From ef12e72a01f3022c55e5a8e0fa1caebdc7efcfce Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 3 Feb 2014 12:13:08 -0500 Subject: locks: fix posix lock range overflow handling In the 32-bit case fcntl assigns the 64-bit f_pos and i_size to a 32-bit off_t. The existing range checks also seem to depend on signed arithmetic wrapping when it overflows. In practice maybe that works, but we can be more careful. That also allows us to make a more reliable distinction between -EINVAL and -EOVERFLOW. Note that in the 32-bit case SEEK_CUR or SEEK_END might allow the caller to set a lock with starting point no longer representable as a 32-bit value. We could return -EOVERFLOW in such cases, but the locks code is capable of handling such ranges, so we choose to be lenient here. The only problem is that subsequent GETLK calls on such a lock will fail with EOVERFLOW. While we're here, do some cleanup including consolidating code for the flock and flock64 cases. Signed-off-by: J. Bruce Fields Signed-off-by: Jeff Layton --- include/uapi/asm-generic/fcntl.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 95e46c8e05f..36025f77c6e 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -186,8 +186,6 @@ struct flock { }; #endif -#ifndef CONFIG_64BIT - #ifndef HAVE_ARCH_STRUCT_FLOCK64 #ifndef __ARCH_FLOCK64_PAD #define __ARCH_FLOCK64_PAD @@ -202,6 +200,5 @@ struct flock64 { __ARCH_FLOCK64_PAD }; #endif -#endif /* !CONFIG_64BIT */ #endif /* _ASM_GENERIC_FCNTL_H */ -- cgit v1.2.3-70-g09d2 From 5d50ffd7c31dab47c6b828841ca1ec70a1b40169 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 3 Feb 2014 12:13:10 -0500 Subject: locks: add new fcntl cmd values for handling file private locks Due to some unfortunate history, POSIX locks have very strange and unhelpful semantics. The thing that usually catches people by surprise is that they are dropped whenever the process closes any file descriptor associated with the inode. This is extremely problematic for people developing file servers that need to implement byte-range locks. Developers often need a "lock management" facility to ensure that file descriptors are not closed until all of the locks associated with the inode are finished. Additionally, "classic" POSIX locks are owned by the process. Locks taken between threads within the same process won't conflict with one another, which renders them useless for synchronization between threads. This patchset adds a new type of lock that attempts to address these issues. These locks conflict with classic POSIX read/write locks, but have semantics that are more like BSD locks with respect to inheritance and behavior on close. This is implemented primarily by changing how fl_owner field is set for these locks. Instead of having them owned by the files_struct of the process, they are instead owned by the filp on which they were acquired. Thus, they are inherited across fork() and are only released when the last reference to a filp is put. These new semantics prevent them from being merged with classic POSIX locks, even if they are acquired by the same process. These locks will also conflict with classic POSIX locks even if they are acquired by the same process or on the same file descriptor. The new locks are managed using a new set of cmd values to the fcntl() syscall. The initial implementation of this converts these values to "classic" cmd values at a fairly high level, and the details are not exposed to the underlying filesystem. We may eventually want to push this handing out to the lower filesystem code but for now I don't see any need for it. Also, note that with this implementation the new cmd values are only available via fcntl64() on 32-bit arches. There's little need to add support for legacy apps on a new interface like this. Signed-off-by: Jeff Layton --- arch/arm/kernel/sys_oabi-compat.c | 3 +++ fs/compat.c | 35 +++++++++++++++++++++---- fs/fcntl.c | 35 +++++++++++++++++-------- fs/locks.c | 54 ++++++++++++++++++++++++++++++++++++--- include/uapi/asm-generic/fcntl.h | 16 ++++++++++++ security/selinux/hooks.c | 3 +++ 6 files changed, 126 insertions(+), 20 deletions(-) (limited to 'include/uapi') diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 3e94811690c..702bd329d9d 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -203,6 +203,9 @@ asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, int ret; switch (cmd) { + case F_GETLKP: + case F_SETLKP: + case F_SETLKPW: case F_GETLK64: case F_SETLK64: case F_SETLKW64: diff --git a/fs/compat.c b/fs/compat.c index 6af20de2c1a..f340dcf11f6 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -399,12 +399,28 @@ static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *u } #endif +static unsigned int +convert_fcntl_cmd(unsigned int cmd) +{ + switch (cmd) { + case F_GETLK64: + return F_GETLK; + case F_SETLK64: + return F_SETLK; + case F_SETLKW64: + return F_SETLKW; + } + + return cmd; +} + asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg) { mm_segment_t old_fs; struct flock f; long ret; + unsigned int conv_cmd; switch (cmd) { case F_GETLK: @@ -441,16 +457,18 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, case F_GETLK64: case F_SETLK64: case F_SETLKW64: + case F_GETLKP: + case F_SETLKP: + case F_SETLKPW: ret = get_compat_flock64(&f, compat_ptr(arg)); if (ret != 0) break; old_fs = get_fs(); set_fs(KERNEL_DS); - ret = sys_fcntl(fd, (cmd == F_GETLK64) ? F_GETLK : - ((cmd == F_SETLK64) ? F_SETLK : F_SETLKW), - (unsigned