_signature(rqst, iov_hdr_index, server, sigptr, &server->secmech.sdesccmacaes->shash); if (!rc) diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index c62f7c95683c..e459c97151b3 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -17,6 +17,7 @@ #include <linux/highmem.h> #include "smbdirect.h" #include "cifs_debug.h" +#include "cifsproto.h" static struct smbd_response *get_empty_queue_buffer( struct smbd_connection *info); @@ -2003,10 +2004,12 @@ read_rfc1002_done: * return value: actual data read */ static int smbd_recv_page(struct smbd_connection *info, - struct page *page, unsigned int to_read) + struct page *page, unsigned int page_offset, + unsigned int to_read) { int ret; char *to_address; + void *page_address; /* make sure we have the page ready for read */ ret = wait_event_interruptible( @@ -2014,16 +2017,17 @@ static int smbd_recv_page(struct smbd_connection *info, info->reassembly_data_length >= to_read || info->transport_status != SMBD_CONNECTED); if (ret) - return 0; + return ret; /* now we can read from reassembly queue and not sleep */ - to_address = kmap_atomic(page); + page_address = kmap_atomic(page); + to_address = (char *) page_address + page_offset; log_read(INFO, "reading from page=%p address=%p to_read=%d\n", page, to_address, to_read); ret = smbd_recv_buf(info, to_address, to_read); - kunmap_atomic(to_address); + kunmap_atomic(page_address); return ret; } @@ -2037,7 +2041,7 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) { char *buf; struct page *page; - unsigned int to_read; + unsigned int to_read, page_offset; int rc; info->smbd_recv_pending++; @@ -2051,15 +2055,16 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) case READ | ITER_BVEC: page = msg->msg_iter.bvec->bv_page; + page_offset = msg->msg_iter.bvec->bv_offset; to_read = msg->msg_iter.bvec->bv_len; - rc = smbd_recv_page(info, page, to_read); + rc = smbd_recv_page(info, page, page_offset, to_read); break; default: /* It's a bug in upper layer to get there */ cifs_dbg(VFS, "CIFS: invalid msg type %d\n", msg->msg_iter.type); - rc = -EIO; + rc = -EINVAL; } info->smbd_recv_pending--; @@ -2082,7 +2087,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) struct kvec vec; int nvecs; int size; - int buflen = 0, remaining_data_length; + unsigned int buflen = 0, remaining_data_length; int start, i, j; int max_iov_size = info->max_send_size - sizeof(struct smbd_data_transfer); @@ -2113,10 +2118,17 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) buflen += iov[i].iov_len; } - /* add in the page array if there is one */ + /* + * Add in the page array if there is one. The caller needs to set + * rq_tailsz to PAGE_SIZE when the buffer has multiple pages and + * ends at page boundary + */ if (rqst->rq_npages) { - buflen += rqst->rq_pagesz * (rqst->rq_npages - 1); - buflen += rqst->rq_tailsz; + if (rqst->rq_npages == 1) + buflen += rqst->rq_tailsz; + else + buflen += rqst->rq_pagesz * (rqst->rq_npages - 1) - + rqst->rq_offset + rqst->rq_tailsz; } if (buflen + sizeof(struct smbd_data_transfer) > @@ -2213,8 +2225,9 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) /* now sending pages if there are any */ for (i = 0; i < rqst->rq_npages; i++) { - buflen = (i == rqst->rq_npages-1) ? - rqst->rq_tailsz : rqst->rq_pagesz; + unsigned int offset; + + rqst_page_get_length(rqst, i, &buflen, &offset); nvecs = (buflen + max_iov_size - 1) / max_iov_size; log_write(INFO, "sending pages buflen=%d nvecs=%d\n", buflen, nvecs); @@ -2225,9 +2238,11 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) remaining_data_length -= size; log_write(INFO, "sending pages i=%d offset=%d size=%d" " remaining_data_length=%d\n", - i, j*max_iov_size, size, remaining_data_length); + i, j*max_iov_size+offset, size, + remaining_data_length); rc = smbd_post_send_page( - info, rqst->rq_pages[i], j*max_iov_size, + info, rqst->rq_pages[i], + j*max_iov_size + offset, size, remaining_data_length); if (rc) goto done; @@ -2284,37 +2299,37 @@ static void smbd_mr_recovery_work(struct work_struct *work) if (smbdirect_mr->state == MR_INVALIDATED || smbdirect_mr->state == MR_ERROR) { - if (smbdirect_mr->state == MR_INVALIDATED) { + /* recover this MR entry */ + rc = ib_dereg_mr(smbdirect_mr->mr); + if (rc) { + log_rdma_mr(ERR, + "ib_dereg_mr failed rc=%x\n", + rc); + smbd_disconnect_rdma_connection(info); + continue; + } + + smbdirect_mr->mr = ib_alloc_mr( + info->pd, info->mr_type, + info->max_frmr_depth); + if (IS_ERR(smbdirect_mr->mr)) { + log_rdma_mr(ERR, + "ib_alloc_mr failed mr_type=%x " + "max_frmr_depth=%x\n", + info->mr_type, + info->max_frmr_depth); + smbd_disconnect_rdma_connection(info); + continue; + } + + if (smbdirect_mr->state == MR_INVALIDATED) ib_dma_unmap_sg( info->id->device, smbdirect_mr->sgl, smbdirect_mr->sgl_count, smbdirect_mr->dir); - smbdirect_mr->state = MR_READY; - } else if (smbdirect_mr->state == MR_ERROR) { - - /* recover this MR entry */ - rc = ib_dereg_mr(smbdirect_mr->mr); - if (rc) { - log_rdma_mr(ERR, - "ib_dereg_mr failed rc=%x\n", - rc); - smbd_disconnect_rdma_connection(info); - } - smbdirect_mr->mr = ib_alloc_mr( - info->pd, info->mr_type, - info->max_frmr_depth); - if (IS_ERR(smbdirect_mr->mr)) { - log_rdma_mr(ERR, - "ib_alloc_mr failed mr_type=%x " - "max_frmr_depth=%x\n", - info->mr_type, - info->max_frmr_depth); - smbd_disconnect_rdma_connection(info); - } + smbdirect_mr->state = MR_READY; - smbdirect_mr->state = MR_READY; - } /* smbdirect_mr->state is updated by this function * and is read and updated by I/O issuing CPUs trying * to get a MR, the call to atomic_inc_return @@ -2460,7 +2475,7 @@ again: */ struct smbd_mr *smbd_register_mr( struct smbd_connection *info, struct page *pages[], int num_pages, - int tailsz, bool writing, bool need_invalidate) + int offset, int tailsz, bool writing, bool need_invalidate) { struct smbd_mr *smbdirect_mr; int rc, i; @@ -2483,17 +2498,31 @@ struct smbd_mr *smbd_register_mr( smbdirect_mr->sgl_count = num_pages; sg_init_table(smbdirect_mr->sgl, num_pages); - for (i = 0; i < num_pages - 1; i++) - sg_set_page(&smbdirect_mr->sgl[i], pages[i], PAGE_SIZE, 0); + log_rdma_mr(INFO, "num_pages=0x%x offset=0x%x tailsz=0x%x\n", + num_pages, offset, tailsz); + + if (num_pages == 1) { + sg_set_page(&smbdirect_mr->sgl[0], pages[0], tailsz, offset); + goto skip_multiple_pages; + } + /* We have at least two pages to register */ + sg_set_page( + &smbdirect_mr->sgl[0], pages[0], PAGE_SIZE - offset, offset); + i = 1; + while (i < num_pages - 1) { + sg_set_page(&smbdirect_mr->sgl[i], pages[i], PAGE_SIZE, 0); + i++; + } sg_set_page(&smbdirect_mr->sgl[i], pages[i], tailsz ? tailsz : PAGE_SIZE, 0); +skip_multiple_pages: dir = writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; smbdirect_mr->dir = dir; rc = ib_dma_map_sg(info->id->device, smbdirect_mr->sgl, num_pages, dir); if (!rc) { - log_rdma_mr(INFO, "ib_dma_map_sg num_pages=%x dir=%x rc=%x\n", + log_rdma_mr(ERR, "ib_dma_map_sg num_pages=%x dir=%x rc=%x\n", num_pages, dir, rc); goto dma_map_error; } @@ -2501,8 +2530,8 @@ struct smbd_mr *smbd_register_mr( rc = ib_map_mr_sg(smbdirect_mr->mr, smbdirect_mr->sgl, num_pages, NULL, PAGE_SIZE); if (rc != num_pages) { - log_rdma_mr(INFO, - "ib_map_mr_sg failed rc = %x num_pages = %x\n", + log_rdma_mr(ERR, + "ib_map_mr_sg failed rc = %d num_pages = %x\n", rc, num_pages); goto map_mr_error; } diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h index f9038daea194..1e419c21dc60 100644 --- a/fs/cifs/smbdirect.h +++ b/fs/cifs/smbdirect.h @@ -321,7 +321,7 @@ struct smbd_mr { /* Interfaces to register and deregister MR for RDMA read/write */ struct smbd_mr *smbd_register_mr( struct smbd_connection *info, struct page *pages[], int num_pages, - int tailsz, bool writing, bool need_invalidate); + int offset, int tailsz, bool writing, bool need_invalidate); int smbd_deregister_mr(struct smbd_mr *mr); #else diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e7254e386b79..24887a0898c0 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -212,10 +212,24 @@ rqst_len(struct smb_rqst *rqst) for (i = 0; i < rqst->rq_nvec; i++) buflen += iov[i].iov_len; - /* add in the page array if there is one */ + /* + * Add in the page array if there is one. The caller needs to make + * sure rq_offset and rq_tailsz are set correctly. If a buffer of + * multiple pages ends at page boundary, rq_tailsz needs to be set to + * PAGE_SIZE. + */ if (rqst->rq_npages) { - buflen += rqst->rq_pagesz * (rqst->rq_npages - 1); - buflen += rqst->rq_tailsz; + if (rqst->rq_npages == 1) + buflen += rqst->rq_tailsz; + else { + /* + * If there is more than one page, calculate the + * buffer length based on rq_offset and rq_tailsz + */ + buflen += rqst->rq_pagesz * (rqst->rq_npages - 1) - + rqst->rq_offset; + buflen += rqst->rq_tailsz; + } } return buflen; @@ -274,15 +288,13 @@ __smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst) /* now walk the page array and send each page in it */ for (i = 0; i < rqst->rq_npages; i++) { - size_t len = i == rqst->rq_npages - 1 - ? rqst->rq_tailsz - : rqst->rq_pagesz; - struct bio_vec bvec = { - .bv_page = rqst->rq_pages[i], - .bv_len = len - }; + struct bio_vec bvec; + + bvec.bv_page = rqst->rq_pages[i]; + rqst_page_get_length(rqst, i, &bvec.bv_len, &bvec.bv_offset); + iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC, - &bvec, 1, len); + &bvec, 1, bvec.bv_len); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) break; diff --git a/fs/compat.c b/fs/compat.c index 190b38b39d9e..4a0aaaf53217 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -16,79 +16,12 @@ */ #include <linux/compat.h> -#include <linux/ncp_mount.h> #include <linux/nfs4_mount.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/uaccess.h> #include "internal.h" -struct compat_ncp_mount_data { - compat_int_t version; - compat_uint_t ncp_fd; - __compat_uid_t mounted_uid; - compat_pid_t wdog_pid; - unsigned char mounted_vol[NCP_VOLNAME_LEN + 1]; - compat_uint_t time_out; - compat_uint_t retry_count; - compat_uint_t flags; - __compat_uid_t uid; - __compat_gid_t gid; - compat_mode_t file_mode; - compat_mode_t dir_mode; -}; - -struct compat_ncp_mount_data_v4 { - compat_int_t version; - compat_ulong_t flags; - compat_ulong_t mounted_uid; - compat_long_t wdog_pid; - compat_uint_t ncp_fd; - compat_uint_t time_out; - compat_uint_t retry_count; - compat_ulong_t uid; - compat_ulong_t gid; - compat_ulong_t file_mode; - compat_ulong_t dir_mode; -}; - -static void *do_ncp_super_data_conv(void *raw_data) -{ - int version = *(unsigned int *)raw_data; - - if (version == 3) { - struct compat_ncp_mount_data *c_n = raw_data; - struct ncp_mount_data *n = raw_data; - - n->dir_mode = c_n->dir_mode; - n->file_mode = c_n->file_mode; - n->gid = c_n->gid; - n->uid = c_n->uid; - memmove (n->mounted_vol, c_n->mounted_vol, (sizeof (c_n->mounted_vol) + 3 * sizeof (unsigned int))); - n->wdog_pid = c_n->wdog_pid; - n->mounted_uid = c_n->mounted_uid; - } else if (version == 4) { - struct compat_ncp_mount_data_v4 *c_n = raw_data; - struct ncp_mount_data_v4 *n = raw_data; - - n->dir_mode = c_n->dir_mode; - n->file_mode = c_n->file_mode; - n->gid = c_n->gid; - n->uid = c_n->uid; - n->retry_count = c_n->retry_count; - n->time_out = c_n->time_out; - n->ncp_fd = c_n->ncp_fd; - n->wdog_pid = c_n->wdog_pid; - n->mounted_uid = c_n->mounted_uid; - n->flags = c_n->flags; - } else if (version != 5) { - return NULL; - } - - return raw_data; -} - - struct compat_nfs_string { compat_uint_t len; compat_uptr_t data; @@ -154,7 +87,6 @@ static int do_nfs4_super_data_conv(void *raw_data) return 0; } -#define NCPFS_NAME "ncpfs" #define NFS4_NAME "nfs4" COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, @@ -183,9 +115,7 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, goto out2; if (kernel_type && options) { - if (!strcmp(kernel_type, NCPFS_NAME)) { - do_ncp_super_data_conv(options); - } else if (!strcmp(kernel_type, NFS4_NAME)) { + if (!strcmp(kernel_type, NFS4_NAME)) { retval = -EINVAL; if (do_nfs4_super_data_conv(options)) goto out3; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index ef80085ed564..9907475b4226 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -38,8 +38,6 @@ #include <linux/ppp-ioctl.h> #include <linux/if_pppox.h> #include <linux/mtio.h> -#include <linux/auto_fs.h> -#include <linux/auto_fs4.h> #include <linux/tty.h> #include <linux/vt_kern.h> #include <linux/fb.h> @@ -351,6 +351,19 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping, } } +static struct page *dax_busy_page(void *entry) +{ + unsigned long pfn; + + for_each_mapped_pfn(entry, pfn) { + struct page *page = pfn_to_page(pfn); + + if (page_ref_count(page) > 1) + return page; + } + return NULL; +} + /* * Find radix tree entry at given index. If it points to an exceptional entry, * return it with the radix tree entry locked. If the radix tree doesn't @@ -492,6 +505,90 @@ restart: return entry; } +/** + * dax_layout_busy_page - find first pinned page in @mapping + * @mapping: address space to scan for a page with ref count > 1 + * + * DAX requires ZONE_DEVICE mapped pages. These pages are never + * 'onlined' to the page allocator so they are considered idle when + * page->count == 1. A filesystem uses this interface to determine if + * any page in the mapping is busy, i.e. for DMA, or other + * get_user_pages() usages. + * + * It is expected that the filesystem is holding locks to block the + * establishment of new mappings in this address_space. I.e. it expects + * to be able to run unmap_mapping_range() and subsequently not race + * mapping_mapped() becoming true. + */ +struct page *dax_layout_busy_page(struct address_space *mapping) +{ + pgoff_t indices[PAGEVEC_SIZE]; + struct page *page = NULL; + struct pagevec pvec; + pgoff_t index, end; + unsigned i; + + /* + * In the 'limited' case get_user_pages() for dax is disabled. + */ + if (IS_ENABLED(CONFIG_FS_DAX_LIMITED)) + return NULL; + + if (!dax_mapping(mapping) || !mapping_mapped(mapping)) + return NULL; + + pagevec_init(&pvec); + index = 0; + end = -1; + + /* + * If we race get_user_pages_fast() here either we'll see the + * elevated page count in the pagevec_lookup and wait, or + * get_user_pages_fast() will see that the page it took a reference + * against is no longer mapped in the page tables and bail to the + * get_user_pages() slow path. The slow path is protected by + * pte_lock() and pmd_lock(). New references are not taken without + * holding those locks, and unmap_mapping_range() will not zero the + * pte or pmd without holding the respective lock, so we are + * guaranteed to either see new references or prevent new + * references from being established. + */ + unmap_mapping_range(mapping, 0, 0, 1); + + while (index < end && pagevec_lookup_entries(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE), + indices)) { + for (i = 0; i < pagevec_count(&pvec); i++) { + struct page *pvec_ent = pvec.pages[i]; + void *entry; + + index = indices[i]; + if (index >= end) + break; + + if (!radix_tree_exceptional_entry(pvec_ent)) + continue; + + xa_lock_irq(&mapping->i_pages); + entry = get_unlocked_mapping_entry(mapping, index, NULL); + if (entry) + page = dax_busy_page(entry); + put_unlocked_mapping_entry(mapping, index, entry); + xa_unlock_irq(&mapping->i_pages); + if (page) + break; + } + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); + index++; + + if (page) + break; + } + return page; +} +EXPORT_SYMBOL_GPL(dax_layout_busy_page); + static int __dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index, bool trunc) { @@ -905,14 +1002,13 @@ out: * If this page is ever written to we will re-fault and change the mapping to * point to real DAX storage instead. */ -static int dax_load_hole(struct address_space *mapping, void *entry, +static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry, struct vm_fault *vmf) { struct inode *inode = mapping->host; unsigned long vaddr = vmf->address; - int ret = VM_FAULT_NOPAGE; + vm_fault_t ret = VM_FAULT_NOPAGE; struct page *zero_page; - void *entry2; pfn_t pfn; zero_page = ZERO_PAGE(0); @@ -922,14 +1018,9 @@ static int dax_load_hole(struct