2007-04-29 14:05:22 +00:00
|
|
|
/*
|
|
|
|
* $FreeBSD$
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
2015-08-14 14:58:04 +00:00
|
|
|
* It'd be nice to automatically generate the syscall symbols, but we
|
|
|
|
* don't know to what version they will eventually belong to, so for now
|
2007-04-29 14:05:22 +00:00
|
|
|
* it has to be manual.
|
|
|
|
*/
|
2006-03-13 00:53:21 +00:00
|
|
|
FBSD_1.0 {
|
|
|
|
__acl_aclcheck_fd;
|
|
|
|
__acl_aclcheck_file;
|
|
|
|
__acl_aclcheck_link;
|
|
|
|
__acl_delete_fd;
|
|
|
|
__acl_delete_file;
|
|
|
|
__acl_delete_link;
|
|
|
|
__acl_get_fd;
|
|
|
|
__acl_get_file;
|
|
|
|
__acl_get_link;
|
|
|
|
__acl_set_fd;
|
|
|
|
__acl_set_file;
|
|
|
|
__acl_set_link;
|
|
|
|
__getcwd;
|
|
|
|
__mac_execve;
|
|
|
|
__mac_get_fd;
|
|
|
|
__mac_get_file;
|
|
|
|
__mac_get_link;
|
|
|
|
__mac_get_pid;
|
|
|
|
__mac_get_proc;
|
|
|
|
__mac_set_fd;
|
|
|
|
__mac_set_file;
|
|
|
|
__mac_set_link;
|
|
|
|
__mac_set_proc;
|
|
|
|
__setugid;
|
|
|
|
__syscall;
|
|
|
|
__sysctl;
|
|
|
|
_umtx_op;
|
|
|
|
abort2;
|
|
|
|
accept;
|
|
|
|
access;
|
|
|
|
acct;
|
|
|
|
adjtime;
|
|
|
|
aio_cancel;
|
|
|
|
aio_error;
|
2006-07-23 13:08:54 +00:00
|
|
|
aio_fsync;
|
2006-03-13 00:53:21 +00:00
|
|
|
aio_read;
|
|
|
|
aio_return;
|
|
|
|
aio_suspend;
|
|
|
|
aio_waitcomplete;
|
|
|
|
aio_write;
|
|
|
|
audit;
|
|
|
|
auditctl;
|
|
|
|
auditon;
|
|
|
|
bind;
|
|
|
|
chdir;
|
|
|
|
chflags;
|
|
|
|
chmod;
|
|
|
|
chown;
|
|
|
|
chroot;
|
|
|
|
clock_getres;
|
|
|
|
clock_gettime;
|
|
|
|
clock_settime;
|
|
|
|
close;
|
|
|
|
connect;
|
|
|
|
dup;
|
|
|
|
dup2;
|
|
|
|
eaccess;
|
|
|
|
execve;
|
|
|
|
extattr_delete_fd;
|
|
|
|
extattr_delete_file;
|
|
|
|
extattr_delete_link;
|
|
|
|
extattr_get_fd;
|
|
|
|
extattr_get_file;
|
|
|
|
extattr_get_link;
|
|
|
|
extattr_list_fd;
|
|
|
|
extattr_list_file;
|
|
|
|
extattr_list_link;
|
|
|
|
extattr_set_fd;
|
|
|
|
extattr_set_file;
|
|
|
|
extattr_set_link;
|
|
|
|
extattrctl;
|
|
|
|
fchdir;
|
|
|
|
fchflags;
|
|
|
|
fchmod;
|
|
|
|
fchown;
|
|
|
|
fcntl;
|
|
|
|
fhopen;
|
|
|
|
flock;
|
|
|
|
fork;
|
|
|
|
fpathconf;
|
|
|
|
fsync;
|
|
|
|
futimes;
|
|
|
|
getaudit;
|
|
|
|
getaudit_addr;
|
|
|
|
getauid;
|
|
|
|
getcontext;
|
|
|
|
getdtablesize;
|
|
|
|
getegid;
|
|
|
|
geteuid;
|
|
|
|
getfh;
|
|
|
|
getgid;
|
|
|
|
getgroups;
|
|
|
|
getitimer;
|
|
|
|
getpeername;
|
|
|
|
getpgid;
|
|
|
|
getpgrp;
|
|
|
|
getpid;
|
|
|
|
getppid;
|
|
|
|
getpriority;
|
|
|
|
getresgid;
|
|
|
|
getresuid;
|
|
|
|
getrlimit;
|
|
|
|
getrusage;
|
|
|
|
getsid;
|
|
|
|
getsockname;
|
|
|
|
getsockopt;
|
|
|
|
gettimeofday;
|
|
|
|
getuid;
|
|
|
|
ioctl;
|
|
|
|
issetugid;
|
|
|
|
jail;
|
|
|
|
jail_attach;
|
|
|
|
kenv;
|
|
|
|
kill;
|
|
|
|
kldfind;
|
|
|
|
kldfirstmod;
|
|
|
|
kldload;
|
|
|
|
kldnext;
|
|
|
|
kldstat;
|
|
|
|
kldsym;
|
|
|
|
kldunload;
|
|
|
|
