2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* syscalls.h - Linux syscall interfaces (non-arch-specific)
|
|
|
|
*
|
|
|
|
* Copyright (c) 2004 Randy Dunlap
|
|
|
|
* Copyright (c) 2004 Open Source Development Labs
|
|
|
|
*
|
|
|
|
* This file is released under the GPLv2.
|
|
|
|
* See the file COPYING for more details.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _LINUX_SYSCALLS_H
|
|
|
|
#define _LINUX_SYSCALLS_H
|
|
|
|
|
|
|
|
struct epoll_event;
|
|
|
|
struct iattr;
|
|
|
|
struct inode;
|
|
|
|
struct iocb;
|
|
|
|
struct io_event;
|
|
|
|
struct iovec;
|
|
|
|
struct itimerspec;
|
|
|
|
struct itimerval;
|
|
|
|
struct kexec_segment;
|
|
|
|
struct linux_dirent;
|
|
|
|
struct linux_dirent64;
|
|
|
|
struct list_head;
|
2010-03-11 07:21:15 +08:00
|
|
|
struct mmap_arg_struct;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct msgbuf;
|
separate kernel- and userland-side msghdr
Kernel-side struct msghdr is (currently) using the same layout as
userland one, but it's not a one-to-one copy - even without considering
32bit compat issues, we have msg_iov, msg_name and msg_control copied
to kernel[1]. It's fairly localized, so we get away with a few functions
where that knowledge is needed (and we could shrink that set even
more). Pretty much everything deals with the kernel-side variant and
the few places that want userland one just use a bunch of force-casts
to paper over the differences.
The thing is, kernel-side definition of struct msghdr is *not* exposed
in include/uapi - libc doesn't see it, etc. So we can add struct user_msghdr,
with proper annotations and let the few places that ever deal with those
beasts use it for userland pointers. Saner typechecking aside, that will
allow to change the layout of kernel-side msghdr - e.g. replace
msg_iov/msg_iovlen there with struct iov_iter, getting rid of the need
to modify the iovec as we copy data to/from it, etc.
We could introduce kernel_msghdr instead, but that would create much more
noise - the absolute majority of the instances would need to have the
type switched to kernel_msghdr and definition of struct msghdr in
include/linux/socket.h is not going to be seen by userland anyway.
This commit just introduces user_msghdr and switches the few places that
are dealing with userland-side msghdr to it.
[1] actually, it's even trickier than that - we copy msg_control for
sendmsg, but keep the userland address on recvmsg.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2014-04-07 02:03:05 +08:00
|
|
|
struct user_msghdr;
|
2009-10-13 14:40:10 +08:00
|
|
|
struct mmsghdr;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct msqid_ds;
|
|
|
|
struct new_utsname;
|
|
|
|
struct nfsctl_arg;
|
|
|
|
struct __old_kernel_stat;
|
2010-03-11 07:21:21 +08:00
|
|
|
struct oldold_utsname;
|
|
|
|
struct old_utsname;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct pollfd;
|
|
|
|
struct rlimit;
|
2010-05-05 00:03:50 +08:00
|
|
|
struct rlimit64;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct rusage;
|
|
|
|
struct sched_param;
|
sched: Add new scheduler syscalls to support an extended scheduling parameters ABI
Add the syscalls needed for supporting scheduling algorithms
with extended scheduling parameters (e.g., SCHED_DEADLINE).
In general, it makes possible to specify a periodic/sporadic task,
that executes for a given amount of runtime at each instance, and is
scheduled according to the urgency of their own timing constraints,
i.e.:
- a (maximum/typical) instance execution time,
- a minimum interval between consecutive instances,
- a time constraint by which each instance must be completed.
Thus, both the data structure that holds the scheduling parameters of
the tasks and the system calls dealing with it must be extended.
Unfortunately, modifying the existing struct sched_param would break
the ABI and result in potentially serious compatibility issues with
legacy binaries.
For these reasons, this patch:
- defines the new struct sched_attr, containing all the fields
that are necessary for specifying a task in the computational
model described above;
- defines and implements the new scheduling related syscalls that
manipulate it, i.e., sched_setattr() and sched_getattr().
Syscalls are introduced for x86 (32 and 64 bits) and ARM only, as a
proof of concept and for developing and testing purposes. Making them
available on other architectures is straightforward.
Since no "user" for these new parameters is introduced in this patch,
the implementation of the new system calls is just identical to their
already existing counterpart. Future patches that implement scheduling
policies able to exploit the new data structure must also take care of
modifying the sched_*attr() calls accordingly with their own purposes.
Signed-off-by: Dario Faggioli <raistlin@linux.it>
[ Rewrote to use sched_attr. ]
Signed-off-by: Juri Lelli <juri.lelli@gmail.com>
[ Removed sched_setscheduler2() for now. ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1383831828-15501-3-git-send-email-juri.lelli@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-07 21:43:36 +08:00
|
|
|
struct sched_attr;
|
2010-03-11 07:21:13 +08:00
|
|
|
struct sel_arg_struct;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct semaphore;
|
|
|
|
struct sembuf;
|
|
|
|
struct shmid_ds;
|
|
|
|
struct sockaddr;
|
|
|
|
struct stat;
|
|
|
|
struct stat64;
|
|
|
|
struct statfs;
|
|
|
|
struct statfs64;
|
statx: Add a system call to make enhanced file info available
Add a system call to make extended file information available, including
file creation and some attribute flags where available through the
underlying filesystem.
The getattr inode operation is altered to take two additional arguments: a
u32 request_mask and an unsigned int flags that indicate the
synchronisation mode. This change is propagated to the vfs_getattr*()
function.
Functions like vfs_stat() are now inline wrappers around new functions
vfs_statx() and vfs_statx_fd() to reduce stack usage.
========
OVERVIEW
========
The idea was initially proposed as a set of xattrs that could be retrieved
with getxattr(), but the general preference proved to be for a new syscall
with an extended stat structure.
A number of requests were gathered for features to be included. The
following have been included:
(1) Make the fields a consistent size on all arches and make them large.
(2) Spare space, request flags and information flags are provided for
future expansion.
(3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an
__s64).
(4) Creation time: The SMB protocol carries the creation time, which could
be exported by Samba, which will in turn help CIFS make use of
FS-Cache as that can be used for coherency data (stx_btime).
This is also specified in NFSv4 as a recommended attribute and could
be exported by NFSD [Steve French].
(5) Lightweight stat: Ask for just those details of interest, and allow a
netfs (such as NFS) to approximate anything not of interest, possibly
without going to the server [Trond Myklebust, Ulrich Drepper, Andreas
Dilger] (AT_STATX_DONT_SYNC).
(6) Heavyweight stat: Force a netfs to go to the server, even if it thinks
its cached attributes are up to date [Trond Myklebust]
(AT_STATX_FORCE_SYNC).
And the following have been left out for future extension:
(7) Data version number: Could be used by userspace NFS servers [Aneesh
Kumar].
Can also be used to modify fill_post_wcc() in NFSD which retrieves
i_version directly, but has just called vfs_getattr(). It could get
it from the kstat struct if it used vfs_xgetattr() instead.
(There's disagreement on the exact semantics of a single field, since
not all filesystems do this the same way).
(8) BSD stat compatibility: Including more fields from the BSD stat such
as creation time (st_btime) and inode generation number (st_gen)
[Jeremy Allison, Bernd Schubert].
(9) Inode generation number: Useful for FUSE and userspace NFS servers
[Bernd Schubert].
(This was asked for but later deemed unnecessary with the
open-by-handle capability available and caused disagreement as to
whether it's a security hole or not).
(10) Extra coherency data may be useful in making backups [Andreas Dilger].
(No particular data were offered, but things like last backup
timestamp, the data version number and the DOS archive bit would come
into this category).
(11) Allow the filesystem to indicate what it can/cannot provide: A
filesystem can now say it doesn't support a standard stat feature if
that isn't available, so if, for instance, inode numbers or UIDs don't
exist or are fabricated locally...
(This requires a separate system call - I have an fsinfo() call idea
for this).
(12) Store a 16-byte volume ID in the superblock that can be returned in
struct xstat [Steve French].
(Deferred to fsinfo).
(13) Include granularity fields in the time data to indicate the
granularity of each of the times (NFSv4 time_delta) [Steve French].
(Deferred to fsinfo).
(14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags.
Note that the Linux IOC flags are a mess and filesystems such as Ext4
define flags that aren't in linux/fs.h, so translation in the kernel
may be a necessity (or, possibly, we provide the filesystem type too).
(Some attributes are made available in stx_attributes, but the general
feeling was that the IOC flags were to ext[234]-specific and shouldn't
be exposed through statx this way).
(15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer,
Michael Kerrisk].
(Deferred, probably to fsinfo. Finding out if there's an ACL or
seclabal might require extra filesystem operations).
(16) Femtosecond-resolution timestamps [Dave Chinner].
(A __reserved field has been left in the statx_timestamp struct for
this - if there proves to be a need).
(17) A set multiple attributes syscall to go with this.
===============
NEW SYSTEM CALL
===============
The new system call is:
int ret = statx(int dfd,
const char *filename,
unsigned int flags,
unsigned int mask,
struct statx *buffer);
The dfd, filename and flags parameters indicate the file to query, in a
similar way to fstatat(). There is no equivalent of lstat() as that can be
emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is
also no equivalent of fstat() as that can be emulated by passing a NULL
filename to statx() with the fd of interest in dfd.
Whether or not statx() synchronises the attributes with the backing store
can be controlled by OR'ing a value into the flags argument (this typically
only affects network filesystems):
(1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this
respect.
(2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise
its attributes with the server - which might require data writeback to
occur to get the timestamps correct.
(3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a
network filesystem. The resulting values should be considered
approximate.
mask is a bitmask indicating the fields in struct statx that are of
interest to the caller. The user should set this to STATX_BASIC_STATS to
get the basic set returned by stat(). It should be noted that asking for
more information may entail extra I/O operations.
buffer points to the destination for the data. This must be 256 bytes in
size.
======================
MAIN ATTRIBUTES RECORD
======================
The following structures are defined in which to return the main attribute
set:
struct statx_timestamp {
__s64 tv_sec;
__s32 tv_nsec;
__s32 __reserved;
};
struct statx {
__u32 stx_mask;
__u32 stx_blksize;
__u64 stx_attributes;
__u32 stx_nlink;
__u32 stx_uid;
__u32 stx_gid;
__u16 stx_mode;
__u16 __spare0[1];
__u64 stx_ino;
__u64 stx_size;
__u64 stx_blocks;
__u64 __spare1[1];
struct statx_timestamp stx_atime;
struct statx_timestamp stx_btime;
struct statx_timestamp stx_ctime;
struct statx_timestamp stx_mtime;
__u32 stx_rdev_major;
__u32 stx_rdev_minor;
__u32 stx_dev_major;
__u32 stx_dev_minor;
__u64 __spare2[14];
};
The defined bits in request_mask and stx_mask are:
STATX_TYPE Want/got stx_mode & S_IFMT
STATX_MODE Want/got stx_mode & ~S_IFMT
STATX_NLINK Want/got stx_nlink
STATX_UID Want/got stx_uid
STATX_GID Want/got stx_gid
STATX_ATIME Want/got stx_atime{,_ns}
STATX_MTIME Want/got stx_mtime{,_ns}
STATX_CTIME Want/got stx_ctime{,_ns}
STATX_INO Want/got stx_ino
STATX_SIZE Want/got stx_size
STATX_BLOCKS Want/got stx_blocks
STATX_BASIC_STATS [The stuff in the normal stat struct]
STATX_BTIME Want/got stx_btime{,_ns}
STATX_ALL [All currently available stuff]
stx_btime is the file creation time, stx_mask is a bitmask indicating the
data provided and __spares*[] are where as-yet undefined fields can be
placed.
