From 819671ff849b07b9831b91de879ddc5da4b333d4 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:25 +0100 Subject: syscalls: define and explain goal to not call syscalls in the kernel The syscall entry points to the kernel defined by SYSCALL_DEFINEx() and COMPAT_SYSCALL_DEFINEx() should only be called from userspace through kernel entry points, but not from the kernel itself. This will allow cleanups and optimizations to the entry paths *and* to the parts of the kernel code which currently need to pretend to be userspace in order to make use of syscalls. Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a78186d826d7..0526286a0314 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -941,4 +941,11 @@ asmlinkage long sys_pkey_free(int pkey); asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); + +/* + * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. + * Instead, use one of the functions which work equivalently, such as + * the ksys_xyzyyz() functions prototyped below. + */ + #endif -- cgit v1.2.3 From d53238cd51a80f6f2e5b9d64830c62e2086787bd Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:37 +0100 Subject: kernel: open-code sys_rt_sigpending() in sys_sigpending() A similar but not fully equivalent code path is already open-coded three times (in sys_rt_sigpending and in the two compat stubs), so do it a fourth time here. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 2 +- kernel/signal.c | 15 ++++++++++++--- 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0526286a0314..a63e21e7a3af 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -288,7 +288,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data); asmlinkage long sys_personality(unsigned int personality); -asmlinkage long sys_sigpending(old_sigset_t __user *set); +asmlinkage long sys_sigpending(old_sigset_t __user *uset); asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, old_sigset_t __user *oset); asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, diff --git a/kernel/signal.c b/kernel/signal.c index c6e4c83dc090..985c61749bcf 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3629,11 +3629,20 @@ int __compat_save_altstack(compat_stack_t __user *uss, unsigned long sp) /** * sys_sigpending - examine pending signals - * @set: where mask of pending signal is returned + * @uset: where mask of pending signal is returned */ -SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set) +SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, uset) { - return sys_rt_sigpending((sigset_t __user *)set, sizeof(old_sigset_t)); + sigset_t set; + int err; + + if (sizeof(old_sigset_t) > sizeof(*uset)) + return -EINVAL; + + err = do_sigpending(&set); + if (!err && copy_to_user(uset, &set, sizeof(old_sigset_t))) + err = -EFAULT; + return err; } #ifdef CONFIG_COMPAT -- cgit v1.2.3 From ab0d1e85bfd0c25260f02cd3708d5abdfb5b5a9c Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 4 Mar 2018 21:54:05 +0100 Subject: fs/quota: use COMPAT_SYSCALL_DEFINE for sys32_quotactl() While sys32_quotactl() is only needed on x86, it can use the recommended COMPAT_SYSCALL_DEFINEx() machinery for its setup. Acked-by: Jan Kara Cc: Christoph Hellwig Signed-off-by: Dominik Brodowski --- arch/x86/entry/syscalls/syscall_32.tbl | 2 +- fs/quota/compat.c | 5 +++-- include/linux/compat.h | 3 +++ include/linux/syscalls.h | 2 -- kernel/sys_ni.c | 2 +- 5 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index ef6edaf285cd..c58f75b088c5 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -137,7 +137,7 @@ 128 i386 init_module sys_init_module 129 i386 delete_module sys_delete_module 130 i386 get_kernel_syms -131 i386 quotactl sys_quotactl sys32_quotactl +131 i386 quotactl sys_quotactl compat_sys_quotactl32 132 i386 getpgid sys_getpgid 133 i386 fchdir sys_fchdir 134 i386 bdflush sys_bdflush diff --git a/fs/quota/compat.c b/fs/quota/compat.c index 1577a2fd51f4..c30572857619 100644 --- a/fs/quota/compat.c +++ b/fs/quota/compat.c @@ -41,8 +41,9 @@ struct compat_fs_quota_stat { __u16 qs_iwarnlimit; }; -asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, - qid_t id, void __user *addr) +COMPAT_SYSCALL_DEFINE4(quotactl32, unsigned int, cmd, + const char __user *, special, qid_t, id, + void __user *, addr) { unsigned int cmds; struct if_dqblk __user *dqblk; diff --git a/include/linux/compat.h b/include/linux/compat.h index 16c3027074a2..f1649a5e6716 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -461,6 +461,9 @@ asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); +asmlinkage long compat_sys_quotactl32(unsigned int cmd, + const char __user *special, qid_t id, void __user *addr); + #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, const struct compat_iovec __user *vec, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a63e21e7a3af..6ab7ed71a8b6 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -241,8 +241,6 @@ static inline void addr_limit_user_check(void) #endif } -asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special, - qid_t id, void __user *addr); asmlinkage long sys_time(time_t __user *tloc); asmlinkage long sys_stime(time_t __user *tptr); asmlinkage long sys_gettimeofday(struct timeval __user *tv, diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index b5189762d275..951dbda5c2b4 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -18,7 +18,7 @@ asmlinkage long sys_ni_syscall(void) } cond_syscall(sys_quotactl); -cond_syscall(sys32_quotactl); +cond_syscall(compat_sys_quotactl32); cond_syscall(sys_acct); cond_syscall(sys_lookup_dcookie); cond_syscall(compat_sys_lookup_dcookie); -- cgit v1.2.3 From 312db1aa1dc7bff133d95c92efcc5e42b57cefa6 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:39 +0100 Subject: fs: add ksys_mount() helper; remove in-kernel calls to sys_mount() Using this helper allows us to avoid the in-kernel calls to the sys_mount() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mount(). In the near future, all callers of ksys_mount() should be converted to call do_mount() directly. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- drivers/base/devtmpfs.c | 5 +++-- fs/namespace.c | 10 ++++++++-- include/linux/syscalls.h | 3 +++ init/do_mounts.c | 4 ++-- init/do_mounts_initrd.c | 6 +++--- 5 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 50025d7959cb..4afb04686c8e 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -356,7 +356,8 @@ int devtmpfs_mount(const char *mntdir) if (!thread) return 0; - err = sys_mount("devtmpfs", (char *)mntdir, "devtmpfs", MS_SILENT, NULL); + err = ksys_mount("devtmpfs", (char *)mntdir, "devtmpfs", MS_SILENT, + NULL); if (err) printk(KERN_INFO "devtmpfs: error mounting %i\n", err); else @@ -382,7 +383,7 @@ static int devtmpfsd(void *p) *err = sys_unshare(CLONE_NEWNS); if (*err) goto out; - *err = sys_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, options); + *err = ksys_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, options); if (*err) goto out; sys_chdir("/.."); /* will traverse into overmounted root */ diff --git a/fs/namespace.c b/fs/namespace.c index 9d1374ab6e06..642b8b229944 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3032,8 +3032,8 @@ struct dentry *mount_subtree(struct vfsmount *mnt, const char *name) } EXPORT_SYMBOL(mount_subtree); -SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, - char __user *, type, unsigned long, flags, void __user *, data) +int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, + unsigned long flags, void __user *data) { int ret; char *kernel_type; @@ -3066,6 +3066,12 @@ out_type: return ret; } +SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name, + char __user *, type, unsigned long, flags, void __user *, data) +{ + return ksys_mount(dev_name, dir_name, type, flags, data); +} + /* * Return true if path is reachable from root * diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 6ab7ed71a8b6..3a9f9c534624 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -946,4 +946,7 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, * the ksys_xyzyyz() functions prototyped below. */ +int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, + unsigned long flags, void __user *data); + #endif diff --git a/init/do_mounts.c b/init/do_mounts.c index 7cf4f6dafd5f..eb768de43d84 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -363,7 +363,7 @@ static void __init get_fs_names(char *page) static int __init do_mount_root(char *name, char *fs, int flags, void *data) { struct super_block *s; - int err = sys_mount(name, "/root", fs, flags, data); + int err = ksys_mount(name, "/root", fs, flags, data); if (err) return err; @@ -599,7 +599,7 @@ void __init prepare_namespace(void) mount_root(); out: devtmpfs_mount("dev"); - sys_mount(".", "/", NULL, MS_MOVE, NULL); + ksys_mount(".", "/", NULL, MS_MOVE, NULL); sys_chroot("."); } diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 53d4f0f326e7..7868a6039fb4 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -43,7 +43,7 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) sys_dup(0); /* move initrd over / and chdir/chroot in initrd root */ sys_chdir("/root"); - sys_mount(".", "/", NULL, MS_MOVE, NULL); + ksys_mount(".", "/", NULL, MS_MOVE, NULL); sys_chroot("."); sys_setsid(); return 0; @@ -81,7 +81,7 @@ static void __init handle_initrd(void) current->flags &= ~PF_FREEZER_SKIP; /* move initrd to rootfs' /old */ - sys_mount("..", ".", NULL, MS_MOVE, NULL); + ksys_mount("..", ".", NULL, MS_MOVE, NULL); /* switch root and cwd back to / of rootfs */ sys_chroot(".."); @@ -95,7 +95,7 @@ static void __init handle_initrd(void) mount_root(); printk(KERN_NOTICE "Trying to move old root to /initrd ... "); - error = sys_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL); + error = ksys_mount("/old", "/root/initrd", NULL, MS_MOVE, NULL); if (!error) printk("okay\n"); else { -- cgit v1.2.3 From 3a18ef5c1b3935cb05888fc37964321f7bd6231d Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:40 +0100 Subject: fs: add ksys_umount() helper; remove in-kernel call to sys_umount() Using this helper allows us to avoid the in-kernel call to the sys_umount() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as ksys_umount(). In the near future, the only fs-external caller of ksys_umount() should be converted to call do_umount() directly. Then, ksys_umount() can be moved within sys_umount() again. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- fs/namespace.c | 9 +++++++-- include/linux/syscalls.h | 1 + init/do_mounts_initrd.c | 2 +- 3 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/namespace.c b/fs/namespace.c index 642b8b229944..e398f32d7541 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1680,7 +1680,7 @@ static inline bool may_mandlock(void) * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD */ -SYSCALL_DEFINE2(umount, char __user *, name, int, flags) +int ksys_umount(char __user *name, int flags) { struct path path; struct mount *mnt; @@ -1720,6 +1720,11 @@ out: return retval; } +SYSCALL_DEFINE2(umount, char __user *, name, int, flags) +{ + return ksys_umount(name, flags); +} + #ifdef __ARCH_WANT_SYS_OLDUMOUNT /* @@ -1727,7 +1732,7 @@ out: */ SYSCALL_DEFINE1(oldumount, char __user *, name) { - return sys_umount(name, 0); + return ksys_umount(name, 0); } #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3a9f9c534624..48964c408c7b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -948,5 +948,6 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, unsigned long flags, void __user *data); +int ksys_umount(char __user *name, int flags); #endif diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 7868a6039fb4..1c4da8353332 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -105,7 +105,7 @@ static void __init handle_initrd(void) else printk("failed\n"); printk(KERN_NOTICE "Unmounting old root\n"); - sys_umount("/old", MNT_DETACH); + ksys_umount("/old", MNT_DETACH); printk(KERN_NOTICE "Trying to free ramdisk memory ... "); if (fd < 0) { error = fd; -- cgit v1.2.3 From c7248321a3d42ffba78db0dde88d1c49ca1c045f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:40 +0100 Subject: fs: add ksys_dup{,3}() helper; remove in-kernel calls to sys_dup{,3}() Using ksys_dup() and ksys_dup3() as helper functions allows us to avoid the in-kernel calls to the sys_dup() and sys_dup3() syscalls. The ksys_ prefix denotes that these functions are meant as a drop-in replacement for the syscalls. In particular, they use the same calling convention as sys_dup{,3}(). In the near future, the fs-external callers of ksys_dup{,3}() should be converted to call do_dup2() directly. Then, ksys_dup{,3}() can be moved within sys_dup{,3}() again. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- fs/file.c | 16 +++++++++++++--- include/linux/syscalls.h | 1 + init/do_mounts_initrd.c | 4 ++-- init/main.c | 4 ++-- 4 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/file.c b/fs/file.c index 42f0db4bd0fb..d304004f0b65 100644 --- a/fs/file.c +++ b/fs/file.c @@ -870,7 +870,7 @@ out_unlock: return err; } -SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) +static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; @@ -904,6 +904,11 @@ out_unlock: return err; } +SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) +{ + return ksys_dup3(oldfd, newfd, flags); +} + SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ @@ -916,10 +921,10 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) rcu_read_unlock(); return retval; } - return sys_dup3(oldfd, newfd, 0); + return ksys_dup3(oldfd, newfd, 0); } -SYSCALL_DEFINE1(dup, unsigned int, fildes) +int ksys_dup(unsigned int fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); @@ -934,6 +939,11 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes) return ret; } +SYSCALL_DEFINE1(dup, unsigned int, fildes) +{ + return ksys_dup(fildes); +} + int f_dupfd(unsigned int from, struct file *file, unsigned flags) { int err; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 48964c408c7b..50876ae1d17b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -949,5 +949,6 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, unsigned long flags, void __user *data); int ksys_umount(char __user *name, int flags); +int ksys_dup(unsigned int fildes); #endif diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 1c4da8353332..e8573e1776f6 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -39,8 +39,8 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) sys_unshare(CLONE_FS | CLONE_FILES); /* stdin/stdout/stderr for /linuxrc */ sys_open("/dev/console", O_RDWR, 0); - sys_dup(0); - sys_dup(0); + ksys_dup(0); + ksys_dup(0); /* move initrd over / and chdir/chroot in initrd root */ sys_chdir("/root"); ksys_mount(".", "/", NULL, MS_MOVE, NULL); diff --git a/init/main.c b/init/main.c index 969eaf140ef0..b8649d1466e1 100644 --- a/init/main.c +++ b/init/main.c @@ -1077,8 +1077,8 @@ static noinline void __init kernel_init_freeable(void) if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) pr_err("Warning: unable to open an initial console.\n"); - (void) sys_dup(0); - (void) sys_dup(0); + (void) ksys_dup(0); + (void) ksys_dup(0); /* * check if there is an early userspace init. If yes, let it do all * the work -- cgit v1.2.3 From a16fe33ab5572e52ef4cb9719d6eb49623b2528a Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:41 +0100 Subject: fs: add ksys_chroot() helper; remove-in kernel calls to sys_chroot() Using this helper allows us to avoid the in-kernel calls to the sys_chroot() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_chroot(). In the near future, the fs-external callers of ksys_chroot() should be converted to use kern_path()/set_fs_root() directly. Then ksys_chroot() can be moved within sys_chroot() again. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- drivers/base/devtmpfs.c | 2 +- fs/open.c | 7 ++++++- include/linux/syscalls.h | 1 + init/do_mounts.c | 2 +- init/do_mounts_initrd.c | 4 ++-- 5 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 4afb04686c8e..5743f04014ca 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -387,7 +387,7 @@ static int devtmpfsd(void *p) if (*err) goto out; sys_chdir("/.."); /* will traverse into overmounted root */ - sys_chroot("."); + ksys_chroot("."); complete(&setup_done); while (1) { spin_lock(&req_lock); diff --git a/fs/open.c b/fs/open.c index 7ea118471dce..7a475e8a2e41 100644 --- a/fs/open.c +++ b/fs/open.c @@ -479,7 +479,7 @@ out: return error; } -SYSCALL_DEFINE1(chroot, const char __user *, filename) +int ksys_chroot(const char __user *filename) { struct path path; int error; @@ -512,6 +512,11 @@ out: return error; } +SYSCALL_DEFINE1(chroot, const char __user *, filename) +{ + return ksys_chroot(filename); +} + static int chmod_common(const struct path *path, umode_t mode) { struct inode *inode = path->dentry->d_inode; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 50876ae1d17b..920a0db1871d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -950,5 +950,6 @@ int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, unsigned long flags, void __user *data); int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); +int ksys_chroot(const char __user *filename); #endif diff --git a/init/do_mounts.c b/init/do_mounts.c index eb768de43d84..2f06f7827b0c 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -600,7 +600,7 @@ void __init prepare_namespace(void) out: devtmpfs_mount("dev"); ksys_mount(".", "/", NULL, MS_MOVE, NULL); - sys_chroot("."); + ksys_chroot("."); } static bool is_tmpfs; diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index e8573e1776f6..71293265ac4b 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -44,7 +44,7 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) /* move initrd over / and chdir/chroot in initrd root */ sys_chdir("/root"); ksys_mount(".", "/", NULL, MS_MOVE, NULL); - sys_chroot("."); + ksys_chroot("."); sys_setsid(); return 0; } @@ -83,7 +83,7 @@ static void __init handle_initrd(void) /* move initrd to rootfs' /old */ ksys_mount("..", ".", NULL, MS_MOVE, NULL); /* switch root and cwd back to / of rootfs */ - sys_chroot(".."); + ksys_chroot(".."); if (new_decode_dev(real_root_dev) == Root_RAM0) { sys_chdir("/old"); -- cgit v1.2.3 From e7a3e8b2edf544ec28f689385c3adc2903f46ec0 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:41 +0100 Subject: fs: add ksys_write() helper; remove in-kernel calls to sys_write() Using this helper allows us to avoid the in-kernel calls to the sys_write() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_write(). In the near future, the do_mounts / initramfs callers of ksys_write() should be converted to use filp_open() and vfs_write() instead. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Cc: linux-s390@vger.kernel.org Signed-off-by: Dominik Brodowski --- arch/s390/kernel/compat_linux.c | 2 +- fs/read_write.c | 9 +++++++-- include/linux/syscalls.h | 1 + init/do_mounts_rd.c | 4 ++-- init/initramfs.c | 2 +- 5 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 79b7a3438d54..5a9cfde5fc28 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -468,7 +468,7 @@ COMPAT_SYSCALL_DEFINE3(s390_write, unsigned int, fd, const char __user *, buf, c if ((compat_ssize_t) count < 0) return -EINVAL; - return sys_write(fd, buf, count); + return ksys_write(fd, buf, count); } /* diff --git a/fs/read_write.c b/fs/read_write.c index f8547b82dfb3..8e8f0b4f52e2 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -578,8 +578,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) return ret; } -SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, - size_t, count) +ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -595,6 +594,12 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, return ret; } +SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, + size_t, count) +{ + return ksys_write(fd, buf, count); +} + SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 920a0db1871d..80524faa9664 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -951,5 +951,6 @@ int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type, int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); +ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); #endif diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 99e0b649fc0e..2d365c398ccc 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -270,7 +270,7 @@ int __init rd_load_image(char *from) printk("Loading disk #%d... ", disk); } sys_read(in_fd, buf, BLOCK_SIZE); - sys_write(out_fd, buf, BLOCK_SIZE); + ksys_write(out_fd, buf, BLOCK_SIZE); #if !defined(CONFIG_S390) if (!(i % 16)) { pr_cont("%c\b", rotator[rotate & 0x3]); @@ -317,7 +317,7 @@ static long __init compr_fill(void *buf, unsigned long len) static long __init compr_flush(void *window, unsigned long outcnt) { - long written = sys_write(crd_outfd, window, outcnt); + long written = ksys_write(crd_outfd, window, outcnt); if (written != outcnt) { if (decompress_error == 0) printk(KERN_ERR diff --git a/init/initramfs.c b/init/initramfs.c index 7e99a0038942..6f972df15bf2 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -27,7 +27,7 @@ static ssize_t __init xwrite(int fd, const char *p, size_t count) /* sys_write only can write MAX_RW_COUNT aka 2G-4K bytes at most */ while (count) { - ssize_t rv = sys_write(fd, p, count); + ssize_t rv = ksys_write(fd, p, count); if (rv < 0) { if (rv == -EINTR || rv == -EAGAIN) -- cgit v1.2.3 From 447016e9681965fda8dcd9e4fd3c55308a6fd166 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:46 +0100 Subject: fs: add ksys_chdir() helper; remove in-kernel calls to sys_chdir() Using this helper allows us to avoid the in-kernel calls to the sys_chdir() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_chdir(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- drivers/base/devtmpfs.c | 2 +- fs/open.c | 7 ++++++- include/linux/syscalls.h | 1 + init/do_mounts.c | 2 +- init/do_mounts_initrd.c | 8 ++++---- 5 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 5743f04014ca..3f7ee954fd2c 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -386,7 +386,7 @@ static int devtmpfsd(void *p) *err = ksys_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, options); if (*err) goto out; - sys_chdir("/.."); /* will traverse into overmounted root */ + ksys_chdir("/.."); /* will traverse into overmounted root */ ksys_chroot("."); complete(&setup_done); while (1) { diff --git a/fs/open.c b/fs/open.c index 7a475e8a2e41..a19b8277c439 100644 --- a/fs/open.c +++ b/fs/open.c @@ -431,7 +431,7 @@ SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) return sys_faccessat(AT_FDCWD, filename, mode); } -SYSCALL_DEFINE1(chdir, const char __user *, filename) +int ksys_chdir(const char __user *filename) { struct path path; int error; @@ -457,6 +457,11 @@ out: return error; } +SYSCALL_DEFINE1(chdir, const char __user *, filename) +{ + return ksys_chdir(filename); +} + SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct fd f = fdget_raw(fd); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 80524faa9664..090645b48447 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -952,5 +952,6 @@ int ksys_umount(char __user *name, int flags); int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); +int ksys_chdir(const char __user *filename); #endif diff --git a/init/do_mounts.c b/init/do_mounts.c index 2f06f7827b0c..89f18985fa90 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -367,7 +367,7 @@ static int __init do_mount_root(char *name, char *fs, int flags, void *data) if (err) return err; - sys_chdir("/root"); + ksys_chdir("/root"); s = current->fs->pwd.dentry->d_sb; ROOT_DEV = s->s_dev; printk(KERN_INFO diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 71293265ac4b..83f396d30b9a 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -42,7 +42,7 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) ksys_dup(0); ksys_dup(0); /* move initrd over / and chdir/chroot in initrd root */ - sys_chdir("/root"); + ksys_chdir("/root"); ksys_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); sys_setsid(); @@ -61,7 +61,7 @@ static void __init handle_initrd(void) /* mount initrd on rootfs' /root */ mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY); sys_mkdir("/old", 0700); - sys_chdir("/old"); + ksys_chdir("/old"); /* try loading default modules from initrd */ load_default_modules(); @@ -86,11 +86,11 @@ static void __init handle_initrd(void) ksys_chroot(".."); if (new_decode_dev(real_root_dev) == Root_RAM0) { - sys_chdir("/old"); + ksys_chdir("/old"); return; } - sys_chdir("/"); + ksys_chdir("/"); ROOT_DEV = new_decode_dev(real_root_dev); mount_root(); -- cgit v1.2.3 From 0f32ab8cfac478be053cb526ced8918ef6f4df47 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:47 +0100 Subject: fs: add ksys_unlink() wrapper; remove in-kernel calls to sys_unlink() Using this wrapper allows us to avoid the in-kernel calls to the sys_unlink() syscall. The ksys_ prefix denotes that this function is meant s a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_unlink(). In the near future, all callers of ksys_unlink() should be converted to call do_unlinkat() directly or, at least, to operate on regular kernel pointers. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 11 +++++++++++ init/do_mounts.h | 2 +- init/do_mounts_initrd.c | 4 ++-- init/do_mounts_rd.c | 2 +- init/initramfs.c | 4 ++-- 5 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 090645b48447..7cbfb41e666b 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -954,4 +954,15 @@ int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); +/* + * The following kernel syscall equivalents are just wrappers to fs-internal + * functions. Therefore, provide stubs to be inlined at the callsites. + */ +extern long do_unlinkat(int dfd, struct filename *name); + +static inline long ksys_unlink(const char __user *pathname) +{ + return do_unlinkat(AT_FDCWD, getname(pathname)); +} + #endif diff --git a/init/do_mounts.h b/init/do_mounts.h index 5b05c8f93f47..401f90ee1eeb 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -16,7 +16,7 @@ extern int root_mountflags; static inline int create_dev(char *name, dev_t dev) { - sys_unlink(name); + ksys_unlink(name); return sys_mknod(name, S_IFBLK|0600, new_encode_dev(dev)); } diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 83f396d30b9a..e9e9e1c67d31 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -128,11 +128,11 @@ bool __init initrd_load(void) * mounted in the normal path. */ if (rd_load_image("/initrd.image") && ROOT_DEV != Root_RAM0) { - sys_unlink("/initrd.image"); + ksys_unlink("/initrd.image"); handle_initrd(); return true; } } - sys_unlink("/initrd.image"); + ksys_unlink("/initrd.image"); return false; } diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 2d365c398ccc..5b69056f610a 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -288,7 +288,7 @@ noclose_input: sys_close(out_fd); out: kfree(buf); - sys_unlink("/dev/ram"); + ksys_unlink("/dev/ram"); return res; } diff --git a/init/initramfs.c b/init/initramfs.c index 6f972df15bf2..08eb551168a8 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -319,7 +319,7 @@ static void __init clean_path(char *path, umode_t fmode) if (S_ISDIR(st.mode)) sys_rmdir(path); else - sys_unlink(path); + ksys_unlink(path); } } @@ -591,7 +591,7 @@ static void __init clean_rootfs(void) if (S_ISDIR(st.mode)) sys_rmdir(dirp->d_name); else - sys_unlink(dirp->d_name); + ksys_unlink(dirp->d_name); } num -= dirp->d_reclen; -- cgit v1.2.3 From f459dffae1c6026928bbe8e972daecb635b7b5e9 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:48 +0100 Subject: fs: add ksys_rmdir() wrapper; remove in-kernel calls to sys_rmdir() Using this wrapper allows us to avoid the in-kernel calls to the sys_rmdir() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_rmdir(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/internal.h | 1 + fs/namei.c | 2 +- include/linux/syscalls.h | 7 +++++++ init/initramfs.c | 4 ++-- 4 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/internal.h b/fs/internal.h index df262f41a0ef..0eda35fa1743 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -55,6 +55,7 @@ extern void __init chrdev_init(void); extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); +long do_rmdir(int dfd, const char __user *pathname); long do_unlinkat(int dfd, struct filename *name); /* diff --git a/fs/namei.c b/fs/namei.c index 524e829ffc7d..8545151f74e9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3872,7 +3872,7 @@ out: } EXPORT_SYMBOL(vfs_rmdir); -static long do_rmdir(int dfd, const char __user *pathname) +long do_rmdir(int dfd, const char __user *pathname) { int error = 0; struct filename *name; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 7cbfb41e666b..746043a05884 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -965,4 +965,11 @@ static inline long ksys_unlink(const char __user *pathname) return do_unlinkat(AT_FDCWD, getname(pathname)); } +extern long do_rmdir(int dfd, const char __user *pathname); + +static inline long ksys_rmdir(const char __user *pathname) +{ + return do_rmdir(AT_FDCWD, pathname); +} + #endif diff --git a/init/initramfs.c b/init/initramfs.c index 08eb551168a8..73bbb227f868 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -317,7 +317,7 @@ static void __init clean_path(char *path, umode_t fmode) if (!vfs_lstat(path, &st) && (st.mode ^ fmode) & S_IFMT) { if (S_ISDIR(st.mode)) - sys_rmdir(path); + ksys_rmdir(path); else ksys_unlink(path); } @@ -589,7 +589,7 @@ static void __init clean_rootfs(void) WARN_ON_ONCE(ret); if (!ret) { if (S_ISDIR(st.mode)) - sys_rmdir(dirp->d_name); + ksys_rmdir(dirp->d_name); else ksys_unlink(dirp->d_name); } -- cgit v1.2.3 From 0101db7a301981a008296d522d8c1f456b0fe837 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:49 +0100 Subject: fs: add do_mkdirat() helper and ksys_mkdir() wrapper; remove in-kernel calls to syscall Using the fs-internal do_mkdirat() helper allows us to get rid of fs-internal calls to the sys_mkdirat() syscall. Introducing the ksys_mkdir() wrapper allows us to avoid the in-kernel calls to the sys_mkdir() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mkdir(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/internal.h | 1 + fs/namei.c | 9 +++++++-- include/linux/syscalls.h | 7 +++++++ init/do_mounts_initrd.c | 2 +- init/initramfs.c | 2 +- init/noinitramfs.c | 4 ++-- 6 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/internal.h b/fs/internal.h index 0eda35fa1743..53846bd4d9d7 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -55,6 +55,7 @@ extern void __init chrdev_init(void); extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); +long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); long do_rmdir(int dfd, const char __user *pathname); long do_unlinkat(int dfd, struct filename *name); diff --git a/fs/namei.c b/fs/namei.c index 8545151f74e9..dcf506227509 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3803,7 +3803,7 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } EXPORT_SYMBOL(vfs_mkdir); -SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) +long do_mkdirat(int dfd, const char __user *pathname, umode_t mode) { struct dentry *dentry; struct path path; @@ -3828,9 +3828,14 @@ retry: return error; } +SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) +{ + return do_mkdirat(dfd, pathname, mode); +} + SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { - return sys_mkdirat(AT_FDCWD, pathname, mode); + return do_mkdirat(AT_FDCWD, pathname, mode); } int vfs_rmdir(struct inode *dir, struct dentry *dentry) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 746043a05884..c982cb5f4e50 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -972,4 +972,11 @@ static inline long ksys_rmdir(const char __user *pathname) return do_rmdir(AT_FDCWD, pathname); } +extern long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); + +static inline long ksys_mkdir(const char __user *pathname, umode_t mode) +{ + return do_mkdirat(AT_FDCWD, pathname, mode); +} + #endif diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index e9e9e1c67d31..99922d1ebfe6 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -60,7 +60,7 @@ static void __init handle_initrd(void) create_dev("/dev/root.old", Root_RAM0); /* mount initrd on rootfs' /root */ mount_block_root("/dev/root.old", root_mountflags & ~MS_RDONLY); - sys_mkdir("/old", 0700); + ksys_mkdir("/old", 0700); ksys_chdir("/old"); /* try loading default modules from initrd */ diff --git a/init/initramfs.c b/init/initramfs.c