address_space *mapping, void *entry, } pfn = page_to_pfn_t(zero_page); - entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn, - RADIX_DAX_ZERO_PAGE, false); - if (IS_ERR(entry2)) { - ret = VM_FAULT_SIGBUS; - goto out; - } - - vm_insert_mixed(vmf->vma, vaddr, pfn); + dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE, + false); + ret = vmf_insert_mixed(vmf->vma, vaddr, pfn); out: trace_dax_load_hole(inode, vmf, ret); return ret; @@ -991,6 +1082,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iov_iter *iter = data; loff_t end = pos + length, done = 0; ssize_t ret = 0; + size_t xfer; int id; if (iov_iter_rw(iter) == READ) { @@ -1054,18 +1146,20 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data, * vfs_write(), depending on which operation we are doing. */ if (iov_iter_rw(iter) == WRITE) - map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr, + xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); else - map_len = copy_to_iter(kaddr, map_len, iter); - if (map_len <= 0) { - ret = map_len ? map_len : -EFAULT; - break; - } + xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr, + map_len, iter); + + pos += xfer; + length -= xfer; + done += xfer; - pos += map_len; - length -= map_len; - done += map_len; + if (xfer == 0) + ret = -EFAULT; + if (xfer < map_len) + break; } dax_read_unlock(id); @@ -1112,7 +1206,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, } EXPORT_SYMBOL_GPL(dax_iomap_rw); -static int dax_fault_return(int error) +static vm_fault_t dax_fault_return(int error) { if (error == 0) return VM_FAULT_NOPAGE; @@ -1132,7 +1226,7 @@ static bool dax_fault_is_synchronous(unsigned long flags, && (iomap->flags & IOMAP_F_DIRTY); } -static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, +static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops) { struct vm_area_struct *vma = vmf->vma; @@ -1145,18 +1239,18 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, int error, major = 0; bool write = vmf->flags & FAULT_FLAG_WRITE; bool sync; - int vmf_ret = 0; + vm_fault_t ret = 0; void *entry; pfn_t pfn; - trace_dax_pte_fault(inode, vmf, vmf_ret); + trace_dax_pte_fault(inode, vmf, ret); /* * Check whether offset isn't beyond end of file now. Caller is supposed * to hold locks serializing us with truncate / punch hole so this is * a reliable test. */ if (pos >= i_size_read(inode)) { - vmf_ret = VM_FAULT_SIGBUS; + ret = VM_FAULT_SIGBUS; goto out; } @@ -1165,7 +1259,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, entry = grab_mapping_entry(mapping, vmf->pgoff, 0); if (IS_ERR(entry)) { - vmf_ret = dax_fault_return(PTR_ERR(entry)); + ret = dax_fault_return(PTR_ERR(entry)); goto out; } @@ -1176,7 +1270,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, * retried. */ if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) { - vmf_ret = VM_FAULT_NOPAGE; + ret = VM_FAULT_NOPAGE; goto unlock_entry; } @@ -1189,7 +1283,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, if (iomap_errp) *iomap_errp = error; if (error) { - vmf_ret = dax_fault_return(error); + ret = dax_fault_return(error); goto unlock_entry; } if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) { @@ -1219,9 +1313,9 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, goto error_finish_iomap; __SetPageUptodate(vmf->cow_page); - vmf_ret = finish_fault(vmf); - if (!vmf_ret) - vmf_ret = VM_FAULT_DONE_COW; + ret = finish_fault(vmf); + if (!ret) + ret = VM_FAULT_DONE_COW; goto finish_iomap; } @@ -1240,10 +1334,6 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn, 0, write && !sync); - if (IS_ERR(entry)) { - error = PTR_ERR(entry); - goto error_finish_iomap; - } /* * If we are doing synchronous page fault and inode needs fsync, @@ -1257,23 +1347,20 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, goto error_finish_iomap; } *pfnp = pfn; - vmf_ret = VM_FAULT_NEEDDSYNC | major; + ret = VM_FAULT_NEEDDSYNC | major; goto finish_iomap; } trace_dax_insert_mapping(inode, vmf, entry); if (write) - error = vm_insert_mixed_mkwrite(vma, vaddr, pfn); + ret = vmf_insert_mixed_mkwrite(vma, vaddr, pfn); else - error = vm_insert_mixed(vma, vaddr, pfn); + ret = vmf_insert_mixed(vma, vaddr, pfn); - /* -EBUSY is fine, somebody else faulted on the same PTE */ - if (error == -EBUSY) - error = 0; - break; + goto finish_iomap; case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (!write) { - vmf_ret = dax_load_hole(mapping, entry, vmf); + ret = dax_load_hole(mapping, entry, vmf); goto finish_iomap; } /*FALLTHRU*/ @@ -1284,12 +1371,12 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, } error_finish_iomap: - vmf_ret = dax_fault_return(error) | major; + ret = dax_fault_return(error); finish_iomap: if (ops->iomap_end) { int copied = PAGE_SIZE; - if (vmf_ret & VM_FAULT_ERROR) + if (ret & VM_FAULT_ERROR) copied = 0; /* * The fault is done by now and there's no way back (other @@ -1302,12 +1389,12 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, unlock_entry: put_locked_mapping_entry(mapping, vmf->pgoff); out: - trace_dax_pte_fault_done(inode, vmf, vmf_ret); - return vmf_ret; + trace_dax_pte_fault_done(inode, vmf, ret); + return ret | major; } #ifdef CONFIG_FS_DAX_PMD -static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, +static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, void *entry) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; @@ -1327,8 +1414,6 @@ static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, pfn = page_to_pfn_t(zero_page); ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false); - if (IS_ERR(ret)) - goto fallback; ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { @@ -1348,7 +1433,7 @@ fallback: return VM_FAULT_FALLBACK; } -static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, +static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, const struct iomap_ops *ops) { struct vm_area_struct *vma = vmf->vma; @@ -1358,7 +1443,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, bool sync; unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT; struct inode *inode = mapping->host; - int result = VM_FAULT_FALLBACK; + vm_fault_t result = VM_FAULT_FALLBACK; struct iomap iomap = { 0 }; pgoff_t max_pgoff, pgoff; void *entry; @@ -1450,8 +1535,6 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_PMD, write && !sync); - if (IS_ERR(entry)) - goto finish_iomap; /* * If we are doing synchronous page fault and inode needs fsync, @@ -1509,7 +1592,7 @@ out: return result; } #else -static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, +static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, const struct iomap_ops *ops) { return VM_FAULT_FALLBACK; @@ -1529,7 +1612,7 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, * has done all the necessary locking for page fault to proceed * successfully. */ -int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, +vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops) { switch (pe_size) { @@ -1553,14 +1636,14 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault); * DAX file. It takes care of marking corresponding radix tree entry as dirty * as well. */ -static int dax_insert_pfn_mkwrite(struct vm_fault *vmf, +static vm_fault_t dax_insert_pfn_mkwrite(struct vm_fault *vmf, enum page_entry_size pe_size, pfn_t pfn) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; void *entry, **slot; pgoff_t index = vmf->pgoff; - int vmf_ret, error; + vm_fault_t ret; xa_lock_irq(&mapping->i_pages); entry = get_unlocked_mapping_entry(mapping, index, &slot); @@ -1579,21 +1662,20 @@ static int dax_insert_pfn_mkwrite(struct vm_fault *vmf, xa_unlock_irq(&mapping->i_pages); switch (pe_size) { case PE_SIZE_PTE: - error = vm_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn); - vmf_ret = dax_fault_return(error); + ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn); break; #ifdef CONFIG_FS_DAX_PMD case PE_SIZE_PMD: - vmf_ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, + ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, pfn, true); break; #endif default: - vmf_ret = VM_FAULT_FALLBACK; + ret = VM_FAULT_FALLBACK; } put_locked_mapping_entry(mapping, index); - trace_dax_insert_pfn_mkwrite(mapping->host, vmf, vmf_ret); - return vmf_ret; + trace_dax_insert_pfn_mkwrite(mapping->host, vmf, ret); + return ret; } /** @@ -1606,8 +1688,8 @@ static int dax_insert_pfn_mkwrite(struct vm_fault *vmf, * stored persistently on the media and handles inserting of appropriate page * table entry. */ -int dax_finish_sync_fault(struct vm_fault *vmf, enum page_entry_size pe_size, - pfn_t pfn) +vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, + enum page_entry_size pe_size, pfn_t pfn) { int err; loff_t start = ((loff_t)vmf->pgoff) << PAGE_SHIFT; diff --git a/fs/exec.c b/fs/exec.c index 30a36c2a39bf..2d4e0075bd24 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1824,6 +1824,7 @@ static int __do_execve_file(int fd, struct filename *filename, current->fs->in_exec = 0; current->in_execve = 0; membarrier_execve(current); + rseq_execve(current); acct_update_integrals(current); task_numa_free(current); free_bprm(bprm); diff --git a/fs/fcntl.c b/fs/fcntl.c index c42169459298..12273b6ea56d 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -23,7 +23,7 @@ #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> -#include <linux/shmem_fs.h> +#include <linux/memfd.h> #include <linux/compat.h> #include <linux/poll.h> diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 2577ef1034ef..2a153aed4c19 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -26,8 +26,7 @@ #include "hpfs.h" #define EIOERROR EIO -#define EFSERROR EPERM -#define EMEMERROR ENOMEM +#define EFSERROR EUCLEAN #define ANODE_ALLOC_FWD 512 #define FNODE_ALLOC_FWD 0 diff --git a/fs/iomap.c b/fs/iomap.c index 206539d369a8..7d1e9f45f098 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1046,6 +1046,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length, bio_set_dev(bio, iomap->bdev); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); bio->bi_write_hint = dio->iocb->ki_hint; + bio->bi_ioprio = dio->iocb->ki_ioprio; bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 97a972efab83..68728de12864 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -788,35 +788,34 @@ static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres, spin_unlock(&lockres->l_lock); } -static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres, - struct ocfs2_lock_holder *oh) -{ - spin_lock(&lockres->l_lock); - list_del(&oh->oh_list); - spin_unlock(&lockres->l_lock); - - put_pid(oh->oh_owner_pid); -} - -static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres) +static struct ocfs2_lock_holder * +ocfs2_pid_holder(struct ocfs2_lock_res *lockres, + struct pid *pid) { struct ocfs2_lock_holder *oh; - struct pid *pid; - /* look in the list of holders for one with the current task as owner */ spin_lock(&lockres->l_lock); - pid = task_pid(current); list_for_each_entry(oh, &lockres->l_holders, oh_list) { if (oh->oh_owner_pid == pid) { spin_unlock(&lockres->l_lock); - return 1; + return oh; } } spin_unlock(&lockres->l_lock); + return NULL; +} - return 0; +static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres, + struct ocfs2_lock_holder *oh) +{ + spin_lock(&lockres->l_lock); + list_del(&oh->oh_list); + spin_unlock(&lockres->l_lock); + + put_pid(oh->oh_owner_pid); } + static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres, int level) { @@ -2610,34 +2609,93 @@ void ocfs2_inode_unlock(struct inode *inode, * * return < 0 on error, return == 0 if there's no lock holder on the stack * before this call, return == 1 if this call would be a recursive locking. + * return == -1 if this lock attempt will cause an upgrade which is forbidden. + * + * When taking lock levels into account,we face some different situations. + * + * 1. no lock is held + * In this case, just lock the inode as requested and return 0 + * + * 2. We are holding a lock + * For this situation, things diverges into several cases + * + * wanted holding what to do + * ex ex see 2.1 below + * ex pr see 2.2 below + * pr ex see 2.1 below + * pr pr see 2.1 below + * + * 2.1 lock level that is been held is compatible + * with the wanted level, so no lock action will be tacken. + * + * 2.2 Otherwise, an upgrade is needed, but it is forbidden. + * + * Reason why upgrade within a process is forbidden is that + * lock upgrade may cause dead lock. The following illustrates + * how it happens. + * + * thread on node1 thread on node2 + * ocfs2_inode_lock_tracker(ex=0) + * + * <====== ocfs2_inode_lock_tracker(ex=1) + * + * ocfs2_inode_lock_tracker(ex=1) */ int ocfs2_inode_lock_tracker(struct inode *inode, struct buffer_head **ret_bh, int ex, struct ocfs2_lock_holder *oh) { - int status; - int arg_flags = 0, has_locked; + int status = 0; struct ocfs2_lock_res *lockres; + struct ocfs2_lock_holder *tmp_oh; + struct pid *pid = task_pid(current); + lockres = &OCFS2_I(inode)->ip_inode_lockres; - has_locked = ocfs2_is_locked_by_me(lockres); - /* Just get buffer head if the cluster lock has been taken */ - if (has_locked) - arg_flags = OCFS2_META_LOCK_GETBH; + tmp_oh = ocfs2_pid_holder(lockres, pid); - if (likely(!has_locked || ret_bh)) { - status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags); + if (!tmp_oh) { + /* + * This corresponds to the case 1. + * We haven't got any lock before. + */ + status = ocfs2_inode_lock_full(inode, ret_bh, ex, 0); if (status < 0) { if (status != -ENOENT) mlog_errno(status); return status; } - } - if (!has_locked) + + oh->oh_ex = ex; ocfs2_add_holder(lockres, oh); + return 0; + } - return has_locked; + if (unlikely(ex && !tmp_oh->oh_ex)) { + /* + * case 2.2 upgrade may cause dead lock, forbid it. + */ + mlog(ML_ERROR, "Recursive locking is not permitted to " + "upgrade to EX level from PR level.\n"); + dump_stack(); + return -EINVAL; + } + + /* + * case 2.1 OCFS2_META_LOCK_GETBH flag make ocfs2_inode_lock_full. + * ignore the lock level and just update it. + */ + if (ret_bh) { + status = ocfs2_inode_lock_full(inode, ret_bh, ex, + OCFS2_META_LOCK_GETBH); + if (status < 0) { + if (status != -ENOENT) + mlog_errno(status); + return status; + } + } + return tmp_oh ? 1 : 0; } void ocfs2_inode_unlock_tracker(struct inode *inode, @@ -2649,12 +2707,13 @@ void ocfs2_inode_unlock_tracker(struct inode *inode, lockres = &OCFS2_I(inode)->ip_inode_lockres; /* had_lock means that the currect process already takes the cluster - * lock previously. If had_lock is 1, we have nothing to do here, and - * it will get unlocked where we got the lock. + * lock previously. + * If had_lock is 1, we have nothing to do here. + * If had_lock is 0, we will release the lock. */ if (!had_lock) { + ocfs2_inode_unlock(inode, oh->oh_ex); ocfs2_remove_holder(lockres, oh); - ocfs2_inode_unlock(inode, ex); } } diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index 256e0a9067b8..4ec1c828f6e0 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -96,6 +96,7 @@ struct ocfs2_trim_fs_info { struct ocfs2_lock_holder { struct list_head oh_list; struct pid *oh_owner_pid; + int oh_ex; }; /* ocfs2_inode_lock_full() 'arg_flags' flags */ diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 6ee94bc23f5b..a2a8603d27e0 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -563,8 +563,8 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb, return ret; } -static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start, - u32 clusters_to_add, int mark_unwritten) +static int ocfs2_extend_allocation(struct inode *inode, u32 logical_start, + u32 clusters_to_add, int mark_unwritten) { int status = 0; int restart_func = 0; @@ -1035,8 +1035,8 @@ int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, clusters_to_add -= oi->ip_clusters; if (clusters_to_add) { - ret = __ocfs2_extend_allocation(inode, oi->ip_clusters, - clusters_to_add, 0); + ret = ocfs2_extend_allocation(inode, oi->ip_clusters, + clusters_to_add, 0); if (ret) { mlog_errno(ret); goto out; @@ -1493,7 +1493,7 @@ static int ocfs2_allocate_unwritten_extents(struct inode *inode, goto next; } - ret = __ocfs2_extend_allocation(inode, cpos, alloc_size, 