Time fields are structures with separate seconds and nanoseconds fields
plus a reserved field in case we want to add even finer resolution. Note
that times will be negative if before 1970; in such a case, the nanosecond
fields will also be negative if not zero.
The bits defined in the stx_attributes field convey information about a
file, how it is accessed, where it is and what it does. The following
attributes map to FS_*_FL flags and are the same numerical value:
STATX_ATTR_COMPRESSED File is compressed by the fs
STATX_ATTR_IMMUTABLE File is marked immutable
STATX_ATTR_APPEND File is append-only
STATX_ATTR_NODUMP File is not to be dumped
STATX_ATTR_ENCRYPTED File requires key to decrypt in fs
Within the kernel, the supported flags are listed by:
KSTAT_ATTR_FS_IOC_FLAGS
[Are any other IOC flags of sufficient general interest to be exposed
through this interface?]
New flags include:
STATX_ATTR_AUTOMOUNT Object is an automount trigger
These are for the use of GUI tools that might want to mark files specially,
depending on what they are.
Fields in struct statx come in a number of classes:
(0) stx_dev_*, stx_blksize.
These are local system information and are always available.
(1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino,
stx_size, stx_blocks.
These will be returned whether the caller asks for them or not. The
corresponding bits in stx_mask will be set to indicate whether they
actually have valid values.
If the caller didn't ask for them, then they may be approximated. For
example, NFS won't waste any time updating them from the server,
unless as a byproduct of updating something requested.
If the values don't actually exist for the underlying object (such as
UID or GID on a DOS file), then the bit won't be set in the stx_mask,
even if the caller asked for the value. In such a case, the returned
value will be a fabrication.
Note that there are instances where the type might not be valid, for
instance Windows reparse points.
(2) stx_rdev_*.
This will be set only if stx_mode indicates we're looking at a
blockdev or a chardev, otherwise will be 0.
(3) stx_btime.
Similar to (1), except this will be set to 0 if it doesn't exist.
=======
TESTING
=======
The following test program can be used to test the statx system call:
samples/statx/test-statx.c
Just compile and run, passing it paths to the files you want to examine.
The file is built automatically if CONFIG_SAMPLES is enabled.
Here's some example output. Firstly, an NFS directory that crosses to
another FSID. Note that the AUTOMOUNT attribute is set because transiting
this directory will cause d_automount to be invoked by the VFS.
[root@andromeda ~]# /tmp/test-statx -A /warthog/data
statx(/warthog/data) = 0
results=7ff
Size: 4096 Blocks: 8 IO Block: 1048576 directory
Device: 00:26 Inode: 1703937 Links: 125
Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041
Access: 2016-11-24 09:02:12.219699527+0000
Modify: 2016-11-17 10:44:36.225653653+0000
Change: 2016-11-17 10:44:36.225653653+0000
Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------)
Secondly, the result of automounting on that directory.
[root@andromeda ~]# /tmp/test-statx /warthog/data
statx(/warthog/data) = 0
results=7ff
Size: 4096 Blocks: 8 IO Block: 1048576 directory
Device: 00:27 Inode: 2 Links: 125
Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041
Access: 2016-11-24 09:02:12.219699527+0000
Modify: 2016-11-17 10:44:36.225653653+0000
Change: 2016-11-17 10:44:36.225653653+0000
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
|
|
|
struct statx;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct __sysctl_args;
|
|
|
|
struct sysinfo;
|
|
|
|
struct timespec;
|
|
|
|
struct timeval;
|
|
|
|
struct timex;
|
|
|
|
struct timezone;
|
|
|
|
struct tms;
|
|
|
|
struct utimbuf;
|
|
|
|
struct mq_attr;
|
2006-02-01 19:04:33 +08:00
|
|
|
struct compat_stat;
|
|
|
|
struct compat_timeval;
|
2006-05-23 22:46:40 +08:00
|
|
|
struct robust_list_head;
|
2006-09-26 16:52:28 +08:00
|
|
|
struct getcpu_cache;
|
2009-01-14 21:13:55 +08:00
|
|
|
struct old_linux_dirent;
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
|
|
|
struct perf_event_attr;
|
2011-01-29 21:13:26 +08:00
|
|
|
struct file_handle;
|
2012-12-15 03:09:47 +08:00
|
|
|
struct sigaltstack;
|
2014-09-26 15:16:58 +08:00
|
|
|
union bpf_attr;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/aio_abi.h>
|
|
|
|
#include <linux/capability.h>
|
2012-11-26 11:24:19 +08:00
|
|
|
#include <linux/signal.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/list.h>
|
2011-11-24 09:12:59 +08:00
|
|
|
#include <linux/bug.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/sem.h>
|
|
|
|
#include <asm/siginfo.h>
|
2009-08-11 04:52:47 +08:00
|
|
|
#include <linux/unistd.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/quota.h>
|
|
|
|
#include <linux/key.h>
|
2009-04-09 02:40:59 +08:00
|
|
|
#include <trace/syscall.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-04-05 17:53:01 +08:00
|
|
|
#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 <asm/syscall_wrapper.h>
|
|
|
|
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
|
|
|
|
|
2013-01-22 04:03:44 +08:00
|
|
|
/*
|
|
|
|
* __MAP - apply a macro to syscall arguments
|
|
|
|
* __MAP(n, m, t1, a1, t2, a2, ..., tn, an) will expand to
|
|
|
|
* m(t1, a1), m(t2, a2), ..., m(tn, an)
|
|
|
|
* The first argument must be equal to the amount of type/name
|
|
|
|
* pairs given. Note that this list of pairs (i.e. the arguments
|
|
|
|
* of __MAP starting at the third one) is in the same format as
|
|
|
|
* for SYSCALL_DEFINE<n>/COMPAT_SYSCALL_DEFINE<n>
|
|
|
|
*/
|
2013-03-06 04:36:40 +08:00
|
|
|
#define __MAP0(m,...)
|
2013-01-22 04:03:44 +08:00
|
|
|
#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__)
|
|
|
|
#define __MAP5(m,t,a,...) m(t,a), __MAP4(m,__VA_ARGS__)
|
|
|
|
#define __MAP6(m,t,a,...) m(t,a), __MAP5(m,__VA_ARGS__)
|
|
|
|
#define __MAP(n,...) __MAP##n(__VA_ARGS__)
|
|
|
|
|
|
|
|
#define __SC_DECL(t, a) t a
|
2017-07-08 23:40:39 +08:00
|
|
|
#define __TYPE_AS(t, v) __same_type((__force t)0, v)
|
|
|
|
#define __TYPE_IS_L(t) (__TYPE_AS(t, 0L))
|
|
|
|
#define __TYPE_IS_UL(t) (__TYPE_AS(t, 0UL))
|
|
|
|
#define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL))
|
2013-01-22 04:16:58 +08:00
|
|
|
#define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a
|
2017-07-08 23:40:39 +08:00
|
|
|
#define __SC_CAST(t, a) (__force t) a
|
2013-01-22 04:25:54 +08:00
|
|
|
#define __SC_ARGS(t, a) a
|
2013-01-22 04:16:58 +08:00
|
|
|
#define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long))
|
2009-01-14 21:13:59 +08:00
|
|
|
|
2009-03-13 22:42:11 +08:00
|
|
|
#ifdef CONFIG_FTRACE_SYSCALLS
|
2013-01-22 04:03:44 +08:00
|
|
|
#define __SC_STR_ADECL(t, a) #a
|
|
|
|
#define __SC_STR_TDECL(t, a) #t
|
2009-03-13 22:42:11 +08:00
|
|
|
|
2015-05-05 23:45:27 +08:00
|
|
|
extern struct trace_event_class event_class_syscall_enter;
|
|
|
|
extern struct trace_event_class event_class_syscall_exit;
|
2010-04-23 22:00:22 +08:00
|
|
|
extern struct trace_event_functions enter_syscall_print_funcs;
|
|
|
|
extern struct trace_event_functions exit_syscall_print_funcs;
|
2010-04-20 22:47:33 +08:00
|
|
|
|
2009-08-11 04:52:47 +08:00
|
|
|
#define SYSCALL_TRACE_ENTER_EVENT(sname) \
|
tracing: Replace syscall_meta_data struct array with pointer array
Currently the syscall_meta structures for the syscall tracepoints are
placed in the __syscall_metadata section, and at link time, the linker
makes one large array of all these syscall metadata structures. On boot
up, this array is read (much like the initcall sections) and the syscall
data is processed.
The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.
A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).
Instead of packing the structures into an array, the structures' addresses
are now put into the __syscall_metadata section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).
By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.
The __syscall_metadata section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: David Miller <davem@davemloft.net>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-03 06:06:09 +08:00
|
|
|
static struct syscall_metadata __syscall_meta_##sname; \
|
2015-05-05 23:45:27 +08:00
|
|
|
static struct trace_event_call __used \
|
2009-08-11 04:52:47 +08:00
|
|
|
event_enter_##sname = { \
|
2010-04-22 00:27:06 +08:00
|
|
|
.class = &event_class_syscall_enter, \
|
2014-04-10 05:06:08 +08:00
|
|
|
{ \
|
|
|
|
.name = "sys_enter"#sname, \
|
|
|
|
}, \
|
2010-04-23 22:00:22 +08:00
|
|
|
.event.funcs = &enter_syscall_print_funcs, \
|
2009-12-01 16:23:30 +08:00
|
|
|
.data = (void *)&__syscall_meta_##sname,\
|
2013-10-24 21:34:19 +08:00
|
|
|
.flags = TRACE_EVENT_FL_CAP_ANY, \
|
2010-11-18 09:11:42 +08:00
|
|
|
}; \
|
2015-05-05 23:45:27 +08:00
|
|
|
static struct trace_event_call __used \
|
tracing: Replace trace_event struct array with pointer array
Currently the trace_event structures are placed in the _ftrace_events
section, and at link time, the linker makes one large array of all
the trace_event structures. On boot up, this array is read (much like
the initcall sections) and the events are processed.
The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.
A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).
Instead of packing the structures into an array, the structures' addresses
are now put into the _ftrace_event section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).
