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 +- 1 file changed, 1 insertion(+), 1 deletion(-) (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, -- 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 --- include/linux/syscalls.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/syscalls.h') 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, -- 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 --- include/linux/syscalls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 +++++++++++ 1 file changed, 11 insertions(+) (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 -- 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 --- 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 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 -- 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 --- 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 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 -- 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 --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- 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 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 -- 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 --- include/linux/syscalls.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- 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 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 -- 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 --- include/linux/syscalls.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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 + 1 file changed, 1 insertion(+) (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 -- 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 --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/syscalls.h') 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 --- 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 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 --- include/linux/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/syscalls.h') 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 --- include/linux/syscalls.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/syscalls.h') 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 -- 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 --- include/linux/syscalls.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/syscalls.h') 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 -- 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/syscalls.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/syscalls.h') 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/syscalls.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/syscalls.h') 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 +++++++++++++++++++++++ 1 file changed, 23 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. -- 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 --- include/linux/syscalls.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/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 --- include/linux/syscalls.h | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) (limited to 'include/linux/syscalls.h') 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 */ /* -- cgit v1.2.3