1); + ret = ocfs2_extend_allocation(inode, cpos, alloc_size, 1); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h index 1fdc9839cd93..7eb7f03531f6 100644 --- a/fs/ocfs2/file.h +++ b/fs/ocfs2/file.h @@ -65,8 +65,6 @@ int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size, u64 zero_to); int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, loff_t zero_to); -int ocfs2_extend_allocation(struct inode *inode, u32 logical_start, - u32 clusters_to_add, int mark_unwritten); int ocfs2_setattr(struct dentry *dentry, struct iattr *attr); int ocfs2_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index ab30c005cc4b..994726ada857 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -402,7 +402,7 @@ out_err: static void o2ffg_update_histogram(struct ocfs2_info_free_chunk_list *hist, unsigned int chunksize) { - int index; + u32 index; index = __ilog2_u32(chunksize); if (index >= OCFS2_INFO_MAX_HIST) diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index fb9a20e3d608..05220b365fb9 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -44,11 +44,11 @@ #include "ocfs2_trace.h" -static int ocfs2_fault(struct vm_fault *vmf) +static vm_fault_t ocfs2_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; sigset_t oldset; - int ret; + vm_fault_t ret; ocfs2_block_signals(&oldset); ret = filemap_fault(vmf); @@ -59,10 +59,11 @@ static int ocfs2_fault(struct vm_fault *vmf) return ret; } -static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, - struct page *page) +static vm_fault_t __ocfs2_page_mkwrite(struct file *file, + struct buffer_head *di_bh, struct page *page) { - int ret = VM_FAULT_NOPAGE; + int err; + vm_fault_t ret = VM_FAULT_NOPAGE; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; loff_t pos = page_offset(page); @@ -105,15 +106,12 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, if (page->index == last_index) len = ((size - 1) & ~PAGE_MASK) + 1; - ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, + err = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_MMAP, &locked_page, &fsdata, di_bh, page); - if (ret) { - if (ret != -ENOSPC) - mlog_errno(ret); - if (ret == -ENOMEM) - ret = VM_FAULT_OOM; - else - ret = VM_FAULT_SIGBUS; + if (err) { + if (err != -ENOSPC) + mlog_errno(err); + ret = vmf_error(err); goto out; } @@ -121,20 +119,21 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh, ret = VM_FAULT_NOPAGE; goto out; } - ret = ocfs2_write_end_nolock(mapping, pos, len, len, fsdata); - BUG_ON(ret != len); + err = ocfs2_write_end_nolock(mapping, pos, len, len, fsdata); + BUG_ON(err != len); ret = VM_FAULT_LOCKED; out: return ret; } -static int ocfs2_page_mkwrite(struct vm_fault *vmf) +static vm_fault_t ocfs2_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); struct buffer_head *di_bh = NULL; sigset_t oldset; - int ret; + int err; + vm_fault_t ret; sb_start_pagefault(inode->i_sb); ocfs2_block_signals(&oldset); @@ -144,13 +143,10 @@ static int ocfs2_page_mkwrite(struct vm_fault *vmf) * node. Taking the data lock will also ensure that we don't * attempt page truncation as part of a downconvert. */ - ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (ret < 0) { - mlog_errno(ret); - if (ret == -ENOMEM) - ret = VM_FAULT_OOM; - else - ret = VM_FAULT_SIGBUS; + err = ocfs2_inode_lock(inode, &di_bh, 1); + if (err < 0) { + mlog_errno(err); + ret = vmf_error(err); goto out; } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 8dd6f703c819..b7ca84bc3df7 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -2332,8 +2332,7 @@ int ocfs2_orphan_del(struct ocfs2_super *osb, struct buffer_head *orphan_dir_bh, bool dio) { - const int namelen = OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN; - char name[namelen + 1]; + char name[OCFS2_DIO_ORPHAN_PREFIX_LEN + OCFS2_ORPHAN_NAMELEN + 1]; struct ocfs2_dinode *orphan_fe; int status = 0; struct ocfs2_dir_lookup_result lookup = { NULL, }; diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index 5bb4a89f9045..7071ad0dec90 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -807,11 +807,11 @@ struct ocfs2_dir_block_trailer { * in this block. (unused) */ /*10*/ __u8 db_signature[8]; /* Signature for verification */ __le64 db_reserved2; - __le64 db_free_next; /* Next block in list (unused) */ -/*20*/ __le64 db_blkno; /* Offset on disk, in blocks */ - __le64 db_parent_dinode; /* dinode which owns me, in +/*20*/ __le64 db_free_next; /* Next block in list (unused) */ + __le64 db_blkno; /* Offset on disk, in blocks */ +/*30*/ __le64 db_parent_dinode; /* dinode which owns me, in blocks */ -/*30*/ struct ocfs2_block_check db_check; /* Error checking */ + struct ocfs2_block_check db_check; /* Error checking */ /*40*/ }; diff --git a/fs/proc/array.c b/fs/proc/array.c index 004077f1a7bf..0ceb3b6b37e7 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -268,7 +268,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) unsigned long flags; sigset_t pending, shpending, blocked, ignored, caught; int num_threads = 0; - unsigned long qsize = 0; + unsigned int qsize = 0; unsigned long qlim = 0; sigemptyset(&pending); diff --git a/fs/proc/base.c b/fs/proc/base.c index af128b374143..4aa9ce5df02f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -205,171 +205,129 @@ static int proc_root_link(struct dentry *dentry, struct path *path) return result; } -static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, - size_t _count, loff_t *pos) +static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, + size_t count, loff_t *ppos) { - struct task_struct *tsk; - struct mm_struct *mm; - char *page; - unsigned long count = _count; unsigned long arg_start, arg_end, env_start, env_end; - unsigned long len1, len2, len; - unsigned long p; - char c; - ssize_t rv; - - BUG_ON(*pos < 0); + unsigned long pos, len; + char *page; - tsk = get_proc_task(file_inode(file)); - if (!tsk) - return -ESRCH; - mm = get_task_mm(tsk); - put_task_struct(tsk); - if (!mm) - return 0; /* Check if process spawned far enough to have cmdline. */ - if (!mm->env_end) { - rv = 0; - goto out_mmput; - } - - page = (char *)__get_free_page(GFP_KERNEL); - if (!page) { - rv = -ENOMEM; - goto out_mmput; - } + if (!mm->env_end) + return 0; - down_read(&mm->mmap_sem); + spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; - up_read(&mm->mmap_sem); - - BUG_ON(arg_start > arg_end); - BUG_ON(env_start > env_end); + spin_unlock(&mm->arg_lock); - len1 = arg_end - arg_start; - len2 = env_end - env_start; + if (arg_start >= arg_end) + return 0; - /* Empty ARGV. */ - if (len1 == 0) { - rv = 0; - goto out_free_page; - } /* - * Inherently racy -- command line shares address space - * with code and data. + * We have traditionally allowed the user to re-write + * the argument strings and overflow the end result + * into the environment section. But only do that if + * the environment area is contiguous to the arguments. */ - rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON); - if (rv <= 0) - goto out_free_page; - - rv = 0; - - if (c == '\0') { - /* Command line (set of strings) occupies whole ARGV. */ - if (len1 <= *pos) - goto out_free_page; - - p = arg_start + *pos; - len = len1 - *pos; - while (count > 0 && len > 0) { - unsigned int _count; - int nr_read; - - _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); - if (nr_read < 0) - rv = nr_read; - if (nr_read <= 0) - goto out_free_page; - - if (copy_to_user(buf, page, nr_read)) { - rv = -EFAULT; - goto out_free_page; - } + if (env_start != arg_end || env_start >= env_end) + env_start = env_end = arg_end; - p += nr_read; - len -= nr_read; - buf += nr_read; - count -= nr_read; - rv += nr_read; - } - } else { - /* - * Command line (1 string) occupies ARGV and - * extends into ENVP. - */ - struct { - unsigned long p; - unsigned long len; - } cmdline[2] = { - { .p = arg_start, .len = len1 }, - { .p = env_start, .len = len2 }, - }; - loff_t pos1 = *pos; - unsigned int i; + /* We're not going to care if "*ppos" has high bits set */ + pos = arg_start + *ppos; + + /* .. but we do check the result is in the proper range */ + if (pos < arg_start || pos >= env_end) + return 0; + + /* .. and we never go past env_end */ + if (env_end - pos < count) + count = env_end - pos; + + page = (char *)__get_free_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + len = 0; + while (count) { + int got; + size_t size = min_t(size_t, PAGE_SIZE, count); + + got = access_remote_vm(mm, pos, page, size, FOLL_ANON); + if (got <= 0) + break; - i = 0; - while (i < 2 && pos1 >= cmdline[i].len) { - pos1 -= cmdline[i].len; - i++; + /* Don't walk past a NUL character once you hit arg_end */ + if (pos + got >= arg_end) { + int n = 0; + + /* + * If we started before 'arg_end' but ended up + * at or after it, we start the NUL character + * check at arg_end-1 (where we expect the normal + * EOF to be). + * + * NOTE! This is smaller than 'got', because + * pos + got >= arg_end + */ + if (pos < arg_end) + n = arg_end - pos - 1; + + /* Cut off at first NUL after 'n' */ + got = n + strnlen(page+n, got-n); + if (!got) + break; } - while (i < 2) { - p = cmdline[i].p + pos1; - len = cmdline[i].len - pos1; - while (count > 0 && len > 0) { - unsigned int _count, l; - int nr_read; - bool final; - - _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); - if (nr_read < 0) - rv = nr_read; - if (nr_read <= 0) - goto out_free_page; - - /* - * Command line can be shorter than whole ARGV - * even if last "marker" byte says it is not. - */ - final = false; - l = strnlen(page, nr_read); - if (l < nr_read) { - nr_read = l; - final = true; - } - - if (copy_to_user(buf, page, nr_read)) { - rv = -EFAULT; - goto out_free_page; - } - - p += nr_read; - len -= nr_read; - buf += nr_read; - count -= nr_read; - rv += nr_read; - - if (final) - goto out_free_page; - } - /* Only first chunk can be read partially. */ - pos1 = 0; - i++; + got -= copy_to_user(buf, page, got); + if (unlikely(!got)) { + if (!len) + len = -EFAULT; + break; } + pos += got; + buf += got; + len += got; + count -= got; } -out_free_page: free_page((unsigned long)page); -out_mmput: + return len; +} + +static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, + size_t count, loff_t *pos) +{ + struct mm_struct *mm; + ssize_t ret; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); - if (rv > 0) - *pos += rv; - return rv; + return ret; +} + +static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, + size_t count, loff_t *pos) +{ + struct task_struct *tsk; + ssize_t ret; + + BUG_ON(*pos < 0); + + tsk = get_proc_task(file_inode(file)); + if (!tsk) + return -ESRCH; + ret = get_task_cmdline(tsk, buf, count, pos); + put_task_struct(tsk); + if (ret > 0) + *pos += ret; + return ret; } static const struct file_operations proc_pid_cmdline_ops = { @@ -430,7 +388,6 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct stack_trace trace; unsigned long *entries; int err; - int i; entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL); if (!entries) @@ -443,6 +400,8 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, err = lock_trace(task); if (!err) { + unsigned int i; + save_stack_trace_tsk(task, &trace); for (i = 0; i < trace.nr_entries; i++) { @@ -927,10 +886,10 @@ static ssize_t environ_read(struct file *file, char __user *buf, if (!mmget_not_zero(mm)) goto free; - down_read(&mm->mmap_sem); + spin_lock(&mm->arg_lock); env_start = mm->env_start; env_end = mm->env_end; - up_read(&mm->mmap_sem); + spin_unlock(&mm->arg_lock); while (count > 0) { size_t this_len, max_len; @@ -1784,9 +1743,9 @@ int pid_getattr(const struct path *path, struct kstat *stat, generic_fillattr(inode, stat); - rcu_read_lock(); stat->uid = GLOBAL_ROOT_UID; stat->gid = GLOBAL_ROOT_GID; + rcu_read_lock(); task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) { @@ -1875,7 +1834,7 @@ const struct dentry_operations pid_dentry_operations = * by stat. */ bool proc_fill_cache(struct file *file, struct dir_context *ctx, - const char *name, int len, + const char *name, unsigned int len, instantiate_t instantiate, struct task_struct *task, const void *ptr) { struct dentry *child, *dir = file->f_path.dentry; @@ -1894,19 +1853,19 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, struct dentry *res; res = instantiate(child, task, ptr); d_lookup_done(child); - if (IS_ERR(res)) - goto end_instantiate; if (unlikely(res)) { dput(child); child = res; + if (IS_ERR(child)) + goto end_instantiate; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; -end_instantiate: dput(child); +end_instantiate: return dir_emit(ctx, name, len, ino, type); } @@ -3251,7 +3210,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx) iter.task; iter.tgid += 1, iter = next_tgid(ns, iter)) { char name[10 + 1]; - int len; + unsigned int len; cond_resched(); if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE)) @@ -3578,7 +3537,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) task; task = next_tid(task), ctx->pos++) { char name[10 + 1]; - int len; + unsigned int len; tid = task_pid_nr_ns(task, ns); len = snprintf(name, sizeof(name), "%u", tid); if (!proc_fill_cache(file, ctx, name, len, diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 05b9893e9a22..81882a13212d 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -248,7 +248,7 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, struct file *f; struct fd_data data; char name[10 + 1]; - int len; + unsigned int len; f = fcheck_files(files, fd); if (!f) diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 93eb1906c28d..50cb22a08c2f 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -163,7 +163,7 @@ extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ typedef struct dentry *instantiate_t(struct dentry *, struct task_struct *, const void *); -extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int, +bool proc_fill_cache(struct file *, struct dir_context *, const char *, unsigned int, instantiate_t, struct task_struct *, const void *); /* diff --git a/fs/proc/page.c b/fs/proc/page.c index 1491918a33c3..792c78a49174 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -154,6 +154,8 @@ u64 stable_page_flags(struct page *page) if (PageBalloon(page)) u |= 1 << KPF_BALLOON; + if (PageTable(page)) + u |= 1 << KPF_PGTABLE; if (page_is_idle(page)) u |= 1 << KPF_IDLE; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7e074138d2f2..597969db9e90 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1259,8 +1259,9 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, if (pte_swp_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; entry = pte_to_swp_entry(pte); - frame = swp_type(entry) | - (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + if (pm->show_pfn) + frame = swp_type(entry) | + (swp_offset(entry) << MAX_SWAPFILES_SHIFT); flags |= PM_SWAP; if (is_migration_entry(entry)) page = migration_entry_to_page(entry); @@ -1311,11 +1312,14 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION else if (is_swap_pmd(pmd)) { swp_entry_t entry = pmd_to_swp_entry(pmd); - unsigned long offset = swp_offset(entry); + unsigned long offset; - offset += (addr & ~PMD_MASK) >> PAGE_SHIFT; - frame = swp_type(entry) | - (offset << MAX_SWAPFILES_SHIFT); + if (pm->show_pfn) { + offset = swp_offset(entry) + + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + frame = swp_type(entry) | + (offset << MAX_SWAPFILES_SHIFT); + } flags |= PM_SWAP; if (pmd_swp_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; @@ -1333,10 +1337,12 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, err = add_to_pagemap(addr, &pme, pm); if (err) break; - if (pm->show_pfn && (flags & PM_PRESENT)) - frame++; - else if (flags & PM_SWAP) - frame += (1 << MAX_SWAPFILES_SHIFT); + if (pm->show_pfn) { + if (flags & PM_PRESENT) + frame++; + else if (flags & PM_SWAP) + frame += (1 << MAX_SWAPFILES_SHIFT); + } } spin_unlock(ptl); return err; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 1acb2ff505e6..28b80713a163 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1513,7 +1513,7 @@ static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags) * mmap()d file has taken write protection fault and is being made writable. * UBIFS