By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.
The _ftrace_event section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: David Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
|
|
|
__attribute__((section("_ftrace_events"))) \
|
2011-01-26 16:49:00 +08:00
|
|
|
*__event_enter_##sname = &event_enter_##sname;
|
2009-08-11 04:52:47 +08:00
|
|
|
|
|
|
|
#define SYSCALL_TRACE_EXIT_EVENT(sname) \
|
tracing: Replace syscall_meta_data struct array with pointer array
Currently the syscall_meta structures for the syscall tracepoints are
placed in the __syscall_metadata section, and at link time, the linker
makes one large array of all these syscall metadata structures. On boot
up, this array is read (much like the initcall sections) and the syscall
data is processed.
The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.
A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).
Instead of packing the structures into an array, the structures' addresses
are now put into the __syscall_metadata section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).
By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.
The __syscall_metadata section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: David Miller <davem@davemloft.net>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-03 06:06:09 +08:00
|
|
|
static struct syscall_metadata __syscall_meta_##sname; \
|
2015-05-05 23:45:27 +08:00
|
|
|
static struct trace_event_call __used \
|
2009-08-11 04:52:47 +08:00
|
|
|
event_exit_##sname = { \
|
2010-04-22 00:27:06 +08:00
|
|
|
.class = &event_class_syscall_exit, \
|
2014-04-10 05:06:08 +08:00
|
|
|
{ \
|
|
|
|
.name = "sys_exit"#sname, \
|
|
|
|
}, \
|
2010-04-23 22:00:22 +08:00
|
|
|
.event.funcs = &exit_syscall_print_funcs, \
|
2009-12-01 16:23:30 +08:00
|
|
|
.data = (void *)&__syscall_meta_##sname,\
|
2013-10-24 21:34:19 +08:00
|
|
|
.flags = TRACE_EVENT_FL_CAP_ANY, \
|
2010-11-18 09:11:42 +08:00
|
|
|
}; \
|
2015-05-05 23:45:27 +08:00
|
|
|
static struct trace_event_call __used \
|
tracing: Replace trace_event struct array with pointer array
Currently the trace_event structures are placed in the _ftrace_events
section, and at link time, the linker makes one large array of all
the trace_event structures. On boot up, this array is read (much like
the initcall sections) and the events are processed.
The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.
A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).
Instead of packing the structures into an array, the structures' addresses
are now put into the _ftrace_event section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).
By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.
The _ftrace_event section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: David Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-01-27 22:15:30 +08:00
|
|
|
__attribute__((section("_ftrace_events"))) \
|
2011-01-26 16:49:00 +08:00
|
|
|
*__event_exit_##sname = &event_exit_##sname;
|
2009-08-11 04:52:47 +08:00
|
|
|
|
2013-03-06 04:36:40 +08:00
|
|
|
#define SYSCALL_METADATA(sname, nb, ...) \
|
|
|
|
static const char *types_##sname[] = { \
|
|
|
|
__MAP(nb,__SC_STR_TDECL,__VA_ARGS__) \
|
|
|
|
}; \
|
|
|
|
static const char *args_##sname[] = { \
|
|
|
|
__MAP(nb,__SC_STR_ADECL,__VA_ARGS__) \
|
|
|
|
}; \
|
2009-08-19 15:54:51 +08:00
|
|
|
SYSCALL_TRACE_ENTER_EVENT(sname); \
|
|
|
|
SYSCALL_TRACE_EXIT_EVENT(sname); \
|
2010-04-22 22:35:55 +08:00
|
|
|
static struct syscall_metadata __used \
|
2009-03-13 22:42:11 +08:00
|
|
|
__syscall_meta_##sname = { \
|
|
|
|
.name = "sys"#sname, \
|
2011-02-03 11:27:20 +08:00
|
|
|
.syscall_nr = -1, /* Filled in at boot */ \
|
2009-03-13 22:42:11 +08:00
|
|
|
.nb_args = nb, \
|
2013-03-06 04:36:40 +08:00
|
|
|
.types = nb ? types_##sname : NULL, \
|
|
|
|
.args = nb ? args_##sname : NULL, \
|
2009-08-19 15:54:51 +08:00
|
|
|
.enter_event = &event_enter_##sname, \
|
|
|
|
.exit_event = &event_exit_##sname, \
|
2010-04-22 22:35:55 +08:00
|
|
|
.enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
|
tracing: Replace syscall_meta_data struct array with pointer array
Currently the syscall_meta structures for the syscall tracepoints are
placed in the __syscall_metadata section, and at link time, the linker
makes one large array of all these syscall metadata structures. On boot
up, this array is read (much like the initcall sections) and the syscall
data is processed.
The problem is that there is no guarantee that gcc will place complex
structures nicely together in an array format. Two structures in the
same file may be placed awkwardly, because gcc has no clue that they
are suppose to be in an array.
A hack was used previous to force the alignment to 4, to pack the
structures together. But this caused alignment issues with other
architectures (sparc).
Instead of packing the structures into an array, the structures' addresses
are now put into the __syscall_metadata section. As pointers are always the
natural alignment, gcc should always pack them tightly together
(otherwise initcall, extable, etc would also fail).
By having the pointers to the structures in the section, we can still
iterate the trace_events without causing unnecessary alignment problems
with other architectures, or depending on the current behaviour of
gcc that will likely change in the future just to tick us kernel developers
off a little more.
The __syscall_metadata section is also moved into the .init.data section
as it is now only needed at boot up.
Suggested-by: David Miller <davem@davemloft.net>
Acked-by: David S. Miller <davem@davemloft.net>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-03 06:06:09 +08:00
|
|
|
}; \
|
|
|
|
static struct syscall_metadata __used \
|
|
|
|
__attribute__((section("__syscalls_metadata"))) \
|
|
|
|
*__p_syscall_meta_##sname = &__syscall_meta_##sname;
|
2017-08-05 07:00:09 +08:00
|
|
|
|
|
|
|
static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
|
|
|
|
{
|
|
|
|
return tp_event->class == &event_class_syscall_enter ||
|
|
|
|
tp_event->class == &event_class_syscall_exit;
|
|
|
|
}
|
|
|
|
|
2013-03-06 04:36:40 +08:00
|
|
|
#else
|
|
|
|
#define SYSCALL_METADATA(sname, nb, ...)
|
2017-08-05 07:00:09 +08:00
|
|
|
|
|
|
|
static inline int is_syscall_trace_event(struct trace_event_call *tp_event)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2013-03-06 04:36:40 +08:00
|
|
|
#endif
|
2009-03-13 22:42:11 +08:00
|
|
|
|
2018-04-05 17:53:01 +08:00
|
|
|
#ifndef SYSCALL_DEFINE0
|
2009-03-13 22:42:11 +08:00
|
|
|
#define SYSCALL_DEFINE0(sname) \
|
2013-03-06 04:36:40 +08:00
|
|
|
SYSCALL_METADATA(_##sname, 0); \
|
2018-03-22 09:59:08 +08:00
|
|
|
asmlinkage long sys_##sname(void); \
|
|
|
|
ALLOW_ERROR_INJECTION(sys_##sname, ERRNO); \
|
2009-03-13 22:42:11 +08:00
|
|
|
asmlinkage long sys_##sname(void)
|
2018-04-05 17:53:01 +08:00
|
|
|
#endif /* SYSCALL_DEFINE0 */
|
2009-03-13 22:42:11 +08:00
|
|
|
|
2009-02-12 05:04:38 +08:00
|
|
|
#define SYSCALL_DEFINE1(name, ...) SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
|
|
|
|
#define SYSCALL_DEFINE2(name, ...) SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
|
|
|
|
#define SYSCALL_DEFINE3(name, ...) SYSCALL_DEFINEx(3, _##name, __VA_ARGS__)
|
|
|
|
#define SYSCALL_DEFINE4(name, ...) SYSCALL_DEFINEx(4, _##name, __VA_ARGS__)
|
|
|
|
#define SYSCALL_DEFINE5(name, ...) SYSCALL_DEFINEx(5, _##name, __VA_ARGS__)
|
|
|
|
#define SYSCALL_DEFINE6(name, ...) SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)
|
2009-01-14 21:13:59 +08:00
|
|
|
|
2017-09-08 09:36:15 +08:00
|
|
|
#define SYSCALL_DEFINE_MAXARGS 6
|
|
|
|
|
2009-03-13 22:42:11 +08:00
|
|
|
#define SYSCALL_DEFINEx(x, sname, ...) \
|
2013-03-06 04:36:40 +08:00
|
|
|
SYSCALL_METADATA(sname, x, __VA_ARGS__) \
|
2009-03-13 22:42:11 +08:00
|
|
|
__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
|
|
|
|
|
2013-01-22 04:25:54 +08:00
|
|
|
#define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
|
2018-04-05 17:53:01 +08:00
|
|
|
|
|
|
|
#ifndef __SYSCALL_DEFINEx
|
2009-03-13 22:42:11 +08:00
|
|
|
#define __SYSCALL_DEFINEx(x, name, ...) \
|
2013-11-13 07:08:36 +08:00
|
|
|
asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
|
|
|
|
__attribute__((alias(__stringify(SyS##name)))); \
|
2018-03-22 09:59:08 +08:00
|
|
|
ALLOW_ERROR_INJECTION(sys##name, ERRNO); \
|
2013-01-22 04:03:44 +08:00
|
|
|
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \
|
2013-09-12 05:23:28 +08:00
|
|
|
asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
|
2013-01-22 04:03:44 +08:00
|
|
|
asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
|
2009-01-14 21:13:59 +08:00
|
|
|
{ \
|
2013-01-22 04:25:54 +08:00
|
|
|
long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \
|
2013-01-22 04:03:44 +08:00
|
|
|
__MAP(x,__SC_TEST,__VA_ARGS__); \
|
2013-01-22 04:25:54 +08:00
|
|
|
__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \
|
|
|
|
return ret; \
|
2009-01-14 21:13:59 +08:00
|
|
|
} \
|
2013-01-22 04:03:44 +08:00
|
|
|
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
|
2018-04-05 17:53:01 +08:00
|
|
|
#endif /* __SYSCALL_DEFINEx */
|
2009-01-14 21:13:59 +08:00
|
|
|
|
2017-06-15 09:12:01 +08:00
|
|
|
/*
|
|
|
|
* Called before coming back to user-mode. Returning to user-mode with an
|
|
|
|
* address limit different than USER_DS can allow to overwrite kernel memory.