index 73bbb227f868..ca538a5f9fa9 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -352,7 +352,7 @@ static int __init do_name(void) } } } else if (S_ISDIR(mode)) { - sys_mkdir(collected, mode); + ksys_mkdir(collected, mode); sys_chown(collected, uid, gid); sys_chmod(collected, mode); dir_add(collected, mtime); diff --git a/init/noinitramfs.c b/init/noinitramfs.c index 267739d85179..a08a9d937e60 100644 --- a/init/noinitramfs.c +++ b/init/noinitramfs.c @@ -29,7 +29,7 @@ static int __init default_rootfs(void) { int err; - err = sys_mkdir((const char __user __force *) "/dev", 0755); + err = ksys_mkdir((const char __user __force *) "/dev", 0755); if (err < 0) goto out; @@ -39,7 +39,7 @@ static int __init default_rootfs(void) if (err < 0) goto out; - err = sys_mkdir((const char __user __force *) "/root", 0700); + err = ksys_mkdir((const char __user __force *) "/root", 0700); if (err < 0) goto out; -- cgit v1.2.3 From b724e846b491ef8db943be8086226c9d8da31877 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:49 +0100 Subject: fs: add do_symlinkat() helper and ksys_symlink() wrapper; remove in-kernel calls to syscall Using the fs-internal do_symlinkat() helper allows us to get rid of fs-internal calls to the sys_symlinkat() syscall. Introducing the ksys_symlink() wrapper allows us to avoid the in-kernel calls to the sys_symlink() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_symlink(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/internal.h | 2 ++ fs/namei.c | 12 +++++++++--- include/linux/syscalls.h | 9 +++++++++ init/initramfs.c | 2 +- 4 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/internal.h b/fs/internal.h index 53846bd4d9d7..a3f04ca2a08b 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -58,6 +58,8 @@ extern int vfs_path_lookup(struct dentry *, struct vfsmount *, long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); long do_rmdir(int dfd, const char __user *pathname); long do_unlinkat(int dfd, struct filename *name); +long do_symlinkat(const char __user *oldname, int newdfd, + const char __user *newname); /* * namespace.c diff --git a/fs/namei.c b/fs/namei.c index dcf506227509..e15da92209d5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4113,8 +4113,8 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname) } EXPORT_SYMBOL(vfs_symlink); -SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, - int, newdfd, const char __user *, newname) +long do_symlinkat(const char __user *oldname, int newdfd, + const char __user *newname) { int error; struct filename *from; @@ -4144,9 +4144,15 @@ out_putname: return error; } +SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, + int, newdfd, const char __user *, newname) +{ + return do_symlinkat(oldname, newdfd, newname); +} + SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { - return sys_symlinkat(oldname, AT_FDCWD, newname); + return do_symlinkat(oldname, AT_FDCWD, newname); } /** diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c982cb5f4e50..39c5cef86a10 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -979,4 +979,13 @@ static inline long ksys_mkdir(const char __user *pathname, umode_t mode) return do_mkdirat(AT_FDCWD, pathname, mode); } +extern long do_symlinkat(const char __user *oldname, int newdfd, + const char __user *newname); + +static inline long ksys_symlink(const char __user *oldname, + const char __user *newname) +{ + return do_symlinkat(oldname, AT_FDCWD, newname); +} + #endif diff --git a/init/initramfs.c b/init/initramfs.c index ca538a5f9fa9..cd9571a113b6 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -392,7 +392,7 @@ static int __init do_symlink(void) { collected[N_ALIGN(name_len) + body_len] = '\0'; clean_path(collected, 0); - sys_symlink(collected + N_ALIGN(name_len), collected); + ksys_symlink(collected + N_ALIGN(name_len), collected); sys_lchown(collected, uid, gid); do_utime(collected, mtime); state = SkipIt; -- cgit v1.2.3 From 87c4e19262d81862886207be3c8795f6576d5a52 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:50 +0100 Subject: fs: add do_mknodat() helper and ksys_mknod() wrapper; remove in-kernel calls to syscall Using the fs-internal do_mknodat() helper allows us to get rid of fs-internal calls to the sys_mknodat() syscall. Introducing the ksys_mknod() wrapper allows us to avoid the in-kernel calls to sys_mknod() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mknod(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/internal.h | 2 ++ fs/namei.c | 12 +++++++++--- include/linux/syscalls.h | 9 +++++++++ init/do_mounts.h | 2 +- init/initramfs.c | 2 +- init/noinitramfs.c | 2 +- 6 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/internal.h b/fs/internal.h index a3f04ca2a08b..4f0b67054c54 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -55,6 +55,8 @@ extern void __init chrdev_init(void); extern int user_path_mountpoint_at(int, const char __user *, unsigned int, struct path *); extern int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); +long do_mknodat(int dfd, const char __user *filename, umode_t mode, + unsigned int dev); long do_mkdirat(int dfd, const char __user *pathname, umode_t mode); long do_rmdir(int dfd, const char __user *pathname); long do_unlinkat(int dfd, struct filename *name); diff --git a/fs/namei.c b/fs/namei.c index e15da92209d5..8459a18cdd18 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3728,8 +3728,8 @@ static int may_mknod(umode_t mode) } } -SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, - unsigned, dev) +long do_mknodat(int dfd, const char __user *filename, umode_t mode, + unsigned int dev) { struct dentry *dentry; struct path path; @@ -3772,9 +3772,15 @@ out: return error; } +SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, + unsigned int, dev) +{ + return do_mknodat(dfd, filename, mode, dev); +} + SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { - return sys_mknodat(AT_FDCWD, filename, mode, dev); + return do_mknodat(AT_FDCWD, filename, mode, dev); } int vfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 39c5cef86a10..0b4fd684f0f1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -988,4 +988,13 @@ static inline long ksys_symlink(const char __user *oldname, return do_symlinkat(oldname, AT_FDCWD, newname); } +extern long do_mknodat(int dfd, const char __user *filename, umode_t mode, + unsigned int dev); + +static inline long ksys_mknod(const char __user *filename, umode_t mode, + unsigned int dev) +{ + return do_mknodat(AT_FDCWD, filename, mode, dev); +} + #endif diff --git a/init/do_mounts.h b/init/do_mounts.h index 401f90ee1eeb..0bb0806de4ce 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -17,7 +17,7 @@ extern int root_mountflags; static inline int create_dev(char *name, dev_t dev) { ksys_unlink(name); - return sys_mknod(name, S_IFBLK|0600, new_encode_dev(dev)); + return ksys_mknod(name, S_IFBLK|0600, new_encode_dev(dev)); } static inline u32 bstat(char *name) diff --git a/init/initramfs.c b/init/initramfs.c index cd9571a113b6..2972ed0ab399 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -359,7 +359,7 @@ static int __init do_name(void) } else if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { if (maybe_link() == 0) { - sys_mknod(collected, mode, rdev); + ksys_mknod(collected, mode, rdev); sys_chown(collected, uid, gid); sys_chmod(collected, mode); do_utime(collected, mtime); diff --git a/init/noinitramfs.c b/init/noinitramfs.c index a08a9d937e60..f4bad8436c93 100644 --- a/init/noinitramfs.c +++ b/init/noinitramfs.c @@ -33,7 +33,7 @@ static int __init default_rootfs(void) if (err < 0) goto out; - err = sys_mknod((const char __user __force *) "/dev/console", + err = ksys_mknod((const char __user __force *) "/dev/console", S_IFCHR | S_IRUSR | S_IWUSR, new_encode_dev(MKDEV(5, 1))); if (err < 0) -- cgit v1.2.3 From 46ea89eb652a365e10257016d09dcf1aaf23cf63 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:53 +0100 Subject: fs: add do_linkat() helper and ksys_link() wrapper; remove in-kernel calls to syscall Using the fs-internal do_linkat() helper allows us to get rid of fs-internal calls to the sys_linkat() syscall. Introducing the ksys_link() wrapper allows us to avoid the in-kernel calls to sys_link() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_link(). In the near future, the only fs-external user of ksys_link() should be converted to use vfs_link() instead. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/internal.h | 2 ++ fs/namei.c | 12 +++++++++--- include/linux/syscalls.h | 9 +++++++++ init/initramfs.c | 2 +- 4 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/internal.h b/fs/internal.h index 4f0b67054c54..91e6fc93fcb5 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -62,6 +62,8 @@ long do_rmdir(int dfd, const char __user *pathname); long do_unlinkat(int dfd, struct filename *name); long do_symlinkat(const char __user *oldname, int newdfd, const char __user *newname); +int do_linkat(int olddfd, const char __user *oldname, int newdfd, + const char __user *newname, int flags); /* * namespace.c diff --git a/fs/namei.c b/fs/namei.c index 8459a18cdd18..10148235829f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4250,8 +4250,8 @@ EXPORT_SYMBOL(vfs_link); * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ -SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, - int, newdfd, const char __user *, newname, int, flags) +int do_linkat(int olddfd, const char __user *oldname, int newdfd, + const char __user *newname, int flags) { struct dentry *new_dentry; struct path old_path, new_path; @@ -4315,9 +4315,15 @@ out: return error; } +SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, + int, newdfd, const char __user *, newname, int, flags) +{ + return do_linkat(olddfd, oldname, newdfd, newname, flags); +} + SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { - return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); + return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } /** diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0b4fd684f0f1..827ed917630c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -997,4 +997,13 @@ static inline long ksys_mknod(const char __user *filename, umode_t mode, return do_mknodat(AT_FDCWD, filename, mode, dev); } +extern int do_linkat(int olddfd, const char __user *oldname, int newdfd, + const char __user *newname, int flags); + +static inline long ksys_link(const char __user *oldname, + const char __user *newname) +{ + return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); +} + #endif diff --git a/init/initramfs.c b/init/initramfs.c index 2972ed0ab399..5855ab632b4e 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -306,7 +306,7 @@ static int __init maybe_link(void) if (nlink >= 2) { char *old = find_link(major, minor, ino, mode, collected); if (old) - return (sys_link(old, collected) < 0) ? -1 : 1; + return (ksys_link(old, collected) < 0) ? -1 : 1; } return 0; } -- cgit v1.2.3 From 03450e271a160bc07a2c48e5769e0ba338582d77 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:53 +0100 Subject: fs: add ksys_fchmod() and do_fchmodat() helpers and ksys_chmod() wrapper; remove in-kernel calls to syscall Using the fs-internal do_fchmodat() helper allows us to get rid of fs-internal calls to the sys_fchmodat() syscall. Introducing the ksys_fchmod() helper and the ksys_chmod() wrapper allows us to avoid the in-kernel calls to the sys_fchmod() and sys_chmod() syscalls. The ksys_ prefix denotes that these functions are meant as a drop-in replacement for the syscalls. In particular, they use the same calling convention as sys_fchmod() and sys_chmod(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/internal.h | 2 ++ fs/open.c | 17 ++++++++++++++--- include/linux/syscalls.h | 8 ++++++++ init/initramfs.c | 6 +++--- 4 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/internal.h b/fs/internal.h index 91e6fc93fcb5..2474bf460f96 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -119,6 +119,8 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname, extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); +int do_fchmodat(int dfd, const char __user *filename, umode_t mode); + extern int open_check_o_direct(struct file *f); extern int vfs_open(const struct path *, struct file *, const struct cred *); extern struct file *filp_clone_open(struct file *); diff --git a/fs/open.c b/fs/open.c index a19b8277c439..6037f2bf418c 100644 --- a/fs/open.c +++ b/fs/open.c @@ -551,7 +551,7 @@ out_unlock: return error; } -SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) +int ksys_fchmod(unsigned int fd, umode_t mode) { struct fd f = fdget(fd); int err = -EBADF; @@ -564,7 +564,12 @@ SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) return err; } -SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode) +SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode) +{ + return ksys_fchmod(fd, mode); +} + +int do_fchmodat(int dfd, const char __user *filename, umode_t mode) { struct path path; int error; @@ -582,9 +587,15 @@ retry: return error; } +SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, + umode_t, mode) +{ + return do_fchmodat(dfd, filename, mode); +} + SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) { - return sys_fchmodat(AT_FDCWD, filename, mode); + return do_fchmodat(AT_FDCWD, filename, mode); } static int chown_common(const struct path *path, uid_t user, gid_t group) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 827ed917630c..dd6c306f4f00 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -953,6 +953,7 @@ int ksys_dup(unsigned int fildes); int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); +int ksys_fchmod(unsigned int fd, umode_t mode); /* * The following kernel syscall equivalents are just wrappers to fs-internal @@ -1006,4 +1007,11 @@ static inline long ksys_link(const char __user *oldname, return do_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); } +extern int do_fchmodat(int dfd, const char __user *filename, umode_t mode); + +static inline int ksys_chmod(const char __user *filename, umode_t mode) +{ + return do_fchmodat(AT_FDCWD, filename, mode); +} + #endif diff --git a/init/initramfs.c b/init/initramfs.c index 5855ab632b4e..16c3c23076e2 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -344,7 +344,7 @@ static int __init do_name(void) if (wfd >= 0) { sys_fchown(wfd, uid, gid); - sys_fchmod(wfd, mode); + ksys_fchmod(wfd, mode); if (body_len) sys_ftruncate(wfd, body_len); vcollected = kstrdup(collected, GFP_KERNEL); @@ -354,14 +354,14 @@ static int __init do_name(void) } else if (S_ISDIR(mode)) { ksys_mkdir(collected, mode); sys_chown(collected, uid, gid); - sys_chmod(collected, mode); + ksys_chmod(collected, mode); dir_add(collected, mtime); } else if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { if (maybe_link() == 0) { ksys_mknod(collected, mode, rdev); sys_chown(collected, uid, gid); - sys_chmod(collected, mode); + ksys_chmod(collected, mode); do_utime(collected, mtime); } } -- cgit v1.2.3 From cbfe20f565228966f0249f016752437df95df679 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:54 +0100 Subject: fs: add do_faccessat() helper and ksys_access() wrapper; remove in-kernel calls to syscall Using the fs-internal do_faccessat() helper allows us to get rid of fs-internal calls to the sys_faccessat() syscall. Introducing the ksys_access() wrapper allows us to avoid the in-kernel calls to the sys_access() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_access(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/internal.h | 1 + fs/open.c | 9 +++++++-- include/linux/syscalls.h | 7 +++++++ init/main.c | 3 ++- 4 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/internal.h b/fs/internal.h index 2474bf460f96..26f4f05b52ef 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -119,6 +119,7 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname, extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); +long do_faccessat(int dfd, const char __user *filename, int mode); int do_fchmodat(int dfd, const char __user *filename, umode_t mode); extern int open_check_o_direct(struct file *f); diff --git a/fs/open.c b/fs/open.c index 6037f2bf418c..0fc8188be31a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -350,7 +350,7 @@ SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) * We do this by temporarily clearing all FS-related capabilities and * switching the fsuid/fsgid around to the real ones. */ -SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) +long do_faccessat(int dfd, const char __user *filename, int mode) { const struct cred *old_cred; struct cred *override_cred; @@ -426,9 +426,14 @@ out: return res; } +SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) +{ + return do_faccessat(dfd, filename, mode); +} + SYSCALL_DEFINE2(access, const char __user *, filename, int, mode) { - return sys_faccessat(AT_FDCWD, filename, mode); + return do_faccessat(AT_FDCWD, filename, mode); } int ksys_chdir(const char __user *filename) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index dd6c306f4f00..33f06de090ea 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1014,4 +1014,11 @@ static inline int ksys_chmod(const char __user *filename, umode_t mode) return do_fchmodat(AT_FDCWD, filename, mode); } +extern long do_faccessat(int dfd, const char __user *filename, int mode); + +static inline long ksys_access(const char __user *filename, int mode) +{ + return do_faccessat(AT_FDCWD, filename, mode); +} + #endif diff --git a/init/main.c b/init/main.c index b8649d1466e1..d0ded4322c6b 100644 --- a/init/main.c +++ b/init/main.c @@ -1087,7 +1087,8 @@ static noinline void __init kernel_init_freeable(void) if (!ramdisk_execute_command) ramdisk_execute_command = "/init"; - if (sys_access((const char __user *) ramdisk_execute_command, 0) != 0) { + if (ksys_access((const char __user *) + ramdisk_execute_command, 0) != 0) { ramdisk_execute_command = NULL; prepare_namespace(); } -- cgit v1.2.3 From 55731b3cda3a85ee888dac3bf1f36489f275c187 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:55 +0100 Subject: fs: add do_fchownat(), ksys_fchown() helpers and ksys_{,l}chown() wrappers Using the fs-interal do_fchownat() wrapper allows us to get rid of fs-internal calls to the sys_fchownat() syscall. Introducing the ksys_fchown() helper and the ksys_{,}chown() wrappers allows us to avoid the in-kernel calls to the sys_{,l,f}chown() syscalls. The ksys_ prefix denotes that these functions are meant as a drop-in replacement for the syscalls. In particular, they use the same calling convention as sys_{,l,f}chown(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- arch/s390/kernel/compat_linux.c | 6 +++--- fs/internal.h | 2 ++ fs/open.c | 23 +++++++++++++++++------ include/linux/syscalls.h | 17 +++++++++++++++++ init/initramfs.c | 8 ++++---- kernel/uid16.c | 6 +++--- 6 files changed, 46 insertions(+), 16 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 5a9cfde5fc28..9a9bb395359c 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -89,18 +89,18 @@ COMPAT_SYSCALL_DEFINE3(s390_chown16, const char __user *, filename, u16, user, u16, group) { - return sys_chown(filename, low2highuid(user), low2highgid(group)); + return ksys_chown(filename, low2highuid(user), low2highgid(group)); } COMPAT_SYSCALL_DEFINE3(s390_lchown16, const char __user *, filename, u16, user, u16, group) { - return sys_lchown(filename, low2highuid(user), low2highgid(group)); + return ksys_lchown(filename, low2highuid(user), low2highgid(group)); } COMPAT_SYSCALL_DEFINE3(s390_fchown16, unsigned int, fd, u16, user, u16, group) { - return sys_fchown(fd, low2highuid(user), low2highgid(group)); + return ksys_fchown(fd, low2highuid(user), low2highgid(group)); } COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid) diff --git a/fs/internal.h b/fs/internal.h index 26f4f05b52ef..c797480cbd6f 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -121,6 +121,8 @@ extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, long do_faccessat(int dfd, const char __user *filename, int mode); int do_fchmodat(int dfd, const char __user *filename, umode_t mode); +int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, + int flag); extern int open_check_o_direct(struct file *f); extern int vfs_open(const struct path *, struct file *, const struct cred *); diff --git a/fs/open.c b/fs/open.c index 0fc8188be31a..7b2eccb541f2 100644 --- a/fs/open.c +++ b/fs/open.c @@ -645,8 +645,8 @@ retry_deleg: return error; } -SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, - gid_t, group, int, flag) +int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, + int flag) { struct path path; int error = -EINVAL; @@ -677,18 +677,24 @@ out: return error; } +SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user, + gid_t, group, int, flag) +{ + return do_fchownat(dfd, filename, user, group, flag); +} + SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group) { - return sys_fchownat(AT_FDCWD, filename, user, group, 0); + return do_fchownat(AT_FDCWD, filename, user, group, 0); } SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group) { - return sys_fchownat(AT_FDCWD, filename, user, group, - AT_SYMLINK_NOFOLLOW); + return do_fchownat(AT_FDCWD, filename, user, group, + AT_SYMLINK_NOFOLLOW); } -SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) +int ksys_fchown(unsigned int fd, uid_t user, gid_t group) { struct fd f = fdget(fd); int error = -EBADF; @@ -708,6 +714,11 @@ out: return error; } +SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) +{ + return ksys_fchown(fd, user, group); +} + int open_check_o_direct(struct file *f) { /* NB: we're sure to have correct a_ops only after f_op->open */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 33f06de090ea..df0d1e818a6e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -954,6 +954,7 @@ int ksys_chroot(const char __user *filename); ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); int ksys_fchmod(unsigned int fd, umode_t mode); +int ksys_fchown(unsigned int fd, uid_t user, gid_t group); /* * The following kernel syscall equivalents are just wrappers to fs-internal @@ -1021,4 +1022,20 @@ static inline long ksys_access(const char __user *filename, int mode) return do_faccessat(AT_FDCWD, filename, mode); } +extern int do_fchownat(int dfd, const char __user *filename, uid_t user, + gid_t group, int flag); + +static inline long ksys_chown(const char __user *filename, uid_t user, + gid_t group) +{ + return do_fchownat(AT_FDCWD, filename, user, group, 0); +} + +static inline long ksys_lchown(const char __user *filename, uid_t user, + gid_t group) +{ + return do_fchownat(AT_FDCWD, filename, user, group, + AT_SYMLINK_NOFOLLOW); +} + #endif diff --git a/init/initramfs.c b/init/initramfs.c index 16c3c23076e2..35173bef7c00 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -343,7 +343,7 @@ static int __init do_name(void) wfd = sys_open(collected, openflags, mode); if (wfd >= 0) { - sys_fchown(wfd, uid, gid); + ksys_fchown(wfd, uid, gid); ksys_fchmod(wfd, mode); if (body_len) sys_ftruncate(wfd, body_len); @@ -353,14 +353,14 @@ static int __init do_name(void) } } else if (S_ISDIR(mode)) { ksys_mkdir(collected, mode); - sys_chown(collected, uid, gid); + ksys_chown(collected, uid, gid); ksys_chmod(collected, mode); dir_add(collected, mtime); } else if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { if (maybe_link() == 0) { ksys_mknod(collected, mode, rdev); - sys_chown(collected, uid, gid); + ksys_chown(collected, uid, gid); ksys_chmod(collected, mode); do_utime(collected, mtime); } @@ -393,7 +393,7 @@ static int __init do_symlink(void) collected[N_ALIGN(name_len) + body_len] = '\0'; clean_path(collected, 0); ksys_symlink(collected + N_ALIGN(name_len), collected); - sys_lchown(collected, uid, gid); + ksys_lchown(collected, uid, gid); do_utime(collected, mtime); state = SkipIt; next_state = Reset; diff --git a/kernel/uid16.c b/kernel/uid16.c index 7b930edfe461..af6925d8599b 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -22,17 +22,17 @@ SYSCALL_DEFINE3(chown16, const char __user *, filename, old_uid_t, user, old_gid_t, group) { - return sys_chown(filename, low2highuid(user), low2highgid(group)); + return ksys_chown(filename, low2highuid(user), low2highgid(group)); } SYSCALL_DEFINE3(lchown16, const char __user *, filename, old_uid_t, user, old_gid_t, group) { - return sys_lchown(filename, low2highuid(user), low2highgid(group)); + return ksys_lchown(filename, low2highuid(user), low2highgid(group)); } SYSCALL_DEFINE3(fchown16, unsigned int, fd, old_uid_t, user, old_gid_t, group) { - return sys_fchown(fd, low2highuid(user), low2highgid(group)); + return ksys_fchown(fd, low2highuid(user), low2highgid(group)); } SYSCALL_DEFINE2(setregid16, old_gid_t, rgid, old_gid_t, egid) -- cgit v1.2.3 From 411d9475cf901b5a6d2996b46cb5726184a4fa50 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:54 +0100 Subject: fs: add ksys_ftruncate() wrapper; remove in-kernel calls to sys_ftruncate() Using the ksys_ftruncate() wrapper allows us to get rid of in-kernel calls to the sys_ftruncate() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_ftruncate(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- arch/mips/kernel/linux32.c | 2 +- arch/parisc/kernel/sys_parisc.c | 4 ++-- arch/powerpc/kernel/sys_ppc32.c | 2 +- arch/s390/kernel/compat_linux.c | 2 +- arch/sparc/kernel/sys_sparc32.c | 2 +- arch/x86/ia32/sys_ia32.c | 2 +- fs/internal.h | 1 + fs/open.c | 2 +- include/linux/syscalls.h | 7 +++++++ init/initramfs.c | 2 +- 10 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index b332f6fc1e72..3c90449742a0 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -88,7 +88,7 @@ SYSCALL_DEFINE4(32_truncate64, const char __user *, path, SYSCALL_DEFINE4(32_ftruncate64, unsigned long, fd, unsigned long, __dummy, unsigned long, a2, unsigned long, a3) { - return sys_ftruncate(fd, merge_64(a2, a3)); + return ksys_ftruncate(fd, merge_64(a2, a3)); } SYSCALL_DEFINE5(32_llseek, unsigned int, fd, unsigned int, offset_high, diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 378a754ca186..6d2a64859c22 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -298,7 +298,7 @@ asmlinkage long parisc_truncate64(const char __user * path, asmlinkage long parisc_ftruncate64(unsigned int fd, unsigned int high, unsigned int low) { - return sys_ftruncate(fd, (long)high << 32 | low); + return ksys_ftruncate(fd, (long)high << 32 | low); } /* stubs for the benefit of the syscall_table since truncate64 and truncate @@ -309,7 +309,7 @@ asmlinkage long sys_truncate64(const char __user * path, unsigned long length) } asmlinkage long sys_ftruncate64(unsigned int fd, unsigned long length) { - return sys_ftruncate(fd, length); + return ksys_ftruncate(fd, length); } asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg) { diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 15f216d022e2..e0c9b7f1bf38 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -107,7 +107,7 @@ asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo, asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long high, unsigned long low) { - return sys_ftruncate(fd, (high << 32) | low); + return ksys_ftruncate(fd, (high << 32) | low); } long ppc32_fadvise64(int fd, u32 unused, u32 offset_high, u32 offset_low, diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 9a9bb395359c..9c5e975f71a6 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -307,7 +307,7 @@ COMPAT_SYSCALL_DEFINE3(s390_truncate64, const char __user *, path, u32, high, u3 COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low) { - return sys_ftruncate(fd, (unsigned long)high << 32 | low); + return ksys_ftruncate(fd, (unsigned long)high << 32 | low); } COMPAT_SYSCALL_DEFINE5(s390_pread64, unsigned int, fd, char __user *, ubuf, diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 6d964bdefbaa..d64b425fff93 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -65,7 +65,7 @@ asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned if ((int)high < 0) return -EINVAL; else - return sys_ftruncate(fd, (high << 32) | low); + return ksys_ftruncate(fd, (high << 32) | low); } static int cp_compat_stat64(struct kstat *stat, diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 23a5260eae67..1979e5b4ad9a 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -61,7 +61,7 @@ COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, unsigned long, offset_low, unsigned long, offset_high) { - return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); + return ksys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low); } /* diff --git a/fs/internal.h b/fs/internal.h index c797480cbd6f..980d005b21b4 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -119,6 +119,7 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname, extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, const char *, const struct open_flags *); +long do_sys_ftruncate(unsigned int fd, loff_t length, int small); long do_faccessat(int dfd, const char __user *filename, int mode); int do_fchmodat(int dfd, const char __user *filename, umode_t mode); int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, diff --git a/fs/open.c b/fs/open.c index 7b2eccb541f2..b3f3b2cd9f19 100644 --- a/fs/open.c +++ b/fs/open.c @@ -162,7 +162,7 @@ COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length } #endif -static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) +long do_sys_ftruncate(unsigned int fd, loff_t length, int small) { struct inode *inode; struct dentry *dentry; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index df0d1e818a6e..41023177c8ec 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1038,4 +1038,11 @@ static inline long ksys_lchown(const char __user *filename, uid_t user, AT_SYMLINK_NOFOLLOW); } +extern long do_sys_ftruncate(unsigned int fd, loff_t length, int small); + +static inline long ksys_ftruncate(unsigned int fd, unsigned long length) +{ + return do_sys_ftruncate(fd, length, 1); +} + #endif diff --git a/init/initramfs.c b/init/initramfs.c index 35173bef7c00..0d3b001b0dc5 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -346,7 +346,7 @@ static int __init do_name(void) ksys_fchown(wfd, uid, gid); ksys_fchmod(wfd, mode); if (body_len) - sys_ftruncate(wfd, body_len); + ksys_ftruncate(wfd, body_len); vcollected = kstrdup(collected, GFP_KERNEL); state = CopyFile; } -- cgit v1.2.3 From 2ca2a09d6215fd9621aa3e2db7cc9428a61f2911 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:55 +0100 Subject: fs: add ksys_close() wrapper; remove in-kernel calls to sys_close() Using the ksys_close() wrapper allows us to get rid of in-kernel calls to the sys_close() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_close(), with one subtle difference: The few places which checked the return value did not care about the return value re-writing in sys_close(), so simply use a wrapper around __close_fd(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/autofs4/dev-ioctl.c | 2 +- fs/binfmt_misc.c | 2 +- fs/file.c | 1 + fs/open.c | 1 - include/linux/syscalls.h | 12 ++++++++++++ init/do_mounts.c | 4 ++-- init/do_mounts_initrd.c | 2 +- init/do_mounts_md.c | 8 ++++---- init/do_mounts_rd.c | 6 +++--- init/initramfs.c | 8 ++++---- 10 files changed, 29 insertions(+), 17 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index b7c816f39404..26f6b4f41ce6 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -310,7 +310,7 @@ static int autofs_dev_ioctl_closemount(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { - return sys_close(param->ioctlfd); + return ksys_close(param->ioctlfd); } /* diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index a7c5a9861bef..a41b48f82a70 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -241,7 +241,7 @@ ret: return retval; error: if (fd_binary > 0) - sys_close(fd_binary); + ksys_close(fd_binary); bprm->interp_flags = 0; bprm->interp_data = 0; goto ret; diff --git a/fs/file.c b/fs/file.c index d304004f0b65..7ffd6e9d103d 100644 --- a/fs/file.c +++ b/fs/file.c @@ -638,6 +638,7 @@ out_unlock: spin_unlock(&files->file_lock); return -EBADF; } +EXPORT_SYMBOL(__close_fd); /* for ksys_close() */ void do_close_on_exec(struct files_struct *files) { diff --git a/fs/open.c b/fs/open.c index b3f3b2cd9f19..710102fc262b 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1200,7 +1200,6 @@ SYSCALL_DEFINE1(close, unsigned int, fd) return retval; } -EXPORT_SYMBOL(sys_close); /* * This routine simulates a hangup on the tty, to arrange that users diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 41023177c8ec..38805f3447ea 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1045,4 +1045,16 @@ static inline long ksys_ftruncate(unsigned int fd, unsigned long length) return do_sys_ftruncate(fd, length, 1); } +extern int __close_fd(struct files_struct *files, unsigned int fd); + +/* + * In contrast to sys_close(), this stub does not check whether the syscall + * should or should not be restarted, but returns the raw error codes from + * __close_fd(). + */ +static inline int ksys_close(unsigned int fd) +{ + return __close_fd(current->files, fd); +} + #endif diff --git a/init/do_mounts.c b/init/do_mounts.c index 89f18985fa90..a28dd42d1f84 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -492,7 +492,7 @@ void __init change_floppy(char *fmt, ...) fd = sys_open("/dev/root", O_RDWR | O_NDELAY, 0); if (fd >= 0) { sys_ioctl(fd, FDEJECT, 0); - sys_close(fd); + ksys_close(fd); } printk(KERN_NOTICE "VFS: Insert %s and press ENTER\n", buf); fd = sys_open("/dev/console", O_RDWR, 0); @@ -503,7 +503,7 @@ void __init change_floppy(char *fmt, ...) sys_read(fd, &c, 1); termios.c_lflag |= ICANON; sys_ioctl(fd, TCSETSF, (long)&termios); - sys_close(fd); + ksys_close(fd); } } #endif diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 99922d1ebfe6..6907c6dbc443 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -111,7 +111,7 @@ static void __init handle_initrd(void) error = fd; } else { error = sys_ioctl(fd, BLKFLSBUF, 0); - sys_close(fd); + ksys_close(fd); } printk(!error ? "okay\n" : "failed\n"); } diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index 3f733c760a8c..ebd4013d589e 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -191,7 +191,7 @@ static void __init md_setup_drive(void) printk(KERN_WARNING "md: Ignoring md=%d, already autodetected. (Use raid=noautodetect)\n", minor); - sys_close(fd); + ksys_close(fd); continue; } @@ -243,11 +243,11 @@ static void __init md_setup_drive(void) * boot a kernel with devfs compiled in from partitioned md * array without it */ - sys_close(fd); + ksys_close(fd); fd = sys_open(name, 0, 0); sys_ioctl(fd, BLKRRPART, 0); } - sys_close(fd); + ksys_close(fd); } } @@ -297,7 +297,7 @@ static void __init autodetect_raid(void) fd = sys_open("/dev/md0", 0, 0); if (fd >= 0) { sys_ioctl(fd, RAID_AUTORUN, raid_autopart); - sys_close(fd); + ksys_close(fd); } } diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 5b69056f610a..f1aa341862d3 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -257,7 +257,7 @@ int __init rd_load_image(char *from) if (i && (i % devblocks == 0)) { printk("done disk #%d.