must ensure page is budgeted for. */ -static int ubifs_vm_page_mkwrite(struct vm_fault *vmf) +static vm_fault_t ubifs_vm_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); @@ -1567,8 +1567,7 @@ static int ubifs_vm_page_mkwrite(struct vm_fault *vmf) if (unlikely(page->mapping != inode->i_mapping || page_offset(page) > i_size_read(inode))) { /* Page got truncated out from underneath us */ - err = -EINVAL; - goto out_unlock; + goto sigbus; } if (PagePrivate(page)) @@ -1597,12 +1596,10 @@ static int ubifs_vm_page_mkwrite(struct vm_fault *vmf) wait_for_stable_page(page); return VM_FAULT_LOCKED; -out_unlock: +sigbus: unlock_page(page); ubifs_release_budget(c, &req); - if (err) - err = VM_FAULT_SIGBUS; - return err; + return VM_FAULT_SIGBUS; } static const struct vm_operations_struct ubifs_file_vm_ops = { diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index 7b35e3d6cde7..a03a47cf880d 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -49,7 +49,7 @@ * maximum size. So dark watermark is the amount of free + dirty space in LEB * which are guaranteed to be reclaimable. If LEB has less space, the GC might * be unable to reclaim it. So, LEBs with free + dirty greater than dark - * watermark are "good" LEBs from GC's point of few. The other LEBs are not so + * watermark are "good" LEBs from GC's point of view. The other LEBs are not so * good, and GC takes extra care when moving them. */ diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 04c4ec6483e5..da8afdfccaa6 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -98,9 +98,8 @@ static inline void zero_trun_node_unused(struct ubifs_trun_node *trun) * * This function reserves space in journal head @head. If the reservation * succeeded, the journal head stays locked and later has to be unlocked using - * 'release_head()'. 'write_node()' and 'write_head()' functions also unlock - * it. Returns zero in case of success, %-EAGAIN if commit has to be done, and - * other negative error codes in case of other failures. + * 'release_head()'. Returns zero in case of success, %-EAGAIN if commit has to + * be done, and other negative error codes in case of other failures. */ static int reserve_space(struct ubifs_info *c, int jhead, int len) { diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index 8c795e6392b1..7cffa120a750 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -167,10 +167,10 @@ void ubifs_add_bud(struct ubifs_info *c, struct ubifs_bud *bud) * @lnum: LEB number of the bud * @offs: starting offset of the bud * - * This function writes reference node for the new bud LEB @lnum it to the log, - * and adds it to the buds tress. It also makes sure that log size does not + * This function writes a reference node for the new bud LEB @lnum to the log, + * and adds it to the buds trees. It also makes sure that log size does not * exceed the 'c->max_bud_bytes' limit. Returns zero in case of success, - * %-EAGAIN if commit is required, and a negative error codes in case of + * %-EAGAIN if commit is required, and a negative error code in case of * failure. */ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index 235654c2fe89..78da65b2fb85 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -619,7 +619,7 @@ static struct ubifs_pnode *next_pnode_to_dirty(struct ubifs_info *c, /** * pnode_lookup - lookup a pnode in the LPT. * @c: UBIFS file-system description object - * @i: pnode number (0 to main_lebs - 1) + * @i: pnode number (0 to (main_lebs - 1) / UBIFS_LPT_FANOUT)) * * This function returns a pointer to the pnode on success or a negative * error code on failure. diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index ae5c02f22f3e..85c2a43082b7 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -223,9 +223,6 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r) dbg_mntk(&r->key, "LEB %d:%d len %d deletion %d sqnum %llu key ", r->lnum, r->offs, r->len, r->deletion, r->sqnum); - /* Set c->replay_sqnum to help deal with dangling branches. */ - c->replay_sqnum = r->sqnum; - if (is_hash_key(c, &r->key)) { if (r->deletion) err = ubifs_tnc_remove_nm(c, &r->key, &r->nm); @@ -1037,7 +1034,7 @@ int ubifs_replay_journal(struct ubifs_info *c) * The head of the log must always start with the * "commit start" node on a properly formatted UBIFS. * But we found no nodes at all, which means that - * someting went wrong and we cannot proceed mounting + * something went wrong and we cannot proceed mounting * the file-system. */ ubifs_err(c, "no UBIFS nodes found at the log head LEB %d:%d, possibly corrupted", diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 5ee7af879cc4..209d6369ae71 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1206,7 +1206,6 @@ struct ubifs_debug_info; * @replay_list: temporary list used during journal replay * @replay_buds: list of buds to replay * @cs_sqnum: sequence number of first node in the log (commit start node) - * @replay_sqnum: sequence number of node currently being replayed * @unclean_leb_list: LEBs to recover when re-mounting R/O mounted FS to R/W * mode * @rcvrd_mst_node: recovered master node to write when re-mounting R/O mounted @@ -1438,7 +1437,6 @@ struct ubifs_info { struct list_head replay_list; struct list_head replay_buds; unsigned long long cs_sqnum; - unsigned long long replay_sqnum; struct list_head unclean_leb_list; struct ubifs_mst_node *rcvrd_mst_node; struct rb_root size_tree; diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 759f1a209dbb..6f720fdf5020 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -139,7 +139,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host, inode->i_op = &empty_iops; inode->i_fop = &empty_fops; - inode->i_flags |= S_SYNC | S_NOATIME | S_NOCMTIME | S_NOQUOTA; + inode->i_flags |= S_SYNC | S_NOATIME | S_NOCMTIME; ui = ubifs_inode(inode); ui->xattr = 1; ui->flags |= UBIFS_XATTR_FL; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index cec550c8468f..123bf7d516fc 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -62,6 +62,8 @@ struct userfaultfd_ctx { enum userfaultfd_state state; /* released */ bool released; + /* memory mappings are changing because of non-cooperative event */ + bool mmap_changing; /* mm with one ore more vmas attached to this userfaultfd_ctx */ struct mm_struct *mm; }; @@ -641,6 +643,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, * already released. */ out: + WRITE_ONCE(ctx->mmap_changing, false); userfaultfd_ctx_put(ctx); } @@ -686,10 +689,12 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) ctx->state = UFFD_STATE_RUNNING; ctx->features = octx->features; ctx->released = false; + ctx->mmap_changing = false; ctx->mm = vma->vm_mm; mmgrab(ctx->mm); userfaultfd_ctx_get(octx); + WRITE_ONCE(octx->mmap_changing, true); fctx->orig = octx; fctx->new = ctx; list_add_tail(&fctx->list, fcs); @@ -732,6 +737,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, if (ctx && (ctx->features & UFFD_FEATURE_EVENT_REMAP)) { vm_ctx->ctx = ctx; userfaultfd_ctx_get(ctx); + WRITE_ONCE(ctx->mmap_changing, true); } } @@ -772,6 +778,7 @@ bool userfaultfd_remove(struct vm_area_struct *vma, return true; userfaultfd_ctx_get(ctx); + WRITE_ONCE(ctx->mmap_changing, true); up_read(&mm->mmap_sem); msg_init(&ewq.msg); @@ -815,6 +822,7 @@ int userfaultfd_unmap_prep(struct vm_area_struct *vma, return -ENOMEM; userfaultfd_ctx_get(ctx); + WRITE_ONCE(ctx->mmap_changing, true); unmap_ctx->ctx = ctx; unmap_ctx->start = start; unmap_ctx->end = end; @@ -1653,6 +1661,10 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; + ret = -EAGAIN; + if (READ_ONCE(ctx->mmap_changing)) + goto out; + ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, /* don't copy "copy" last field */ @@ -1674,7 +1686,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, goto out; if (mmget_not_zero(ctx->mm)) { ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src, - uffdio_copy.len); + uffdio_copy.len, &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; @@ -1705,6 +1717,10 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; + ret = -EAGAIN; + if (READ_ONCE(ctx->mmap_changing)) + goto out; + ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, /* don't copy "zeropage" last field */ @@ -1721,7 +1737,8 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, if (mmget_not_zero(ctx->mm)) { ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start, - uffdio_zeropage.range.len); + uffdio_zeropage.range.len, + &ctx->mmap_changing); mmput(ctx->mm); } else { return -ESRCH; @@ -1900,6 +1917,7 @@ SYSCALL_DEFINE1(userfaultfd, int, flags) ctx->features = 0; ctx->state = UFFD_STATE_WAIT_API; ctx->released = false; + ctx->mmap_changing = false; ctx->mm = current->mm; /* prevent the mm struct to be freed */ mmgrab(ctx->mm); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 0e3fb8978344..bed07dfbb85e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -312,7 +312,7 @@ restart: if (error <= 0) return error; - error = xfs_break_layouts(inode, iolock); + error = xfs_break_layouts(inode, iolock, BREAK_WRITE); if (error) return error; @@ -731,6 +731,69 @@ xfs_file_write_iter( return xfs_file_buffered_aio_write(iocb, from); } +static void +xfs_wait_dax_page( + struct inode *inode, + bool *did_unlock) +{ + struct xfs_inode *ip = XFS_I(inode); + + *did_unlock = true; + xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); + schedule(); + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); +} + +static int +xfs_break_dax_layouts( + struct inode *inode, + uint iolock, + bool *did_unlock) +{ + struct page *page; + + ASSERT(xfs_isilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL)); + + page = dax_layout_busy_page(inode->i_mapping); + if (!page) + return 0; + + return ___wait_var_event(&page->_refcount, + atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE, + 0, 0, xfs_wait_dax_page(inode, did_unlock)); +} + +int +xfs_break_layouts( + struct inode *inode, + uint *iolock, + enum layout_break_reason reason) +{ + bool retry; + int error; + + ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)); + + do { + retry = false; + switch (reason) { + case BREAK_UNMAP: + error = xfs_break_dax_layouts(inode, *iolock, &retry); + if (error || retry) + break; + /* fall through */ + case BREAK_WRITE: + error = xfs_break_leased_layouts(inode, iolock, &retry); + break; + default: + WARN_ON_ONCE(1); + error = -EINVAL; + } + } while (error == 0 && retry); + + return error; +} + #define XFS_FALLOC_FL_SUPPORTED \ (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \ @@ -747,7 +810,7 @@ xfs_file_fallocate( struct xfs_inode *ip = XFS_I(inode); long error; enum xfs_prealloc_flags flags = 0; - uint iolock = XFS_IOLOCK_EXCL; + uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; loff_t new_size = 0; bool do_file_insert = false; @@ -757,13 +820,10 @@ xfs_file_fallocate( return -EOPNOTSUPP; xfs_ilock(ip, iolock); - error = xfs_break_layouts(inode, &iolock); + error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP); if (error) goto out_unlock; - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - iolock |= XFS_MMAPLOCK_EXCL; - if (mode & FALLOC_FL_PUNCH_HOLE) { error = xfs_free_file_space(ip, offset, len); if (error) diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 00fee6824745..a91d9fb1effc 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -379,6 +379,20 @@ static inline void xfs_ifunlock(struct xfs_inode *ip) >> XFS_ILOCK_SHIFT) /* + * Layouts are broken in the BREAK_WRITE case to ensure that + * layout-holders do not collide with local writes. Additionally, + * layouts are broken in the BREAK_UNMAP case to make sure the + * layout-holder has a consistent view of the file's extent map. While + * BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases, + * BREAK_UNMAP breaks additionally require waiting for busy dax-pages to + * go idle. + */ +enum layout_break_reason { + BREAK_WRITE, + BREAK_UNMAP, +}; + +/* * For multiple groups support: if S_ISGID bit is set in the parent * directory, group of new file is set to that of the parent, and * new subdirectory gets S_ISGID bit from parent. @@ -453,6 +467,8 @@ enum xfs_prealloc_flags { int xfs_update_prealloc_flags(struct xfs_inode *ip, enum xfs_prealloc_flags flags); +int xfs_break_layouts(struct inode *inode, uint *iolock, + enum layout_break_reason reason); /* from xfs_iops.c */ extern void xfs_setup_inode(struct xfs_inode *ip); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 5dd9e22b4a4c..32b680522abd 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -39,7 +39,6 @@ #include "xfs_icache.h" #include "xfs_symlink.h" #include "xfs_trans.h" -#include "xfs_pnfs.h" #include "xfs_acl.h" #include "xfs_btree.h" #include <linux/fsmap.h> @@ -614,7 +613,7 @@ xfs_ioc_space( struct xfs_inode *ip = XFS_I(inode); struct iattr iattr; enum xfs_prealloc_flags flags = 0; - uint iolock = XFS_IOLOCK_EXCL; + uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; int error; /* @@ -644,13 +643,10 @@ xfs_ioc_space( return error; xfs_ilock(ip, iolock); - error = xfs_break_layouts(inode, &iolock); + error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP); if (error) goto out_unlock; - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); - iolock |= XFS_MMAPLOCK_EXCL; - switch (bf->l_whence) { case 0: /*SEEK_SET*/ break; diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index b0eb49bb4918..3b4be06fdaa5 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -37,7 +37,6 @@ #include "xfs_da_btree.h" #include "xfs_dir2.h" #include "xfs_trans_space.h" -#include "xfs_pnfs.h" #include "xfs_iomap.h" #include <linux/capability.h> @@ -1030,14 +1029,19 @@ xfs_vn_setattr( int error; if (iattr->ia_valid & ATTR_SIZE) { - struct xfs_inode *ip = XFS_I(d_inode(dentry)); - uint iolock = XFS_IOLOCK_EXCL; + struct inode *inode = d_inode(dentry); + struct xfs_inode *ip = XFS_I(inode); + uint iolock; - error = xfs_break_layouts(d_inode(dentry), &iolock); - if (error) + xfs_ilock(ip, XFS_MMAPLOCK_EXCL); + iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; + + error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP); + if (error) { + xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); return error; + } - xfs_ilock(ip, XFS_MMAPLOCK_EXCL); error = xfs_vn_setattr_size(dentry, iattr); xfs_iunlock(ip, XFS_MMAPLOCK_EXCL); } else { diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index aa6c5c193f45..f44c3599527d 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -31,19 +31,20 @@ * rules in the page fault path we don't bother. */ int -xfs_break_layouts( +xfs_break_leased_layouts( struct inode *inode, - uint *iolock) + uint *iolock, + bool *did_unlock) { struct xfs_inode *ip = XFS_I(inode); int error; - ASSERT(xfs_isilocked(ip, XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)); - while ((error = break_layout(inode, false) == -EWOULDBLOCK)) { xfs_iunlock(ip, *iolock); + *did_unlock = true; error = break_layout(inode, true); - *iolock = XFS_IOLOCK_EXCL; + *iolock &= ~XFS_IOLOCK_SHARED; + *iolock |= XFS_IOLOCK_EXCL; xfs_ilock(ip, *iolock); } @@ -120,8 +121,8 @@ xfs_fs_map_blocks( * Lock out any other I/O before we flush and invalidate the pagecache, * and then hand out a layout to the remote system. This is very * similar to direct I/O, except that the synchronization is much more - * complicated. See the comment near xfs_break_layouts for a detailed - * explanation. + * complicated. See the comment near xfs_break_leased_layouts + * for a detailed explanation. */ xfs_ilock(ip, XFS_IOLOCK_EXCL); diff --git a/fs/xfs/xfs_pnfs.h b/fs/xfs/xfs_pnfs.h index bf45951e28fe..940c6c2ad88c 100644 --- a/fs/xfs/xfs_pnfs.h +++ b/fs/xfs/xfs_pnfs.h @@ -9,10 +9,11 @@ int xfs_fs_map_blocks(struct inode *inode, loff_t offset, u64 length, int xfs_fs_commit_blocks(struct inode *inode, struct iomap *maps, int nr_maps, struct iattr *iattr); -int xfs_break_layouts(struct inode *inode, uint *iolock); +int xfs_break_leased_layouts(struct inode *inode, uint *iolock, + bool *did_unlock); #else static inline int -xfs_break_layouts(struct inode *inode, uint *iolock) +xfs_break_leased_layouts(struct inode *inode, uint *iolock, bool *did_unlock) { return 0; } |