|
|
|
|
*/
|
|
|
|
static inline void addr_limit_user_check(void)
|
|
|
|
{
|
2017-09-07 23:30:44 +08:00
|
|
|
#ifdef TIF_FSCHECK
|
2017-06-15 09:12:01 +08:00
|
|
|
if (!test_thread_flag(TIF_FSCHECK))
|
|
|
|
return;
|
2017-09-07 23:30:44 +08:00
|
|
|
#endif
|
2017-06-15 09:12:01 +08:00
|
|
|
|
2017-09-07 23:30:44 +08:00
|
|
|
if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
|
|
|
|
"Invalid address limit on user-mode return"))
|
|
|
|
force_sig(SIGKILL, current);
|
|
|
|
|
|
|
|
#ifdef TIF_FSCHECK
|
2017-06-15 09:12:01 +08:00
|
|
|
clear_thread_flag(TIF_FSCHECK);
|
|
|
|
#endif
|
2017-09-07 23:30:44 +08:00
|
|
|
}
|
2017-06-15 09:12:01 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
2018-04-05 17:53:01 +08:00
|
|
|
*
|
|
|
|
* 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.
|
2018-03-26 03:50:11 +08:00
|
|
|
*/
|
2018-04-05 17:53:01 +08:00
|
|
|
#ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
|
2018-03-26 03:50:11 +08:00
|
|
|
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);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* fs/xattr.c */
|
2008-04-29 15:59:41 +08:00
|
|
|
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,
|
|
|
|
const void __user *value, size_t size, int flags);
|
|
|
|
asmlinkage long sys_fsetxattr(int fd, const char __user *name,
|
|
|
|
const void __user *value, size_t size, int flags);
|
2009-01-14 21:13:54 +08:00
|
|
|
asmlinkage long sys_getxattr(const char __user *path, const char __user *name,
|
|
|
|
void __user *value, size_t size);
|
|
|
|
asmlinkage long sys_lgetxattr(const char __user *path, const char __user *name,
|
|
|
|
void __user *value, size_t size);
|
|
|
|
asmlinkage long sys_fgetxattr(int fd, const char __user *name,
|
|
|
|
void __user *value, size_t size);
|
|
|
|
asmlinkage long sys_listxattr(const char __user *path, char __user *list,
|
|
|
|
size_t size);
|
|
|
|
asmlinkage long sys_llistxattr(const char __user *path, char __user *list,
|
|
|
|
size_t size);
|
|
|
|
asmlinkage long sys_flistxattr(int fd, char __user *list, size_t size);
|
2008-04-29 15:59:41 +08:00
|
|
|
asmlinkage long sys_removexattr(const char __user *path,
|
|
|
|
const char __user *name);
|
|
|
|
asmlinkage long sys_lremovexattr(const char __user *path,
|
|
|
|
const char __user *name);
|
|
|
|
asmlinkage long sys_fremovexattr(int fd, const char __user *name);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* fs/dcache.c */
|
|
|
|
asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* 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);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* 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);
|
2005-04-17 06:20:36 +08:00
|
|
|
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
|
2018-03-26 03:50:11 +08:00
|
|
|
|
|
|
|
/* 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 */
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_ioctl(unsigned int fd, unsigned int cmd,
|
|
|
|
unsigned long arg);
|
2018-03-26 03:50:11 +08:00
|
|
|
|
|
|
|
/* 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 */
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_flock(unsigned int fd, unsigned int cmd);
|
2018-03-26 03:50:11 +08:00
|
|
|
|
|
|
|
/* 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);
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_close(unsigned int fd);
|
|
|
|
asmlinkage long sys_vhangup(void);
|
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* 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 */
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_llseek(unsigned int fd, unsigned long offset_high,
|
|
|
|
unsigned long offset_low, loff_t __user *result,
|
2012-12-18 07:59:39 +08:00
|
|
|
unsigned int whence);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_lseek(unsigned int fd, off_t offset,
|
|
|
|
unsigned int whence);
|
2009-01-14 21:13:54 +08:00
|
|
|
asmlinkage long sys_read(unsigned int fd, char __user *buf, size_t count);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_write(unsigned int fd, const char __user *buf,
|
|
|
|
size_t count);
|
2009-01-14 21:13:54 +08:00
|
|
|
asmlinkage long sys_readv(unsigned long fd,
|
|
|
|
const struct iovec __user *vec,
|
|
|
|
unsigned long vlen);
|
|
|
|
asmlinkage long sys_writev(unsigned long fd,
|
|
|
|
const struct iovec __user *vec,
|
|
|
|
unsigned long vlen);
|
|
|
|
asmlinkage long sys_pread64(unsigned int fd, char __user *buf,
|
|
|
|
size_t count, loff_t pos);
|
|
|
|
asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
|
|
|
|
size_t count, loff_t pos);
|
2009-04-03 07:59:23 +08:00
|
|
|
asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec,
|
Make non-compat preadv/pwritev use native register size
Instead of always splitting the file offset into 32-bit 'high' and 'low'
parts, just split them into the largest natural word-size - which in C
terms is 'unsigned long'.
This allows 64-bit architectures to avoid the unnecessary 32-bit
shifting and masking for native format (while the compat interfaces will
obviously always have to do it).
This also changes the order of 'high' and 'low' to be "low first". Why?
Because when we have it like this, the 64-bit system calls now don't use
the "pos_high" argument at all, and it makes more sense for the native
system call to simply match the user-mode prototype.
This results in a much more natural calling convention, and allows the
compiler to generate much more straightforward code. On x86-64, we now
generate
testq %rcx, %rcx # pos_l
js .L122 #,
movq %rcx, -48(%rbp) # pos_l, pos
from the C source
loff_t pos = pos_from_hilo(pos_h, pos_l);
...
if (pos < 0)
return -EINVAL;
and the 'pos_h' register isn't even touched. It used to generate code
like
mov %r8d, %r8d # pos_low, pos_low
salq $32, %rcx #, tmp71
movq %r8, %rax # pos_low, pos.386
orq %rcx, %rax # tmp71, pos.386
js .L122 #,
movq %rax, -48(%rbp) # pos.386, pos
which isn't _that_ horrible, but it does show how the natural word size
is just a more sensible interface (same arguments will hold in the user
level glibc wrapper function, of course, so the kernel side is just half
of the equation!)
Note: in all cases the user code wrapper can again be the same. You can
just do
#define HALF_BITS (sizeof(unsigned long)*4)
__syscall(PWRITEV, fd, iov, count, offset, (offset >> HALF_BITS) >> HALF_BITS);
or something like that. That way the user mode wrapper will also be
nicely passing in a zero (it won't actually have to do the shifts, the
compiler will understand what is going on) for the last argument.
And that is a good idea, even if nobody will necessarily ever care: if
we ever do move to a 128-bit lloff_t, this particular system call might
be left alone. Of course, that will be the least of our worries if we
really ever need to care, so this may not be worth really caring about.
[ Fixed for lost 'loff_t' cast noticed by Andrew Morton ]
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 23:03:22 +08:00
|
|
|
unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
|
2009-04-03 07:59:23 +08:00
|
|
|
asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec,
|
Make non-compat preadv/pwritev use native register size
Instead of always splitting the file offset into 32-bit 'high' and 'low'
parts, just split them into the largest natural word-size - which in C
terms is 'unsigned long'.
This allows 64-bit architectures to avoid the unnecessary 32-bit
shifting and masking for native format (while the compat interfaces will
obviously always have to do it).
This also changes the order of 'high' and 'low' to be "low first". Why?
Because when we have it like this, the 64-bit system calls now don't use
the "pos_high" argument at all, and it makes more sense for the native
system call to simply match the user-mode prototype.
This results in a much more natural calling convention, and allows the
compiler to generate much more straightforward code. On x86-64, we now
generate
testq %rcx, %rcx # pos_l
js .L122 #,
movq %rcx, -48(%rbp) # pos_l, pos
from the C source
loff_t pos = pos_from_hilo(pos_h, pos_l);
...
if (pos < 0)
return -EINVAL;
and the 'pos_h' register isn't even touched. It used to generate code
like
mov %r8d, %r8d # pos_low, pos_low
salq $32, %rcx #, tmp71
movq %r8, %rax # pos_low, pos.386
orq %rcx, %rax # tmp71, pos.386
js .L122 #,
movq %rax, -48(%rbp) # pos.386, pos
which isn't _that_ horrible, but it does show how the natural word size
is just a more sensible interface (same arguments will hold in the user
level glibc wrapper function, of course, so the kernel side is just half
of the equation!)
Note: in all cases the user code wrapper can again be the same. You can
just do
#define HALF_BITS (sizeof(unsigned long)*4)
__syscall(PWRITEV, fd, iov, count, offset, (offset >> HALF_BITS) >> HALF_BITS);
or something like that. That way the user mode wrapper will also be
nicely passing in a zero (it won't actually have to do the shifts, the
compiler will understand what is going on) for the last argument.
And that is a good idea, even if nobody will necessarily ever care: if
we ever do move to a 128-bit lloff_t, this particular system call might
be left alone. Of course, that will be the least of our worries if we
really ever need to care, so this may not be worth really caring about.
[ Fixed for lost 'loff_t' cast noticed by Andrew Morton ]
Acked-by: Gerd Hoffmann <kraxel@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-03 23:03:22 +08:00
|
|
|
unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* 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,
|
2006-10-11 16:21:44 +08:00
|
|
|
size_t sigsetsize);
|
2018-03-26 03:50:11 +08:00
|
|
|
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);
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_sethostname(char __user *name, int len);
|
|
|
|
asmlinkage long sys_setdomainname(char __user *name, int len);
|
|
|
|
asmlinkage long sys_getrlimit(unsigned int resource,
|
|
|
|
struct rlimit __user *rlim);
|
|
|
|
asmlinkage long sys_setrlimit(unsigned int resource,
|
|
|
|
struct rlimit __user *rlim);
|
|
|
|
asmlinkage long sys_getrusage(int who, struct rusage __user *ru);
|
|
|
|
asmlinkage long sys_umask(int mask);
|
2018-03-26 03:50:11 +08:00
|
|
|
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);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* ipc/msg.c */
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_msgget(key_t key, int msgflg);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf);
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_msgrcv(int msqid, struct msgbuf __user *msgp,
|
|
|
|
size_t msgsz, long msgtyp, int msgflg);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_msgsnd(int msqid, struct msgbuf __user *msgp,
|
|
|
|
size_t msgsz, int msgflg);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* ipc/sem.c */
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_semget(key_t key, int nsems, int semflg);
|
2013-03-06 04:04:55 +08:00
|
|
|
asmlinkage long sys_semctl(int semid, int semnum, int cmd, unsigned long arg);
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_semtimedop(int semid, struct sembuf __user *sops,
|
|
|
|
unsigned nsops,
|
|
|
|
const struct timespec __user *timeout);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_semop(int semid, struct sembuf __user *sops,
|
|
|
|
unsigned nsops);
|
|
|
|
|
|
|
|
/* ipc/shm.c */
|
2005-04-17 06:20:36 +08:00
|
|
|
asmlinkage long sys_shmget(key_t key, size_t size, int flag);
|
|
|
|
asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg);
|
|
|
|
asmlinkage long sys_shmdt(char __user *shmaddr);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* 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);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* mm/filemap.c */
|
|
|
|
asmlinkage long sys_readahead(int fd, loff_t offset, size_t count);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* 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);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* security/keys/keyctl.c */
|
2005-04-17 06:20:36 +08:00
|
|
|
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);
|
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* arch/example/kernel/sys_example.c */
|
2012-11-29 12:04:26 +08:00
|
|
|
#ifdef CONFIG_CLONE_BACKWARDS
|
clone: support passing tls argument via C rather than pt_regs magic
clone has some of the quirkiest syscall handling in the kernel, with a
pile of special cases, historical curiosities, and architecture-specific
calling conventions. In particular, clone with CLONE_SETTLS accepts a
parameter "tls" that the C entry point completely ignores and some
assembly entry points overwrite; instead, the low-level arch-specific
code pulls the tls parameter out of the arch-specific register captured
as part of pt_regs on entry to the kernel. That's a massive hack, and
it makes the arch-specific code only work when called via the specific
existing syscall entry points; because of this hack, any new clone-like
system call would have to accept an identical tls argument in exactly
the same arch-specific position, rather than providing a unified system
call entry point across architectures.