\n", disk++); rotate = 0; - if (sys_close(in_fd)) { + if (ksys_close(in_fd)) { printk("Error closing the disk.\n"); goto noclose_input; } @@ -283,9 +283,9 @@ int __init rd_load_image(char *from) successful_load: res = 1; done: - sys_close(in_fd); + ksys_close(in_fd); noclose_input: - sys_close(out_fd); + ksys_close(out_fd); out: kfree(buf); ksys_unlink("/dev/ram"); diff --git a/init/initramfs.c b/init/initramfs.c index 0d3b001b0dc5..ce2bcad97cdf 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -373,7 +373,7 @@ static int __init do_copy(void) if (byte_count >= body_len) { if (xwrite(wfd, victim, body_len) != body_len) error("write error"); - sys_close(wfd); + ksys_close(wfd); do_utime(vcollected, mtime); kfree(vcollected); eat(body_len); @@ -574,7 +574,7 @@ static void __init clean_rootfs(void) buf = kzalloc(BUF_SIZE, GFP_KERNEL); WARN_ON(!buf); if (!buf) { - sys_close(fd); + ksys_close(fd); return; } @@ -602,7 +602,7 @@ static void __init clean_rootfs(void) num = sys_getdents64(fd, dirp, BUF_SIZE); } - sys_close(fd); + ksys_close(fd); kfree(buf); } #endif @@ -639,7 +639,7 @@ static int __init populate_rootfs(void) pr_err("/initrd.image: incomplete write (%zd != %ld)\n", written, initrd_end - initrd_start); - sys_close(fd); + ksys_close(fd); free_initrd(); } done: -- cgit v1.2.3 From bae217ea8c7e123ed3fb1064909a262924771bbb Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:56 +0100 Subject: fs: add ksys_open() wrapper; remove in-kernel calls to sys_open() Using this wrapper allows us to avoid the in-kernel calls to the sys_open() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_open(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- fs/open.c | 2 +- include/linux/syscalls.h | 11 +++++++++++ init/do_mounts.c | 4 ++-- init/do_mounts_initrd.c | 4 ++-- init/do_mounts_md.c | 6 +++--- init/do_mounts_rd.c | 6 +++--- init/initramfs.c | 6 +++--- init/main.c | 2 +- 8 files changed, 26 insertions(+), 15 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/open.c b/fs/open.c index 710102fc262b..8a42a2961130 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1151,7 +1151,7 @@ COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, fla */ SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode) { - return sys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode); + return ksys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode); } #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 38805f3447ea..f9df17dcec1c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1057,4 +1057,15 @@ static inline int ksys_close(unsigned int fd) return __close_fd(current->files, fd); } +extern long do_sys_open(int dfd, const char __user *filename, int flags, + umode_t mode); + +static inline long ksys_open(const char __user *filename, int flags, + umode_t mode) +{ + if (force_o_largefile()) + flags |= O_LARGEFILE; + return do_sys_open(AT_FDCWD, filename, flags, mode); +} + #endif diff --git a/init/do_mounts.c b/init/do_mounts.c index a28dd42d1f84..cc1103477071 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -489,13 +489,13 @@ void __init change_floppy(char *fmt, ...) va_start(args, fmt); vsprintf(buf, fmt, args); va_end(args); - fd = sys_open("/dev/root", O_RDWR | O_NDELAY, 0); + fd = ksys_open("/dev/root", O_RDWR | O_NDELAY, 0); if (fd >= 0) { sys_ioctl(fd, FDEJECT, 0); ksys_close(fd); } printk(KERN_NOTICE "VFS: Insert %s and press ENTER\n", buf); - fd = sys_open("/dev/console", O_RDWR, 0); + fd = ksys_open("/dev/console", O_RDWR, 0); if (fd >= 0) { sys_ioctl(fd, TCGETS, (long)&termios); termios.c_lflag &= ~ICANON; diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 6907c6dbc443..cedca8fd2590 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -38,7 +38,7 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) { sys_unshare(CLONE_FS | CLONE_FILES); /* stdin/stdout/stderr for /linuxrc */ - sys_open("/dev/console", O_RDWR, 0); + ksys_open("/dev/console", O_RDWR, 0); ksys_dup(0); ksys_dup(0); /* move initrd over / and chdir/chroot in initrd root */ @@ -99,7 +99,7 @@ static void __init handle_initrd(void) if (!error) printk("okay\n"); else { - int fd = sys_open("/dev/root.old", O_RDWR, 0); + int fd = ksys_open("/dev/root.old", O_RDWR, 0); if (error == -ENOENT) printk("/initrd does not exist. Ignored.\n"); else diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index ebd4013d589e..76dcfaada3ed 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -181,7 +181,7 @@ static void __init md_setup_drive(void) partitioned ? "_d" : "", minor, md_setup_args[ent].device_names); - fd = sys_open(name, 0, 0); + fd = ksys_open(name, 0, 0); if (fd < 0) { printk(KERN_ERR "md: open failed - cannot start " "array %s\n", name); @@ -244,7 +244,7 @@ static void __init md_setup_drive(void) * array without it */ ksys_close(fd); - fd = sys_open(name, 0, 0); + fd = ksys_open(name, 0, 0); sys_ioctl(fd, BLKRRPART, 0); } ksys_close(fd); @@ -294,7 +294,7 @@ static void __init autodetect_raid(void) wait_for_device_probe(); - fd = sys_open("/dev/md0", 0, 0); + fd = ksys_open("/dev/md0", 0, 0); if (fd >= 0) { sys_ioctl(fd, RAID_AUTORUN, raid_autopart); ksys_close(fd); diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index f1aa341862d3..a6706314baa7 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -196,11 +196,11 @@ int __init rd_load_image(char *from) char rotator[4] = { '|' , '/' , '-' , '\\' }; #endif - out_fd = sys_open("/dev/ram", O_RDWR, 0); + out_fd = ksys_open("/dev/ram", O_RDWR, 0); if (out_fd < 0) goto out; - in_fd = sys_open(from, O_RDONLY, 0); + in_fd = ksys_open(from, O_RDONLY, 0); if (in_fd < 0) goto noclose_input; @@ -262,7 +262,7 @@ int __init rd_load_image(char *from) goto noclose_input; } change_floppy("disk #%d", disk); - in_fd = sys_open(from, O_RDONLY, 0); + in_fd = ksys_open(from, O_RDONLY, 0); if (in_fd < 0) { printk("Error opening disk.\n"); goto noclose_input; diff --git a/init/initramfs.c b/init/initramfs.c index ce2bcad97cdf..5f2ff1d2370e 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -340,7 +340,7 @@ static int __init do_name(void) int openflags = O_WRONLY|O_CREAT; if (ml != 1) openflags |= O_TRUNC; - wfd = sys_open(collected, openflags, mode); + wfd = ksys_open(collected, openflags, mode); if (wfd >= 0) { ksys_fchown(wfd, uid, gid); @@ -567,7 +567,7 @@ static void __init clean_rootfs(void) struct linux_dirent64 *dirp; int num; - fd = sys_open("/", O_RDONLY, 0); + fd = ksys_open("/", O_RDONLY, 0); WARN_ON(fd < 0); if (fd < 0) return; @@ -629,7 +629,7 @@ static int __init populate_rootfs(void) } printk(KERN_INFO "rootfs image is not initramfs (%s)" "; looks like an initrd\n", err); - fd = sys_open("/initrd.image", + fd = ksys_open("/initrd.image", O_WRONLY|O_CREAT, 0700); if (fd >= 0) { ssize_t written = xwrite(fd, (char *)initrd_start, diff --git a/init/main.c b/init/main.c index d0ded4322c6b..e77951ae2c19 100644 --- a/init/main.c +++ b/init/main.c @@ -1074,7 +1074,7 @@ static noinline void __init kernel_init_freeable(void) do_basic_setup(); /* Open the /dev/console on the rootfs, this should never fail */ - if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) + if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0) pr_err("Warning: unable to open an initial console.\n"); (void) ksys_dup(0); -- cgit v1.2.3 From 454dab3f965ec24fda8fbe135c8dad4c5b238a86 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:34:04 +0100 Subject: fs: add ksys_getdents64() helper; remove in-kernel calls to sys_getdents64() Using this helper allows us to avoid the in-kernel calls to the sys_getdents64() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_getdents64(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- fs/readdir.c | 11 +++++++++-- include/linux/syscalls.h | 2 ++ init/initramfs.c | 4 ++-- 3 files changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/readdir.c b/fs/readdir.c index 1b83b0ad183b..d97f548e6323 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -292,8 +292,8 @@ efault: return -EFAULT; } -SYSCALL_DEFINE3(getdents64, unsigned int, fd, - struct linux_dirent64 __user *, dirent, unsigned int, count) +int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, + unsigned int count) { struct fd f; struct linux_dirent64 __user * lastdirent; @@ -326,6 +326,13 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, return error; } + +SYSCALL_DEFINE3(getdents64, unsigned int, fd, + struct linux_dirent64 __user *, dirent, unsigned int, count) +{ + return ksys_getdents64(fd, dirent, count); +} + #ifdef CONFIG_COMPAT struct compat_old_linux_dirent { compat_ulong_t d_ino; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index f9df17dcec1c..c056aff6d7ad 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -955,6 +955,8 @@ ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count); int ksys_chdir(const char __user *filename); int ksys_fchmod(unsigned int fd, umode_t mode); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); +int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, + unsigned int count); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/init/initramfs.c b/init/initramfs.c index 5f2ff1d2370e..13643c46ebab 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -579,7 +579,7 @@ static void __init clean_rootfs(void) } dirp = buf; - num = sys_getdents64(fd, dirp, BUF_SIZE); + num = ksys_getdents64(fd, dirp, BUF_SIZE); while (num > 0) { while (num > 0) { struct kstat st; @@ -599,7 +599,7 @@ static void __init clean_rootfs(void) } dirp = buf; memset(buf, 0, BUF_SIZE); - num = sys_getdents64(fd, dirp, BUF_SIZE); + num = ksys_getdents64(fd, dirp, BUF_SIZE); } ksys_close(fd); -- cgit v1.2.3 From cbb60b924b9f3e4d7c67a1c9dcf981718f926e4e Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:43:59 +0100 Subject: fs: add ksys_ioctl() helper; remove in-kernel calls to sys_ioctl() Using this helper allows us to avoid the in-kernel calls to the sys_ioctl() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_ioctl(). After careful review, at least some of these calls could be converted to do_vfs_ioctl() in future. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- fs/ioctl.c | 7 ++++++- include/linux/syscalls.h | 1 + init/do_mounts.c | 8 ++++---- init/do_mounts_initrd.c | 2 +- init/do_mounts_md.c | 15 ++++++++------- init/do_mounts_rd.c | 4 ++-- 6 files changed, 22 insertions(+), 15 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/ioctl.c b/fs/ioctl.c index 5ace7efb0d04..4823431d1c9d 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -689,7 +689,7 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, return error; } -SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) +int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg) { int error; struct fd f = fdget(fd); @@ -702,3 +702,8 @@ SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) fdput(f); return error; } + +SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) +{ + return ksys_ioctl(fd, cmd, arg); +} diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index c056aff6d7ad..5a959efd8fb7 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -957,6 +957,7 @@ int ksys_fchmod(unsigned int fd, umode_t mode); int ksys_fchown(unsigned int fd, uid_t user, gid_t group); int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count); +int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/init/do_mounts.c b/init/do_mounts.c index cc1103477071..b17e0095eb4e 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -491,18 +491,18 @@ void __init change_floppy(char *fmt, ...) va_end(args); fd = ksys_open("/dev/root", O_RDWR | O_NDELAY, 0); if (fd >= 0) { - sys_ioctl(fd, FDEJECT, 0); + ksys_ioctl(fd, FDEJECT, 0); ksys_close(fd); } printk(KERN_NOTICE "VFS: Insert %s and press ENTER\n", buf); fd = ksys_open("/dev/console", O_RDWR, 0); if (fd >= 0) { - sys_ioctl(fd, TCGETS, (long)&termios); + ksys_ioctl(fd, TCGETS, (long)&termios); termios.c_lflag &= ~ICANON; - sys_ioctl(fd, TCSETSF, (long)&termios); + ksys_ioctl(fd, TCSETSF, (long)&termios); sys_read(fd, &c, 1); termios.c_lflag |= ICANON; - sys_ioctl(fd, TCSETSF, (long)&termios); + ksys_ioctl(fd, TCSETSF, (long)&termios); ksys_close(fd); } } diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index cedca8fd2590..03ec0c1b7553 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -110,7 +110,7 @@ static void __init handle_initrd(void) if (fd < 0) { error = fd; } else { - error = sys_ioctl(fd, BLKFLSBUF, 0); + error = ksys_ioctl(fd, BLKFLSBUF, 0); ksys_close(fd); } printk(!error ? "okay\n" : "failed\n"); diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index 76dcfaada3ed..7d85d172bc7e 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -187,7 +187,7 @@ static void __init md_setup_drive(void) "array %s\n", name); continue; } - if (sys_ioctl(fd, SET_ARRAY_INFO, 0) == -EBUSY) { + if (ksys_ioctl(fd, SET_ARRAY_INFO, 0) == -EBUSY) { printk(KERN_WARNING "md: Ignoring md=%d, already autodetected. (Use raid=noautodetect)\n", minor); @@ -210,7 +210,7 @@ static void __init md_setup_drive(void) ainfo.state = (1 << MD_SB_CLEAN); ainfo.layout = 0; ainfo.chunk_size = md_setup_args[ent].chunk; - err = sys_ioctl(fd, SET_ARRAY_INFO, (long)&ainfo); + err = ksys_ioctl(fd, SET_ARRAY_INFO, (long)&ainfo); for (i = 0; !err && i <= MD_SB_DISKS; i++) { dev = devices[i]; if (!dev) @@ -220,7 +220,8 @@ static void __init md_setup_drive(void) dinfo.state = (1<= 0) { - sys_ioctl(fd, RAID_AUTORUN, raid_autopart); + ksys_ioctl(fd, RAID_AUTORUN, raid_autopart); ksys_close(fd); } } diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index a6706314baa7..4dafaed5736f 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -218,7 +218,7 @@ int __init rd_load_image(char *from) * NOTE NOTE: nblocks is not actually blocks but * the number of kibibytes of data to load into a ramdisk. */ - if (sys_ioctl(out_fd, BLKGETSIZE, (unsigned long)&rd_blocks) < 0) + if (ksys_ioctl(out_fd, BLKGETSIZE, (unsigned long)&rd_blocks) < 0) rd_blocks = 0; else rd_blocks >>= 1; @@ -232,7 +232,7 @@ int __init rd_load_image(char *from) /* * OK, time to copy in the data */ - if (sys_ioctl(in_fd, BLKGETSIZE, (unsigned long)&devblocks) < 0) + if (ksys_ioctl(in_fd, BLKGETSIZE, (unsigned long)&devblocks) < 0) devblocks = 0; else devblocks >>= 1; -- cgit v1.2.3 From 76847e4344350970e1c2e27c28b5abb3c588c5b3 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:51:17 +0100 Subject: fs: add ksys_lseek() helper; remove in-kernel calls to sys_lseek() Using this helper allows us to avoid the in-kernel calls to the sys_lseek() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_lseek(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- fs/read_write.c | 9 +++++++-- include/linux/syscalls.h | 1 + init/do_mounts_rd.c | 8 ++++---- 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/fs/read_write.c b/fs/read_write.c index 8e8f0b4f52e2..b38b008a078e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -301,7 +301,7 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(vfs_llseek); -SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) +off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); @@ -319,10 +319,15 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) return retval; } +SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) +{ + return ksys_lseek(fd, offset, whence); +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { - return sys_lseek(fd, offset, whence); + return ksys_lseek(fd, offset, whence); } #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 5a959efd8fb7..0f24e5334569 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -958,6 +958,7 @@ int ksys_fchown(unsigned int fd, uid_t user, gid_t group); int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count); int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); +off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 4dafaed5736f..13e54148c0e0 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -90,7 +90,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) /* * Read block 0 to test for compressed kernel */ - sys_lseek(fd, start_block * BLOCK_SIZE, 0); + ksys_lseek(fd, start_block * BLOCK_SIZE, 0); sys_read(fd, buf, size); *decompressor = decompress_method(buf, size, &compress_name); @@ -136,7 +136,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) /* * Read 512 bytes further to check if cramfs is padded */ - sys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0); + ksys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0); sys_read(fd, buf, size); if (cramfsb->magic == CRAMFS_MAGIC) { @@ -150,7 +150,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) /* * Read block 1 to test for minix and ext2 superblock */ - sys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0); + ksys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0); sys_read(fd, buf, size); /* Try minix */ @@ -178,7 +178,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) start_block); done: - sys_lseek(fd, start_block * BLOCK_SIZE, 0); + ksys_lseek(fd, start_block * BLOCK_SIZE, 0); kfree(buf); return nblocks; } -- cgit v1.2.3 From 3ce4a7bf66263748194b77ccefd284be963c6304 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Tue, 13 Mar 2018 21:56:26 +0100 Subject: fs: add ksys_read() helper; remove in-kernel calls to sys_read() Using this helper allows us to avoid the in-kernel calls to the sys_read() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_read(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- arch/s390/kernel/compat_linux.c | 2 +- fs/read_write.c | 7 ++++++- include/linux/syscalls.h | 1 + init/do_mounts.c | 2 +- init/do_mounts_rd.c | 10 +++++----- 5 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 9c5e975f71a6..af0469f204fd 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -460,7 +460,7 @@ COMPAT_SYSCALL_DEFINE3(s390_read, unsigned int, fd, char __user *, buf, compat_s if ((compat_ssize_t) count < 0) return -EINVAL; - return sys_read(fd, buf, count); + return ksys_read(fd, buf, count); } COMPAT_SYSCALL_DEFINE3(s390_write, unsigned int, fd, const char __user *, buf, compat_size_t, count) diff --git a/fs/read_write.c b/fs/read_write.c index b38b008a078e..fc441e1ac683 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -568,7 +568,7 @@ static inline void file_pos_write(struct file *file, loff_t pos) file->f_pos = pos; } -SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) +ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -583,6 +583,11 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) return ret; } +SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) +{ + return ksys_read(fd, buf, count); +} + ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { struct fd f = fdget_pos(fd); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0f24e5334569..3a2e90842ff8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -959,6 +959,7 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count); int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); +ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/init/do_mounts.c b/init/do_mounts.c index b17e0095eb4e..2c71dabe5626 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -500,7 +500,7 @@ void __init change_floppy(char *fmt, ...) ksys_ioctl(fd, TCGETS, (long)&termios); termios.c_lflag &= ~ICANON; ksys_ioctl(fd, TCSETSF, (long)&termios); - sys_read(fd, &c, 1); + ksys_read(fd, &c, 1); termios.c_lflag |= ICANON; ksys_ioctl(fd, TCSETSF, (long)&termios); ksys_close(fd); diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 13e54148c0e0..12c159824c7b 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -91,7 +91,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) * Read block 0 to test for compressed kernel */ ksys_lseek(fd, start_block * BLOCK_SIZE, 0); - sys_read(fd, buf, size); + ksys_read(fd, buf, size); *decompressor = decompress_method(buf, size, &compress_name); if (compress_name) { @@ -137,7 +137,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) * Read 512 bytes further to check if cramfs is padded */ ksys_lseek(fd, start_block * BLOCK_SIZE + 0x200, 0); - sys_read(fd, buf, size); + ksys_read(fd, buf, size); if (cramfsb->magic == CRAMFS_MAGIC) { printk(KERN_NOTICE @@ -151,7 +151,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) * Read block 1 to test for minix and ext2 superblock */ ksys_lseek(fd, (start_block+1) * BLOCK_SIZE, 0); - sys_read(fd, buf, size); + ksys_read(fd, buf, size); /* Try minix */ if (minixsb->s_magic == MINIX_SUPER_MAGIC || @@ -269,7 +269,7 @@ int __init rd_load_image(char *from) } printk("Loading disk #%d... ", disk); } - sys_read(in_fd, buf, BLOCK_SIZE); + ksys_read(in_fd, buf, BLOCK_SIZE); ksys_write(out_fd, buf, BLOCK_SIZE); #if !defined(CONFIG_S390) if (!(i % 16)) { @@ -307,7 +307,7 @@ static int crd_infd, crd_outfd; static long __init compr_fill(void *buf, unsigned long len) { - long r = sys_read(crd_infd, buf, len); + long r = ksys_read(crd_infd, buf, len); if (r < 0) printk(KERN_ERR "RAMDISK: error while reading compressed data"); else if (r == 0) -- cgit v1.2.3 From 70f68ee81e2e9ad5105b8d2bd324e890e94c6ad9 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Wed, 14 Mar 2018 22:35:11 +0100 Subject: fs: add ksys_sync() helper; remove in-kernel calls to sys_sync() Using this helper allows us to avoid the in-kernel calls to the sys_sync() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_sync(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Alexander Viro Signed-off-by: Dominik Brodowski --- arch/sparc/kernel/setup_32.c | 2 +- drivers/tty/sysrq.c | 2 +- fs/sync.c | 7 ++++++- include/linux/syscalls.h | 1 + kernel/power/hibernate.c | 2 +- kernel/power/suspend.c | 2 +- kernel/power/user.c | 2 +- 7 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index 2e3a3e203061..13664c377196 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -86,7 +86,7 @@ static void prom_sync_me(void) show_free_areas(0, NULL); if (!is_idle_task(current)) { local_irq_enable(); - sys_sync(); + ksys_sync(); local_irq_disable(); } prom_printf("Returning to prom\n"); diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index b674793be478..6364890575ec 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -660,7 +660,7 @@ static void sysrq_do_reset(struct timer_list *t) state->reset_requested = true; - sys_sync(); + ksys_sync(); kernel_restart(NULL); } diff --git a/fs/sync.c b/fs/sync.c index 6e0a2cbaf6de..602ae94bb67e 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -105,7 +105,7 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg) * just write metadata (such as inodes or bitmaps) to block device page cache * and do not sync it on their own in ->sync_fs(). */ -SYSCALL_DEFINE0(sync) +void ksys_sync(void) { int nowait = 0, wait = 1; @@ -117,6 +117,11 @@ SYSCALL_DEFINE0(sync) iterate_bdevs(fdatawait_one_bdev, NULL); if (unlikely(laptop_mode)) laptop_sync_completion(); +} + +SYSCALL_DEFINE0(sync) +{ + ksys_sync(); return 0; } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3a2e90842ff8..0a9942b3e718 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -960,6 +960,7 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); +void ksys_sync(void); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a5c36e9c56a6..4710f1b142fc 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -701,7 +701,7 @@ int hibernate(void) } pr_info("Syncing filesystems ... \n"); - sys_sync(); + ksys_sync(); pr_info("done.\n"); error = freeze_processes(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 0685c4499431..4c10be0f4843 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -560,7 +560,7 @@ static int enter_state(suspend_state_t state) #ifndef CONFIG_SUSPEND_SKIP_SYNC trace_suspend_resume(TPS("sync_filesystems"), 0, true); pr_info("Syncing filesystems ... "); - sys_sync(); + ksys_sync(); pr_cont("done.\n"); trace_suspend_resume(TPS("sync_filesystems"), 0, false); #endif diff --git a/kernel/power/user.c b/kernel/power/user.c index 22df9f7ff672..75c959de4b29 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -224,7 +224,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, break; printk("Syncing filesystems ... "); - sys_sync(); + ksys_sync(); printk("done.\n"); error = freeze_processes(); -- cgit v1.2.3 From 9b32105ec6b13d32d5db6a6e7992c97ce54b5ea7 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:42 +0100 Subject: kernel: add ksys_unshare() helper; remove in-kernel calls to sys_unshare() Using this helper allows us to avoid the in-kernel calls to the sys_unshare() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_unshare(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Cc: Ingo Molnar Signed-off-by: Dominik Brodowski --- drivers/base/devtmpfs.c | 2 +- include/linux/syscalls.h | 1 + init/do_mounts_initrd.c | 2 +- kernel/fork.c | 7 ++++++- 4 files changed, 9 insertions(+), 3 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 3f7ee954fd2c..f7768077e817 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -380,7 +380,7 @@ static int devtmpfsd(void *p) { char options[] = "mode=0755"; int *err = p; - *err = sys_unshare(CLONE_NEWNS); + *err = ksys_unshare(CLONE_NEWNS); if (*err) goto out; *err = ksys_mount("devtmpfs", "/", "devtmpfs", MS_SILENT, options); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 0a9942b3e718..e724dda509e0 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -961,6 +961,7 @@ int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); +int ksys_unshare(unsigned long unshare_flags); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index 03ec0c1b7553..d1d3e53bdeef 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -36,7 +36,7 @@ __setup("noinitrd", no_initrd); static int init_linuxrc(struct subprocess_info *info, struct cred *new) { - sys_unshare(CLONE_FS | CLONE_FILES); + ksys_unshare(CLONE_FS | CLONE_FILES); /* stdin/stdout/stderr for /linuxrc */ ksys_open("/dev/console", O_RDWR, 0); ksys_dup(0); diff --git a/kernel/fork.c b/kernel/fork.c index b1e031aac9db..f71b67dc156d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2354,7 +2354,7 @@ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp * constructed. Here we are modifying the current, active, * task_struct. */ -SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) +int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *fd, *new_fd = NULL; @@ -2470,6 +2470,11 @@ bad_unshare_out: return err; } +SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) +{ + return ksys_unshare(unshare_flags); +} + /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to -- cgit v1.2.3 From e2aaa9f423367ee03755d632555c242629a08d00 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Fri, 16 Mar 2018 12:36:06 +0100 Subject: kernel: add ksys_setsid() helper; remove in-kernel call to sys_setsid() Using this helper allows us to avoid the in-kernel call to the sys_setsid() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_setsid(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1 + init/do_mounts_initrd.c | 2 +- kernel/sys.c | 7 ++++++- 3 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e724dda509e0..4dd685ee425d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -962,6 +962,7 @@ off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence); ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); int ksys_unshare(unsigned long unshare_flags); +int ksys_setsid(void); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index d1d3e53bdeef..5a91aefa7305 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -45,7 +45,7 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new) ksys_chdir("/root"); ksys_mount(".", "/", NULL, MS_MOVE, NULL); ksys_chroot("."); - sys_setsid(); + ksys_setsid(); return 0; } diff --git a/kernel/sys.c b/kernel/sys.c index 550f47788ae4..ad692183dfe9 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1150,7 +1150,7 @@ static void set_special_pids(struct pid *pid) change_pid(curr, PIDTYPE_PGID, pid); } -SYSCALL_DEFINE0(setsid) +int ksys_setsid(void) { struct task_struct *group_leader = current->group_leader; struct pid *sid = task_pid(group_leader); @@ -1183,6 +1183,11 @@ out: return err; } +SYSCALL_DEFINE0(setsid) +{ + return ksys_setsid(); +} + DECLARE_RWSEM(uts_sem); #ifdef COMPAT_UTS_MACHINE -- cgit v1.2.3 From 806cbae1228cc1a19b978c4513f6851e9ab7f388 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:47 +0100 Subject: fs: add ksys_sync_file_range helper(); remove in-kernel calls to syscall Using this helper allows us to avoid the in-kernel calls to the sys_sync_file_range() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_sync_file_range(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- arch/mips/kernel/linux32.c | 2 +- arch/parisc/kernel/sys_parisc.c | 2 +- arch/powerpc/kernel/sys_ppc32.c | 2 +- arch/s390/kernel/compat_linux.c | 2 +- arch/sparc/kernel/sys_sparc32.c | 2 +- arch/x86/ia32/sys_ia32.c | 6 +++--- fs/sync.c | 12 +++++++++--- include/linux/syscalls.h | 2 ++ 8 files changed, 19 insertions(+), 11 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 3c90449742a0..57b3310873f0 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -139,7 +139,7 @@ asmlinkage long sys32_sync_file_range(int fd, int __pad, unsigned long a4, unsigned long a5, int flags) { - return sys_sync_file_range(fd, + return ksys_sync_file_range(fd, merge_64(a2, a3), merge_64(a4, a5), flags); } diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 6d2a64859c22..ef995b5d97ef 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -360,7 +360,7 @@ asmlinkage long parisc_sync_file_range(int fd, u32 hi_off, u32 lo_off, u32 hi_nbytes, u32 lo_nbytes, unsigned int flags) { - return sys_sync_file_range(fd, (loff_t)hi_off << 32 | lo_off, + return ksys_sync_file_range(fd, (loff_t)hi_off << 32 | lo_off, (loff_t)hi_nbytes << 32 | lo_nbytes, flags); } diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index e0c9b7f1bf38..664e4c5b5855 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -124,5 +124,5 @@ asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags, loff_t offset = ((loff_t)offset_hi << 32) | offset_lo; loff_t nbytes = ((loff_t)nbytes_hi << 32) | nbytes_lo; - return sys_sync_file_range(fd, offset, nbytes, flags); + return ksys_sync_file_range(fd, offset, nbytes, flags); } diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index af0469f204fd..605f6f026e44 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -509,7 +509,7 @@ COMPAT_SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, arg COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow, u32, nhigh, u32, nlow, unsigned int, flags) { - return sys_sync_file_range(fd, ((loff_t)offhigh << 32) + offlow, + return ksys_sync_file_range(fd, ((loff_t)offhigh << 32) + offlow, ((u64)nhigh << 32) + nlow, flags); } diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index d64b425fff93..af18b9ff86be 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -241,7 +241,7 @@ long compat_sys_fadvise64_64(int fd, long sys32_sync_file_range(unsigned int fd, unsigned long off_high, unsigned long off_low, unsigned long nb_high, unsigned long nb_low, unsigned int flags) { - return sys_sync_file_range(fd, + return ksys_sync_file_range(fd, (off_high << 32) | off_low, (nb_high << 32) | nb_low, flags); diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 1979e5b4ad9a..0c5f8932c136 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -209,9 +209,9 @@ COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, unsigned int, off_hi, unsigned int, n_low, unsigned int, n_hi, int, flags) { - return sys_sync_file_range(fd, - ((u64)off_hi << 32) | off_low, - ((u64)n_hi << 32) | n_low, flags); + return ksys_sync_file_range(fd, + ((u64)off_hi << 32) | off_low, + ((u64)n_hi << 32) | n_low, flags); } COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, diff --git a/fs/sync.c b/fs/sync.c index 602ae94bb67e..9908a114d506 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -285,8 +285,8 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd) * already-instantiated disk blocks, there are no guarantees here that the data * will be available after a crash. */ -SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, - unsigned int, flags) +int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, + unsigned int flags) { int ret; struct fd f; @@ -364,10 +364,16 @@ out: return ret; } +SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes, + unsigned int, flags) +{ + return ksys_sync_file_range(fd, offset, nbytes, flags); +} + /* It would be nice if people remember that not all the world's an i386 when they introduce new system calls */ SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags, loff_t, offset, loff_t, nbytes) { - return sys_sync_file_range(fd, offset, nbytes, flags); + return ksys_sync_file_range(fd, offset, nbytes, flags); } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 4dd685ee425d..331da76f66e2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -963,6 +963,8 @@ ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count); void ksys_sync(void); int ksys_unshare(unsigned long unshare_flags); int ksys_setsid(void); +int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, + unsigned int flags); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From df260e21e6cd5d2dfc1fe9b6a3bbf747e72b3bed Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:32:11 +0100 Subject: fs: add ksys_truncate() wrapper; remove in-kernel calls to sys_truncate() Using the ksys_truncate() wrapper allows us to get rid of in-kernel calls to the sys_truncate() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_truncate(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- arch/mips/kernel/linux32.c | 2 +- arch/parisc/kernel/sys_parisc.c | 6 +++--- arch/powerpc/kernel/sys_ppc32.c | 2 +- arch/s390/kernel/compat_linux.c | 2 +- arch/sparc/kernel/sys_sparc32.c | 2 +- arch/x86/ia32/sys_ia32.c | 3 ++- fs/open.c | 2 +- include/linux/syscalls.h | 7 +++++++ 8 files changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 57b3310873f0..58e7dd27f106 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -82,7 +82,7 @@ struct rlimit32 { SYSCALL_DEFINE4(32_truncate64, const char __user *, path, unsigned long, __dummy, unsigned long, a2, unsigned long, a3) { - return sys_truncate(path, merge_64(a2, a3)); + return ksys_truncate(path, merge_64(a2, a3)); } SYSCALL_DEFINE4(32_ftruncate64, unsigned long, fd, unsigned long, __dummy, diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index ef995b5d97ef..3377a00163c3 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -292,7 +292,7 @@ asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len, asmlinkage long parisc_truncate64(const char __user * path, unsigned int high, unsigned int low) { - return sys_truncate(path, (long)high << 32 | low); + return ksys_truncate(path, (long)high << 32 | low); } asmlinkage long parisc_ftruncate64(unsigned int fd, @@ -305,7 +305,7 @@ asmlinkage long parisc_ftruncate64(unsigned int fd, * are identical on LP64 */ asmlinkage long sys_truncate64(const char __user * path, unsigned long length) { - return sys_truncate(path, length); + return ksys_truncate(path, length); } asmlinkage long sys_ftruncate64(unsigned int fd, unsigned long length) { @@ -320,7 +320,7 @@ asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg asmlinkage long parisc_truncate64(const char __user * path, unsigned int high, unsigned int low) { - return sys_truncate64(path, (loff_t)high << 32 | low); + return ksys_truncate(path, (loff_t)high << 32 | low); } asmlinkage long parisc_ftruncate64(unsigned int fd, diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 664e4c5b5855..a0a251d7c9c5 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -94,7 +94,7 @@ compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offhi, u32 offlo, u32 co asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4, unsigned long high, unsigned long low) { - return sys_truncate(path, (high << 32) | low); + return ksys_truncate(path, (high << 32) | low); } asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo, diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 605f6f026e44..e4092ec17ea5 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -302,7 +302,7 @@ COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, compat_ulong_t, second, COMPAT_SYSCALL_DEFINE3(s390_truncate64, const char __user *, path, u32, high, u32, low) { - return sys_truncate(path, (unsigned long)high << 32 | low); + return ksys_truncate(path, (unsigned long)high << 32 | low); } COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low) diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index af18b9ff86be..aab2428b17b5 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -57,7 +57,7 @@ asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, u if ((int)high < 0) return -EINVAL; else - return sys_truncate(path, (high << 32) | low); + return ksys_truncate(path, (high << 32) | low); } asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low) diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 0c5f8932c136..90e7a2b3dc5b 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -55,7 +55,8 @@ COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename, unsigned long, offset_low, unsigned long, offset_high) { - return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low); + return ksys_truncate(filename, + ((loff_t) offset_high << 32) | offset_low); } COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd, diff --git a/fs/open.c b/fs/open.c index 8a42a2961130..2e816fc7bd56 100644 --- a/fs/open.c +++ b/fs/open.c @@ -128,7 +128,7 @@ out: } EXPORT_SYMBOL_GPL(vfs_truncate); -static long do_sys_truncate(const char __user *pathname, loff_t length) +long do_sys_truncate(const char __user *pathname, loff_t length) { unsigned int lookup_flags = LOOKUP_FOLLOW; struct path path; diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 331da76f66e2..78b79e3a1279 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1078,4 +1078,11 @@ static inline long ksys_open(const char __user *filename, int flags, return do_sys_open(AT_FDCWD, filename, flags, mode); } +extern long do_sys_truncate(const char __user *pathname, loff_t length); + +static inline long ksys_truncate(const char __user *pathname, loff_t length) +{ + return do_sys_truncate(pathname, length); +} + #endif -- cgit v1.2.3 From 36028d5dd71175c332ab634e089e16dbdfe3812b Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:38:31 +0100 Subject: fs: add ksys_p{read,write}64() helpers; remove in-kernel calls to syscalls Using the ksys_p{read,write}64() wrappers allows us to get rid of in-kernel calls to the sys_pread64() and sys_pwrite64() syscalls. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_p{read,write}64(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- arch/mips/kernel/linux32.c | 4 ++-- arch/parisc/kernel/sys_parisc.c | 4 ++-- arch/powerpc/kernel/sys_ppc32.c | 4 ++-- arch/s390/kernel/compat_linux.c | 4 ++-- arch/sh/kernel/sys_sh32.c | 4 ++-- arch/sparc/kernel/sys_sparc32.c | 4 ++-- arch/x86/ia32/sys_ia32.c | 8 ++++---- fs/read_write.c | 20 ++++++++++++++++---- include/linux/syscalls.h | 4 ++++ 9 files changed, 36 insertions(+), 20 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 58e7dd27f106..91e85e2f8aa5 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -105,13 +105,13 @@ SYSCALL_DEFINE5(32_llseek, unsigned int, fd, unsigned int, offset_high, SYSCALL_DEFINE6(32_pread, unsigned long, fd, char __user *, buf, size_t, count, unsigned long, unused, unsigned long, a4, unsigned long, a5) { - return sys_pread64(fd, buf, count, merge_64(a4, a5)); + return ksys_pread64(fd, buf, count, merge_64(a4, a5)); } SYSCALL_DEFINE6(32_pwrite, unsigned int, fd, const char __user *, buf, size_t, count, u32, unused, u64, a4, u64, a5) { - return sys_pwrite64(fd, buf, count, merge_64(a4, a5)); + return ksys_pwrite64(fd, buf, count, merge_64(a4, a5)); } SYSCALL_DEFINE1(32_personality, unsigned long, personality) diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 3377a00163c3..4f47e8379854 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -333,13 +333,13 @@ asmlinkage long parisc_ftruncate64(unsigned int fd, asmlinkage ssize_t parisc_pread64(unsigned int fd, char __user *buf, size_t count, unsigned int high, unsigned int low) { - return sys_pread64(fd, buf, count, (loff_t)high << 32 | low); + return ksys_pread64(fd, buf, count, (loff_t)high << 32 | low); } asmlinkage ssize_t parisc_pwrite64(unsigned int fd, const char __user *buf, size_t count, unsigned int high, unsigned int low) { - return sys_pwrite64(fd, buf, count, (loff_t)high << 32 | low); + return ksys_pwrite64(fd, buf, count, (loff_t)high << 32 | low); } asmlinkage ssize_t parisc_readahead(int fd, unsigned int high, unsigned int low, diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index a0a251d7c9c5..36a651e6e033 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -77,13 +77,13 @@ unsigned long compat_sys_mmap2(unsigned long addr, size_t len, compat_ssize_t compat_sys_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, u32 reg6, u32 poshi, u32 poslo) { - return sys_pread64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo); + return ksys_pread64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo); } compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, u32 reg6, u32 poshi, u32 poslo) { - return sys_pwrite64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo); + return ksys_pwrite64(fd, ubuf, count, ((loff_t)poshi << 32) | poslo); } compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offhi, u32 offlo, u32 count) diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index e4092ec17ea5..71e2c5bc4926 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -315,7 +315,7 @@ COMPAT_SYSCALL_DEFINE5(s390_pread64, unsigned int, fd, char __user *, ubuf, { if ((compat_ssize_t) count < 0) return -EINVAL; - return sys_pread64(fd, ubuf, count, (unsigned long)high << 32 | low); + return ksys_pread64(fd, ubuf, count, (unsigned long)high << 32 | low); } COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubuf, @@ -323,7 +323,7 @@ COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubu { if ((compat_ssize_t) count < 0) return -EINVAL; - return sys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low); + return ksys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low); } COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, count) diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index f8dc8bfd4606..c37ee3d0c803 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -39,13 +39,13 @@ asmlinkage int sys_sh_pipe(void) asmlinkage ssize_t sys_pread_wrapper(unsigned int fd, char __user *buf, size_t count, long dummy, loff_t pos) { - return sys_pread64(fd, buf, count, pos); + return ksys_pread64(fd, buf, count, pos); } asmlinkage ssize_t sys_pwrite_wrapper(unsigned int fd, const char __user *buf, size_t count, long dummy, loff_t pos) { - return sys_pwrite64(fd, buf, count, pos); + return ksys_pwrite64(fd, buf, count, pos); } asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1, diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index aab2428b17b5..40c0d2e1db1d 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -200,7 +200,7 @@ asmlinkage compat_ssize_t sys32_pread64(unsigned int fd, unsigned long poshi, unsigned long poslo) { - return sys_pread64(fd, ubuf, count, (poshi << 32) | poslo); + return ksys_pread64(fd, ubuf, count, (poshi << 32) | poslo); } asmlinkage compat_ssize_t sys32_pwrite64(unsigned int fd, @@ -209,7 +209,7 @@ asmlinkage compat_ssize_t sys32_pwrite64(unsigned int fd, unsigned long poshi, unsigned long poslo) { - return sys_pwrite64(fd, ubuf, count, (poshi << 32) | poslo); + return ksys_pwrite64(fd, ubuf, count, (poshi << 32) | poslo); } asmlinkage long compat_sys_readahead(int fd, diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 90e7a2b3dc5b..c08c25f73d79 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -174,15 +174,15 @@ COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf, u32, count, u32, poslo, u32, poshi) { - return sys_pread64(fd, ubuf, count, - ((loff_t)AA(poshi) << 32) | AA(poslo)); + return ksys_pread64(fd, ubuf, count, + ((loff_t)AA(poshi) << 32) | AA(poslo)); } COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf, u32, count, u32, poslo, u32, poshi) { - return sys_pwrite64(fd, ubuf, count, - ((loff_t)AA(poshi) << 32) | AA(poslo)); + return ksys_pwrite64(fd, ubuf, count, + ((loff_t)AA(poshi) << 32) | AA(poslo)); } diff --git a/fs/read_write.c b/fs/read_write.c index fc441e1ac683..c4eabbfc90df 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -610,8 +610,8 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, return ksys_write(fd, buf, count); } -SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, - size_t, count, loff_t, pos) +ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, + loff_t pos) { struct fd f; ssize_t ret = -EBADF; @@ -630,8 +630,14 @@ SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, return ret; } -SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, - size_t, count, loff_t, pos) +SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, + size_t, count, loff_t, pos) +{ + return ksys_pread64(fd, buf, count, pos); +} + +ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, + size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; @@ -650,6 +656,12 @@ SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, return ret; } +SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, + size_t, count, loff_t, pos) +{ + return ksys_pwrite64(fd, buf, count, pos); +} + static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 78b79e3a1279..a30e4c2d0c27 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -965,6 +965,10 @@ int ksys_unshare(unsigned long unshare_flags); int ksys_setsid(void); int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes, unsigned int flags); +ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, + loff_t pos); +ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, + size_t count, loff_t pos); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From edf292c76b884a499cc60ad5cdada2663cc39a2f Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:46:32 +0100 Subject: fs: add ksys_fallocate() wrapper; remove in-kernel calls to sys_fallocate() Using the ksys_fallocate() wrapper allows us to get rid of in-kernel calls to the sys_fallocate() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_fallocate(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Al Viro Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- arch/mips/kernel/linux32.c | 4 ++-- arch/parisc/kernel/sys_parisc.c | 4 ++-- arch/powerpc/kernel/sys_ppc32.c | 2 +- arch/s390/kernel/compat_linux.c | 4 ++-- arch/sparc/kernel/sys_sparc32.c | 4 ++-- arch/x86/ia32/sys_ia32.c | 4 ++-- fs/open.c | 7 ++++++- include/linux/syscalls.h | 1 + 8 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 91e85e2f8aa5..0779d474c8ad 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -157,6 +157,6 @@ asmlinkage long sys32_fadvise64_64(int fd, int __pad, asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_a2, unsigned offset_a3, unsigned len_a4, unsigned len_a5) { - return sys_fallocate(fd, mode, merge_64(offset_a2, offset_a3), - merge_64(len_a4, len_a5)); + return ksys_fallocate(fd, mode, merge_64(offset_a2, offset_a3), + merge_64(len_a4, len_a5)); } diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 4f47e8379854..588fab336ddd 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -367,8 +367,8 @@ asmlinkage long parisc_sync_file_range(int fd, asmlinkage long parisc_fallocate(int fd, int mode, u32 offhi, u32 offlo, u32 lenhi, u32 lenlo) { - return sys_fallocate(fd, mode, ((u64)offhi << 32) | offlo, - ((u64)lenhi << 32) | lenlo); + return ksys_fallocate(fd, mode, ((u64)offhi << 32) | offlo, + ((u64)lenhi << 32) | lenlo); } long parisc_personality(unsigned long personality) diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 36a651e6e033..68f11e1065f8 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -100,7 +100,7 @@ asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4, asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo, u32 lenhi, u32 lenlo) { - return sys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo, + return ksys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo, ((loff_t)lenhi << 32) | lenlo); } diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 71e2c5bc4926..039858f9f128 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -516,6 +516,6 @@ COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow, COMPAT_SYSCALL_DEFINE6(s390_fallocate, int, fd, int, mode, u32, offhigh, u32, offlow, u32, lenhigh, u32, lenlow) { - return sys_fallocate(fd, mode, ((loff_t)offhigh << 32) + offlow, - ((u64)lenhigh << 32) + lenlow); + return ksys_fallocate(fd, mode, ((loff_t)offhigh << 32) + offlow, + ((u64)lenhigh << 32) + lenlow); } diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 40c0d2e1db1d..4ba62d676632 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -250,6 +250,6 @@ long sys32_sync_file_range(unsigned int fd, unsigned long off_high, unsigned lon asmlinkage long compat_sys_fallocate(int fd, int mode, u32 offhi, u32 offlo, u32 lenhi, u32 lenlo) { - return sys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo, - ((loff_t)lenhi << 32) | lenlo); + return ksys_fallocate(fd, mode, ((loff_t)offhi << 32) | offlo, + ((loff_t)lenhi << 32) | lenlo); } diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index c08c25f73d79..df2acb13623f 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -226,8 +226,8 @@ COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, unsigned int, offset_lo, unsigned int, offset_hi, unsigned int, len_lo, unsigned int, len_hi) { - return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, - ((u64)len_hi << 32) | len_lo); + return ksys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo, + ((u64)len_hi << 32) | len_lo); } /* diff --git a/fs/open.c b/fs/open.c index 2e816fc7bd56..d0e955b558ad 100644 --- a/fs/open.c +++ b/fs/open.c @@ -333,7 +333,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) } EXPORT_SYMBOL_GPL(vfs_fallocate); -SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) +int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len) { struct fd f = fdget(fd); int error = -EBADF; @@ -345,6 +345,11 @@ SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) return error; } +SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len) +{ + return ksys_fallocate(fd, mode, offset, len); +} + /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a30e4c2d0c27..613b8127834d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -969,6 +969,7 @@ ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos); ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); +int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len); /* * The following kernel syscall equivalents are just wrappers to fs-internal -- cgit v1.2.3 From 9d5b7c956b09daab955fb2a42447d5d89ff15093 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:45 +0100 Subject: mm: add ksys_fadvise64_64() helper; remove in-kernel call to sys_fadvise64_64() Using the ksys_fadvise64_64() helper allows us to avoid the in-kernel calls to the sys_fadvise64_64() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as ksys_fadvise64_64(). Some compat stubs called sys_fadvise64(), which then just passed through the arguments to sys_fadvise64_64(). Get rid of this indirection, and call ksys_fadvise64_64() directly. This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Dominik Brodowski --- arch/arm/kernel/sys_arm.c | 2 +- arch/mips/kernel/linux32.c | 2 +- arch/parisc/kernel/sys_parisc.c | 2 +- arch/powerpc/kernel/sys_ppc32.c | 4 ++-- arch/powerpc/kernel/syscalls.c | 4 ++-- arch/s390/kernel/compat_linux.c | 5 +++-- arch/sh/kernel/sys_sh32.c | 8 ++++---- arch/sparc/kernel/sys_sparc32.c | 10 +++++----- arch/x86/ia32/sys_ia32.c | 12 ++++++------ arch/xtensa/kernel/syscall.c | 2 +- include/linux/syscalls.h | 9 +++++++++ mm/fadvise.c | 10 ++++++++-- 12 files changed, 43 insertions(+), 27 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c index 3151f5623d0e..bdf7514204ab 100644 --- a/arch/arm/kernel/sys_arm.c +++ b/arch/arm/kernel/sys_arm.c @@ -35,5 +35,5 @@ asmlinkage long sys_arm_fadvise64_64(int fd, int advice, loff_t offset, loff_t len) { - return sys_fadvise64_64(fd, offset, len, advice); + return ksys_fadvise64_64(fd, offset, len, advice); } diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 0779d474c8ad..1c5785e72db4 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -149,7 +149,7 @@ asmlinkage long sys32_fadvise64_64(int fd, int __pad, unsigned long a4, unsigned long a5, int flags) { - return sys_fadvise64_64(fd, + return ksys_fadvise64_64(fd, merge_64(a2, a3), merge_64(a4, a5), flags); } diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 588fab336ddd..f36ab1f09595 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -352,7 +352,7 @@ asmlinkage long parisc_fadvise64_64(int fd, unsigned int high_off, unsigned int low_off, unsigned int high_len, unsigned int low_len, int advice) { - return sys_fadvise64_64(fd, (loff_t)high_off << 32 | low_off, + return ksys_fadvise64_64(fd, (loff_t)high_off << 32 | low_off, (loff_t)high_len << 32 | low_len, advice); } diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 68f11e1065f8..0b95fa13307f 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -113,8 +113,8 @@ asmlinkage int compat_sys_ftruncate64(unsigned int fd, u32 reg4, unsigned long h long ppc32_fadvise64(int fd, u32 unused, u32 offset_high, u32 offset_low, size_t len, int advice) { - return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low, len, - advice); + return ksys_fadvise64_64(fd, (u64)offset_high << 32 | offset_low, len, + advice); } asmlinkage long compat_sys_sync_file_range2(int fd, unsigned int flags, diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index a877bf8269fe..ecb981eea74b 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -119,8 +119,8 @@ long ppc64_personality(unsigned long personality) long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, u32 len_high, u32 len_low) { - return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low, - (u64)len_high << 32 | len_low, advice); + return ksys_fadvise64_64(fd, (u64)offset_high << 32 | offset_low, + (u64)len_high << 32 | len_low, advice); } long sys_switch_endian(void) diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 039858f9f128..9bb897e443a6 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -483,7 +483,8 @@ COMPAT_SYSCALL_DEFINE5(s390_fadvise64, int, fd, u32, high, u32, low, compat_size advise = POSIX_FADV_DONTNEED; else if (advise == 5) advise = POSIX_FADV_NOREUSE; - return sys_fadvise64(fd, (unsigned long)high << 32 | low, len, advise); + return ksys_fadvise64_64(fd, (unsigned long)high << 32 | low, len, + advise); } struct fadvise64_64_args { @@ -503,7 +504,7 @@ COMPAT_SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, arg a.advice = POSIX_FADV_DONTNEED; else if (a.advice == 5) a.advice = POSIX_FADV_NOREUSE; - return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice); + return ksys_fadvise64_64(a.fd, a.offset, a.len, a.advice); } COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow, diff --git a/arch/sh/kernel/sys_sh32.c b/arch/sh/kernel/sys_sh32.c index c37ee3d0c803..9dca568509a5 100644 --- a/arch/sh/kernel/sys_sh32.c +++ b/arch/sh/kernel/sys_sh32.c @@ -52,10 +52,10 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1, u32 len0, u32 len1, int advice) { #ifdef __LITTLE_ENDIAN__ - return sys_fadvise64_64(fd, (u64)offset1 << 32 | offset0, - (u64)len1 << 32 | len0, advice); + return ksys_fadvise64_64(fd, (u64)offset1 << 32 | offset0, + (u64)len1 << 32 | len0, advice); #else - return sys_fadvise64_64(fd, (u64)offset0 << 32 | offset1, - (u64)len0 << 32 | len1, advice); + return ksys_fadvise64_64(fd, (u64)offset0 << 32 | offset1, + (u64)len0 << 32 | len1, advice); #endif } diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 4ba62d676632..4da66aed50b4 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -225,7 +225,7 @@ long compat_sys_fadvise64(int fd, unsigned long offlo, compat_size_t len, int advice) { - return sys_fadvise64_64(fd, (offhi << 32) | offlo, len, advice); + return ksys_fadvise64_64(fd, (offhi << 32) | offlo, len, advice); } long compat_sys_fadvise64_64(int fd, @@ -233,10 +233,10 @@ long compat_sys_fadvise64_64(int fd, unsigned long lenhi, unsigned long lenlo, int advice) { - return sys_fadvise64_64(fd, - (offhi << 32) | offlo, - (lenhi << 32) | lenlo, - advice); + return ksys_fadvise64_64(fd, + (offhi << 32) | offlo, + (lenhi << 32) | lenlo, + advice); } long sys32_sync_file_range(unsigned int fd, unsigned long off_high, unsigned long off_low, unsigned long nb_high, unsigned long nb_low, unsigned int flags) diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index df2acb13623f..401bd8ec9cf0 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -194,10 +194,10 @@ COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, __u32, offset_high, __u32, len_low, __u32, len_high, int, advice) { - return sys_fadvise64_64(fd, - (((u64)offset_high)<<32) | offset_low, - (((u64)len_high)<<32) | len_low, - advice); + return ksys_fadvise64_64(fd, + (((u64)offset_high)<<32) | offset_low, + (((u64)len_high)<<32) | len_low, + advice); } COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, @@ -218,8 +218,8 @@ COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo, unsigned int, offset_hi, size_t, len, int, advice) { - return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, - len, advice); + return ksys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo, + len, advice); } COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode, diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c index 74afbf02d07e..8201748da05b 100644 --- a/arch/xtensa/kernel/syscall.c +++ b/arch/xtensa/kernel/syscall.c @@ -55,7 +55,7 @@ asmlinkage long xtensa_shmat(int shmid, char __user *shmaddr, int shmflg) asmlinkage long xtensa_fadvise64_64(int fd, int advice, unsigned long long offset, unsigned long long len) { - return sys_fadvise64_64(fd, offset, len, advice); + return ksys_fadvise64_64(fd, offset, len, advice); } #ifdef CONFIG_MMU diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 613b8127834d..466d408deefd 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -970,6 +970,15 @@ ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len); +#ifdef CONFIG_ADVISE_SYSCALLS +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice); +#else +static inline int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, + int advice) +{ + return -EINVAL; +} +#endif /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/mm/fadvise.c b/mm/fadvise.c index 767887f5f3bf..afa41491d324 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -26,7 +26,8 @@ * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could * deactivate the pages and clear PG_Referenced. */ -SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) + +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) { struct fd f = fdget(fd); struct inode *inode; @@ -185,11 +186,16 @@ out: return ret; } +SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) +{ + return ksys_fadvise64_64(fd, offset, len, advice); +} + #ifdef __ARCH_WANT_SYS_FADVISE64 SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice) { - return sys_fadvise64_64(fd, offset, len, advice); + return ksys_fadvise64_64(fd, offset, len, advice); } #endif -- cgit v1.2.3 From a90f590a1bee36fc2129cfb38ceec24a555bb12d Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 11 Mar 2018 11:34:46 +0100 Subject: mm: add ksys_mmap_pgoff() helper; remove in-kernel calls to sys_mmap_pgoff() Using this helper allows us to avoid the in-kernel calls to the sys_mmap_pgoff() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_mmap_pgoff(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Dominik Brodowski --- arch/alpha/kernel/osf_sys.c | 2 +- arch/arm64/kernel/sys.c | 2 +- arch/ia64/kernel/sys_ia64.c | 4 ++-- arch/m68k/kernel/sys_m68k.c | 2 +- arch/microblaze/kernel/sys_microblaze.c | 6 +++--- arch/mips/kernel/linux32.c | 4 ++-- arch/mips/kernel/syscall.c | 6 ++++-- arch/parisc/kernel/sys_parisc.c | 6 +++--- arch/powerpc/kernel/syscalls.c | 2 +- arch/riscv/kernel/sys_riscv.c | 4 ++-- arch/s390/kernel/compat_linux.c | 6 +++--- arch/s390/kernel/sys_s390.c | 2 +- arch/sh/kernel/sys_sh.c | 4 ++-- arch/sparc/kernel/sys_sparc_32.c | 6 +++--- arch/sparc/kernel/sys_sparc_64.c | 2 +- arch/um/kernel/syscall.c | 2 +- arch/x86/ia32/sys_ia32.c | 2 +- arch/x86/kernel/sys_x86_64.c | 2 +- include/linux/syscalls.h | 3 +++ mm/mmap.c | 17 ++++++++++++----- mm/nommu.c | 17 ++++++++++++----- 21 files changed, 60 insertions(+), 41 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index fa1a392ca9a2..89faa6f4de47 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -189,7 +189,7 @@ SYSCALL_DEFINE6(osf_mmap, unsigned long, addr, unsigned long, len, goto out; if (off & ~PAGE_MASK) goto out; - ret = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); + ret = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); out: return ret; } diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c index 26fe8ea93ea2..72981bae10eb 100644 --- a/arch/arm64/kernel/sys.c +++ b/arch/arm64/kernel/sys.c @@ -34,7 +34,7 @@ asmlinkage long sys_mmap(unsigned long addr, unsigned long len, if (offset_in_page(off) != 0) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); } SYSCALL_DEFINE1(arm64_personality, unsigned int, personality) diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index 085adfcc74a4..9ebe1d633abc 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -139,7 +139,7 @@ int ia64_mmap_check(unsigned long addr, unsigned long len, asmlinkage unsigned long sys_mmap2 (unsigned long addr, unsigned long len, int prot, int flags, int fd, long pgoff) { - addr = sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); + addr = ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); if (!IS_ERR((void *) addr)) force_successful_syscall_return(); return addr; @@ -151,7 +151,7 @@ sys_mmap (unsigned long addr, unsigned long len, int prot, int flags, int fd, lo if (offset_in_page(off) != 0) return -EINVAL; - addr = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); + addr = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); if (!IS_ERR((void *) addr)) force_successful_syscall_return(); return addr; diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c index 27e10af5153a..6363ec83a290 100644 --- a/arch/m68k/kernel/sys_m68k.c +++ b/arch/m68k/kernel/sys_m68k.c @@ -46,7 +46,7 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, * so we need to shift the argument down by 1; m68k mmap64(3) * (in libc) expects the last argument of mmap2 in 4Kb units. */ - return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } /* Convert virtual (user) address VADDR to physical address PADDR */ diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c index f1e1f666ddde..ed9f34da1a2a 100644 --- a/arch/microblaze/kernel/sys_microblaze.c +++ b/arch/microblaze/kernel/sys_microblaze.c @@ -40,7 +40,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, if (pgoff & ~PAGE_MASK) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff >> PAGE_SHIFT); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff >> PAGE_SHIFT); } SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, @@ -50,6 +50,6 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, if (pgoff & (~PAGE_MASK >> 12)) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, - pgoff >> (PAGE_SHIFT - 12)); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + pgoff >> (PAGE_SHIFT - 12)); } diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 1c5785e72db4..0571ab7b68b0 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -67,8 +67,8 @@ SYSCALL_DEFINE6(32_mmap2, unsigned long, addr, unsigned long, len, { if (pgoff & (~PAGE_MASK >> 12)) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, - pgoff >> (PAGE_SHIFT-12)); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + pgoff >> (PAGE_SHIFT-12)); } #define RLIM_INFINITY32 0x7fffffff diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 58c6f634b550..69c17b549fd3 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -63,7 +63,8 @@ SYSCALL_DEFINE6(mips_mmap, unsigned long, addr, unsigned long, len, { if (offset & ~PAGE_MASK) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + offset >> PAGE_SHIFT); } SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len, @@ -73,7 +74,8 @@ SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len, if (pgoff & (~PAGE_MASK >> 12)) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff >> (PAGE_SHIFT-12)); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + pgoff >> (PAGE_SHIFT - 12)); } save_static_function(sys_fork); diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index f36ab1f09595..080d566654ea 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -270,8 +270,8 @@ asmlinkage unsigned long sys_mmap2(unsigned long addr, unsigned long len, { /* Make sure the shift for mmap2 is constant (12), no matter what PAGE_SIZE we have. */ - return sys_mmap_pgoff(addr, len, prot, flags, fd, - pgoff >> (PAGE_SHIFT - 12)); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + pgoff >> (PAGE_SHIFT - 12)); } asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len, @@ -279,7 +279,7 @@ asmlinkage unsigned long sys_mmap(unsigned long addr, unsigned long len, unsigned long offset) { if (!