long)&f); + conv_cmd = convert_fcntl_cmd(cmd); + ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f); set_fs(old_fs); - if (cmd == F_GETLK64 && ret == 0) { + if ((conv_cmd == F_GETLK || conv_cmd == F_GETLKP) && ret == 0) { /* need to return lock information - see above for commentary */ if (f.l_start > COMPAT_LOFF_T_MAX) ret = -EOVERFLOW; @@ -471,8 +489,15 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg) { - if ((cmd == F_GETLK64) || (cmd == F_SETLK64) || (cmd == F_SETLKW64)) + switch (cmd) { + case F_GETLK64: + case F_SETLK64: + case F_SETLKW64: + case F_GETLKP: + case F_SETLKP: + case F_SETLKPW: return -EINVAL; + } return compat_sys_fcntl64(fd, cmd, arg); } diff --git a/fs/fcntl.c b/fs/fcntl.c index 7ef7f2d2b60..9ead1596399 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -272,9 +272,19 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, case F_SETFL: err = setfl(fd, filp, arg); break; +#if BITS_PER_LONG != 32 + /* 32-bit arches must use fcntl64() */ + case F_GETLKP: +#endif case F_GETLK: err = fcntl_getlk(filp, cmd, (struct flock __user *) arg); break; +#if BITS_PER_LONG != 32 + /* 32-bit arches must use fcntl64() */ + case F_SETLKP: + case F_SETLKPW: +#endif + /* Fallthrough */ case F_SETLK: case F_SETLKW: err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg); @@ -388,17 +398,20 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, goto out1; switch (cmd) { - case F_GETLK64: - err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg); - break; - case F_SETLK64: - case F_SETLKW64: - err = fcntl_setlk64(fd, f.file, cmd, - (struct flock64 __user *) arg); - break; - default: - err = do_fcntl(fd, cmd, arg, f.file); - break; + case F_GETLK64: + case F_GETLKP: + err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg); + break; + case F_SETLK64: + case F_SETLKW64: + case F_SETLKP: + case F_SETLKPW: + err = fcntl_setlk64(fd, f.file, cmd, + (struct flock64 __user *) arg); + break; + default: + err = do_fcntl(fd, cmd, arg, f.file); + break; } out1: fdput(f); diff --git a/fs/locks.c b/fs/locks.c index ed9fb769b88..3b54b98236e 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1930,6 +1930,12 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l) if (error) goto out; + if (cmd == F_GETLKP) { + cmd = F_GETLK; + file_lock.fl_flags |= FL_FILE_PVT; + file_lock.fl_owner = (fl_owner_t)filp; + } + error = vfs_test_lock(filp, &file_lock); if (error) goto out; @@ -2049,10 +2055,26 @@ again: error = flock_to_posix_lock(filp, file_lock, &flock); if (error) goto out; - if (cmd == F_SETLKW) { + + /* + * If the cmd is requesting file-private locks, then set the + * FL_FILE_PVT flag and override the owner. + */ + switch (cmd) { + case F_SETLKP: + cmd = F_SETLK; + file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_owner = (fl_owner_t)filp; + break; + case F_SETLKPW: + cmd = F_SETLKW; + file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_owner = (fl_owner_t)filp; + /* Fallthrough */ + case F_SETLKW: file_lock->fl_flags |= FL_SLEEP; } - + error = do_lock_file_wait(filp, cmd, file_lock); /* @@ -2098,6 +2120,12 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l) if (error) goto out; + if (cmd == F_GETLKP) { + cmd = F_GETLK64; + file_lock.fl_flags |= FL_FILE_PVT; + file_lock.fl_owner = (fl_owner_t)filp; + } + error = vfs_test_lock(filp, &file_lock); if (error) goto out; @@ -2150,10 +2178,26 @@ again: error = flock64_to_posix_lock(filp, file_lock, &flock); if (error) goto out; - if (cmd == F_SETLKW64) { + + /* + * If the cmd is requesting file-private locks, then set the + * FL_FILE_PVT flag and override the owner. + */ + switch (cmd) { + case F_SETLKP: + cmd = F_SETLK64; + file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_owner = (fl_owner_t)filp; + break; + case F_SETLKPW: + cmd = F_SETLKW64; + file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_owner = (fl_owner_t)filp; + /* Fallthrough */ + case F_SETLKW64: file_lock->fl_flags |= FL_SLEEP; } - + error = do_lock_file_wait(filp, cmd, file_lock); /* @@ -2221,6 +2265,8 @@ void locks_remove_file(struct file *filp) if (!inode->i_flock) return; + locks_remove_posix(filp, (fl_owner_t)filp); + if (filp->f_op->flock) { struct file_lock fl = { .fl_pid = current->tgid, diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h index 36025f77c6e..a9b13f8b359 100644 --- a/include/uapi/asm-generic/fcntl.h +++ b/include/uapi/asm-generic/fcntl.h @@ -132,6 +132,22 @@ #define F_GETOWNER_UIDS 17 #endif +/* + * fd "private" POSIX locks. + * + * Usually POSIX locks held by a process are released on *any* close and are + * not inherited across a fork(). + * + * These cmd values will set locks that conflict with normal POSIX locks, but + * are "owned" by the opened file, not the process. This means that they are + * inherited across fork() like BSD (flock) locks, and they are only released + * automatically when the last reference to the the open file against which + * they were acquired is put. + */ +#define F_GETLKP 36 +#define F_SETLKP 37 +#define F_SETLKPW 38 + #define F_OWNER_TID 0 #define F_OWNER_PID 1 #define F_OWNER_PGRP 2 diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4b34847208c..3aa87637488 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3302,6 +3302,9 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd, case F_GETLK: case F_SETLK: case F_SETLKW: + case F_GETLKP: + case F_SETLKP: + case F_SETLKPW: #if BITS_PER_LONG == 32 case F_GETLK64: case F_SETLK64: -- cgit v1.2.3-70-g09d2