The first patch allows architectures to handle the tls argument via
normal C parameter passing, if they opt in by selecting
HAVE_COPY_THREAD_TLS. The second patch makes 32-bit and 64-bit x86 opt
into this.
These two patches came out of the clone4 series, which isn't ready for
this merge window, but these first two cleanup patches were entirely
uncontroversial and have acks. I'd like to go ahead and submit these
two so that other architectures can begin building on top of this and
opting into HAVE_COPY_THREAD_TLS. However, I'm also happy to wait and
send these through the next merge window (along with v3 of clone4) if
anyone would prefer that.
This patch (of 2):
clone with CLONE_SETTLS accepts an argument to set the thread-local
storage area for the new thread. sys_clone declares an int argument
tls_val in the appropriate point in the argument list (based on the
various CLONE_BACKWARDS variants), but doesn't actually use or pass along
that argument. Instead, sys_clone calls do_fork, which calls
copy_process, which calls the arch-specific copy_thread, and copy_thread
pulls the corresponding syscall argument out of the pt_regs captured at
kernel entry (knowing what argument of clone that architecture passes tls
in).
Apart from being awful and inscrutable, that also only works because only
one code path into copy_thread can pass the CLONE_SETTLS flag, and that
code path comes from sys_clone with its architecture-specific
argument-passing order. This prevents introducing a new version of the
clone system call without propagating the same architecture-specific
position of the tls argument.
However, there's no reason to pull the argument out of pt_regs when
sys_clone could just pass it down via C function call arguments.
Introduce a new CONFIG_HAVE_COPY_THREAD_TLS for architectures to opt into,
and a new copy_thread_tls that accepts the tls parameter as an additional
unsigned long (syscall-argument-sized) argument. Change sys_clone's tls
argument to an unsigned long (which does not change the ABI), and pass
that down to copy_thread_tls.
Architectures that don't opt into copy_thread_tls will continue to ignore
the C argument to sys_clone in favor of the pt_regs captured at kernel
entry, and thus will be unable to introduce new versions of the clone
syscall.
Patch co-authored by Josh Triplett and Thiago Macieira.
Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thiago Macieira <thiago.macieira@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:19 +08:00
|
|
|
asmlinkage long sys_clone(unsigned long, unsigned long, int __user *, unsigned long,
|
2012-11-29 12:04:26 +08:00
|
|
|
int __user *);
|
|
|
|
#else
|
2013-08-14 07:00:53 +08:00
|
|
|
#ifdef CONFIG_CLONE_BACKWARDS3
|
|
|
|
asmlinkage long sys_clone(unsigned long, unsigned long, int, int __user *,
|
clone: support passing tls argument via C rather than pt_regs magic
clone has some of the quirkiest syscall handling in the kernel, with a
pile of special cases, historical curiosities, and architecture-specific
calling conventions. In particular, clone with CLONE_SETTLS accepts a
parameter "tls" that the C entry point completely ignores and some
assembly entry points overwrite; instead, the low-level arch-specific
code pulls the tls parameter out of the arch-specific register captured
as part of pt_regs on entry to the kernel. That's a massive hack, and
it makes the arch-specific code only work when called via the specific
existing syscall entry points; because of this hack, any new clone-like
system call would have to accept an identical tls argument in exactly
the same arch-specific position, rather than providing a unified system
call entry point across architectures.
The first patch allows architectures to handle the tls argument via
normal C parameter passing, if they opt in by selecting
HAVE_COPY_THREAD_TLS. The second patch makes 32-bit and 64-bit x86 opt
into this.
These two patches came out of the clone4 series, which isn't ready for
this merge window, but these first two cleanup patches were entirely
uncontroversial and have acks. I'd like to go ahead and submit these
two so that other architectures can begin building on top of this and
opting into HAVE_COPY_THREAD_TLS. However, I'm also happy to wait and
send these through the next merge window (along with v3 of clone4) if
anyone would prefer that.
This patch (of 2):
clone with CLONE_SETTLS accepts an argument to set the thread-local
storage area for the new thread. sys_clone declares an int argument
tls_val in the appropriate point in the argument list (based on the
various CLONE_BACKWARDS variants), but doesn't actually use or pass along
that argument. Instead, sys_clone calls do_fork, which calls
copy_process, which calls the arch-specific copy_thread, and copy_thread
pulls the corresponding syscall argument out of the pt_regs captured at
kernel entry (knowing what argument of clone that architecture passes tls
in).
Apart from being awful and inscrutable, that also only works because only
one code path into copy_thread can pass the CLONE_SETTLS flag, and that
code path comes from sys_clone with its architecture-specific
argument-passing order. This prevents introducing a new version of the
clone system call without propagating the same architecture-specific
position of the tls argument.
However, there's no reason to pull the argument out of pt_regs when
sys_clone could just pass it down via C function call arguments.
Introduce a new CONFIG_HAVE_COPY_THREAD_TLS for architectures to opt into,
and a new copy_thread_tls that accepts the tls parameter as an additional
unsigned long (syscall-argument-sized) argument. Change sys_clone's tls
argument to an unsigned long (which does not change the ABI), and pass
that down to copy_thread_tls.
Architectures that don't opt into copy_thread_tls will continue to ignore
the C argument to sys_clone in favor of the pt_regs captured at kernel
entry, and thus will be unable to introduce new versions of the clone
syscall.
Patch co-authored by Josh Triplett and Thiago Macieira.
Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thiago Macieira <thiago.macieira@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:19 +08:00
|
|
|
int __user *, unsigned long);
|
2013-08-14 07:00:53 +08:00
|
|
|
#else
|
2012-11-29 12:04:26 +08:00
|
|
|
asmlinkage long sys_clone(unsigned long, unsigned long, int __user *,
|
clone: support passing tls argument via C rather than pt_regs magic
clone has some of the quirkiest syscall handling in the kernel, with a
pile of special cases, historical curiosities, and architecture-specific
calling conventions. In particular, clone with CLONE_SETTLS accepts a
parameter "tls" that the C entry point completely ignores and some
assembly entry points overwrite; instead, the low-level arch-specific
code pulls the tls parameter out of the arch-specific register captured
as part of pt_regs on entry to the kernel. That's a massive hack, and
it makes the arch-specific code only work when called via the specific
existing syscall entry points; because of this hack, any new clone-like
system call would have to accept an identical tls argument in exactly
the same arch-specific position, rather than providing a unified system
call entry point across architectures.
The first patch allows architectures to handle the tls argument via
normal C parameter passing, if they opt in by selecting
HAVE_COPY_THREAD_TLS. The second patch makes 32-bit and 64-bit x86 opt
into this.
These two patches came out of the clone4 series, which isn't ready for
this merge window, but these first two cleanup patches were entirely
uncontroversial and have acks. I'd like to go ahead and submit these
two so that other architectures can begin building on top of this and
opting into HAVE_COPY_THREAD_TLS. However, I'm also happy to wait and
send these through the next merge window (along with v3 of clone4) if
anyone would prefer that.
This patch (of 2):
clone with CLONE_SETTLS accepts an argument to set the thread-local
storage area for the new thread. sys_clone declares an int argument
tls_val in the appropriate point in the argument list (based on the
various CLONE_BACKWARDS variants), but doesn't actually use or pass along
that argument. Instead, sys_clone calls do_fork, which calls
copy_process, which calls the arch-specific copy_thread, and copy_thread
pulls the corresponding syscall argument out of the pt_regs captured at
kernel entry (knowing what argument of clone that architecture passes tls
in).
Apart from being awful and inscrutable, that also only works because only
one code path into copy_thread can pass the CLONE_SETTLS flag, and that
code path comes from sys_clone with its architecture-specific
argument-passing order. This prevents introducing a new version of the
clone system call without propagating the same architecture-specific
position of the tls argument.
However, there's no reason to pull the argument out of pt_regs when
sys_clone could just pass it down via C function call arguments.
Introduce a new CONFIG_HAVE_COPY_THREAD_TLS for architectures to opt into,
and a new copy_thread_tls that accepts the tls parameter as an additional
unsigned long (syscall-argument-sized) argument. Change sys_clone's tls
argument to an unsigned long (which does not change the ABI), and pass
that down to copy_thread_tls.
Architectures that don't opt into copy_thread_tls will continue to ignore
the C argument to sys_clone in favor of the pt_regs captured at kernel
entry, and thus will be unable to introduce new versions of the clone
syscall.
Patch co-authored by Josh Triplett and Thiago Macieira.
Signed-off-by: Josh Triplett <josh@joshtriplett.org>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thiago Macieira <thiago.macieira@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-26 06:01:19 +08:00
|
|
|
int __user *, unsigned long);
|
2012-11-29 12:04:26 +08:00
|
|
|
#endif
|
2013-08-14 07:00:53 +08:00
|
|
|
#endif
|
2012-10-21 01:32:30 +08:00
|
|
|
asmlinkage long sys_execve(const char __user *filename,
|
|
|
|
const char __user *const __user *argv,
|
|
|
|
const char __user *const __user *envp);
|
2008-12-10 19:33:23 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/* 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);
|
perf: Do the big rename: Performance Counters -> Performance Events
Bye-bye Performance Counters, welcome Performance Events!
In the past few months the perfcounters subsystem has grown out its
initial role of counting hardware events, and has become (and is
becoming) a much broader generic event enumeration, reporting, logging,
monitoring, analysis facility.
Naming its core object 'perf_counter' and naming the subsystem
'perfcounters' has become more and more of a misnomer. With pending
code like hw-breakpoints support the 'counter' name is less and
less appropriate.
All in one, we've decided to rename the subsystem to 'performance
events' and to propagate this rename through all fields, variables
and API names. (in an ABI compatible fashion)
The word 'event' is also a bit shorter than 'counter' - which makes
it slightly more convenient to write/handle as well.
Thanks goes to Stephane Eranian who first observed this misnomer and
suggested a rename.
User-space tooling and ABI compatibility is not affected - this patch
should be function-invariant. (Also, defconfigs were not touched to
keep the size down.)