(offset & ~PAGE_MASK)) { - return sys_mmap_pgoff(addr, len, prot, flags, fd, + return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT); } else { return -EINVAL; diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index ecb981eea74b..1ef3b80b62a6 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -57,7 +57,7 @@ static inline long do_mmap2(unsigned long addr, size_t len, off >>= shift; } - ret = sys_mmap_pgoff(addr, len, prot, flags, fd, off); + ret = ksys_mmap_pgoff(addr, len, prot, flags, fd, off); out: return ret; } diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 79c78668258e..f7181ed8aafc 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -24,8 +24,8 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, { if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, - offset >> (PAGE_SHIFT - page_shift_offset)); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + offset >> (PAGE_SHIFT - page_shift_offset)); } #ifdef CONFIG_64BIT diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 9bb897e443a6..da5ef7718254 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -442,8 +442,8 @@ COMPAT_SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct_emu31 __user *, arg return -EFAULT; if (a.offset & ~PAGE_MASK) return -EINVAL; - return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, - a.offset >> PAGE_SHIFT); + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); } COMPAT_SYSCALL_DEFINE1(s390_mmap2, struct mmap_arg_struct_emu31 __user *, arg) @@ -452,7 +452,7 @@ COMPAT_SYSCALL_DEFINE1(s390_mmap2, struct mmap_arg_struct_emu31 __user *, arg) if (copy_from_user(&a, arg, sizeof(a))) return -EFAULT; - return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); } COMPAT_SYSCALL_DEFINE3(s390_read, unsigned int, fd, char __user *, buf, compat_size_t, count) diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c index 0090037ab148..31cefe0c28c0 100644 --- a/arch/s390/kernel/sys_s390.c +++ b/arch/s390/kernel/sys_s390.c @@ -53,7 +53,7 @@ SYSCALL_DEFINE1(mmap2, struct s390_mmap_arg_struct __user *, arg) if (copy_from_user(&a, arg, sizeof(a))) goto out; - error = sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); + error = ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset); out: return error; } diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c index 724911c59e7d..f8afc014e084 100644 --- a/arch/sh/kernel/sys_sh.c +++ b/arch/sh/kernel/sys_sh.c @@ -35,7 +35,7 @@ asmlinkage int old_mmap(unsigned long addr, unsigned long len, { if (off & ~PAGE_MASK) return -EINVAL; - return sys_mmap_pgoff(addr, len, prot, flags, fd, off>>PAGE_SHIFT); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, off>>PAGE_SHIFT); } asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, @@ -51,7 +51,7 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, pgoff >>= PAGE_SHIFT - 12; - return sys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); } /* sys_cacheflush -- flush (part of) the processor cache. */ diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c index 990703b7cf4d..d980da4ffd7b 100644 --- a/arch/sparc/kernel/sys_sparc_32.c +++ b/arch/sparc/kernel/sys_sparc_32.c @@ -104,8 +104,8 @@ asmlinkage long sys_mmap2(unsigned long addr, unsigned long len, { /* Make sure the shift for mmap2 is constant (12), no matter what PAGE_SIZE we have. */ - return sys_mmap_pgoff(addr, len, prot, flags, fd, - pgoff >> (PAGE_SHIFT - 12)); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + pgoff >> (PAGE_SHIFT - 12)); } asmlinkage long sys_mmap(unsigned long addr, unsigned long len, @@ -113,7 +113,7 @@ asmlinkage long sys_mmap(unsigned long addr, unsigned long len, unsigned long off) { /* no alignment check? */ - return sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); + return ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); } long sparc_remap_file_pages(unsigned long start, unsigned long size, diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index 55416db482ad..ebb84dc8a5a7 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -458,7 +458,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, goto out; if (off & ~PAGE_MASK) goto out; - retval = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); + retval = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); out: return retval; } diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c index 6258676bed85..35f7047bdebc 100644 --- a/arch/um/kernel/syscall.c +++ b/arch/um/kernel/syscall.c @@ -22,7 +22,7 @@ long old_mmap(unsigned long addr, unsigned long len, if (offset & ~PAGE_MASK) goto out; - err = sys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT); + err = ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> PAGE_SHIFT); out: return err; } diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index 401bd8ec9cf0..bff71b9ae3f5 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -166,7 +166,7 @@ COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg) if (a.offset & ~PAGE_MASK) return -EINVAL; - return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset>>PAGE_SHIFT); } diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 676774b9bb8d..a3f15ed545b5 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -97,7 +97,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, if (off & ~PAGE_MASK) goto out; - error = sys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); + error = ksys_mmap_pgoff(addr, len, prot, flags, fd, off >> PAGE_SHIFT); out: return error; } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 466d408deefd..ec866c959e7d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -979,6 +979,9 @@ static inline int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, return -EINVAL; } #endif +unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/mm/mmap.c b/mm/mmap.c index 9efdc021ad22..aa0dc8231c0d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1488,9 +1488,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr, return addr; } -SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, - unsigned long, prot, unsigned long, flags, - unsigned long, fd, unsigned long, pgoff) +unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval; @@ -1537,6 +1537,13 @@ out_fput: return retval; } +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); +} + #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; @@ -1556,8 +1563,8 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) if (offset_in_page(a.offset)) return -EINVAL; - return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, - a.offset >> PAGE_SHIFT); + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ diff --git a/mm/nommu.c b/mm/nommu.c index ebb6e618dade..cad329629530 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1423,9 +1423,9 @@ error_getting_region: return -ENOMEM; } -SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, - unsigned long, prot, unsigned long, flags, - unsigned long, fd, unsigned long, pgoff) +unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff) { struct file *file = NULL; unsigned long retval = -EBADF; @@ -1447,6 +1447,13 @@ out: return retval; } +SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, pgoff) +{ + return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff); +} + #ifdef __ARCH_WANT_SYS_OLD_MMAP struct mmap_arg_struct { unsigned long addr; @@ -1466,8 +1473,8 @@ SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg) if (offset_in_page(a.offset)) return -EINVAL; - return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, - a.offset >> PAGE_SHIFT); + return ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, + a.offset >> PAGE_SHIFT); } #endif /* __ARCH_WANT_SYS_OLD_MMAP */ -- cgit v1.2.3 From c7b95d5156a9ee70f800bd2e47a9eba677be73e1 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 19 Mar 2018 17:51:36 +0100 Subject: mm: add ksys_readahead() helper; remove in-kernel calls to sys_readahead() Using this helper allows us to avoid the in-kernel calls to the sys_readahead() syscall. The ksys_ prefix denotes that this function is meant as a drop-in replacement for the syscall. In particular, it uses the same calling convention as sys_readahead(). This patch is part of a series which removes in-kernel calls to syscalls. On this basis, the syscall entry path can be streamlined. For details, see http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net Cc: Andrew Morton Cc: linux-mm@kvack.org Signed-off-by: Dominik Brodowski --- arch/mips/kernel/linux32.c | 2 +- arch/parisc/kernel/sys_parisc.c | 2 +- arch/powerpc/kernel/sys_ppc32.c | 2 +- arch/s390/kernel/compat_linux.c | 2 +- arch/sparc/kernel/sys_sparc32.c | 2 +- arch/x86/ia32/sys_ia32.c | 2 +- include/linux/syscalls.h | 1 + mm/readahead.c | 7 ++++++- 8 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c index 0571ab7b68b0..318f1c05c5b3 100644 --- a/arch/mips/kernel/linux32.c +++ b/arch/mips/kernel/linux32.c @@ -131,7 +131,7 @@ SYSCALL_DEFINE1(32_personality, unsigned long, personality) asmlinkage ssize_t sys32_readahead(int fd, u32 pad0, u64 a2, u64 a3, size_t count) { - return sys_readahead(fd, merge_64(a2, a3), count); + return ksys_readahead(fd, merge_64(a2, a3), count); } asmlinkage long sys32_sync_file_range(int fd, int __pad, diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index 080d566654ea..8c99ebbe2bac 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -345,7 +345,7 @@ asmlinkage ssize_t parisc_pwrite64(unsigned int fd, const char __user *buf, asmlinkage ssize_t parisc_readahead(int fd, unsigned int high, unsigned int low, size_t count) { - return sys_readahead(fd, (loff_t)high << 32 | low, count); + return ksys_readahead(fd, (loff_t)high << 32 | low, count); } asmlinkage long parisc_fadvise64_64(int fd, diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 0b95fa13307f..c11c73373691 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -88,7 +88,7 @@ compat_ssize_t compat_sys_pwrite64(unsigned int fd, const char __user *ubuf, com compat_ssize_t compat_sys_readahead(int fd, u32 r4, u32 offhi, u32 offlo, u32 count) { - return sys_readahead(fd, ((loff_t)offhi << 32) | offlo, count); + return ksys_readahead(fd, ((loff_t)offhi << 32) | offlo, count); } asmlinkage int compat_sys_truncate64(const char __user * path, u32 reg4, diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index da5ef7718254..8ac38d51ed7d 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -328,7 +328,7 @@ COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubu COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, count) { - return sys_readahead(fd, (unsigned long)high << 32 | low, count); + return ksys_readahead(fd, (unsigned long)high << 32 | low, count); } struct stat64_emu31 { diff --git a/arch/sparc/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c index 4da66aed50b4..f166e5bbf506 100644 --- a/arch/sparc/kernel/sys_sparc32.c +++ b/arch/sparc/kernel/sys_sparc32.c @@ -217,7 +217,7 @@ asmlinkage long compat_sys_readahead(int fd, unsigned long offlo, compat_size_t count) { - return sys_readahead(fd, (offhi << 32) | offlo, count); + return ksys_readahead(fd, (offhi << 32) | offlo, count); } long compat_sys_fadvise64(int fd, diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c index bff71b9ae3f5..bd8a7020b9a7 100644 --- a/arch/x86/ia32/sys_ia32.c +++ b/arch/x86/ia32/sys_ia32.c @@ -203,7 +203,7 @@ COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low, COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo, unsigned int, off_hi, size_t, count) { - return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); + return ksys_readahead(fd, ((u64)off_hi << 32) | off_lo, count); } COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index ec866c959e7d..815fbdd9cca1 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -982,6 +982,7 @@ static inline int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long fd, unsigned long pgoff); +ssize_t ksys_readahead(int fd, loff_t offset, size_t count); /* * The following kernel syscall equivalents are just wrappers to fs-internal diff --git a/mm/readahead.c b/mm/readahead.c index c4ca70239233..4d57b4644f98 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -573,7 +573,7 @@ do_readahead(struct address_space *mapping, struct file *filp, return force_page_cache_readahead(mapping, filp, index, nr); } -SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) +ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; struct fd f; @@ -592,3 +592,8 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) } return ret; } + +SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) +{ + return ksys_readahead(fd, offset, count); +} -- cgit v1.2.3 From 1bec510a9ebf00baa1aa8751e4a5d88b54efb748 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 22 Mar 2018 17:46:57 +0100 Subject: kexec: move sys_kexec_load() prototype to syscalls.h As the syscall function should only be called from the system call table but not from elsewhere in the kernel, move the prototype for sys_kexec_load() to include/syscall.h. Cc: Eric Biederman Cc: kexec@lists.infradead.org Signed-off-by: Dominik Brodowski --- include/linux/kexec.h | 4 ---- include/linux/syscalls.h | 4 ++++ 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index f16f6ceb3875..0ebcbeb21056 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -223,10 +223,6 @@ struct kimage { extern void machine_kexec(struct kimage *image); extern int machine_kexec_prepare(struct kimage *image); extern void machine_kexec_cleanup(struct kimage *image); -extern asmlinkage long sys_kexec_load(unsigned long entry, - unsigned long nr_segments, - struct kexec_segment __user *segments, - unsigned long flags); extern int kernel_kexec(void); extern struct page *kimage_alloc_control_pages(struct kimage *image, unsigned int order); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 815fbdd9cca1..8330f046541e 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -936,6 +936,10 @@ asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len, unsigned long prot, int pkey); asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val); asmlinkage long sys_pkey_free(int pkey); +asmlinkage long sys_kexec_load(unsigned long entry, + unsigned long nr_segments, + struct kexec_segment __user *segments, + unsigned long flags); asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); -- cgit v1.2.3 From 3c1c456f9b96c208c9dc9ad7aa3be36b8d488504 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Sun, 25 Mar 2018 21:50:11 +0200 Subject: syscalls: sort syscall prototypes in include/linux/syscalls.h Shuffle the syscall prototypes in include/linux/syscalls.h around so that they are kept in the same order as in include/uapi/asm-generic/unistd.h. The individual entries are kept the same, and neither modified to bring them in line with kernel coding style nor wrapped in proper ifdefs. Cc: Arnd Bergmann Cc: Andrew Morton Signed-off-by: Dominik Brodowski --- include/linux/syscalls.h | 1226 +++++++++++++++++++++++++--------------------- 1 file changed, 678 insertions(+), 548 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 8330f046541e..1f223b7cf16d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -241,223 +241,28 @@ static inline void addr_limit_user_check(void) #endif } -asmlinkage long sys_time(time_t __user *tloc); -asmlinkage long sys_stime(time_t __user *tptr); -asmlinkage long sys_gettimeofday(struct timeval __user *tv, - struct timezone __user *tz); -asmlinkage long sys_settimeofday(struct timeval __user *tv, - struct timezone __user *tz); -asmlinkage long sys_adjtimex(struct timex __user *txc_p); - -asmlinkage long sys_times(struct tms __user *tbuf); - -asmlinkage long sys_gettid(void); -asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp); -asmlinkage long sys_alarm(unsigned int seconds); -asmlinkage long sys_getpid(void); -asmlinkage long sys_getppid(void); -asmlinkage long sys_getuid(void); -asmlinkage long sys_geteuid(void); -asmlinkage long sys_getgid(void); -asmlinkage long sys_getegid(void); -asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid); -asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid); -asmlinkage long sys_getpgid(pid_t pid); -asmlinkage long sys_getpgrp(void); -asmlinkage long sys_getsid(pid_t pid); -asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist); - -asmlinkage long sys_setregid(gid_t rgid, gid_t egid); -asmlinkage long sys_setgid(gid_t gid); -asmlinkage long sys_setreuid(uid_t ruid, uid_t euid); -asmlinkage long sys_setuid(uid_t uid); -asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid); -asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid); -asmlinkage long sys_setfsuid(uid_t uid); -asmlinkage long sys_setfsgid(gid_t gid); -asmlinkage long sys_setpgid(pid_t pid, pid_t pgid); -asmlinkage long sys_setsid(void); -asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist); - -asmlinkage long sys_acct(const char __user *name); -asmlinkage long sys_capget(cap_user_header_t header, - cap_user_data_t dataptr); -asmlinkage long sys_capset(cap_user_header_t header, - const cap_user_data_t data); -asmlinkage long sys_personality(unsigned int personality); - -asmlinkage long sys_sigpending(old_sigset_t __user *uset); -asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, - old_sigset_t __user *oset); -asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, - struct sigaltstack __user *uoss); - -asmlinkage long sys_getitimer(int which, struct itimerval __user *value); -asmlinkage long sys_setitimer(int which, - struct itimerval __user *value, - struct itimerval __user *ovalue); -asmlinkage long sys_timer_create(clockid_t which_clock, - struct sigevent __user *timer_event_spec, - timer_t __user * created_timer_id); -asmlinkage long sys_timer_gettime(timer_t timer_id, - struct itimerspec __user *setting); -asmlinkage long sys_timer_getoverrun(timer_t timer_id); -asmlinkage long sys_timer_settime(timer_t timer_id, int flags, - const struct itimerspec __user *new_setting, - struct itimerspec __user *old_setting); -asmlinkage long sys_timer_delete(timer_t timer_id); -asmlinkage long sys_clock_settime(clockid_t which_clock, - const struct timespec __user *tp); -asmlinkage long sys_clock_gettime(clockid_t which_clock, - struct timespec __user *tp); -asmlinkage long sys_clock_adjtime(clockid_t which_clock, - struct timex __user *tx); -asmlinkage long sys_clock_getres(clockid_t which_clock, - struct timespec __user *tp); -asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags, - const struct timespec __user *rqtp, - struct timespec __user *rmtp); - -asmlinkage long sys_nice(int increment); -asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, - struct sched_param __user *param); -asmlinkage long sys_sched_setparam(pid_t pid, - struct sched_param __user *param); -asmlinkage long sys_sched_setattr(pid_t pid, - struct sched_attr __user *attr, - unsigned int flags); -asmlinkage long sys_sched_getscheduler(pid_t pid); -asmlinkage long sys_sched_getparam(pid_t pid, - struct sched_param __user *param); -asmlinkage long sys_sched_getattr(pid_t pid, - struct sched_attr __user *attr, - unsigned int size, - unsigned int flags); -asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, - unsigned long __user *user_mask_ptr); -asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, - unsigned long __user *user_mask_ptr); -asmlinkage long sys_sched_yield(void); -asmlinkage long sys_sched_get_priority_max(int policy); -asmlinkage long sys_sched_get_priority_min(int policy); -asmlinkage long sys_sched_rr_get_interval(pid_t pid, - struct timespec __user *interval); -asmlinkage long sys_setpriority(int which, int who, int niceval); -asmlinkage long sys_getpriority(int which, int who); - -asmlinkage long sys_shutdown(int, int); -asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, - void __user *arg); -asmlinkage long sys_restart_syscall(void); -asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, - struct kexec_segment __user *segments, - unsigned long flags); -asmlinkage long sys_kexec_file_load(int kernel_fd, int initrd_fd, - unsigned long cmdline_len, - const char __user *cmdline_ptr, - unsigned long flags); - -asmlinkage long sys_exit(int error_code); -asmlinkage long sys_exit_group(int error_code); -asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, - int options, struct rusage __user *ru); -asmlinkage long sys_waitid(int which, pid_t pid, - struct siginfo __user *infop, - int options, struct rusage __user *ru); -asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options); -asmlinkage long sys_set_tid_address(int __user *tidptr); -asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, - struct timespec __user *utime, u32 __user *uaddr2, - u32 val3); - -asmlinkage long sys_init_module(void __user *umod, unsigned long len, - const char __user *uargs); -asmlinkage long sys_delete_module(const char __user *name_user, - unsigned int flags); - -#ifdef CONFIG_OLD_SIGSUSPEND -asmlinkage long sys_sigsuspend(old_sigset_t mask); -#endif - -#ifdef CONFIG_OLD_SIGSUSPEND3 -asmlinkage long sys_sigsuspend(int unused1, int unused2, old_sigset_t mask); -#endif - -asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); - -#ifdef CONFIG_OLD_SIGACTION -asmlinkage long sys_sigaction(int, const struct old_sigaction __user *, - struct old_sigaction __user *); -#endif - -#ifndef CONFIG_ODD_RT_SIGACTION -asmlinkage long sys_rt_sigaction(int, - const struct sigaction __user *, - struct sigaction __user *, - size_t); -#endif -asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, - sigset_t __user *oset, size_t sigsetsize); -asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); -asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, - siginfo_t __user *uinfo, - const struct timespec __user *uts, - size_t sigsetsize); -asmlinkage long sys_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, - siginfo_t __user *uinfo); -asmlinkage long sys_kill(pid_t pid, int sig); -asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig); -asmlinkage long sys_tkill(pid_t pid, int sig); -asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo); -asmlinkage long sys_sgetmask(void); -asmlinkage long sys_ssetmask(int newmask); -asmlinkage long sys_signal(int sig, __sighandler_t handler); -asmlinkage long sys_pause(void); - -asmlinkage long sys_sync(void); -asmlinkage long sys_fsync(unsigned int fd); -asmlinkage long sys_fdatasync(unsigned int fd); -asmlinkage long sys_bdflush(int func, long data); -asmlinkage long sys_mount(char __user *dev_name, char __user *dir_name, - char __user *type, unsigned long flags, - void __user *data); -asmlinkage long sys_umount(char __user *name, int flags); -asmlinkage long sys_oldumount(char __user *name); -asmlinkage long sys_truncate(const char __user *path, long length); -asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); -asmlinkage long sys_stat(const char __user *filename, - struct __old_kernel_stat __user *statbuf); -asmlinkage long sys_statfs(const char __user * path, - struct statfs __user *buf); -asmlinkage long sys_statfs64(const char __user *path, size_t sz, - struct statfs64 __user *buf); -asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf); -asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, - struct statfs64 __user *buf); -asmlinkage long sys_lstat(const char __user *filename, - struct __old_kernel_stat __user *statbuf); -asmlinkage long sys_fstat(unsigned int fd, - struct __old_kernel_stat __user *statbuf); -asmlinkage long sys_newstat(const char __user *filename, - struct stat __user *statbuf); -asmlinkage long sys_newlstat(const char __user *filename, - struct stat __user *statbuf); -asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf); -asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); -#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) -asmlinkage long sys_stat64(const char __user *filename, - struct stat64 __user *statbuf); -asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf); -asmlinkage long sys_lstat64(const char __user *filename, - struct stat64 __user *statbuf); -asmlinkage long sys_fstatat64(int dfd, const char __user *filename, - struct stat64 __user *statbuf, int flag); -#endif -#if BITS_PER_LONG == 32 -asmlinkage long sys_truncate64(const char __user *path, loff_t length); -asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); -#endif +/* + * These syscall function prototypes are kept in the same order as + * include/uapi/asm-generic/unistd.h. Architecture specific entries go below, + * followed by deprecated or obsolete system calls. + * + * Please note that these prototypes here are only provided for information + * purposes, for static analysis, and for linking from the syscall table. + * These functions should not be called elsewhere from kernel code. + */ +asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx); +asmlinkage long sys_io_destroy(aio_context_t ctx); +asmlinkage long sys_io_submit(aio_context_t, long, + struct iocb __user * __user *); +asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, + struct io_event __user *result); +asmlinkage long sys_io_getevents(aio_context_t ctx_id, + long min_nr, + long nr, + struct io_event __user *events, + struct timespec __user *timeout); +/* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, const void __user *value, size_t size, int flags); asmlinkage long sys_lsetxattr(const char __user *path, const char __user *name, @@ -481,125 +286,126 @@ asmlinkage long sys_lremovexattr(const char __user *path, const char __user *name); asmlinkage long sys_fremovexattr(int fd, const char __user *name); -asmlinkage long sys_brk(unsigned long brk); -asmlinkage long sys_mprotect(unsigned long start, size_t len, - unsigned long prot); -asmlinkage long sys_mremap(unsigned long addr, - unsigned long old_len, unsigned long new_len, - unsigned long flags, unsigned long new_addr); -asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, - unsigned long prot, unsigned long pgoff, - unsigned long flags); -asmlinkage long sys_msync(unsigned long start, size_t len, int flags); -asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice); -asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice); -asmlinkage long sys_munmap(unsigned long addr, size_t len); -asmlinkage long sys_mlock(unsigned long start, size_t len); -asmlinkage long sys_munlock(unsigned long start, size_t len); -asmlinkage long sys_mlockall(int flags); -asmlinkage long sys_munlockall(void); -asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); -asmlinkage long sys_mincore(unsigned long start, size_t len, - unsigned char __user * vec); +/* fs/dcache.c */ +asmlinkage long sys_getcwd(char __user *buf, unsigned long size); -asmlinkage long sys_pivot_root(const char __user *new_root, - const char __user *put_old); -asmlinkage long sys_chroot(const char __user *filename); -asmlinkage long sys_mknod(const char __user *filename, umode_t mode, - unsigned dev); -asmlinkage long sys_link(const char __user *oldname, - const char __user *newname); -asmlinkage long sys_symlink(const char __user *old, const char __user *new); -asmlinkage long sys_unlink(const char __user *pathname); -asmlinkage long sys_rename(const char __user *oldname, - const char __user *newname); -asmlinkage long sys_chmod(const char __user *filename, umode_t mode); -asmlinkage long sys_fchmod(unsigned int fd, umode_t mode); +/* fs/cookies.c */ +asmlinkage long sys_lookup_dcookie(u64 cookie64, char __user *buf, size_t len); + +/* fs/eventfd.c */ +asmlinkage long sys_eventfd2(unsigned int count, int flags); +/* fs/eventpoll.c */ +asmlinkage long sys_epoll_create1(int flags); +asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, + struct epoll_event __user *event); +asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout, + const sigset_t __user *sigmask, + size_t sigsetsize); + +/* fs/fcntl.c */ +asmlinkage long sys_dup(unsigned int fildes); +asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags); asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg); #if BITS_PER_LONG == 32 asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg); #endif -asmlinkage long sys_pipe(int __user *fildes); -asmlinkage long sys_pipe2(int __user *fildes, int flags); -asmlinkage long sys_dup(unsigned int fildes); -asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd); -asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags); -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); + +/* fs/inotify_user.c */ +asmlinkage long sys_inotify_init1(int flags); +asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, + u32 mask); +asmlinkage long sys_inotify_rm_watch(int fd, __s32 wd); + +/* fs/ioctl.c */ asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg); + +/* fs/ioprio.c */ +asmlinkage long sys_ioprio_set(int which, int who, int ioprio); +asmlinkage long sys_ioprio_get(int which, int who); + +/* fs/locks.c */ asmlinkage long sys_flock(unsigned int fd, unsigned int cmd); -asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx); -asmlinkage long sys_io_destroy(aio_context_t ctx); -asmlinkage long sys_io_getevents(aio_context_t ctx_id, - long min_nr, - long nr, - struct io_event __user *events, - struct timespec __user *timeout); -asmlinkage long sys_io_submit(aio_context_t, long, - struct iocb __user * __user *); -asmlinkage long sys_io_cancel(aio_context_t ctx_id, struct iocb __user *iocb, - struct io_event __user *result); -asmlinkage long sys_sendfile(int