kldunloadf;
|
|
|
|
kqueue;
|
2007-05-28 11:36:43 +00:00
|
|
|
kmq_notify; /* Do we want these to be public interfaces? */
|
2007-04-29 14:05:22 +00:00
|
|
|
kmq_open; /* librt uses them to provide mq_xxx. */
|
2006-03-13 00:53:21 +00:00
|
|
|
kmq_setattr;
|
|
|
|
kmq_timedreceive;
|
|
|
|
kmq_timedsend;
|
|
|
|
kmq_unlink;
|
|
|
|
ksem_close;
|
|
|
|
ksem_destroy;
|
|
|
|
ksem_getvalue;
|
|
|
|
ksem_init;
|
|
|
|
ksem_open;
|
|
|
|
ksem_post;
|
|
|
|
ksem_timedwait;
|
|
|
|
ksem_trywait;
|
|
|
|
ksem_unlink;
|
|
|
|
ksem_wait;
|
|
|
|
ktrace;
|
|
|
|
lchflags;
|
|
|
|
lchmod;
|
|
|
|
lchown;
|
|
|
|
lgetfh;
|
|
|
|
link;
|
|
|
|
lio_listio;
|
|
|
|
listen;
|
|
|
|
lutimes;
|
|
|
|
mac_syscall;
|
|
|
|
madvise;
|
|
|
|
mincore;
|
|
|
|
minherit;
|
|
|
|
mkdir;
|
|
|
|
mkfifo;
|
|
|
|
mlock;
|
|
|
|
mlockall;
|
|
|
|
modfind;
|
|
|
|
modfnext;
|
|
|
|
modnext;
|
|
|
|
modstat;
|
|
|
|
mount;
|
|
|
|
mprotect;
|
|
|
|
msgget;
|
|
|
|
msgrcv;
|
|
|
|
msgsnd;
|
|
|
|
msgsys;
|
|
|
|
msync;
|
|
|
|
munlock;
|
|
|
|
munlockall;
|
|
|
|
munmap;
|
|
|
|
nanosleep;
|
|
|
|
nfssvc;
|
|
|
|
nmount;
|
|
|
|
ntp_adjtime;
|
|
|
|
ntp_gettime;
|
|
|
|
open;
|
|
|
|
pathconf;
|
|
|
|
pipe;
|
|
|
|
poll;
|
Integrate the new MPSAFE TTY layer to the FreeBSD operating system.
The last half year I've been working on a replacement TTY layer for the
FreeBSD kernel. The new TTY layer was designed to improve the following:
- Improved driver model:
The old TTY layer has a driver model that is not abstract enough to
make it friendly to use. A good example is the output path, where the
device drivers directly access the output buffers. This means that an
in-kernel PPP implementation must always convert network buffers into
TTY buffers.
If a PPP implementation would be built on top of the new TTY layer
(still needs a hooks layer, though), it would allow the PPP
implementation to directly hand the data to the TTY driver.
- Improved hotplugging:
With the old TTY layer, it isn't entirely safe to destroy TTY's from
the system. This implementation has a two-step destructing design,
where the driver first abandons the TTY. After all threads have left
the TTY, the TTY layer calls a routine in the driver, which can be
used to free resources (unit numbers, etc).
The pts(4) driver also implements this feature, which means
posix_openpt() will now return PTY's that are created on the fly.
- Improved performance:
One of the major improvements is the per-TTY mutex, which is expected
to improve scalability when compared to the old Giant locking.
Another change is the unbuffered copying to userspace, which is both
used on TTY device nodes and PTY masters.
Upgrading should be quite straightforward. Unlike previous versions,
existing kernel configuration files do not need to be changed, except
when they reference device drivers that are listed in UPDATING.