This patch has been generated via the following script:
FILES=$(find * -type f | grep -vE 'oprofile|[^K]config')
sed -i \
-e 's/PERF_EVENT_/PERF_RECORD_/g' \
-e 's/PERF_COUNTER/PERF_EVENT/g' \
-e 's/perf_counter/perf_event/g' \
-e 's/nb_counters/nb_events/g' \
-e 's/swcounter/swevent/g' \
-e 's/tpcounter_event/tp_event/g' \
$FILES
for N in $(find . -name perf_counter.[ch]); do
M=$(echo $N | sed 's/perf_counter/perf_event/g')
mv $N $M
done
FILES=$(find . -name perf_event.*)
sed -i \
-e 's/COUNTER_MASK/REG_MASK/g' \
-e 's/COUNTER/EVENT/g' \
-e 's/\<event\>/event_id/g' \
-e 's/counter/event/g' \
-e 's/Counter/Event/g' \
$FILES
... to keep it as correct as possible. This script can also be
used by anyone who has pending perfcounters patches - it converts
a Linux kernel tree over to the new naming. We tried to time this
change to the point in time where the amount of pending patches
is the smallest: the end of the merge window.
Namespace clashes were fixed up in a preparatory patch - and some
stylistic fallout will be fixed up in a subsequent patch.
( NOTE: 'counters' are still the proper terminology when we deal
with hardware registers - and these sed scripts are a bit
over-eager in renaming them. I've undone some of that, but
in case there's something left where 'counter' would be
better than 'event' we can undo that on an individual basis
instead of touching an otherwise nicely automated patch. )
Suggested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Paul Mackerras <paulus@samba.org>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Kyle McMartin <kyle@mcmartin.ca>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <linux-arch@vger.kernel.org>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
|
|
|
asmlinkage long sys_perf_event_open(
|
|
|
|
struct perf_event_attr __user *attr_uptr,
|
2009-03-04 17:36:51 +08:00
|
|
|
pid_t pid, int cpu, int group_fd, unsigned long flags);
|
2018-03-26 03:50:11 +08:00
|
|
|
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);
|
2009-12-01 06:37:04 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
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);
|
2011-01-29 21:13:26 +08:00
|
|
|
asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name,
|
|
|
|
struct file_handle __user *handle,
|
|
|
|
int __user *mnt_id, int flag);
|
2011-01-29 21:13:26 +08:00
|
|
|
asmlinkage long sys_open_by_handle_at(int mountdirfd,
|
|
|
|
struct file_handle __user *handle,
|
|
|
|
int flags);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_clock_adjtime(clockid_t which_clock,
|
|
|
|
struct timex __user *tx);
|
|
|
|
asmlinkage long sys_syncfs(int fd);
|
2011-05-12 05:06:58 +08:00
|
|
|
asmlinkage long sys_setns(int fd, int nstype);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_sendmmsg(int fd, struct mmsghdr __user *msg,
|
|
|
|
unsigned int vlen, unsigned flags);
|
2011-11-01 08:06:39 +08:00
|
|
|
asmlinkage long sys_process_vm_readv(pid_t pid,
|
|
|
|
const struct iovec __user *lvec,
|
|
|
|
unsigned long liovcnt,
|
|
|
|
const struct iovec __user *rvec,
|
|
|
|
unsigned long riovcnt,
|
|
|
|
unsigned long flags);
|
|
|
|
asmlinkage long sys_process_vm_writev(pid_t pid,
|
|
|
|
const struct iovec __user *lvec,
|
|
|
|
unsigned long liovcnt,
|
|
|
|
const struct iovec __user *rvec,
|
|
|
|
unsigned long riovcnt,
|
|
|
|
unsigned long flags);
|
2012-06-01 07:26:44 +08:00
|
|
|
asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
|
|
|
|
unsigned long idx1, unsigned long idx2);
|
2012-10-22 15:39:41 +08:00
|
|
|
asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags);
|
2018-03-26 03:50:11 +08:00
|
|
|
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);
|
2014-06-26 07:08:24 +08:00
|
|
|
asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
|
|
|
|
const char __user *uargs);
|
random: introduce getrandom(2) system call
The getrandom(2) system call was requested by the LibreSSL Portable
developers. It is analoguous to the getentropy(2) system call in
OpenBSD.
The rationale of this system call is to provide resiliance against
file descriptor exhaustion attacks, where the attacker consumes all
available file descriptors, forcing the use of the fallback code where
/dev/[u]random is not available. Since the fallback code is often not
well-tested, it is better to eliminate this potential failure mode
entirely.
The other feature provided by this new system call is the ability to
request randomness from the /dev/urandom entropy pool, but to block
until at least 128 bits of entropy has been accumulated in the
/dev/urandom entropy pool. Historically, the emphasis in the
/dev/urandom development has been to ensure that urandom pool is
initialized as quickly as possible after system boot, and preferably
before the init scripts start execution.
This is because changing /dev/urandom reads to block represents an
interface change that could potentially break userspace which is not
acceptable. In practice, on most x86 desktop and server systems, in
general the entropy pool can be initialized before it is needed (and
in modern kernels, we will printk a warning message if not). However,
on an embedded system, this may not be the case. And so with this new
interface, we can provide the functionality of blocking until the
urandom pool has been initialized. Any userspace program which uses
this new functionality must take care to assure that if it is used
during the boot process, that it will not cause the init scripts or
other portions of the system startup to hang indefinitely.
SYNOPSIS
#include <linux/random.h>
int getrandom(void *buf, size_t buflen, unsigned int flags);
DESCRIPTION
The system call getrandom() fills the buffer pointed to by buf
with up to buflen random bytes which can be used to seed user
space random number generators (i.e., DRBG's) or for other
cryptographic uses. It should not be used for Monte Carlo
simulations or other programs/algorithms which are doing
probabilistic sampling.
If the GRND_RANDOM flags bit is set, then draw from the
/dev/random pool instead of the /dev/urandom pool. The
/dev/random pool is limited based on the entropy that can be
obtained from environmental noise, so if there is insufficient
entropy, the requested number of bytes may not be returned.
If there is no entropy available at all, getrandom(2) will
either block, or return an error with errno set to EAGAIN if
the GRND_NONBLOCK bit is set in flags.
If the GRND_RANDOM bit is not set, then the /dev/urandom pool
will be used. Unlike using read(2) to fetch data from
/dev/urandom, if the urandom pool has not been sufficiently
initialized, getrandom(2) will block (or return -1 with the
errno set to EAGAIN if the GRND_NONBLOCK bit is set in flags).
The getentropy(2) system call in OpenBSD can be emulated using
the following function:
int getentropy(void *buf, size_t buflen)
{
int ret;
if (buflen > 256)
goto failure;
ret = getrandom(buf, buflen, 0);
if (ret < 0)
return ret;
if (ret == buflen)
return 0;
failure:
errno = EIO;
return -1;
}
RETURN VALUE
On success, the number of bytes that was filled in the buf is
returned. This may not be all the bytes requested by the
caller via buflen if insufficient entropy was present in the
/dev/random pool, or if the system call was interrupted by a
signal.
On error, -1 is returned, and errno is set appropriately.
ERRORS
EINVAL An invalid flag was passed to getrandom(2)
EFAULT buf is outside the accessible address space.
EAGAIN The requested entropy was not available, and
getentropy(2) would have blocked if the
GRND_NONBLOCK flag was not set.
EINTR While blocked waiting for entropy, the call was
interrupted by a signal handler; see the description
of how interrupted read(2) calls on "slow" devices
are handled with and without the SA_RESTART flag
in the signal(7) man page.
NOTES
For small requests (buflen <= 256) getrandom(2) will not
return EINTR when reading from the urandom pool once the
entropy pool has been initialized, and it will return all of
the bytes that have been requested. This is the recommended
way to use getrandom(2), and is designed for compatibility
with OpenBSD's getentropy() system call.
However, if you are using GRND_RANDOM, then getrandom(2) may
block until the entropy accounting determines that sufficient
environmental noise has been gathered such that getrandom(2)
will be operating as a NRBG instead of a DRBG for those people
who are working in the NIST SP 800-90 regime. Since it may
block for a long time, these guarantees do *not* apply. The
user may want to interrupt a hanging process using a signal,
so blocking until all of the requested bytes are returned
would be unfriendly.
For this reason, the user of getrandom(2) MUST always check
the return value, in case it returns some error, or if fewer
bytes than requested was returned. In the case of
!GRND_RANDOM and small request, the latter should never
happen, but the careful userspace code (and all crypto code
should be careful) should check for this anyway!
Finally, unless you are doing long-term key generation (and
perhaps not even then), you probably shouldn't be using
GRND_RANDOM. The cryptographic algorithms used for
/dev/urandom are quite conservative, and so should be
sufficient for all purposes. The disadvantage of GRND_RANDOM
is that it can block, and the increased complexity required to
deal with partially fulfilled getrandom(2) requests.
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Zach Brown <zab@zabbo.net>
2014-07-17 16:13:05 +08:00
|
|
|
asmlinkage long sys_getrandom(char __user *buf, size_t count,
|
|
|
|
unsigned int flags);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags);
|
2014-09-26 15:16:58 +08:00
|
|
|
asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
|
syscalls: implement execveat() system call
This patchset adds execveat(2) for x86, and is derived from Meredydd
Luff's patch from Sept 2012 (https://lkml.org/lkml/2012/9/11/528).
The primary aim of adding an execveat syscall is to allow an
implementation of fexecve(3) that does not rely on the /proc filesystem,
at least for executables (rather than scripts). The current glibc version
of fexecve(3) is implemented via /proc, which causes problems in sandboxed
or otherwise restricted environments.
Given the desire for a /proc-free fexecve() implementation, HPA suggested
(https://lkml.org/lkml/2006/7/11/556) that an execveat(2) syscall would be
an appropriate generalization.
Also, having a new syscall means that it can take a flags argument without
back-compatibility concerns. The current implementation just defines the
AT_EMPTY_PATH and AT_SYMLINK_NOFOLLOW flags, but other flags could be
added in future -- for example, flags for new namespaces (as suggested at
https://lkml.org/lkml/2006/7/11/474).
Related history:
- https://lkml.org/lkml/2006/12/27/123 is an example of someone
realizing that fexecve() is likely to fail in a chroot environment.
- http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=514043 covered
documenting the /proc requirement of fexecve(3) in its manpage, to
"prevent other people from wasting their time".
- https://bugzilla.redhat.com/show_bug.cgi?id=241609 described a
problem where a process that did setuid() could not fexecve()
because it no longer had access to /proc/self/fd; this has since
been fixed.
This patch (of 4):
Add a new execveat(2) system call. execveat() is to execve() as openat()
is to open(): it takes a file descriptor that refers to a directory, and
resolves the filename relative to that.
In addition, if the filename is empty and AT_EMPTY_PATH is specified,
execveat() executes the file to which the file descriptor refers. This
replicates the functionality of fexecve(), which is a system call in other
UNIXen, but in Linux glibc it depends on opening "/proc/self/fd/<fd>" (and
so relies on /proc being mounted).