out_fd, int in_fd, - off_t __user *offset, size_t count); -asmlinkage long sys_sendfile64(int out_fd, int in_fd, - loff_t __user *offset, size_t count); -asmlinkage long sys_readlink(const char __user *path, - char __user *buf, int bufsiz); -asmlinkage long sys_creat(const char __user *pathname, umode_t mode); -asmlinkage long sys_open(const char __user *filename, - int flags, umode_t mode); + +/* fs/namei.c */ +asmlinkage long sys_mknodat(int dfd, const char __user * filename, umode_t mode, + unsigned dev); +asmlinkage long sys_mkdirat(int dfd, const char __user * pathname, umode_t mode); +asmlinkage long sys_unlinkat(int dfd, const char __user * pathname, int flag); +asmlinkage long sys_symlinkat(const char __user * oldname, + int newdfd, const char __user * newname); +asmlinkage long sys_linkat(int olddfd, const char __user *oldname, + int newdfd, const char __user *newname, int flags); +asmlinkage long sys_renameat(int olddfd, const char __user * oldname, + int newdfd, const char __user * newname); + +/* fs/namespace.c */ +asmlinkage long sys_umount(char __user *name, int flags); +asmlinkage long sys_mount(char __user *dev_name, char __user *dir_name, + char __user *type, unsigned long flags, + void __user *data); +asmlinkage long sys_pivot_root(const char __user *new_root, + const char __user *put_old); + +/* fs/nfsctl.c */ + +/* fs/open.c */ +asmlinkage long sys_statfs(const char __user * path, + struct statfs __user *buf); +asmlinkage long sys_statfs64(const char __user *path, size_t sz, + struct statfs64 __user *buf); +asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user *buf); +asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, + struct statfs64 __user *buf); +asmlinkage long sys_truncate(const char __user *path, long length); +asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); +#if BITS_PER_LONG == 32 +asmlinkage long sys_truncate64(const char __user *path, loff_t length); +asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); +#endif +asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); +asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); +asmlinkage long sys_chdir(const char __user *filename); +asmlinkage long sys_fchdir(unsigned int fd); +asmlinkage long sys_chroot(const char __user *filename); +asmlinkage long sys_fchmod(unsigned int fd, umode_t mode); +asmlinkage long sys_fchmodat(int dfd, const char __user * filename, + umode_t mode); +asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, + gid_t group, int flag); +asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); +asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, + umode_t mode); asmlinkage long sys_close(unsigned int fd); -asmlinkage long sys_access(const char __user *filename, int mode); asmlinkage long sys_vhangup(void); -asmlinkage long sys_chown(const char __user *filename, - uid_t user, gid_t group); -asmlinkage long sys_lchown(const char __user *filename, - uid_t user, gid_t group); -asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); -#ifdef CONFIG_HAVE_UID16 -asmlinkage long sys_chown16(const char __user *filename, - old_uid_t user, old_gid_t group); -asmlinkage long sys_lchown16(const char __user *filename, - old_uid_t user, old_gid_t group); -asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group); -asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid); -asmlinkage long sys_setgid16(old_gid_t gid); -asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid); -asmlinkage long sys_setuid16(old_uid_t uid); -asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid); -asmlinkage long sys_getresuid16(old_uid_t __user *ruid, - old_uid_t __user *euid, old_uid_t __user *suid); -asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid); -asmlinkage long sys_getresgid16(old_gid_t __user *rgid, - old_gid_t __user *egid, old_gid_t __user *sgid); -asmlinkage long sys_setfsuid16(old_uid_t uid); -asmlinkage long sys_setfsgid16(old_gid_t gid); -asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist); -asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist); -asmlinkage long sys_getuid16(void); -asmlinkage long sys_geteuid16(void); -asmlinkage long sys_getgid16(void); -asmlinkage long sys_getegid16(void); -#endif -asmlinkage long sys_utime(char __user *filename, - struct utimbuf __user *times); -asmlinkage long sys_utimes(char __user *filename, - struct timeval __user *utimes); -asmlinkage long sys_lseek(unsigned int fd, off_t offset, - unsigned int whence); +/* fs/pipe.c */ +asmlinkage long sys_pipe2(int __user *fildes, int flags); + +/* fs/quota.c */ +asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, + qid_t id, void __user *addr); + +/* fs/readdir.c */ +asmlinkage long sys_getdents64(unsigned int fd, + struct linux_dirent64 __user *dirent, + unsigned int count); + +/* fs/read_write.c */ asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high, unsigned long offset_low, loff_t __user *result, unsigned int whence); +asmlinkage long sys_lseek(unsigned int fd, off_t offset, + unsigned int whence); asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count); -asmlinkage long sys_readahead(int fd, loff_t offset, size_t count); +asmlinkage long sys_write(unsigned int fd, const char __user *buf, + size_t count); asmlinkage long sys_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen); -asmlinkage long sys_write(unsigned int fd, const char __user *buf, - size_t count); asmlinkage long sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen); @@ -609,264 +415,314 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos); asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); -asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - rwf_t flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); -asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - rwf_t flags); -asmlinkage long sys_getcwd(char __user *buf, unsigned long size); -asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); -asmlinkage long sys_chdir(const char __user *filename); -asmlinkage long sys_fchdir(unsigned int fd); -asmlinkage long sys_rmdir(const char __user *pathname); -asmlinkage long sys_lookup_dcookie(u64 cookie64, char __user *buf, size_t len); -asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, - qid_t id, void __user *addr); -asmlinkage long sys_getdents(unsigned int fd, - struct linux_dirent __user *dirent, - unsigned int count); -asmlinkage long sys_getdents64(unsigned int fd, - struct linux_dirent64 __user *dirent, - unsigned int count); -asmlinkage long sys_setsockopt(int fd, int level, int optname, - char __user *optval, int optlen); -asmlinkage long sys_getsockopt(int fd, int level, int optname, - char __user *optval, int __user *optlen); -asmlinkage long sys_bind(int, struct sockaddr __user *, int); -asmlinkage long sys_connect(int, struct sockaddr __user *, int); -asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); -asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); -asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); -asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); -asmlinkage long sys_send(int, void __user *, size_t, unsigned); -asmlinkage long sys_sendto(int, void __user *, size_t, unsigned, - struct sockaddr __user *, int); -asmlinkage long sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags); -asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, - unsigned int vlen, unsigned flags); -asmlinkage long sys_recv(int, void __user *, size_t, unsigned); -asmlinkage long sys_recvfrom(int, void __user *, size_t, unsigned, - struct sockaddr __user *, int __user *); -asmlinkage long sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags); -asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, - unsigned int vlen, unsigned flags, - struct timespec __user *timeout); -asmlinkage long sys_socket(int, int, int); -asmlinkage long sys_socketpair(int, int, int, int __user *); -asmlinkage long sys_socketcall(int call, unsigned long __user *args); -asmlinkage long sys_listen(int, int); -asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, - int timeout); -asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, struct timeval __user *tvp); -asmlinkage long sys_old_select(struct sel_arg_struct __user *arg); -asmlinkage long sys_epoll_create(int size); -asmlinkage long sys_epoll_create1(int flags); -asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, - struct epoll_event __user *event); -asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout); -asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events, - int maxevents, int timeout, - const sigset_t __user *sigmask, +/* fs/sendfile.c */ +asmlinkage long sys_sendfile64(int out_fd, int in_fd, + loff_t __user *offset, size_t count); + +/* fs/select.c */ +asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, + fd_set __user *, struct timespec __user *, + void __user *); +asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, + struct timespec __user *, const sigset_t __user *, + size_t); + +/* fs/signalfd.c */ +asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, int flags); + +/* fs/splice.c */ +asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, + unsigned long nr_segs, unsigned int flags); +asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, + int fd_out, loff_t __user *off_out, + size_t len, unsigned int flags); +asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags); + +/* fs/stat.c */ +asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, + int bufsiz); +asmlinkage long sys_newfstatat(int dfd, const char __user *filename, + struct stat __user *statbuf, int flag); +asmlinkage long sys_newfstat(unsigned int fd, struct stat __user *statbuf); +#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) +asmlinkage long sys_fstat64(unsigned long fd, struct stat64 __user *statbuf); +asmlinkage long sys_fstatat64(int dfd, const char __user *filename, + struct stat64 __user *statbuf, int flag); +#endif + +/* fs/sync.c */ +asmlinkage long sys_sync(void); +asmlinkage long sys_fsync(unsigned int fd); +asmlinkage long sys_fdatasync(unsigned int fd); +asmlinkage long sys_sync_file_range2(int fd, unsigned int flags, + loff_t offset, loff_t nbytes); +asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, + unsigned int flags); + +/* fs/timerfd.c */ +asmlinkage long sys_timerfd_create(int clockid, int flags); +asmlinkage long sys_timerfd_settime(int ufd, int flags, + const struct itimerspec __user *utmr, + struct itimerspec __user *otmr); +asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); + +/* fs/utimes.c */ +asmlinkage long sys_utimensat(int dfd, const char __user *filename, + struct timespec __user *utimes, int flags); + +/* kernel/acct.c */ +asmlinkage long sys_acct(const char __user *name); + +/* kernel/capability.c */ +asmlinkage long sys_capget(cap_user_header_t header, + cap_user_data_t dataptr); +asmlinkage long sys_capset(cap_user_header_t header, + const cap_user_data_t data); + +/* kernel/exec_domain.c */ +asmlinkage long sys_personality(unsigned int personality); + +/* kernel/exit.c */ +asmlinkage long sys_exit(int error_code); +asmlinkage long sys_exit_group(int error_code); +asmlinkage long sys_waitid(int which, pid_t pid, + struct siginfo __user *infop, + int options, struct rusage __user *ru); + +/* kernel/fork.c */ +asmlinkage long sys_set_tid_address(int __user *tidptr); +asmlinkage long sys_unshare(unsigned long unshare_flags); + +/* kernel/futex.c */ +asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, + struct timespec __user *utime, u32 __user *uaddr2, + u32 val3); +asmlinkage long sys_get_robust_list(int pid, + struct robust_list_head __user * __user *head_ptr, + size_t __user *len_ptr); +asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, + size_t len); + +/* kernel/hrtimer.c */ +asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp); + +/* kernel/itimer.c */ +asmlinkage long sys_getitimer(int which, struct itimerval __user *value); +asmlinkage long sys_setitimer(int which, + struct itimerval __user *value, + struct itimerval __user *ovalue); + +/* kernel/kexec.c */ +asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments, + struct kexec_segment __user *segments, + unsigned long flags); + +/* kernel/module.c */ +asmlinkage long sys_init_module(void __user *umod, unsigned long len, + const char __user *uargs); +asmlinkage long sys_delete_module(const char __user *name_user, + unsigned int flags); + +/* kernel/posix-timers.c */ +asmlinkage long sys_timer_create(clockid_t which_clock, + struct sigevent __user *timer_event_spec, + timer_t __user * created_timer_id); +asmlinkage long sys_timer_gettime(timer_t timer_id, + struct itimerspec __user *setting); +asmlinkage long sys_timer_getoverrun(timer_t timer_id); +asmlinkage long sys_timer_settime(timer_t timer_id, int flags, + const struct itimerspec __user *new_setting, + struct itimerspec __user *old_setting); +asmlinkage long sys_timer_delete(timer_t timer_id); +asmlinkage long sys_clock_settime(clockid_t which_clock, + const struct timespec __user *tp); +asmlinkage long sys_clock_gettime(clockid_t which_clock, + struct timespec __user *tp); +asmlinkage long sys_clock_getres(clockid_t which_clock, + struct timespec __user *tp); +asmlinkage long sys_clock_nanosleep(clockid_t which_clock, int flags, + const struct timespec __user *rqtp, + struct timespec __user *rmtp); + +/* kernel/printk.c */ +asmlinkage long sys_syslog(int type, char __user *buf, int len); + +/* kernel/ptrace.c */ +asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, + unsigned long data); +/* kernel/sched/core.c */ + +asmlinkage long sys_sched_setparam(pid_t pid, + struct sched_param __user *param); +asmlinkage long sys_sched_setscheduler(pid_t pid, int policy, + struct sched_param __user *param); +asmlinkage long sys_sched_getscheduler(pid_t pid); +asmlinkage long sys_sched_getparam(pid_t pid, + struct sched_param __user *param); +asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, + unsigned long __user *user_mask_ptr); +asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len, + unsigned long __user *user_mask_ptr); +asmlinkage long sys_sched_yield(void); +asmlinkage long sys_sched_get_priority_max(int policy); +asmlinkage long sys_sched_get_priority_min(int policy); +asmlinkage long sys_sched_rr_get_interval(pid_t pid, + struct timespec __user *interval); + +/* kernel/signal.c */ +asmlinkage long sys_restart_syscall(void); +asmlinkage long sys_kill(pid_t pid, int sig); +asmlinkage long sys_tkill(pid_t pid, int sig); +asmlinkage long sys_tgkill(pid_t tgid, pid_t pid, int sig); +asmlinkage long sys_sigaltstack(const struct sigaltstack __user *uss, + struct sigaltstack __user *uoss); +asmlinkage long sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize); +#ifndef CONFIG_ODD_RT_SIGACTION +asmlinkage long sys_rt_sigaction(int, + const struct sigaction __user *, + struct sigaction __user *, + size_t); +#endif +asmlinkage long sys_rt_sigprocmask(int how, sigset_t __user *set, + sigset_t __user *oset, size_t sigsetsize); +asmlinkage long sys_rt_sigpending(sigset_t __user *set, size_t sigsetsize); +asmlinkage long sys_rt_sigtimedwait(const sigset_t __user *uthese, + siginfo_t __user *uinfo, + const struct timespec __user *uts, size_t sigsetsize); -asmlinkage long sys_gethostname(char __user *name, int len); +asmlinkage long sys_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t __user *uinfo); + +/* kernel/sys.c */ +asmlinkage long sys_setpriority(int which, int who, int niceval); +asmlinkage long sys_getpriority(int which, int who); +asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, + void __user *arg); +asmlinkage long sys_setregid(gid_t rgid, gid_t egid); +asmlinkage long sys_setgid(gid_t gid); +asmlinkage long sys_setreuid(uid_t ruid, uid_t euid); +asmlinkage long sys_setuid(uid_t uid); +asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid); +asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid); +asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid); +asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid); +asmlinkage long sys_setfsuid(uid_t uid); +asmlinkage long sys_setfsgid(gid_t gid); +asmlinkage long sys_times(struct tms __user *tbuf); +asmlinkage long sys_setpgid(pid_t pid, pid_t pgid); +asmlinkage long sys_getpgid(pid_t pid); +asmlinkage long sys_getsid(pid_t pid); +asmlinkage long sys_setsid(void); +asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist); +asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist); +asmlinkage long sys_newuname(struct new_utsname __user *name); asmlinkage long sys_sethostname(char __user *name, int len); asmlinkage long sys_setdomainname(char __user *name, int len); -asmlinkage long sys_newuname(struct new_utsname __user *name); -asmlinkage long sys_uname(struct old_utsname __user *); -asmlinkage long sys_olduname(struct oldold_utsname __user *); - asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim); -#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT -asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim); -#endif asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim); -asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource, - const struct rlimit64 __user *new_rlim, - struct rlimit64 __user *old_rlim); asmlinkage long sys_getrusage(int who, struct rusage __user *ru); asmlinkage long sys_umask(int mask); +asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5); +asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); + +/* kernel/time.c */ +asmlinkage long sys_gettimeofday(struct timeval __user *tv, + struct timezone __user *tz); +asmlinkage long sys_settimeofday(struct timeval __user *tv, + struct timezone __user *tz); +asmlinkage long sys_adjtimex(struct timex __user *txc_p); + +/* kernel/timer.c */ +asmlinkage long sys_getpid(void); +asmlinkage long sys_getppid(void); +asmlinkage long sys_getuid(void); +asmlinkage long sys_geteuid(void); +asmlinkage long sys_getgid(void); +asmlinkage long sys_getegid(void); +asmlinkage long sys_gettid(void); +asmlinkage long sys_sysinfo(struct sysinfo __user *info); + +/* ipc/mqueue.c */ +asmlinkage long sys_mq_open(const char __user *name, int oflag, umode_t mode, struct mq_attr __user *attr); +asmlinkage long sys_mq_unlink(const char __user *name); +asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout); +asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout); +asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification); +asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat); +/* ipc/msg.c */ asmlinkage long sys_msgget(key_t key, int msgflg); -asmlinkage long sys_msgsnd(int msqid, struct msgbuf __user *msgp, - size_t msgsz, int msgflg); +asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp, size_t msgsz, long msgtyp, int msgflg); -asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf); +asmlinkage long sys_msgsnd(int msqid, struct msgbuf __user *msgp, + size_t msgsz, int msgflg); +/* ipc/sem.c */ asmlinkage long sys_semget(key_t key, int nsems, int semflg); -asmlinkage long sys_semop(int semid, struct sembuf __user *sops, - unsigned nsops); asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg); asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops, unsigned nsops, const struct timespec __user *timeout); -asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); +asmlinkage long sys_semop(int semid, struct sembuf __user *sops, + unsigned nsops); + +/* ipc/shm.c */ asmlinkage long sys_shmget(key_t key, size_t size, int flag); -asmlinkage long sys_shmdt(char __user *shmaddr); asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf); -asmlinkage long sys_ipc(unsigned int call, int first, unsigned long second, - unsigned long third, void __user *ptr, long fifth); +asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg); +asmlinkage long sys_shmdt(char __user *shmaddr); -asmlinkage long sys_mq_open(const char __user *name, int oflag, umode_t mode, struct mq_attr __user *attr); -asmlinkage long sys_mq_unlink(const char __user *name); -asmlinkage long sys_mq_timedsend(mqd_t mqdes, const char __user *msg_ptr, size_t msg_len, unsigned int msg_prio, const struct timespec __user *abs_timeout); -asmlinkage long sys_mq_timedreceive(mqd_t mqdes, char __user *msg_ptr, size_t msg_len, unsigned int __user *msg_prio, const struct timespec __user *abs_timeout); -asmlinkage long sys_mq_notify(mqd_t mqdes, const struct sigevent __user *notification); -asmlinkage long sys_mq_getsetattr(mqd_t mqdes, const struct mq_attr __user *mqstat, struct mq_attr __user *omqstat); +/* net/socket.c */ +asmlinkage long sys_socket(int, int, int); +asmlinkage long sys_socketpair(int, int, int, int __user *); +asmlinkage long sys_bind(int, struct sockaddr __user *, int); +asmlinkage long sys_listen(int, int); +asmlinkage long sys_accept(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_connect(int, struct sockaddr __user *, int); +asmlinkage long sys_getsockname(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_getpeername(int, struct sockaddr __user *, int __user *); +asmlinkage long sys_sendto(int, void __user *, size_t, unsigned, + struct sockaddr __user *, int); +asmlinkage long sys_recvfrom(int, void __user *, size_t, unsigned, + struct sockaddr __user *, int __user *); +asmlinkage long sys_setsockopt(int fd, int level, int optname, + char __user *optval, int optlen); +asmlinkage long sys_getsockopt(int fd, int level, int optname, + char __user *optval, int __user *optlen); +asmlinkage long sys_shutdown(int, int); +asmlinkage long sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags); +asmlinkage long sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags); -asmlinkage long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn); -asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn, - unsigned long off, unsigned long len, - void __user *buf); -asmlinkage long sys_pciconfig_write(unsigned long bus, unsigned long dfn, - unsigned long off, unsigned long len, - void __user *buf); +/* mm/filemap.c */ +asmlinkage long sys_readahead(int fd, loff_t offset, size_t count); -asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5); -asmlinkage long sys_swapon(const char __user *specialfile, int swap_flags); -asmlinkage long sys_swapoff(const char __user *specialfile); -asmlinkage long sys_sysctl(struct __sysctl_args __user *args); -asmlinkage long sys_sysinfo(struct sysinfo __user *info); -asmlinkage long sys_sysfs(int option, - unsigned long arg1, unsigned long arg2); -asmlinkage long sys_syslog(int type, char __user *buf, int len); -asmlinkage long sys_uselib(const char __user *library); -asmlinkage long sys_ni_syscall(void); -asmlinkage long sys_ptrace(long request, long pid, unsigned long addr, - unsigned long data); +/* mm/nommu.c, also with MMU */ +asmlinkage long sys_brk(unsigned long brk); +asmlinkage long sys_munmap(unsigned long addr, size_t len); +asmlinkage long sys_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr); +/* security/keys/keyctl.c */ asmlinkage long sys_add_key(const char __user *_type, const char __user *_description, const void __user *_payload, size_t plen, key_serial_t destringid); - asmlinkage long sys_request_key(const char __user *_type, const char __user *_description, const char __user *_callout_info, key_serial_t destringid); - asmlinkage long sys_keyctl(int cmd, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); -asmlinkage long sys_ioprio_set(int which, int who, int ioprio); -asmlinkage long sys_ioprio_get(int which, int who); -asmlinkage long sys_set_mempolicy(int mode, const unsigned long __user *nmask, - unsigned long maxnode); -asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, - const unsigned long __user *from, - const unsigned long __user *to); -asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, - const void __user * __user *pages, - const int __user *nodes, - int __user *status, - int flags); -asmlinkage long sys_mbind(unsigned long start, unsigned long len, - unsigned long mode, - const unsigned long __user *nmask, - unsigned long maxnode, - unsigned flags); -asmlinkage long sys_get_mempolicy(int __user *policy, - unsigned long __user *nmask, - unsigned long maxnode, - unsigned long addr, unsigned long flags); - -asmlinkage long sys_inotify_init(void); -asmlinkage long sys_inotify_init1(int flags); -asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, - u32 mask); -asmlinkage long sys_inotify_rm_watch(int fd, __s32 wd); - -asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, - __u32 __user *ustatus); -asmlinkage long sys_spu_create(const char __user *name, - unsigned int flags, umode_t mode, int fd); - -asmlinkage long sys_mknodat(int dfd, const char __user * filename, umode_t mode, - unsigned dev); -asmlinkage long sys_mkdirat(int dfd, const char __user * pathname, umode_t mode); -asmlinkage long sys_unlinkat(int dfd, const char __user * pathname, int flag); -asmlinkage long sys_symlinkat(const char __user * oldname, - int newdfd, const char __user * newname); -asmlinkage long sys_linkat(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname, int flags); -asmlinkage long sys_renameat(int olddfd, const char __user * oldname, - int newdfd, const char __user * newname); -asmlinkage long sys_renameat2(int olddfd, const char __user *oldname, - int newdfd, const char __user *newname, - unsigned int flags); -asmlinkage long sys_futimesat(int dfd, const char __user *filename, - struct timeval __user *utimes); -asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode); -asmlinkage long sys_fchmodat(int dfd, const char __user * filename, - umode_t mode); -asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, - gid_t group, int flag); -asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, - umode_t mode); -asmlinkage long sys_newfstatat(int dfd, const char __user *filename, - struct stat __user *statbuf, int flag); -asmlinkage long sys_readlinkat(int dfd, const char __user *path, char __user *buf, - int bufsiz); -asmlinkage long sys_utimensat(int dfd, const char __user *filename, - struct timespec __user *utimes, int flags); -asmlinkage long sys_unshare(unsigned long unshare_flags); - -asmlinkage long sys_splice(int fd_in, loff_t __user *off_in, - int fd_out, loff_t __user *off_out, - size_t len, unsigned int flags); - -asmlinkage long sys_vmsplice(int fd, const struct iovec __user *iov, - unsigned long nr_segs, unsigned int flags); - -asmlinkage long sys_tee(int fdin, int fdout, size_t len, unsigned int flags); - -asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes, - unsigned int flags); -asmlinkage long sys_sync_file_range2(int fd, unsigned int flags, - loff_t offset, loff_t nbytes); -asmlinkage long sys_get_robust_list(int pid, - struct robust_list_head __user * __user *head_ptr, - size_t __user *len_ptr); -asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, - size_t len); -asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache); -asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask); -asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, size_t sizemask, int flags); -asmlinkage long sys_timerfd_create(int clockid, int flags); -asmlinkage long sys_timerfd_settime(int ufd, int flags, - const struct itimerspec __user *utmr, - struct itimerspec __user *otmr); -asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); -asmlinkage long sys_eventfd(unsigned int count); -asmlinkage long sys_eventfd2(unsigned int count, int flags); -asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); -asmlinkage long sys_userfaultfd(int flags); -asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); -asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int); -asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, - fd_set __user *, struct timespec __user *, - void __user *); -asmlinkage long sys_ppoll(struct pollfd __user *, unsigned int, - struct timespec __user *, const sigset_t __user *, - size_t); -asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags); -asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, - u64 mask, int fd, - const char __user *pathname); -asmlinkage long sys_syncfs(int fd); - -asmlinkage long sys_fork(void); -asmlinkage long sys_vfork(void); +/* arch/example/kernel/sys_example.c */ #ifdef CONFIG_CLONE_BACKWARDS asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, unsigned long, int __user *); @@ -879,26 +735,80 @@ asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, int __user *, unsigned long); #endif #endif - asmlinkage long sys_execve(const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp); +/* mm/fadvise.c */ +asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice); + +/* mm/, CONFIG_MMU only */ +asmlinkage long sys_swapon(const char __user *specialfile, int swap_flags); +asmlinkage long sys_swapoff(const char __user *specialfile); +asmlinkage long sys_mprotect(unsigned long start, size_t len, + unsigned long prot); +asmlinkage long sys_msync(unsigned long start, size_t len, int flags); +asmlinkage long sys_mlock(unsigned long start, size_t len); +asmlinkage long sys_munlock(unsigned long start, size_t len); +asmlinkage long sys_mlockall(int flags); +asmlinkage long sys_munlockall(void); +asmlinkage long sys_mincore(unsigned long start, size_t len, + unsigned char __user * vec); +asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior); +asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, + unsigned long prot, unsigned long pgoff, + unsigned long flags); +asmlinkage long sys_mbind(unsigned long start, unsigned long len, + unsigned long mode, + const unsigned long __user *nmask, + unsigned long maxnode, + unsigned flags); +asmlinkage long sys_get_mempolicy(int __user *policy, + unsigned long __user *nmask, + unsigned long maxnode, + unsigned long addr, unsigned long flags); +asmlinkage long sys_set_mempolicy(int mode, const unsigned long __user *nmask, + unsigned long maxnode); +asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, + const unsigned long __user *from, + const unsigned long __user *to); +asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, + const void __user * __user *pages, + const int __user *nodes, + int __user *status, + int flags); + +asmlinkage long sys_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, + siginfo_t __user *uinfo); asmlinkage long sys_perf_event_open( struct perf_event_attr __user *attr_uptr, pid_t pid, int cpu, int group_fd, unsigned long flags); +asmlinkage long sys_accept4(int, struct sockaddr __user *, int __user *, int); +asmlinkage long sys_recvmmsg(int fd, struct mmsghdr __user *msg, + unsigned int vlen, unsigned flags, + struct timespec __user *timeout); -asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len, - unsigned long prot, unsigned long flags, - unsigned long fd, unsigned long pgoff); -asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); +asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr, + int options, struct rusage __user *ru); +asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource, + const struct rlimit64 __user *new_rlim, + struct rlimit64 __user *old_rlim); +asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags); +asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, + u64 mask, int fd, + const char __user *pathname); asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name, struct file_handle __user *handle, int __user *mnt_id, int flag); asmlinkage long sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); +asmlinkage long sys_clock_adjtime(clockid_t which_clock, + struct timex __user *tx); +asmlinkage long sys_syncfs(int fd); asmlinkage long sys_setns(int fd, int nstype); +asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg, + unsigned int vlen, unsigned flags); asmlinkage long sys_process_vm_readv(pid_t pid, const struct iovec __user *lvec, unsigned long liovcnt, @@ -911,39 +821,259 @@ asmlinkage long sys_process_vm_writev(pid_t pid, const struct iovec __user *rvec, unsigned long riovcnt, unsigned long flags); - asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type, unsigned long idx1, unsigned long idx2); asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags); +asmlinkage long sys_sched_setattr(pid_t pid, + struct sched_attr __user *attr, + unsigned int flags); +asmlinkage long sys_sched_getattr(pid_t pid, + struct sched_attr __user *attr, + unsigned int size, + unsigned int flags); +asmlinkage long sys_renameat2(int olddfd, const char __user *oldname, + int newdfd, const char __user *newname, + unsigned int flags); asmlinkage long sys_seccomp(unsigned int op, unsigned int flags, const char __user *uargs); asmlinkage long sys_getrandom(char __user *buf, size_t count, unsigned int flags); +asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); - asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); - +asmlinkage long sys_userfaultfd(int flags); asmlinkage long sys_membarrier(int cmd, int flags); +asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in, int fd_out, loff_t __user *off_out, size_t len, unsigned int flags); - -asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); - +asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + rwf_t flags); +asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, unsigned long pos_l, unsigned long pos_h, + rwf_t flags); asmlinkage long sys_pkey_mprotect(unsigned long start, size_t len, unsigned long prot, int pkey); asmlinkage long sys_pkey_alloc(unsigned long flags, unsigned long init_val); asmlinkage long sys_pkey_free(int pkey); -asmlinkage long sys_kexec_load(unsigned long entry, - unsigned long nr_segments, - struct kexec_segment __user *segments, - unsigned long flags); asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags, unsigned mask, struct statx __user *buffer); +/* + * Architecture-specific system calls + */ + +/* arch/x86/kernel/ioport.c */ +asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); + +/* pciconfig: alpha, arm, arm64, ia64, sparc */ +asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn, + unsigned long off, unsigned long len, + void __user *buf); +asmlinkage long sys_pciconfig_write(unsigned long bus, unsigned long dfn, + unsigned long off, unsigned long len, + void __user *buf); +asmlinkage long sys_pciconfig_iobase(long which, unsigned long bus, unsigned long devfn); + +/* powerpc */ +asmlinkage long sys_spu_run(int fd, __u32 __user *unpc, + __u32 __user *ustatus); +asmlinkage long sys_spu_create(const char __user *name, + unsigned int flags, umode_t mode, int fd); + + +/* + * Deprecated system calls which are still defined in + * include/uapi/asm-generic/unistd.h and wanted by >= 1 arch + */ + +/* __ARCH_WANT_SYSCALL_NO_AT */ +asmlinkage long sys_open(const char __user *filename, + int flags, umode_t mode); +asmlinkage long sys_link(const char __user *oldname, + const char __user *newname); +asmlinkage long sys_unlink(const char __user *pathname); +asmlinkage long sys_mknod(const char __user *filename, umode_t mode, + unsigned dev); +asmlinkage long sys_chmod(const char __user *filename, umode_t mode); +asmlinkage long sys_chown(const char __user *filename, + uid_t user, gid_t group); +asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); +asmlinkage long sys_rmdir(const char __user *pathname); +asmlinkage long sys_lchown(const char __user *filename, + uid_t user, gid_t group); +asmlinkage long sys_access(const char __user *filename, int mode); +asmlinkage long sys_rename(const char __user *oldname, + const char __user *newname); +asmlinkage long sys_symlink(const char __user *old, const char __user *new); +asmlinkage long sys_utimes(char __user *filename, + struct timeval __user *utimes); +#if defined(__ARCH_WANT_STAT64) || defined(__ARCH_WANT_COMPAT_STAT64) +asmlinkage long sys_stat64(const char __user *filename, + struct stat64 __user *statbuf); +asmlinkage long sys_lstat64(const char __user *filename, + struct stat64 __user *statbuf); +#endif + +/* __ARCH_WANT_SYSCALL_NO_FLAGS */ +asmlinkage long sys_pipe(int __user *fildes); +asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd); +asmlinkage long sys_epoll_create(int size); +asmlinkage long sys_inotify_init(void); +asmlinkage long sys_eventfd(unsigned int count); +asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask); + +/* __ARCH_WANT_SYSCALL_OFF_T */ +asmlinkage long sys_sendfile(int out_fd, int in_fd, + off_t __user *offset, size_t count); +asmlinkage long sys_newstat(const char __user *filename, + struct stat __user *statbuf); +asmlinkage long sys_newlstat(const char __user *filename, + struct stat __user *statbuf); +asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice); + +/* __ARCH_WANT_SYSCALL_DEPRECATED */ +asmlinkage long sys_alarm(unsigned int seconds); +asmlinkage long sys_getpgrp(void); +asmlinkage long sys_pause(void); +asmlinkage long sys_time(time_t __user *tloc); +asmlinkage long sys_utime(char __user *filename, + struct utimbuf __user *times); +asmlinkage long sys_creat(const char __user *pathname, umode_t mode); +asmlinkage long sys_getdents(unsigned int fd, + struct linux_dirent __user *dirent, + unsigned int count); +asmlinkage long sys_futimesat(int dfd, const char __user *filename, + struct timeval __user *utimes); +asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, + fd_set __user *exp, struct timeval __user *tvp); +asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, + int timeout); +asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, + int maxevents, int timeout); +asmlinkage long sys_ustat(unsigned dev, struct ustat __user *ubuf); +asmlinkage long sys_vfork(void); +asmlinkage long sys_recv(int, void __user *, size_t, unsigned); +asmlinkage long sys_send(int, void __user *, size_t, unsigned); +asmlinkage long sys_bdflush(int func, long data); +asmlinkage long sys_oldumount(char __user *name); +asmlinkage long sys_uselib(const char __user *library); +asmlinkage long sys_sysctl(struct __sysctl_args __user *args); +asmlinkage long sys_sysfs(int option, + unsigned long arg1, unsigned long arg2); +asmlinkage long sys_fork(void); + +/* obsolete: kernel/time/time.c */ +asmlinkage long sys_stime(time_t __user *tptr); + +/* obsolete: kernel/signal.c */ +asmlinkage long sys_sigpending(old_sigset_t __user *uset); +asmlinkage long sys_sigprocmask(int how, old_sigset_t __user *set, + old_sigset_t __user *oset); +#ifdef CONFIG_OLD_SIGSUSPEND +asmlinkage long sys_sigsuspend(old_sigset_t mask); +#endif + +#ifdef CONFIG_OLD_SIGSUSPEND3 +asmlinkage long sys_sigsuspend(int unused1, int unused2, old_sigset_t mask); +#endif + +#ifdef CONFIG_OLD_SIGACTION +asmlinkage long sys_sigaction(int, const struct old_sigaction __user *, + struct old_sigaction __user *); +#endif +asmlinkage long sys_sgetmask(void); +asmlinkage long sys_ssetmask(int newmask); +asmlinkage long sys_signal(int sig, __sighandler_t handler); + +/* obsolete: kernel/sched/core.c */ +asmlinkage long sys_nice(int increment); + +/* obsolete: kernel/kexec_file.c */ +asmlinkage long sys_kexec_file_load(int kernel_fd, int initrd_fd, + unsigned long cmdline_len, + const char __user *cmdline_ptr, + unsigned long flags); + +/* obsolete: kernel/exit.c */ +asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options); + +/* obsolete: kernel/uid16.c */ +#ifdef CONFIG_HAVE_UID16 +asmlinkage long sys_chown16(const char __user *filename, + old_uid_t user, old_gid_t group); +asmlinkage long sys_lchown16(const char __user *filename, + old_uid_t user, old_gid_t group); +asmlinkage long sys_fchown16(unsigned int fd, old_uid_t user, old_gid_t group); +asmlinkage long sys_setregid16(old_gid_t rgid, old_gid_t egid); +asmlinkage long sys_setgid16(old_gid_t gid); +asmlinkage long sys_setreuid16(old_uid_t ruid, old_uid_t euid); +asmlinkage long sys_setuid16(old_uid_t uid); +asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid); +asmlinkage long sys_getresuid16(old_uid_t __user *ruid, + old_uid_t __user *euid, old_uid_t __user *suid); +asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid); +asmlinkage long sys_getresgid16(old_gid_t __user *rgid, + old_gid_t __user *egid, old_gid_t __user *sgid); +asmlinkage long sys_setfsuid16(old_uid_t uid); +asmlinkage long sys_setfsgid16(old_gid_t gid); +asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist); +asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist); +asmlinkage long sys_getuid16(void); +asmlinkage long sys_geteuid16(void); +asmlinkage long sys_getgid16(void); +asmlinkage long sys_getegid16(void); +#endif + +/* obsolete: net/socket.c */ +asmlinkage long sys_socketcall(int call, unsigned long __user *args); + +/* obsolete: fs/stat.c */ +asmlinkage long sys_stat(const char __user *filename, + struct __old_kernel_stat __user *statbuf); +asmlinkage long sys_lstat(const char __user *filename, + struct __old_kernel_stat __user *statbuf); +asmlinkage long sys_fstat(unsigned int fd, + struct __old_kernel_stat __user *statbuf); +asmlinkage long sys_readlink(const char __user *path, + char __user *buf, int bufsiz); + +/* obsolete: fs/select.c */ +asmlinkage long sys_old_select(struct sel_arg_struct __user *arg); + +/* obsolete: fs/readdir.c */ +asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int); + +/* obsolete: kernel/sys.c */ +asmlinkage long sys_gethostname(char __user *name, int len); +asmlinkage long sys_uname(struct old_utsname __user *); +asmlinkage long sys_olduname(struct oldold_utsname __user *); +#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT +asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim); +#endif + +/* obsolete: ipc */ +asmlinkage long sys_ipc(unsigned int call, int first, unsigned long second, + unsigned long third, void __user *ptr, long fifth); + +/* obsolete: mm/ */ +asmlinkage long sys_mmap_pgoff(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long pgoff); +asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); + + +/* + * Not a real system call, but a placeholder for syscalls which are + * not implemented -- see kernel/sys_ni.c + */ +asmlinkage long sys_ni_syscall(void); + + /* * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. * Instead, use one of the functions which work equivalently, such as -- cgit v1.2.3 From c9a211951c7c79cfb5de888d7d9550872868b086 Mon Sep 17 00:00:00 2001 From: Howard McLauchlan Date: Wed, 21 Mar 2018 18:59:08 -0700 Subject: bpf: whitelist all syscalls for error injection Error injection is a useful mechanism to fail arbitrary kernel functions. However, it is often hard to guarantee an error propagates appropriately to user space programs. By injecting into syscalls, we can return arbitrary values to user space directly; this increases flexibility and robustness in testing, allowing us to test user space error paths effectively. The following script, for example, fails calls to sys_open() from a given pid: from bcc import BPF from sys import argv pid = argv[1] prog = r""" int kprobe__SyS_open(struct pt_regs *ctx, const char *pathname, int flags) { u32 pid = bpf_get_current_pid_tgid(); if (pid == %s) bpf_override_return(ctx, -ENOMEM); return 0; } """ % pid b = BPF(text=prog) while 1: b.perf_buffer_poll() This patch whitelists all syscalls defined with SYSCALL_DEFINE and COMPAT_SYSCALL_DEFINE for error injection. These changes are not intended to be considered stable, and would normally be configured off. Signed-off-by: Howard McLauchlan Signed-off-by: Dominik Brodowski --- include/linux/compat.h | 3 +++ include/linux/syscalls.h | 3 +++ 2 files changed, 6 insertions(+) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/compat.h b/include/linux/compat.h index 8cb8710db0ab..9847c5a013c3 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -33,6 +33,8 @@ #endif #define COMPAT_SYSCALL_DEFINE0(name) \ + asmlinkage long compat_sys_##name(void); \ + ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \ asmlinkage long compat_sys_##name(void) #define COMPAT_SYSCALL_DEFINE1(name, ...) \ @@ -52,6 +54,7 @@ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))\ __attribute__((alias(__stringify(compat_SyS##name)))); \ + ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ static inline long C_SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));\ asmlinkage long compat_SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))\ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 1f223b7cf16d..b961184f597a 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -191,6 +191,8 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long sys_##sname(void); \ + ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \ asmlinkage long sys_##sname(void) #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) @@ -210,6 +212,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(SyS##name)))); \ + ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ -- cgit v1.2.3 From 1bd21c6c21e848996339508d3ffb106d505256a8 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:01 +0200 Subject: syscalls/core: Introduce CONFIG_ARCH_HAS_SYSCALL_WRAPPER=y It may be useful for an architecture to override the definitions of the SYSCALL_DEFINE0() and __SYSCALL_DEFINEx() macros in , in particular to use a different calling convention for syscalls. This patch provides a mechanism to do so: It introduces CONFIG_ARCH_HAS_SYSCALL_WRAPPER. If it is enabled, is included in and may be used to define the macros mentioned above. Moreover, as the syscall calling convention may be different if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is set, the syscall function prototypes in are #ifndef'd out in that case. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-3-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- include/linux/syscalls.h | 23 +++++++++++++++++++++++ init/Kconfig | 7 +++++++ 2 files changed, 30 insertions(+) (limited to 'include/linux/syscalls.h') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index b961184f597a..503ab245d4ce 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -81,6 +81,17 @@ union bpf_attr; #include #include +#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER +/* + * It may be useful for an architecture to override the definitions of the + * SYSCALL_DEFINE0() and __SYSCALL_DEFINEx() macros, in particular to use a + * different calling convention for syscalls. To allow for that, the prototypes + * for the sys_*() functions below will *not* be included if + * CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. + */ +#include +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * __MAP - apply a macro to syscall arguments * __MAP(n, m, t1, a1, t2, a2, ..., tn, an) will expand to @@ -189,11 +200,13 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) } #endif +#ifndef SYSCALL_DEFINE0 #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ asmlinkage long sys_##sname(void); \ ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \ asmlinkage long sys_##sname(void) +#endif /* SYSCALL_DEFINE0 */ #define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) @@ -209,6 +222,8 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) __SYSCALL_DEFINEx(x, sname, __VA_ARGS__) #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) + +#ifndef __SYSCALL_DEFINEx #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(SyS##name)))); \ @@ -223,6 +238,7 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) return ret; \ } \ static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) +#endif /* __SYSCALL_DEFINEx */ /* * Called before coming back to user-mode. Returning to user-mode with an @@ -252,7 +268,12 @@ static inline void addr_limit_user_check(void) * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. + * + * As the syscall calling convention may be different from the default + * for architectures overriding the syscall calling convention, do not + * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ +#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long sys_io_setup(unsigned nr_reqs, aio_context_t __user *ctx); asmlinkage long sys_io_destroy(aio_context_t ctx); asmlinkage long sys_io_submit(aio_context_t, long, @@ -1076,6 +1097,8 @@ asmlinkage long sys_old_mmap(struct mmap_arg_struct __user *arg); */ asmlinkage long sys_ni_syscall(void); +#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ + /* * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. diff --git a/init/Kconfig b/init/Kconfig index 2852692d7c9c..068eb6c3bbf7 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1923,3 +1923,10 @@ source "kernel/Kconfig.locks" config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE bool + +# It may be useful for an architecture to override the definitions of the +# SYSCALL_DEFINE() and __SYSCALL_DEFINEx() macros in , +# in particular to use a different calling convention for syscalls. +config ARCH_HAS_SYSCALL_WRAPPER + def_bool n + depends on !COMPAT -- cgit v1.2.3 From fa697140f9a20119a9ec8fd7460cc4314fbdaff3 Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Thu, 5 Apr 2018 11:53:02 +0200 Subject: syscalls/x86: Use 'struct pt_regs' based syscall calling convention for 64-bit syscalls Let's make use of ARCH_HAS_SYSCALL_WRAPPER=y on pure 64-bit x86-64 systems: Each syscall defines a stub which takes struct pt_regs as its only argument. It decodes just those parameters it needs, e.g: asmlinkage long sys_xyzzy(const struct pt_regs *regs) { return SyS_xyzzy(regs->di, regs->si, regs->dx); } This approach avoids leaking random user-provided register content down the call chain. For example, for sys_recv() which is a 4-parameter syscall, the assembly now is (in slightly reordered fashion): : callq <__fentry__> /* decode regs->di, ->si, ->dx and ->r10 */ mov 0x70(%rdi),%rdi mov 0x68(%rdi),%rsi mov 0x60(%rdi),%rdx mov 0x38(%rdi),%rcx [ SyS_recv() is automatically inlined by the compiler, as it is not [yet] used anywhere else ] /* clear %r9 and %r8, the 5th and 6th args */ xor %r9d,%r9d xor %r8d,%r8d /* do the actual work */ callq __sys_recvfrom /* cleanup and return */ cltq retq The only valid place in an x86-64 kernel which rightfully calls a syscall function on its own -- vsyscall -- needs to be modified to pass struct pt_regs onwards as well. To keep the syscall table generation working independent of SYSCALL_PTREGS being enabled, the stubs are named the same as the "original" syscall stubs, i.e. sys_*(). This patch is based on an original proof-of-concept | From: Linus Torvalds | Signed-off-by: Linus Torvalds and was split up and heavily modified by me, in particular to base it on ARCH_HAS_SYSCALL_WRAPPER, to limit it to 64-bit-only for the time being, and to update the vsyscall to the new calling convention. Signed-off-by: Dominik Brodowski Acked-by: Linus Torvalds Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180405095307.3730-4-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/Kconfig | 5 +++ arch/x86/entry/common.c | 4 ++ arch/x86/entry/syscall_64.c | 9 ++++- arch/x86/entry/vsyscall/vsyscall_64.c | 22 +++++++++++ arch/x86/include/asm/syscall.h | 4 ++ arch/x86/include/asm/syscall_wrapper.h | 70 ++++++++++++++++++++++++++++++++++ arch/x86/include/asm/syscalls.h | 7 ++++ include/linux/syscalls.h | 2 +- 8 files changed, 120 insertions(+), 3 deletions(-) create mode 100644 arch/x86/include/asm/syscall_wrapper.h (limited to 'include/linux/syscalls.h') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 27fede438959..67348efc2540 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2954,3 +2954,8 @@ source "crypto/Kconfig" source "arch/x86/kvm/Kconfig" source "lib/Kconfig" + +config SYSCALL_PTREGS + def_bool y + depends on X86_64 && !COMPAT + select ARCH_HAS_SYSCALL_WRAPPER diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index a8b066dbbf48..e1b91bffa988 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -284,9 +284,13 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) nr &= __SYSCALL_MASK; if (likely(nr < NR_syscalls)) { nr = array_index_nospec(nr, NR_syscalls); +#ifdef CONFIG_SYSCALL_PTREGS + regs->ax = sys_call_table[nr](regs); +#else regs->ax = sys_call_table[nr]( regs->di, regs->si, regs->dx, regs->r10, regs->r8, regs->r9); +#endif } syscall_return_slowpath(regs); diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index c176d2fab1da..6197850adf91 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -7,14 +7,19 @@ #include #include +#ifdef CONFIG_SYSCALL_PTREGS +/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */ +extern asmlinkage long sys_ni_syscall(const struct pt_regs *); +#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *); +#else /* CONFIG_SYSCALL_PTREGS */ +extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#endif /* CONFIG_SYSCALL_PTREGS */ #include #undef __SYSCALL_64 #define __SYSCALL_64(nr, sym, qual) [nr] = sym, -extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); - asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 317be365bce3..05eebbf9b989 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -127,6 +127,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) int vsyscall_nr, syscall_nr, tmp; int prev_sig_on_uaccess_err; long ret; +#ifdef CONFIG_SYSCALL_PTREGS + unsigned long orig_dx; +#endif /* * No point in checking CS -- the only way to get here is a user mode @@ -227,19 +230,38 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) ret = -EFAULT; switch (vsyscall_nr) { case 0: +#ifdef CONFIG_SYSCALL_PTREGS + /* this decodes regs->di and regs->si on its own */ + ret = sys_gettimeofday(regs); +#else ret = sys_gettimeofday( (struct timeval __user *)regs->di, (struct timezone __user *)regs->si); +#endif /* CONFIG_SYSCALL_PTREGS */ break; case 1: +#ifdef CONFIG_SYSCALL_PTREGS + /* this decodes regs->di on its own */ + ret = sys_time(regs); +#else ret = sys_time((time_t __user *)regs->di); +#endif /* CONFIG_SYSCALL_PTREGS */ break; case 2: +#ifdef CONFIG_SYSCALL_PTREGS + /* while we could clobber regs->dx, we didn't in the past... */ + orig_dx = regs->dx; + regs->dx = 0; + /* this decodes regs->di, regs->si and regs->dx on its own */ + ret = sys_getcpu(regs); + regs->dx = orig_dx; +#else ret = sys_getcpu((unsigned __user *)regs->di, (unsigned __user *)regs->si, NULL); +#endif /* CONFIG_SYSCALL_PTREGS */ break; } diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 03eedc21246d..17c62373a6f9 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -20,9 +20,13 @@ #include /* for TS_COMPAT */ #include +#ifdef CONFIG_SYSCALL_PTREGS +typedef asmlinkage long (*sys_call_ptr_t)(const struct pt_regs *); +#else typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); +#endif /* CONFIG_SYSCALL_PTREGS */ extern const sys_call_ptr_t sys_call_table[]; #if defined(CONFIG_X86_32) diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h new file mode 100644 index 000000000000..702bdee377af --- /dev/null +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - x86 specific wrappers to syscall definitions + */ + +#ifndef _ASM_X86_SYSCALL_WRAPPER_H +#define _ASM_X86_SYSCALL_WRAPPER_H + +/* + * Instead of the generic __SYSCALL_DEFINEx() definition, this macro takes + * struct pt_regs *regs as the only argument of the syscall stub named + * sys_*(). It decodes just the registers it needs and passes them on to + * the SyS_*() wrapper and then to the SYSC_*() function doing the actual job. + * These wrappers and functions are inlined, meaning that the assembly looks + * as follows (slightly re-ordered): + * + * : <-- syscall with 4 parameters + * callq <__fentry__> + * + * mov 0x70(%rdi),%rdi <-- decode regs->di + * mov 0x68(%rdi),%rsi <-- decode regs->si + * mov 0x60(%rdi),%rdx <-- decode regs->dx + * mov 0x38(%rdi),%rcx <-- decode regs->r10 + * + * xor %r9d,%r9d <-- clear %r9 + * xor %r8d,%r8d <-- clear %r8 + * + * callq __sys_recvfrom <-- do the actual work in __sys_recvfrom() + * which takes 6 arguments + * + * cltq <-- extend return value to 64-bit + * retq <-- return + * + * This approach avoids leaking random user-provided register content down + * the call chain. + * + * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for + * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not + * hurt, there is no need to override it. + */ +#define __SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ + static long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + asmlinkage long sys##name(const struct pt_regs *regs) \ + { \ + return SyS##name(__MAP(x,__SC_ARGS \ + ,,regs->di,,regs->si,,regs->dx \ + ,,regs->r10,,regs->r8,,regs->r9)); \ + } \ + static long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +/* + * For VSYSCALLS, we need to declare these three syscalls with the new + * pt_regs-based calling convention for in-kernel use. + */ +struct pt_regs; +asmlinkage long sys_getcpu(const struct pt_regs *regs); /* di,si,dx */ +asmlinkage long sys_gettimeofday(const struct pt_regs *regs); /* di,si */ +asmlinkage long sys_time(const struct pt_regs *regs); /* di */ + +#endif /* _ASM_X86_SYSCALL_WRAPPER_H */ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index ae6e05fdc24b..e4ad93c05f02 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -18,6 +18,12 @@ /* Common in X86_32 and X86_64 */ /* kernel/ioport.c */ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on); + +#ifndef CONFIG_SYSCALL_PTREGS +/* + * If CONFIG_SYSCALL_PTREGS is enabled, a different syscall calling convention + * is used. Do not include these -- invalid -- prototypes then + */ asmlinkage long sys_ioperm(unsigned long, unsigned long, int); asmlinkage long sys_iopl(unsigned int); @@ -53,4 +59,5 @@ asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); #endif /* CONFIG_X86_32 */ +#endif /* CONFIG_SYSCALL_PTREGS */ #endif /* _ASM_X86_SYSCALLS_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 503ab245d4ce..d7168b3a4b4c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -102,7 +102,7 @@ union bpf_attr; * for SYSCALL_DEFINE/COMPAT_SYSCALL_DEFINE */ #define __MAP0(m,...) -#define __MAP1(m,t,a) m(t,a) +#define __MAP1(m,t,a,...) m(t,a) #define __MAP2(m,t,a,...) m(t,a), __MAP1(m,__VA_ARGS__) #define __MAP3(m,t,a,...) m(t,a), __MAP2(m,__VA_ARGS__) #define __MAP4(m,t,a,...) m(t,a), __MAP3(m,__VA_ARGS__) -- cgit v1.2.3 From e145242ea0df6b7d28fd7186e61d6840fa4bb06e Mon Sep 17 00:00:00 2001 From: Dominik Brodowski Date: Mon, 9 Apr 2018 12:51:42 +0200 Subject: syscalls/core, syscalls/x86: Clean up syscall stub naming convention Tidy the naming convention for compat syscall subs. Hints which describe the purpose of the stub go in front and receive a double underscore to denote that they are generated on-the-fly by the SYSCALL_DEFINEx() macro. For the generic case, this means (0xffffffff prefix removed): 810f08d0 t kernel_waitid # common C function (see kernel/exit.c) __do_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) 810f1aa0 T __se_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long; # casts them to the declared type) 810f1aa0 T sys_waitid # alias to __se_sys_waitid() (taking # parameters as declared), to be included # in syscall table For x86, the naming is as follows: 810efc70 t kernel_waitid # common C function (see kernel/exit.c) __do_sys_waitid # inlined helper doing the actual work # (takes original parameters as declared) 810efd60 t __se_sys_waitid # sign-extending C function calling inlined # helper (takes parameters of type long; # casts them to the declared type) 810f1140 T __ia32_sys_waitid # IA32_EMULATION 32-bit-ptregs -> C stub, # calls __se_sys_waitid(); to be included # in syscall table 810f1110 T sys_waitid # x86 64-bit-ptregs -> C stub, calls # __se_sys_waitid(); to be included in # syscall table For x86, sys_waitid() will be re-named to __x64_sys_waitid in a follow-up patch. Suggested-by: Ingo Molnar Signed-off-by: Dominik Brodowski Cc: Al Viro Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20180409105145.5364-2-linux@dominikbrodowski.net Signed-off-by: Ingo Molnar --- arch/x86/entry/syscalls/syscall_32.tbl | 424 ++++++++++++++++----------------- arch/x86/include/asm/syscall_wrapper.h | 35 +-- include/linux/syscalls.h | 17 +- scripts/bloat-o-meter | 2 +- 4 files changed, 242 insertions(+), 236 deletions(-) (limited to 'include/linux/syscalls.h') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7f09a3da0b3d..539df8f6d0e1 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -4,7 +4,7 @@ # The format is: # # -# The __sys_ia32 and __compat_sys_ia32 stubs are created on-the-fly for +# The __ia32_sys and __compat_sys_ia32 stubs are created on-the-fly for # sys_*() system calls and compat_sys_*() compat system calls if # IA32_EMULATION is defined, and expect struct pt_regs *regs as their only # parameter. @@ -12,284 +12,284 @@ # The abi is always "i386" for this file. # 0 i386 restart_syscall sys_restart_syscall -1 i386 exit sys_exit __sys_ia32_exit +1 i386 exit sys_exit __ia32_sys_exit 2 i386 fork sys_fork -3 i386 read sys_read __sys_ia32_read -4 i386 write sys_write __sys_ia32_write +3 i386 read sys_read __ia32_sys_read +4 i386 write sys_write __ia32_sys_write 5 i386 open sys_open __compat_sys_ia32_open -6 i386 close sys_close __sys_ia32_close -7 i386 waitpid sys_waitpid __sys_ia32_waitpid -8 i386 creat sys_creat __sys_ia32_creat -9 i386 link sys_link __sys_ia32_link -10 i386 unlink sys_unlink __sys_ia32_unlink +6 i386 close sys_close __ia32_sys_close +7 i386 waitpid sys_waitpid __ia32_sys_waitpid +8 i386 creat sys_creat __ia32_sys_creat +9 i386 link sys_link __ia32_sys_link +10 i386 unlink sys_unlink __ia32_sys_unlink 11 i386 execve sys_execve __compat_sys_ia32_execve -12 i386 chdir sys_chdir __sys_ia32_chdir +12 i386 chdir sys_chdir __ia32_sys_chdir 13 i386 time sys_time __compat_sys_ia32_time -14 i386 mknod sys_mknod __sys_ia32_mknod -15 i386 chmod sys_chmod __sys_ia32_chmod -16 i386 lchown sys_lchown16 __sys_ia32_lchown16 +14 i386 mknod sys_mknod __ia32_sys_mknod +15 i386 chmod sys_chmod __ia32_sys_chmod +16 i386 lchown sys_lchown16 __ia32_sys_lchown16 17 i386 break -18 i386 oldstat sys_stat __sys_ia32_stat +18 i386 oldstat sys_stat __ia32_sys_stat 19 i386 lseek sys_lseek __compat_sys_ia32_lseek 20 i386 getpid sys_getpid 21 i386 mount sys_mount __compat_sys_ia32_mount -22 i386 umount sys_oldumount __sys_ia32_oldumount -23 i386 setuid sys_setuid16 __sys_ia32_setuid16 +22 i386 umount sys_oldumount __ia32_sys_oldumount +23 i386 setuid sys_setuid16 __ia32_sys_setuid16 24 i386 getuid sys_getuid16 25 i386 stime sys_stime __compat_sys_ia32_stime 26 i386 ptrace sys_ptrace __compat_sys_ia32_ptrace -27 i386 alarm sys_alarm __sys_ia32_alarm -28 i386 oldfstat sys_fstat __sys_ia32_fstat +27 i386 alarm sys_alarm __ia32_sys_alarm +28 i386 oldfstat sys_fstat __ia32_sys_fstat 29 i386 pause sys_pause 30 i386 utime sys_utime __compat_sys_ia32_utime 31 i386 stty 32 i386 gtty -33 i386 access sys_access __sys_ia32_access -34 i386 nice sys_nice __sys_ia32_nice +33 i386 access sys_access __ia32_sys_access +34 i386 nice sys_nice __ia32_sys_nice 35 i386 ftime 36 i386 sync sys_sync -37 i386 kill sys_kill __sys_ia32_kill -38 i386 rename sys_rename __sys_ia32_rename -39 i386 mkdir sys_mkdir __sys_ia32_mkdir -40 i386 rmdir sys_rmdir __sys_ia32_rmdir -41 i386 dup sys_dup __sys_ia32_dup -42 i386 pipe sys_pipe __sys_ia32_pipe +37 i386 kill sys_kill __ia32_sys_kill +38 i386 rename sys_rename __ia32_sys_rename +39 i386 mkdir sys_mkdir __ia32_sys_mkdir +40 i386 rmdir sys_rmdir __ia32_sys_rmdir +41 i386 dup sys_dup __ia32_sys_dup +42 i386 pipe sys_pipe __ia32_sys_pipe 43 i386 times sys_times __compat_sys_ia32_times 44 i386 prof -45 i386 brk sys_brk __sys_ia32_brk -46 i386 setgid sys_setgid16 __sys_ia32_setgid16 +45 i386 brk sys_brk __ia32_sys_brk +46 i386 setgid sys_setgid16 __ia32_sys_setgid16 47 i386 getgid sys_getgid16 -48 i386 signal sys_signal __sys_ia32_signal +48 i386 signal sys_signal __ia32_sys_signal 49 i386 geteuid sys_geteuid16 50 i386 getegid sys_getegid16 -51 i386 acct sys_acct __sys_ia32_acct -52 i386 umount2 sys_umount __sys_ia32_umount +51 i386 acct sys_acct __ia32_sys_acct +52 i386 umount2 sys_umount __ia32_sys_umount 53 i386 lock 54 i386 ioctl sys_ioctl __compat_sys_ia32_ioctl 55 i386 fcntl sys_fcntl __compat_sys_ia32_fcntl64 56 i386 mpx -57 i386 setpgid sys_setpgid __sys_ia32_setpgid +57 i386 setpgid sys_setpgid __ia32_sys_setpgid 58 i386 ulimit -59 i386 oldolduname sys_olduname __sys_ia32_olduname -60 i386 umask sys_umask __sys_ia32_umask -61 i386 chroot sys_chroot __sys_ia32_chroot +59 i386 oldolduname sys_olduname __ia32_sys_olduname +60 i386 umask sys_umask __ia32_sys_umask +61 i386 chroot sys_chroot __ia32_sys_chroot 62 i386 ustat sys_ustat __compat_sys_ia32_ustat -63 i386 dup2 sys_dup2 __sys_ia32_dup2 +63 i386 dup2 sys_dup2 __ia32_sys_dup2 64 i386 getppid sys_getppid 65 i386 getpgrp sys_getpgrp 66 i386 setsid sys_setsid 67 i386 sigaction sys_sigaction __compat_sys_ia32_sigaction 68 i386 sgetmask sys_sgetmask -69 i386 ssetmask sys_ssetmask __sys_ia32_ssetmask -70 i386 setreuid sys_setreuid16 __sys_ia32_setreuid16 -71 i386 setregid sys_setregid16 __sys_ia32_setregid16 -72 i386 sigsuspend sys_sigsuspend __sys_ia32_sigsuspend +69 i386 ssetmask sys_ssetmask __ia32_sys_ssetmask +70 i386 setreuid sys_setreuid16 __ia32_sys_setreuid16 +71 i386 setregid sys_setregid16 __ia32_sys_setregid16 +72 i386 sigsuspend sys_sigsuspend __ia32_sys_sigsuspend 73 i386 sigpending sys_sigpending __compat_sys_ia32_sigpending -74 i386 sethostname sys_sethostname __sys_ia32_sethostname +74 i386 sethostname sys_sethostname __ia32_sys_sethostname 75 i386 setrlimit sys_setrlimit __compat_sys_ia32_setrlimit 76 i386 getrlimit sys_old_getrlimit __compat_sys_ia32_old_getrlimit 77 i386 getrusage sys_getrusage __compat_sys_ia32_getrusage 78 i386 gettimeofday sys_gettimeofday __compat_sys_ia32_gettimeofday 79 i386 settimeofday sys_settimeofday __compat_sys_ia32_settimeofday -80 i386 getgroups sys_getgroups16 __sys_ia32_getgroups16 -81 i386 setgroups sys_setgroups16 __sys_ia32_setgroups16 +80 i386 getgroups sys_getgroups16 __ia32_sys_getgroups16 +81 i386 setgroups sys_setgroups16 __ia32_sys_setgroups16 82 i386 select sys_old_select __compat_sys_ia32_old_select -83 i386 symlink sys_symlink __sys_ia32_symlink -84 i386 oldlstat sys_lstat __sys_ia32_lstat -85 i386 readlink sys_readlink __sys_ia32_readlink -86 i386 uselib sys_uselib __sys_ia32_uselib -87 i386 swapon sys_swapon __sys_ia32_swapon -88 i386 reboot sys_reboot __sys_ia32_reboot +83 i386 symlink sys_symlink __ia32_sys_symlink +84 i386 oldlstat sys_lstat __ia32_sys_lstat +85 i386 readlink sys_readlink __ia32_sys_readlink +86 i386 uselib sys_uselib __ia32_sys_uselib +87 i386 swapon sys_swapon __ia32_sys_swapon +88 i386 reboot sys_reboot __ia32_sys_reboot 89 i386 readdir sys_old_readdir __compat_sys_ia32_old_readdir 90 i386 mmap sys_old_mmap __compat_sys_ia32_x86_mmap -91 i386 munmap sys_munmap __sys_ia32_munmap +91 i386 munmap sys_munmap __ia32_sys_munmap 92 i386 truncate sys_truncate __compat_sys_ia32_truncate 93 i386 ftruncate sys_ftruncate __compat_sys_ia32_ftruncate -94 i386 fchmod sys_fchmod __sys_ia32_fchmod -95 i386 fchown sys_fchown16 __sys_ia32_fchown16 -96 i386 getpriority sys_getpriority __sys_ia32_getpriority -97 i386 setpriority sys_setpriority __sys_ia32_setpriority +94 i386 fchmod sys_fchmod __ia32_sys_fchmod +95 i386 fchown sys_fchown16 __ia32_sys_fchown16 +96 i386 getpriority sys_getpriority __ia32_sys_getpriority +97 i386 setpriority sys_setpriority __ia32_sys_setpriority 98 i386 profil 99 i386 statfs sys_statfs __compat_sys_ia32_statfs 100 i386 fstatfs sys_fstatfs __compat_sys_ia32_fstatfs -101 i386 ioperm sys_ioperm __sys_ia32_ioperm +101 i386 ioperm sys_ioperm __ia32_sys_ioperm 102 i386 socketcall sys_socketcall __compat_sys_ia32_socketcall -103 i386 syslog sys_syslog __sys_ia32_syslog +103 i386 syslog sys_syslog __ia32_sys_syslog 104 i386 setitimer sys_setitimer __compat_sys_ia32_setitimer 105 i386 getitimer sys_getitimer __compat_sys_ia32_getitimer 106 i386 stat sys_newstat __compat_sys_ia32_newstat 107 i386 lstat sys_newlstat __compat_sys_ia32_newlstat 108 i386 fstat sys_newfstat __compat_sys_ia32_newfstat -109 i386 olduname sys_uname __sys_ia32_uname -110 i386 iopl sys_iopl __sys_ia32_iopl +109 i386 olduname sys_uname __ia32_sys_uname +110 i386 iopl sys_iopl __ia32_sys_iopl 111 i386 vhangup sys_vhangup 112 i386 idle 113 i386 vm86old sys_vm86old sys_ni_syscall 114 i386 wait4 sys_wait4 __compat_sys_ia32_wait4 -115 i386 swapoff sys_swapoff __sys_ia32_swapoff +115 i386 swapoff sys_swapoff __ia32_sys_swapoff 116 i386 sysinfo sys_sysinfo __compat_sys_ia32_sysinfo 117 i386 ipc sys_ipc __compat_sys_ia32_ipc -118 i386 fsync sys_fsync __sys_ia32_fsync +118 i386 fsync sys_fsync __ia32_sys_fsync 119 i386 sigreturn sys_sigreturn sys32_sigreturn 120 i386 clone sys_clone __compat_sys_ia32_x86_clone -121 i386 setdomainname sys_setdomainname __sys_ia32_setdomainname -122 i386 uname sys_newuname __sys_ia32_newuname -123 i386 modify_ldt sys_modify_ldt __sys_ia32_modify_ldt +121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname +122 i386 uname sys_newuname __ia32_sys_newuname +123 i386 modify_ldt sys_modify_ldt __ia32_sys_modify_ldt 124 i386 adjtimex sys_adjtimex __compat_sys_ia32_adjtimex -125 i386 mprotect sys_mprotect __sys_ia32_mprotect +125 i386 mprotect sys_mprotect __ia32_sys_mprotect 126 i386 sigprocmask sys_sigprocmask __compat_sys_ia32_sigprocmask 127 i386 create_module -128 i386 init_module sys_init_module __sys_ia32_init_module -129 i386 delete_module sys_delete_module __sys_ia32_delete_module +128 i386 init_module sys_init_module __ia32_sys_init_module +129 i386 delete_module sys_delete_module __ia32_sys_delete_module 130 i386 get_kernel_syms 131 i386 quotactl sys_quotactl __compat_sys_ia32_quotactl32 -132 i386 getpgid sys_getpgid __sys_ia32_getpgid -133 i386 fchdir sys_fchdir __sys_ia32_fchdir -134 i386 bdflush sys_bdflush __sys_ia32_bdflush -135 i386 sysfs sys_sysfs __sys_ia32_sysfs -136 i386 personality sys_personality __sys_ia32_personality +132 i386 getpgid sys_getpgid __ia32_sys_getpgid +133 i386 fchdir sys_fchdir __ia32_sys_fchdir +134 i386 bdflush sys_bdflush __ia32_sys_bdflush +135 i386 sysfs sys_sysfs __ia32_sys_sysfs +136 i386 personality sys_personality __ia32_sys_personality 137 i386 afs_syscall -138 i386 setfsuid sys_setfsuid16 __sys_ia32_setfsuid16 -139 i386 setfsgid sys_setfsgid16 __sys_ia32_setfsgid16 -140 i386 _llseek sys_llseek __sys_ia32_llseek +138 i386 setfsuid sys_setfsuid16 __ia32_sys_setfsuid16 +139 i386 setfsgid sys_setfsgid16 __ia32_sys_setfsgid16 +140 i386 _llseek sys_llseek __ia32_sys_llseek 141 i386 getdents sys_getdents __compat_sys_ia32_getdents 142 i386 _newselect sys_select __compat_sys_ia32_select -143 i386 flock sys_flock __sys_ia32_flock -144 i386 msync sys_msync __sys_ia32_msync +143 i386 flock sys_flock __ia32_sys_flock +144 i386 msync sys_msync __ia32_sys_msync 145 i386 readv sys_readv __compat_sys_ia32_readv 146 i386 writev sys_writev __compat_sys_ia32_writev -147 i386 getsid sys_getsid __sys_ia32_getsid -148 i386 fdatasync sys_fdatasync __sys_ia32_fdatasync +147 i386 getsid sys_getsid __ia32_sys_getsid +148 i386 fdatasync sys_fdatasync __ia32_sys_fdatasync 149 i386 _sysctl sys_sysctl __compat_sys_ia32_sysctl -150 i386 mlock sys_mlock __sys_ia32_mlock -151 i386 munlock sys_munlock __sys_ia32_munlock -152 i386 mlockall sys_mlockall __sys_ia32_mlockall +150 i386 mlock sys_mlock __ia32_sys_mlock +151 i386 munlock sys_munlock __ia32_sys_munlock +152 i386 mlockall sys_mlockall __ia32_sys_mlockall 153 i386 munlockall sys_munlockall -154 i386 sched_setparam sys_sched_setparam __sys_ia32_sched_setparam -155 i386 sched_getparam sys_sched_getparam __sys_ia32_sched_getparam -156 i386 sched_setscheduler sys_sched_setscheduler __sys_ia32_sched_setscheduler -157 i386 sched_getscheduler sys_sched_getscheduler __sys_ia32_sched_getscheduler +154 i386 sched_setparam sys_sched_setparam __ia32_sys_sched_setparam +155 i386 sched_getparam sys_sched_getparam __ia32_sys_sched_getparam +156 i386 sched_setscheduler sys_sched_setscheduler __ia32_sys_sched_setscheduler +157 i386 sched_getscheduler sys_sched_getscheduler __ia32_sys_sched_getscheduler 158 i386 sched_yield sys_sched_yield -159 i386 sched_get_priority_max sys_sched_get_priority_max __sys_ia32_sched_get_priority_max -160 i386 sched_get_priority_min sys_sched_get_priority_min __sys_ia32_sched_get_priority_min +159 i386 sched_get_priority_max sys_sched_get_priority_max __ia32_sys_sched_get_priority_max +160 i386 sched_get_priority_min sys_sched_get_priority_min __ia32_sys_sched_get_priority_min 161 i386 sched_rr_get_interval sys_sched_rr_get_interval __compat_sys_ia32_sched_rr_get_interval 162 i386 nanosleep sys_nanosleep __compat_sys_ia32_nanosleep -163 i386 mremap sys_mremap __sys_ia32_mremap -164 i386 setresuid sys_setresuid16 __sys_ia32_setresuid16 -165 i386 getresuid sys_getresuid16 __sys_ia32_getresuid16 +163 i386 mremap sys_mremap __ia32_sys_mremap +164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16 +165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16 166 i386 vm86 sys_vm86 sys_ni_syscall 167 i386 query_module -168 i386 poll sys_poll __sys_ia32_poll +168 i386 poll sys_poll __ia32_sys_poll 169 i386 nfsservctl -170 i386 setresgid sys_setresgid16 __sys_ia32_setresgid16 -171 i386 getresgid sys_getresgid16 __sys_ia32_getresgid16 -172 i386 prctl sys_prctl __sys_ia32_prctl +170 i386 setresgid sys_setresgid16 __ia32_sys_setresgid16 +171 i386 getresgid sys_getresgid16 __ia32_sys_getresgid16 +172 i386 prctl sys_prctl __ia32_sys_prctl 173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn 174 i386 rt_sigaction sys_rt_sigaction __compat_sys_ia32_rt_sigaction -175 i386 rt_sigprocmask sys_rt_sigprocmask __sys_ia32_rt_sigprocmask +175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_sys_rt_sigprocmask 176 i386 rt_sigpending sys_rt_sigpending __compat_sys_ia32_rt_sigpending 177 i386 rt_sigtimedwait sys_rt_sigtimedwait __compat_sys_ia32_rt_sigtimedwait 178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __compat_sys_ia32_rt_sigqueueinfo -179 i386 rt_sigsuspend sys_rt_sigsuspend __sys_ia32_rt_sigsuspend +179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_sys_rt_sigsuspend 180 i386 pread64 sys_pread64 __compat_sys_ia32_x86_pread 181 i386 pwrite64 sys_pwrite64 __compat_sys_ia32_x86_pwrite -182 i386 chown sys_chown16 __sys_ia32_chown16 -183 i386 getcwd sys_getcwd __sys_ia32_getcwd -184 i386 capget sys_capget __sys_ia32_capget -185 i386 capset sys_capset __sys_ia32_capset +182 i386 chown sys_chown16 __ia32_sys_chown16 +183 i386 getcwd sys_getcwd __ia32_sys_getcwd +184 i386 capget sys_capget __ia32_sys_capget +185 i386 capset sys_capset __ia32_sys_capset 186 i386 sigaltstack sys_sigaltstack __compat_sys_ia32_sigaltstack 187 i386 sendfile sys_sendfile __compat_sys_ia32_sendfile 188 i386 getpmsg 189 i386 putpmsg 190 i386 vfork sys_vfork 191 i386 ugetrlimit sys_getrlimit __compat_sys_ia32_getrlimit -192 i386 mmap2 sys_mmap_pgoff __sys_ia32_mmap_pgoff +192 i386 mmap2 sys_mmap_pgoff __ia32_sys_mmap_pgoff 193 i386 truncate64 sys_truncate64 __compat_sys_ia32_x86_truncate64 194 i386 ftruncate64 sys_ftruncate64 __compat_sys_ia32_x86_ftruncate64 195 i386 stat64 sys_stat64 __compat_sys_ia32_x86_stat64 196 i386 lstat64 sys_lstat64 __compat_sys_ia32_x86_lstat64 197 i386 fstat64 sys_fstat64 __compat_sys_ia32_x86_fstat64 -198 i386 lchown32 sys_lchown __sys_ia32_lchown +198 i386 lchown32 sys_lchown __ia32_sys_lchown 199 i386 getuid32 sys_getuid 200 i386 getgid32 sys_getgid 201 i386 geteuid32 sys_geteuid 202 i386 getegid32 sys_getegid -203 i386 setreuid32 sys_setreuid __sys_ia32_setreuid -204 i386 setregid32 sys_setregid __sys_ia32_setregid -205 i386 getgroups32 sys_getgroups __sys_ia32_getgroups -206 i386 setgroups32 sys_setgroups __sys_ia32_setgroups -207 i386 fchown32 sys_fchown __sys_ia32_fchown -208 i386 setresuid32 sys_setresuid __sys_ia32_setresuid -209 i386 getresuid32 sys_getresuid __sys_ia32_getresuid -210 i386 setresgid32 sys_setresgid __sys_ia32_setresgid -211 i386 getresgid32 sys_getresgid __sys_ia32_getresgid -212 i386 chown32 sys_chown __sys_ia32_chown -213 i386 setuid32 sys_setuid __sys_ia32_setuid -214 i386 setgid32 sys_setgid __sys_ia32_setgid -215 i386 setfsuid32 sys_setfsuid __sys_ia32_setfsuid -216 i386 setfsgid32 sys_setfsgid __sys_ia32_setfsgid -217 i386 pivot_root sys_pivot_root __sys_ia32_pivot_root -218 i386 mincore sys_mincore __sys_ia32_mincore -219 i386 madvise sys_madvise __sys_ia32_madvise -220 i386 getdents64 sys_getdents64 __sys_ia32_getdents64 +203 i386 setreuid32 sys_setreuid __ia32_sys_setreuid +204 i386 setregid32 sys_setregid __ia32_sys_setregid +205 i386 getgroups32 sys_getgroups __ia32_sys_getgroups +206 i386 setgroups32 sys_setgroups __ia32_sys_setgroups +207 i386 fchown32 sys_fchown __ia32_sys_fchown +208 i386 setresuid32 sys_setresuid __ia32_sys_setresuid +209 i386 getresuid32 sys_getresuid __ia32_sys_getresuid +210 i386 setresgid32 sys_setresgid __ia32_sys_setresgid +211 i386 getresgid32 sys_getresgid __ia32_sys_getresgid +212 i386 chown32 sys_chown __ia32_sys_chown +213 i386 setuid32 sys_setuid __ia32_sys_setuid +214 i386 setgid32 sys_setgid __ia32_sys_setgid +215 i386 setfsuid32 sys_setfsuid __ia32_sys_setfsuid +216 i386 setfsgid32 sys_setfsgid __ia32_sys_setfsgid +217 i386 pivot_root sys_pivot_root __ia32_sys_pivot_root +218 i386 mincore sys_mincore __ia32_sys_mincore +219 i386 madvise sys_madvise __ia32_sys_madvise +220 i386 getdents64 sys_getdents64 __ia32_sys_getdents64 221 i386 fcntl64 sys_fcntl64 __compat_sys_ia32_fcntl64 # 222 is unused # 223 is unused 224 i386 gettid sys_gettid 225 i386 readahead sys_readahead __compat_sys_ia32_x86_readahead -226 i386 setxattr sys_setxattr __sys_ia32_setxattr -227 i386 lsetxattr sys_lsetxattr __sys_ia32_lsetxattr -228 i386 fsetxattr sys_fsetxattr __sys_ia32_fsetxattr -229 i386 getxattr sys_getxattr __sys_ia32_getxattr -230 i386 lgetxattr sys_lgetxattr __sys_ia32_lgetxattr -231 i386 fgetxattr sys_fgetxattr __sys_ia32_fgetxattr -232 i386 listxattr sys_listxattr __sys_ia32_listxattr -233 i386 llistxattr sys_llistxattr __sys_ia32_llistxattr -234 i386 flistxattr sys_flistxattr __sys_ia32_flistxattr -235 i386 removexattr sys_removexattr __sys_ia32_removexattr -236 i386 lremovexattr sys_lremovexattr __sys_ia32_lremovexattr -237 i386 fremovexattr sys_fremovexattr __sys_ia32_fremovexattr -238 i386 tkill sys_tkill __sys_ia32_tkill -239 i386 sendfile64 sys_sendfile64 __sys_ia32_sendfile64 +226 i386 setxattr sys_setxattr __ia32_sys_setxattr +227 i386 lsetxattr sys_lsetxattr __ia32_sys_lsetxattr +228 i386 fsetxattr sys_fsetxattr __ia32_sys_fsetxattr +229 i386 getxattr sys_getxattr __ia32_sys_getxattr +230 i386 lgetxattr sys_lgetxattr __ia32_sys_lgetxattr +231 i386 fgetxattr sys_fgetxattr __ia32_sys_fgetxattr +232 i386 listxattr sys_listxattr __ia32_sys_listxattr +233 i386 llistxattr sys_llistxattr __ia32_sys_llistxattr +234 i386 flistxattr sys_flistxattr __ia32_sys_flistxattr +235 i386 removexattr sys_removexattr __ia32_sys_removexattr +236 i386 lremovexattr sys_lremovexattr __ia32_sys_lremovexattr +237 i386 fremovexattr sys_fremovexattr __ia32_sys_fremovexattr +238 i386 tkill sys_tkill __ia32_sys_tkill +239 i386 sendfile64 sys_sendfile64 __ia32_sys_sendfile64 240 i386 futex sys_futex __compat_sys_ia32_futex 241 i386 sched_setaffinity sys_sched_setaffinity __compat_sys_ia32_sched_setaffinity 242 i386 sched_getaffinity sys_sched_getaffinity __compat_sys_ia32_sched_getaffinity -243 i386 set_thread_area sys_set_thread_area __sys_ia32_set_thread_area -244 i386 get_thread_area sys_get_thread_area __sys_ia32_get_thread_area +243 i386 set_thread_area sys_set_thread_area __ia32_sys_set_thread_area +244 i386 get_thread_area sys_get_thread_area __ia32_sys_get_thread_area 245 i386 io_setup sys_io_setup __compat_sys_ia32_io_setup -246 i386 io_destroy sys_io_destroy __sys_ia32_io_destroy +246 i386 io_destroy sys_io_destroy __ia32_sys_io_destroy 247 i386 io_getevents sys_io_getevents __compat_sys_ia32_io_getevents 248 i386 io_submit sys_io_submit __compat_sys_ia32_io_submit -249 i386 io_cancel sys_io_cancel __sys_ia32_io_cancel +249 i386 io_cancel sys_io_cancel __ia32_sys_io_cancel 250 i386 fadvise64 sys_fadvise64 __compat_sys_ia32_x86_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) -252 i386 exit_group sys_exit_group __sys_ia32_exit_group +252 i386 exit_group sys_exit_group __ia32_sys_exit_group 253 i386 lookup_dcookie sys_lookup_dcookie __compat_sys_ia32_lookup_dcookie -254 i386 epoll_create sys_epoll_create __sys_ia32_epoll_create -255 i386 epoll_ctl sys_epoll_ctl __sys_ia32_epoll_ctl -256 i386 epoll_wait sys_epoll_wait __sys_ia32_epoll_wait -257 i386 remap_file_pages sys_remap_file_pages __sys_ia32_remap_file_pages -258 i386 set_tid_address sys_set_tid_address __sys_ia32_set_tid_address +254 i386 epoll_create sys_epoll_create __ia32_sys_epoll_create +255 i386 epoll_ctl sys_epoll_ctl __ia32_sys_epoll_ctl +256 i386 epoll_wait sys_epoll_wait __ia32_sys_epoll_wait +257 i386 remap_file_pages sys_remap_file_pages __ia32_sys_remap_file_pages +258 i386 set_tid_address sys_set_tid_address __ia32_sys_set_tid_address 259 i386 timer_create sys_timer_create __compat_sys_ia32_timer_create 260 i386 timer_settime sys_timer_settime __compat_sys_ia32_timer_settime 261 i386 timer_gettime sys_timer_gettime __compat_sys_ia32_timer_gettime -262 i386 timer_getoverrun sys_timer_getoverrun __sys_ia32_timer_getoverrun -263 i386 timer_delete sys_timer_delete __sys_ia32_timer_delete +262 i386 timer_getoverrun sys_timer_getoverrun __ia32_sys_timer_getoverrun +263 i386 timer_delete sys_timer_delete __ia32_sys_timer_delete 264 i386 clock_settime sys_clock_settime __compat_sys_ia32_clock_settime 265 i386 clock_gettime sys_clock_gettime __compat_sys_ia32_clock_gettime 266 i386 clock_getres sys_clock_getres __compat_sys_ia32_clock_getres 267 i386 clock_nanosleep sys_clock_nanosleep __compat_sys_ia32_clock_nanosleep 268 i386 statfs64 sys_statfs64 __compat_sys_ia32_statfs64 269 i386 fstatfs64 sys_fstatfs64 __compat_sys_ia32_fstatfs64 -270 i386 tgkill sys_tgkill __sys_ia32_tgkill +270 i386 tgkill sys_tgkill __ia32_sys_tgkill 271 i386 utimes sys_utimes __compat_sys_ia32_utimes 272 i386 fadvise64_64 sys_fadvise64_64 __compat_sys_ia32_x86_fadvise64_64 273 i386 vserver -274 i386 mbind sys_mbind __sys_ia32_mbind +274 i386 mbind sys_mbind __ia32_sys_mbind 275 i386 get_mempolicy sys_get_mempolicy __compat_sys_ia32_get_mempolicy -276 i386 set_mempolicy sys_set_mempolicy __sys_ia32_set_mempolicy +276 i386 set_mempolicy sys_set_mempolicy __ia32_sys_set_mempolicy 277 i386 mq_open sys_mq_open __compat_sys_ia32_mq_open -278 i386 mq_unlink sys_mq_unlink __sys_ia32_mq_unlink +278 i386 mq_unlink sys_mq_unlink __ia32_sys_mq_unlink 279 i386 mq_timedsend sys_mq_timedsend __compat_sys_ia32_mq_timedsend 280 i386 mq_timedreceive sys_mq_timedreceive __compat_sys_ia32_mq_timedreceive 281 i386 mq_notify sys_mq_notify __compat_sys_ia32_mq_notify @@ -297,102 +297,102 @@ 283 i386 kexec_load sys_kexec_load __compat_sys_ia32_kexec_load 284 i386 waitid sys_waitid __compat_sys_ia32_waitid # 285 sys_setaltroot -286 i386 add_key sys_add_key __sys_ia32_add_key -287 i386 request_key sys_request_key __sys_ia32_request_key +286 i386 add_key sys_add_key __ia32_sys_add_key +287 i386 request_key sys_request_key __ia32_sys_request_key 288 i386 keyctl sys_keyctl __compat_sys_ia32_keyctl -289 i386 ioprio_set sys_ioprio_set __sys_ia32_ioprio_set -290 i386 ioprio_get sys_ioprio_get __sys_ia32_ioprio_get +289 i386 ioprio_set sys_ioprio_set __ia32_sys_ioprio_set +290 i386 ioprio_get sys_ioprio_get __ia32_sys_ioprio_get 291 i386 inotify_init sys_inotify_init -292 i386 inotify_add_watch sys_inotify_add_watch __sys_ia32_inotify_add_watch -293 i386 inotify_rm_watch sys_inotify_rm_watch __sys_ia32_inotify_rm_watch -294 i386 migrate_pages sys_migrate_pages __sys_ia32_migrate_pages +292 i386 inotify_add_watch sys_inotify_add_watch __ia32_sys_inotify_add_watch +293 i386 inotify_rm_watch sys_inotify_rm_watch __ia32_sys_inotify_rm_watch +294 i386 migrate_pages sys_migrate_pages __ia32_sys_migrate_pages 295 i386 openat sys_openat __compat_sys_ia32_openat -296 i386 mkdirat sys_mkdirat __sys_ia32_mkdirat -297 i386 mknodat sys_mknodat __sys_ia32_mknodat -298 i386 fchownat sys_fchownat __sys_ia32_fchownat +296 i386 mkdirat sys_mkdirat __ia32_sys_mkdirat +297 i386 mknodat sys_mknodat __ia32_sys_mknodat +298 i386 fchownat sys_fchownat __ia32_sys_fchownat 299 i386 futimesat sys_futimesat __compat_sys_ia32_futimesat 300 i386 fstatat64 sys_fstatat64 __compat_sys_ia32_x86_fstatat -301 i386 unlinkat sys_unlinkat __sys_ia32_unlinkat -302 i386 renameat sys_renameat __sys_ia32_renameat -303 i386 linkat sys_linkat __sys_ia32_linkat -304 i386 symlinkat sys_symlinkat __sys_ia32_symlinkat -305 i386 readlinkat sys_readlinkat __sys_ia32_readlinkat -306 i386 fchmodat sys_fchmodat __sys_ia32_fchmodat -307 i386 faccessat sys_faccessat __sys_ia32_faccessat +301 i386 unlinkat sys_unlinkat __ia32_sys_unlinkat +302 i386 renameat sys_renameat __ia32_sys_renameat +303 i386 linkat sys_linkat __ia32_sys_linkat +304 i386 symlinkat sys_symlinkat __ia32_sys_symlinkat +305 i386 readlinkat sys_readlinkat __ia32_sys_readlinkat +306 i386 fchmodat sys_fchmodat __ia32_sys_fchmodat +307 i386 faccessat sys_faccessat __ia32_sys_faccessat 308 i386 pselect6 sys_pselect6 __compat_sys_ia32_pselect6 309 i386 ppoll sys_ppoll __compat_sys_ia32_ppoll -310 i386 unshare sys_unshare __sys_ia32_unshare +310 i386 unshare sys_unshare __ia32_sys_unshare 311 i386 set_robust_list sys_set_robust_list __compat_sys_ia32_set_robust_list 312 i386 get_robust_list sys_get_robust_list __compat_sys_ia32_get_robust_list -313 i386 splice sys_splice __sys_ia32_splice +313 i386 splice sys_splice __ia32_sys_splice 314 i386 sync_file_range sys_sync_file_range __compat_sys_ia32_x86_sync_file_range -315 i386 tee sys_tee __sys_ia32_tee +315 i386 tee sys_tee __ia32_sys_tee 316 i386 vmsplice sys_vmsplice __compat_sys_ia32_vmsplice 317 i386 move_pages sys_move_pages __compat_sys_ia32_move_pages -318 i386 getcpu sys_getcpu __sys_ia32_getcpu -319 i386 epoll_pwait sys_epoll_pwait __sys_ia32_epoll_pwait +318 i386 getcpu sys_getcpu __ia32_sys_getcpu +319 i386 epoll_pwait sys_epoll_pwait __ia32_sys_epoll_pwait 320 i386 utimensat sys_utimensat __compat_sys_ia32_utimensat 321 i386 signalfd sys_signalfd __compat_sys_ia32_signalfd -322 i386 timerfd_create sys_timerfd_create __sys_ia32_timerfd_create -323 i386 eventfd sys_eventfd __sys_ia32_eventfd +322 i386 timerfd_create sys_timerfd_create __ia32_sys_timerfd_create +323 i386 eventfd sys_eventfd __ia32_sys_eventfd 324 i386 fallocate sys_fallocate __compat_sys_ia32_x86_fallocate 325 i386 timerfd_settime sys_timerfd_settime __compat_sys_ia32_timerfd_settime 326 i386 timerfd_gettime sys_timerfd_gettime __compat_sys_ia32_timerfd_gettime 327 i386 signalfd4 sys_signalfd4 __compat_sys_ia32_signalfd4 -328 i386 eventfd2 sys_eventfd2 __sys_ia32_eventfd2 -329 i386 epoll_create1 sys_epoll_create1 __sys_ia32_epoll_create1 -330 i386 dup3 sys_dup3 __sys_ia32_dup3 -331 i386 pipe2 sys_pipe2 __sys_ia32_pipe2 -332 i386 inotify_init1 sys_inotify_init1 __sys_ia32_inotify_init1 +328 i386 eventfd2 sys_eventfd2 __ia32_sys_eventfd2 +329 i386 epoll_create1 sys_epoll_create1 __ia32_sys_epoll_create1 +330 i386 dup3 sys_dup3 __ia32_sys_dup3 +331 i386 pipe2 sys_pipe2 __ia32_sys_pipe2 +332 i386 inotify_init1 sys_inotify_init1 __ia32_sys_inotify_init1 333 i386 preadv sys_preadv __compat_sys_ia32_preadv 334 i386 pwritev sys_pwritev __compat_sys_ia32_pwritev 335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo __compat_sys_ia32_rt_tgsigqueueinfo -336 i386 perf_event_open sys_perf_event_open __sys_ia32_perf_event_open +336 i386 perf_event_open sys_perf_event_open __ia32_sys_perf_event_open 337 i386 recvmmsg sys_recvmmsg __compat_sys_ia32_recvmmsg -338 i386 fanotify_init sys_fanotify_init __sys_ia32_fanotify_init +338 i386 fanotify_init sys_fanotify_init __ia32_sys_fanotify_init 339 i386 fanotify_mark sys_fanotify_mark __compat_sys_ia32_fanotify_mark -340 i386 prlimit64 sys_prlimit64 __sys_ia32_prlimit64 -341 i386 name_to_handle_at sys_name_to_handle_at __sys_ia32_name_to_handle_at +340 i386 prlimit64 sys_prlimit64 __ia32_sys_prlimit64 +341 i386 name_to_handle_at sys_name_to_handle_at __ia32_sys_name_to_handle_at 342 i386 open_by_handle_at sys_open_by_handle_at __compat_sys_ia32_open_by_handle_at 343 i386 clock_adjtime sys_clock_adjtime __compat_sys_ia32_clock_adjtime -344 i386 syncfs sys_syncfs __sys_ia32_syncfs +344 i386 syncfs sys_syncfs __ia32_sys_syncfs 345 i386 sendmmsg sys_sendmmsg __compat_sys_ia32_sendmmsg -346 i386 setns sys_setns __sys_ia32_setns +346 i386 setns sys_setns __ia32_sys_setns 347 i386 process_vm_readv sys_process_vm_readv __compat_sys_ia32_process_vm_readv 348 i386 process_vm_writev sys_process_vm_writev __compat_sys_ia32_process_vm_writev -349 i386 kcmp sys_kcmp __sys_ia32_kcmp -350 i386 finit_module sys_finit_module __sys_ia32_finit_module -351 i386 sched_setattr sys_sched_setattr __sys_ia32_sched_setattr -352 i386 sched_getattr sys_sched_getattr __sys_ia32_sched_getattr -353 i386 renameat2 sys_renameat2 __sys_ia32_renameat2 -354 i386 seccomp sys_seccomp __sys_ia32_seccomp -355 i386 getrandom sys_getrandom __sys_ia32_getrandom -356 i386 memfd_create sys_memfd_create __sys_ia32_memfd_create -357 i386 bpf sys_bpf __sys_ia32_bpf +349 i386 kcmp sys_kcmp __ia32_sys_kcmp +350 i386 finit_module sys_finit_module __ia32_sys_finit_module +351 i386 sched_setattr sys_sched_setattr __ia32_sys_sched_setattr +352 i386 sched_getattr sys_sched_getattr __ia32_sys_sched_getattr +353 i386 renameat2 sys_renameat2 __ia32_sys_renameat2 +354 i386 seccomp sys_seccomp __ia32_sys_seccomp +355 i386 getrandom sys_getrandom __ia32_sys_getrandom +356 i386 memfd_create sys_memfd_create __ia32_sys_memfd_create +357 i386 bpf sys_bpf __ia32_sys_bpf 358 i386 execveat sys_execveat __compat_sys_ia32_execveat -359 i386 socket sys_socket __sys_ia32_socket -360 i386 socketpair sys_socketpair __sys_ia32_socketpair -361 i386 bind sys_bind __sys_ia32_bind -362 i386 connect sys_connect __sys_ia32_connect -363 i386 listen sys_listen __sys_ia32_listen -364 i386 accept4 sys_accept4 __sys_ia32_accept4 +359 i386 socket sys_socket __ia32_sys_socket +360 i386 socketpair sys_socketpair __ia32_sys_socketpair +361 i386 bind sys_bind __ia32_sys_bind +362 i386 connect sys_connect __ia32_sys_connect +363 i386 listen sys_listen __ia32_sys_listen +364 i386 accept4 sys_accept4 __ia32_sys_accept4 365 i386 getsockopt sys_getsockopt __compat_sys_ia32_getsockopt 366 i386 setsockopt sys_setsockopt __compat_sys_ia32_setsockopt -367 i386 getsockname sys_getsockname __sys_ia32_getsockname -368 i386 getpeername sys_getpeername __sys_ia32_getpeername -369 i386 sendto sys_sendto __sys_ia32_sendto +367 i386 getsockname sys_getsockname __ia32_sys_getsockname +368 i386 getpeername sys_getpeername __ia32_sys_getpeername +369 i386 sendto sys_sendto __ia32_sys_sendto 370 i386 sendmsg sys_sendmsg __compat_sys_ia32_sendmsg 371 i386 recvfrom sys_recvfrom __compat_sys_ia32_recvfrom 372 i386 recvmsg sys_recvmsg __compat_sys_ia32_recvmsg -373 i386 shutdown sys_shutdown __sys_ia32_shutdown -374 i386 userfaultfd sys_userfaultfd __sys_ia32_userfaultfd -375 i386 membarrier sys_membarrier __sys_ia32_membarrier -376 i386 mlock2 sys_mlock2 __sys_ia32_mlock2 -377 i386 copy_file_range sys_copy_file_range __sys_ia32_copy_file_range +373 i386 shutdown sys_shutdown __ia32_sys_shutdown +374 i386 userfaultfd sys_userfaultfd __ia32_sys_userfaultfd +375 i386 membarrier sys_membarrier __ia32_sys_membarrier +376 i386 mlock2 sys_mlock2 __ia32_sys_mlock2 +377 i386 copy_file_range sys_copy_file_range __ia32_sys_copy_file_range 378 i386 preadv2 sys_preadv2 __compat_sys_ia32_preadv2 379 i386 pwritev2 sys_pwritev2 __compat_sys_ia32_pwritev2 -380 i386 pkey_mprotect sys_pkey_mprotect __sys_ia32_pkey_mprotect -381 i386 pkey_alloc sys_pkey_alloc __sys_ia32_pkey_alloc -382 i386 pkey_free sys_pkey_free __sys_ia32_pkey_free -383 i386 statx sys_statx __sys_ia32_statx +380 i386 pkey_mprotect sys_pkey_mprotect __ia32_sys_pkey_mprotect +381 i386 pkey_alloc sys_pkey_alloc __ia32_sys_pkey_alloc +382 i386 pkey_free sys_pkey_free __ia32_sys_pkey_free +383 i386 statx sys_statx __ia32_sys_statx 384 i386 arch_prctl sys_arch_prctl __compat_sys_ia32_arch_prctl diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 49d7e4970110..798a3c2bff4f 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -22,7 +22,7 @@ #ifdef CONFIG_IA32_EMULATION /* * For IA32 emulation, we need to handle "compat" syscalls *and* create - * additional wrappers (aptly named __sys_ia32_sys_xyzzy) which decode the + * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the * ia32 regs in the proper order for shared or "common" syscalls. As some * syscalls may not be implemented, we need to expand COND_SYSCALL in * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this @@ -37,20 +37,20 @@ } \ #define SC_IA32_WRAPPERx(x, name, ...) \ - asmlinkage long __sys_ia32##name(const struct pt_regs *regs); \ - ALLOW_ERROR_INJECTION(__sys_ia32##name, ERRNO); \ - asmlinkage long __sys_ia32##name(const struct pt_regs *regs) \ + asmlinkage long __ia32_sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__ia32_sys##name, ERRNO); \ + asmlinkage long __ia32_sys##name(const struct pt_regs *regs) \ { \ - return SyS##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__)); \ + return __se_sys##name(SC_IA32_REGS_TO_ARGS(x,__VA_ARGS__));\ } #define COND_SYSCALL(name) \ cond_syscall(sys_##name); \ - cond_syscall(__sys_ia32_##name) + cond_syscall(__ia32_sys_##name) #define SYS_NI(name) \ SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers); \ - SYSCALL_ALIAS(__sys_ia32_##name, sys_ni_posix_timers) + SYSCALL_ALIAS(__ia32_sys_##name, sys_ni_posix_timers) #else /* CONFIG_IA32_EMULATION */ #define COMPAT_SC_IA32_STUBx(x, name, ...) @@ -115,9 +115,10 @@ * Instead of the generic __SYSCALL_DEFINEx() definition, this macro takes * struct pt_regs *regs as the only argument of the syscall stub named * sys_*(). It decodes just the registers it needs and passes them on to - * the SyS_*() wrapper and then to the SYSC_*() function doing the actual job. - * These wrappers and functions are inlined, meaning that the assembly looks - * as follows (slightly re-ordered): + * the __se_sys_*() wrapper performing sign extension and then to the + * __do_sys_*() function doing the actual job. These wrappers and functions + * are inlined (at least in very most cases), meaning that the assembly looks + * as follows (slightly re-ordered for better readability): * * : <-- syscall with 4 parameters * callq <__fentry__> @@ -140,7 +141,7 @@ * the call chain. * * If IA32_EMULATION is enabled, this macro generates an additional wrapper - * named __sys_ia32_*() which decodes the struct pt_regs *regs according + * named __ia32_sys_*() which decodes the struct pt_regs *regs according * to the i386 calling convention (bx, cx, dx, si, di, bp). * * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for @@ -151,21 +152,21 @@ #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(const struct pt_regs *regs); \ ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ - static long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long sys##name(const struct pt_regs *regs) \ { \ - return SyS##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ + return __se_sys##name(SC_X86_64_REGS_TO_ARGS(x,__VA_ARGS__));\ } \ SC_IA32_WRAPPERx(x, name, __VA_ARGS__) \ - static long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ - long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\ __MAP(x,__SC_TEST,__VA_ARGS__); \ __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ return ret; \ } \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) /* * For VSYSCALLS, we need to declare these three syscalls with the new diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index d7168b3a4b4c..70fcda1a9049 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -223,21 +223,26 @@ static inline int is_syscall_trace_event(struct trace_event_call *tp_event) #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__) +/* + * The asmlinkage stub is aliased to a function named __se_sys_*() which + * sign-extends 32-bit ints to longs whenever needed. The actual work is + * done within __do_sys_*(). + */ #ifndef __SYSCALL_DEFINEx #define __SYSCALL_DEFINEx(x, name, ...) \ asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ - __attribute__((alias(__stringify(SyS##name)))); \ + __attribute__((alias(__stringify(__se_sys##name)))); \ ALLOW_ERROR_INJECTION(sys##name, ERRNO); \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ - asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ - asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ - long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\ __MAP(x,__SC_TEST,__VA_ARGS__); \ __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ return ret; \ } \ - static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* __SYSCALL_DEFINEx */ /* diff --git a/scripts/bloat-o-meter b/scripts/bloat-o-meter index d84a5674e95e..ce129e61cc65 100755 --- a/scripts/bloat-o-meter +++ b/scripts/bloat-o-meter @@ -30,7 +30,7 @@ def getsizes(file, format): if type in format: # strip generated symbols if name.startswith("__mod_"): continue - if name.startswith("SyS_"): continue + if name.startswith("__se_sys"): continue if name.startswith("compat_SyS_"): continue if name == "linux_banner": continue # statics and some other optimizations adds random .NUMBER -- cgit v1.2.3