The filename fed to the executed program as argv[0] (or the name of the
script fed to a script interpreter) will be of the form "/dev/fd/<fd>"
(for an empty filename) or "/dev/fd/<fd>/<filename>", effectively
reflecting how the executable was found. This does however mean that
execution of a script in a /proc-less environment won't work; also, script
execution via an O_CLOEXEC file descriptor fails (as the file will not be
accessible after exec).
Based on patches by Meredydd Luff.
Signed-off-by: David Drysdale <drysdale@google.com>
Cc: Meredydd Luff <meredydd@senatehouse.org>
Cc: Shuah Khan <shuah.kh@samsung.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Rich Felker <dalias@aerifal.cx>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-12-13 08:57:29 +08:00
|
|
|
asmlinkage long sys_execveat(int dfd, const char __user *filename,
|
|
|
|
const char __user *const __user *argv,
|
|
|
|
const char __user *const __user *envp, int flags);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_userfaultfd(int flags);
|
sys_membarrier(): system-wide memory barrier (generic, x86)
Here is an implementation of a new system call, sys_membarrier(), which
executes a memory barrier on all threads running on the system. It is
implemented by calling synchronize_sched(). It can be used to
distribute the cost of user-space memory barriers asymmetrically by
transforming pairs of memory barriers into pairs consisting of
sys_membarrier() and a compiler barrier. For synchronization primitives
that distinguish between read-side and write-side (e.g. userspace RCU
[1], rwlocks), the read-side can be accelerated significantly by moving
the bulk of the memory barrier overhead to the write-side.
The existing applications of which I am aware that would be improved by
this system call are as follows:
* Through Userspace RCU library (http://urcu.so)
- DNS server (Knot DNS) https://www.knot-dns.cz/
- Network sniffer (http://netsniff-ng.org/)
- Distributed object storage (https://sheepdog.github.io/sheepdog/)
- User-space tracing (http://lttng.org)
- Network storage system (https://www.gluster.org/)
- Virtual routers (https://events.linuxfoundation.org/sites/events/files/slides/DPDK_RCU_0MQ.pdf)
- Financial software (https://lkml.org/lkml/2015/3/23/189)
Those projects use RCU in userspace to increase read-side speed and
scalability compared to locking. Especially in the case of RCU used by
libraries, sys_membarrier can speed up the read-side by moving the bulk of
the memory barrier cost to synchronize_rcu().
* Direct users of sys_membarrier
- core dotnet garbage collector (https://github.com/dotnet/coreclr/issues/198)
Microsoft core dotnet GC developers are planning to use the mprotect()
side-effect of issuing memory barriers through IPIs as a way to implement
Windows FlushProcessWriteBuffers() on Linux. They are referring to
sys_membarrier in their github thread, specifically stating that
sys_membarrier() is what they are looking for.
To explain the benefit of this scheme, let's introduce two example threads:
Thread A (non-frequent, e.g. executing liburcu synchronize_rcu())
Thread B (frequent, e.g. executing liburcu
rcu_read_lock()/rcu_read_unlock())
In a scheme where all smp_mb() in thread A are ordering memory accesses
with respect to smp_mb() present in Thread B, we can change each
smp_mb() within Thread A into calls to sys_membarrier() and each
smp_mb() within Thread B into compiler barriers "barrier()".
Before the change, we had, for each smp_mb() pairs:
Thread A Thread B
previous mem accesses previous mem accesses
smp_mb() smp_mb()
following mem accesses following mem accesses
After the change, these pairs become:
Thread A Thread B
prev mem accesses prev mem accesses
sys_membarrier() barrier()
follow mem accesses follow mem accesses
As we can see, there are two possible scenarios: either Thread B memory
accesses do not happen concurrently with Thread A accesses (1), or they
do (2).
1) Non-concurrent Thread A vs Thread B accesses:
Thread A Thread B
prev mem accesses
sys_membarrier()
follow mem accesses
prev mem accesses
barrier()
follow mem accesses
In this case, thread B accesses will be weakly ordered. This is OK,
because at that point, thread A is not particularly interested in
ordering them with respect to its own accesses.
2) Concurrent Thread A vs Thread B accesses
Thread A Thread B
prev mem accesses prev mem accesses
sys_membarrier() barrier()
follow mem accesses follow mem accesses
In this case, thread B accesses, which are ensured to be in program
order thanks to the compiler barrier, will be "upgraded" to full
smp_mb() by synchronize_sched().
* Benchmarks
On Intel Xeon E5405 (8 cores)
(one thread is calling sys_membarrier, the other 7 threads are busy
looping)
1000 non-expedited sys_membarrier calls in 33s =3D 33 milliseconds/call.
* User-space user of this system call: Userspace RCU library
Both the signal-based and the sys_membarrier userspace RCU schemes
permit us to remove the memory barrier from the userspace RCU
rcu_read_lock() and rcu_read_unlock() primitives, thus significantly
accelerating them. These memory barriers are replaced by compiler
barriers on the read-side, and all matching memory barriers on the
write-side are turned into an invocation of a memory barrier on all
active threads in the process. By letting the kernel perform this
synchronization rather than dumbly sending a signal to every process
threads (as we currently do), we diminish the number of unnecessary wake
ups and only issue the memory barriers on active threads. Non-running
threads do not need to execute such barrier anyway, because these are
implied by the scheduler context switches.
Results in liburcu:
Operations in 10s, 6 readers, 2 writers:
memory barriers in reader: 1701557485 reads, 2202847 writes
signal-based scheme: 9830061167 reads, 6700 writes
sys_membarrier: 9952759104 reads, 425 writes
sys_membarrier (dyn. check): 7970328887 reads, 425 writes
The dynamic sys_membarrier availability check adds some overhead to
the read-side compared to the signal-based scheme, but besides that,
sys_membarrier slightly outperforms the signal-based scheme. However,
this non-expedited sys_membarrier implementation has a much slower grace
period than signal and memory barrier schemes.
Besides diminishing the number of wake-ups, one major advantage of the
membarrier system call over the signal-based scheme is that it does not
need to reserve a signal. This plays much more nicely with libraries,
and with processes injected into for tracing purposes, for which we
cannot expect that signals will be unused by the application.
An expedited version of this system call can be added later on to speed
up the grace period. Its implementation will likely depend on reading
the cpu_curr()->mm without holding each CPU's rq lock.
This patch adds the system call to x86 and to asm-generic.
[1] http://urcu.so
membarrier(2) man page:
MEMBARRIER(2) Linux Programmer's Manual MEMBARRIER(2)
NAME
membarrier - issue memory barriers on a set of threads
SYNOPSIS
#include <linux/membarrier.h>
int membarrier(int cmd, int flags);
DESCRIPTION
The cmd argument is one of the following:
MEMBARRIER_CMD_QUERY
Query the set of supported commands. It returns a bitmask of
supported commands.
MEMBARRIER_CMD_SHARED
Execute a memory barrier on all threads running on the system.
Upon return from system call, the caller thread is ensured that
all running threads have passed through a state where all memory
accesses to user-space addresses match program order between
entry to and return from the system call (non-running threads
are de facto in such a state). This covers threads from all pro=E2=80=90
cesses running on the system. This command returns 0.
The flags argument needs to be 0. For future extensions.
All memory accesses performed in program order from each targeted
thread is guaranteed to be ordered with respect to sys_membarrier(). If
we use the semantic "barrier()" to represent a compiler barrier forcing
memory accesses to be performed in program order across the barrier,
and smp_mb() to represent explicit memory barriers forcing full memory
ordering across the barrier, we have the following ordering table for
each pair of barrier(), sys_membarrier() and smp_mb():
The pair ordering is detailed as (O: ordered, X: not ordered):
barrier() smp_mb() sys_membarrier()
barrier() X X O
smp_mb() X O O
sys_membarrier() O O O
RETURN VALUE
On success, these system calls return zero. On error, -1 is returned,
and errno is set appropriately. For a given command, with flags
argument set to 0, this system call is guaranteed to always return the
same value until reboot.
ERRORS
ENOSYS System call is not implemented.
EINVAL Invalid arguments.
Linux 2015-04-15 MEMBARRIER(2)
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nicholas Miell <nmiell@comcast.net>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Alan Cox <gnomes@lxorguk.ukuu.org.uk>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Pranith Kumar <bobby.prani@gmail.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Shuah Khan <shuahkh@osg.samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-12 04:07:39 +08:00
|
|
|
asmlinkage long sys_membarrier(int cmd, int flags);
|
2018-03-26 03:50:11 +08:00
|
|
|
asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags);
|
2015-11-11 05:53:30 +08:00
|
|
|
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);
|
2018-03-26 03:50:11 +08:00
|
|
|
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);
|
2016-07-30 00:30:18 +08:00
|
|
|
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);
|
statx: Add a system call to make enhanced file info available
Add a system call to make extended file information available, including
file creation and some attribute flags where available through the
underlying filesystem.
The getattr inode operation is altered to take two additional arguments: a
u32 request_mask and an unsigned int flags that indicate the
synchronisation mode. This change is propagated to the vfs_getattr*()
function.
Functions like vfs_stat() are now inline wrappers around new functions
vfs_statx() and vfs_statx_fd() to reduce stack usage.
========
OVERVIEW
========
The idea was initially proposed as a set of xattrs that could be retrieved
with getxattr(), but the general preference proved to be for a new syscall
with an extended stat structure.
A number of requests were gathered for features to be included. The
following have been included:
(1) Make the fields a consistent size on all arches and make them large.
(2) Spare space, request flags and information flags are provided for
future expansion.
(3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an
__s64).
(4) Creation time: The SMB protocol carries the creation time, which could
be exported by Samba, which will in turn help CIFS make use of
FS-Cache as that can be used for coherency data (stx_btime).
This is also specified in NFSv4 as a recommended attribute and could
be exported by NFSD [Steve French].
(5) Lightweight stat: Ask for just those details of interest, and allow a
netfs (such as NFS) to approximate anything not of interest, possibly
without going to the server [Trond Myklebust, Ulrich Drepper, Andreas
Dilger] (AT_STATX_DONT_SYNC).
(6) Heavyweight stat: Force a netfs to go to the server, even if it thinks
its cached attributes are up to date [Trond Myklebust]
(AT_STATX_FORCE_SYNC).
And the following have been left out for future extension:
(7) Data version number: Could be used by userspace NFS servers [Aneesh
Kumar].
Can also be used to modify fill_post_wcc() in NFSD which retrieves
i_version directly, but has just called vfs_getattr(). It could get
it from the kstat struct if it used vfs_xgetattr() instead.
(There's disagreement on the exact semantics of a single field, since
not all filesystems do this the same way).
(8) BSD stat compatibility: Including more fields from the BSD stat such
as creation time (st_btime) and inode generation number (st_gen)
[Jeremy Allison, Bernd Schubert].
(9) Inode generation number: Useful for FUSE and userspace NFS servers
[Bernd Schubert].
(This was asked for but later deemed unnecessary with the
open-by-handle capability available and caused disagreement as to
whether it's a security hole or not).
(10) Extra coherency data may be useful in making backups [Andreas Dilger].
(No particular data were offered, but things like last backup
timestamp, the data version number and the DOS archive bit would come
into this category).
(11) Allow the filesystem to indicate what it can/cannot provide: A
filesystem can now say it doesn't support a standard stat feature if
that isn't available, so if, for instance, inode numbers or UIDs don't
exist or are fabricated locally...
(This requires a separate system call - I have an fsinfo() call idea
for this).
(12) Store a 16-byte volume ID in the superblock that can be returned in
struct xstat [Steve French].
(Deferred to fsinfo).
(13) Include granularity fields in the time data to indicate the
granularity of each of the times (NFSv4 time_delta) [Steve French].
(Deferred to fsinfo).
(14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags.
Note that the Linux IOC flags are a mess and filesystems such as Ext4
define flags that aren't in linux/fs.h, so translation in the kernel
may be a necessity (or, possibly, we provide the filesystem type too).
(Some attributes are made available in stx_attributes, but the general
feeling was that the IOC flags were to ext[234]-specific and shouldn't
be exposed through statx this way).
(15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer,
Michael Kerrisk].
(Deferred, probably to fsinfo. Finding out if there's an ACL or
seclabal might require extra filesystem operations).
(16) Femtosecond-resolution timestamps [Dave Chinner].
(A __reserved field has been left in the statx_timestamp struct for
this - if there proves to be a need).
(17) A set multiple attributes syscall to go with this.
===============
NEW SYSTEM CALL
===============
The new system call is:
int ret = statx(int dfd,
const char *filename,
unsigned int flags,
unsigned int mask,
struct statx *buffer);
The dfd, filename and flags parameters indicate the file to query, in a
similar way to fstatat(). There is no equivalent of lstat() as that can be
emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is
also no equivalent of fstat() as that can be emulated by passing a NULL
filename to statx() with the fd of interest in dfd.
Whether or not statx() synchronises the attributes with the backing store
can be controlled by OR'ing a value into the flags argument (this typically
only affects network filesystems):
(1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this
respect.
(2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise
its attributes with the server - which might require data writeback to
occur to get the timestamps correct.
(3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a
network filesystem. The resulting values should be considered
approximate.
mask is a bitmask indicating the fields in struct statx that are of
interest to the caller. The user should set this to STATX_BASIC_STATS to
get the basic set returned by stat(). It should be noted that asking for
more information may entail extra I/O operations.
buffer points to the destination for the data. This must be 256 bytes in
size.
======================
MAIN ATTRIBUTES RECORD
======================
The following structures are defined in which to return the main attribute
set:
struct statx_timestamp {
__s64 tv_sec;
__s32 tv_nsec;
__s32 __reserved;
};
struct statx {
__u32 stx_mask;
__u32 stx_blksize;
__u64 stx_attributes;
__u32 stx_nlink;
__u32 stx_uid;
__u32 stx_gid;
__u16 stx_mode;
__u16 __spare0[1];
__u64 stx_ino;
__u64 stx_size;
__u64 stx_blocks;
__u64 __spare1[1];
struct statx_timestamp stx_atime;
struct statx_timestamp stx_btime;
struct statx_timestamp stx_ctime;
struct statx_timestamp stx_mtime;
__u32 stx_rdev_major;
__u32 stx_rdev_minor;
__u32 stx_dev_major;
__u32 stx_dev_minor;
__u64 __spare2[14];
};
The defined bits in request_mask and stx_mask are:
STATX_TYPE Want/got stx_mode & S_IFMT
STATX_MODE Want/got stx_mode & ~S_IFMT
STATX_NLINK Want/got stx_nlink
STATX_UID Want/got stx_uid
STATX_GID Want/got stx_gid
STATX_ATIME Want/got stx_atime{,_ns}
STATX_MTIME Want/got stx_mtime{,_ns}
STATX_CTIME Want/got stx_ctime{,_ns}
STATX_INO Want/got stx_ino
STATX_SIZE Want/got stx_size
STATX_BLOCKS Want/got stx_blocks
STATX_BASIC_STATS [The stuff in the normal stat struct]
STATX_BTIME Want/got stx_btime{,_ns}
STATX_ALL [All currently available stuff]
stx_btime is the file creation time, stx_mask is a bitmask indicating the
data provided and __spares*[] are where as-yet undefined fields can be
placed.
Time fields are structures with separate seconds and nanoseconds fields
plus a reserved field in case we want to add even finer resolution. Note
that times will be negative if before 1970; in such a case, the nanosecond
fields will also be negative if not zero.
The bits defined in the stx_attributes field convey information about a
file, how it is accessed, where it is and what it does. The following
attributes map to FS_*_FL flags and are the same numerical value:
STATX_ATTR_COMPRESSED File is compressed by the fs
STATX_ATTR_IMMUTABLE File is marked immutable
STATX_ATTR_APPEND File is append-only
STATX_ATTR_NODUMP File is not to be dumped
STATX_ATTR_ENCRYPTED File requires key to decrypt in fs
Within the kernel, the supported flags are listed by:
KSTAT_ATTR_FS_IOC_FLAGS
[Are any other IOC flags of sufficient general interest to be exposed
through this interface?]
New flags include:
STATX_ATTR_AUTOMOUNT Object is an automount trigger
These are for the use of GUI tools that might want to mark files specially,
depending on what they are.
Fields in struct statx come in a number of classes:
(0) stx_dev_*, stx_blksize.
These are local system information and are always available.
(1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino,
stx_size, stx_blocks.
These will be returned whether the caller asks for them or not. The
corresponding bits in stx_mask will be set to indicate whether they
actually have valid values.
If the caller didn't ask for them, then they may be approximated. For
example, NFS won't waste any time updating them from the server,
unless as a byproduct of updating something requested.
If the values don't actually exist for the underlying object (such as
UID or GID on a DOS file), then the bit won't be set in the stx_mask,
even if the caller asked for the value. In such a case, the returned
value will be a fabrication.
Note that there are instances where the type might not be valid, for
instance Windows reparse points.
(2) stx_rdev_*.
This will be set only if stx_mode indicates we're looking at a
blockdev or a chardev, otherwise will be 0.
(3) stx_btime.
Similar to (1), except this will be set to 0 if it doesn't exist.
=======
TESTING
=======
The following test program can be used to test the statx system call:
samples/statx/test-statx.c
Just compile and run, passing it paths to the files you want to examine.
The file is built automatically if CONFIG_SAMPLES is enabled.
Here's some example output. Firstly, an NFS directory that crosses to
another FSID. Note that the AUTOMOUNT attribute is set because transiting
this directory will cause d_automount to be invoked by the VFS.
[root@andromeda ~]# /tmp/test-statx -A /warthog/data
statx(/warthog/data) = 0
results=7ff
Size: 4096 Blocks: 8 IO Block: 1048576 directory
Device: 00:26 Inode: 1703937 Links: 125
Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041
Access: 2016-11-24 09:02:12.219699527+0000
Modify: 2016-11-17 10:44:36.225653653+0000
Change: 2016-11-17 10:44:36.225653653+0000
Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------)
Secondly, the result of automounting on that directory.
[root@andromeda ~]# /tmp/test-statx /warthog/data
statx(/warthog/data) = 0
results=7ff
Size: 4096 Blocks: 8 IO Block: 1048576 directory
Device: 00:27 Inode: 2 Links: 125
Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041
Access: 2016-11-24 09:02:12.219699527+0000
Modify: 2016-11-17 10:44:36.225653653+0000
Change: 2016-11-17 10:44:36.225653653+0000
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
|
|
|
asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
|
|
|
|
unsigned mask, struct statx __user *buffer);
|
2016-07-30 00:30:18 +08:00
|
|
|
|
2018-03-11 18:34:25 +08:00
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
|
2018-04-05 17:53:01 +08:00
|
|
|
#endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */
|
|
|
|
|
2018-03-26 03:50:11 +08:00
|
|
|
|
2018-03-11 18:34:25 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
|
2018-03-11 18:34:39 +08:00
|
|
|
int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type,
|
|
|
|
unsigned long flags, void __user *data);
|
2018-03-11 18:34:40 +08:00
|
|
|
int ksys_umount(char __user *name, int flags);
|
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 <viro@zeniv.linux.org.uk>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2018-03-11 18:34:40 +08:00
|
|
|
int ksys_dup(unsigned int fildes);
|
2018-03-11 18:34:41 +08:00
|
|
|
int ksys_chroot(const char __user *filename);
|
2018-03-11 18:34:41 +08:00
|
|
|
ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count);
|
2018-03-11 18:34:46 +08:00
|
|
|
int ksys_chdir(const char __user *filename);
|
2018-03-11 18:34:53 +08:00
|
|
|
int ksys_fchmod(unsigned int fd, umode_t mode);
|
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 <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2018-03-11 18:34:55 +08:00
|
|
|
int ksys_fchown(unsigned int fd, uid_t user, gid_t group);
|
2018-03-14 04:34:04 +08:00
|
|
|
int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent,
|
|
|
|
unsigned int count);
|
2018-03-14 04:43:59 +08:00
|
|
|
int ksys_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);
|
2018-03-14 04:51:17 +08:00
|
|
|
off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence);
|
2018-03-14 04:56:26 +08:00
|
|
|
ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count);
|
2018-03-15 05:35:11 +08:00
|
|
|
void ksys_sync(void);
|
2018-03-11 18:34:42 +08:00
|
|
|
int ksys_unshare(unsigned long unshare_flags);
|
2018-03-16 19:36:06 +08:00
|
|
|
int ksys_setsid(void);
|
2018-03-11 18:34:47 +08:00
|
|
|
int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
|
|
|
|
unsigned int flags);
|
2018-03-20 00:38:31 +08:00
|
|
|
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);
|
2018-03-20 00:46:32 +08:00
|
|
|
int ksys_fallocate(int fd, int mode, loff_t offset, loff_t len);
|
2018-03-11 18:34:45 +08:00
|
|
|
#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
|
2018-03-11 18:34:46 +08:00
|
|
|
unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
|
|
|
|
unsigned long prot, unsigned long flags,
|
|
|
|
unsigned long fd, unsigned long pgoff);
|
2018-03-20 00:51:36 +08:00
|
|
|
ssize_t ksys_readahead(int fd, loff_t offset, size_t count);
|
2018-03-11 18:34:39 +08:00
|
|
|
|
2018-03-11 18:34:47 +08:00
|
|
|
/*
|
|
|
|
* 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));
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:48 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:49 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:49 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:50 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:53 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:53 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:54 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
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 <viro@zeniv.linux.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>
2018-03-11 18:34:55 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:54 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:55 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-11 18:34:56 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-03-20 00:32:11 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|