Obtained from: //depot/projects/mpsafetty/...
Approved by: philip (ex-mentor)
Discussed: on the lists, at BSDCan, at the DevSummit
Sponsored by: Snow B.V., the Netherlands
dcons(4) fixed by: kan
2008-08-20 08:31:58 +00:00
|
|
|
posix_openpt;
|
2006-03-13 00:53:21 +00:00
|
|
|
preadv;
|
|
|
|
profil;
|
2009-10-27 10:55:34 +00:00
|
|
|
pselect;
|
2006-03-13 00:53:21 +00:00
|
|
|
ptrace;
|
|
|
|
pwritev;
|
|
|
|
quotactl;
|
|
|
|
read;
|
|
|
|
readlink;
|
|
|
|
readv;
|
|
|
|
reboot;
|
|
|
|
recvfrom;
|
|
|
|
recvmsg;
|
|
|
|
rename;
|
|
|
|
revoke;
|
|
|
|
rfork;
|
|
|
|
rmdir;
|
|
|
|
rtprio;
|
2006-09-21 04:22:46 +00:00
|
|
|
rtprio_thread;
|
2006-03-13 00:53:21 +00:00
|
|
|
sched_get_priority_max;
|
|
|
|
sched_get_priority_min;
|
|
|
|
sched_getparam;
|
|
|
|
sched_getscheduler;
|
|
|
|
sched_rr_get_interval;
|
|
|
|
sched_setparam;
|
|
|
|
sched_setscheduler;
|
|
|
|
sched_yield;
|
|
|
|
select;
|
|
|
|
semget;
|
|
|
|
semop;
|
|
|
|
semsys;
|
|
|
|
sendfile;
|
|
|
|
sendmsg;
|
|
|
|
sendto;
|
|
|
|
setaudit;
|
|
|
|
setaudit_addr;
|
|
|
|
setauid;
|
|
|
|
setegid;
|
|
|
|
seteuid;
|
|
|
|
setgid;
|
|
|
|
setgroups;
|
|
|
|
setitimer;
|
|
|
|
setlogin;
|
|
|
|
setpgid;
|
|
|
|
setpriority;
|
|
|
|
setregid;
|
|
|
|
setresgid;
|
|
|
|
setresuid;
|
|
|
|
setreuid;
|
|
|
|
setrlimit;
|
|
|
|
setsid;
|
|
|
|
setsockopt;
|
|
|
|
settimeofday;
|
|
|
|
setuid;
|
2009-04-02 15:53:29 +00:00
|
|
|
shm_open;
|
|
|
|
shm_unlink;
|
2006-03-13 00:53:21 +00:00
|
|
|
shmat;
|
|
|
|
shmdt;
|
|
|
|
shmget;
|
|
|
|
shmsys;
|
|
|
|
shutdown;
|
|
|
|
sigaction;
|
|
|
|
sigaltstack;
|
|
|
|
sigpending;
|
|
|
|
sigprocmask;
|
|
|
|
sigqueue;
|
|
|
|
sigreturn;
|
|
|
|
sigsuspend;
|
|
|
|
sigtimedwait;
|
|
|
|
sigwait;
|
|
|
|
sigwaitinfo;
|
|
|
|
socket;
|
|
|
|
socketpair;
|
|
|
|
swapon;
|
|
|
|
symlink;
|
|
|
|
sync;
|
|
|
|
sysarch;
|
|
|
|
syscall;
|
|
|
|
thr_create;
|
|
|
|
thr_exit;
|
|
|
|
thr_kill;
|
2007-08-22 01:56:35 +00:00
|
|
|
thr_kill2;
|
2006-03-13 00:53:21 +00:00
|
|
|
thr_new;
|
|
|
|
thr_self;
|
|
|
|
thr_set_name;
|
|
|
|
thr_suspend;
|
|
|
|
thr_wake;
|
2007-05-28 11:36:43 +00:00
|
|
|
ktimer_create; /* Do we want these to be public interfaces? */
|
2007-04-29 14:05:22 +00:00
|
|
|
ktimer_delete; /* librt uses them to provide timer_xxx. */
|
2006-03-13 00:53:21 +00:00
|
|
|
ktimer_getoverrun;
|
|
|
|
ktimer_gettime;
|
|
|
|
ktimer_settime;
|
|
|
|
umask;
|
|
|
|
undelete;
|
|
|
|
unlink;
|
|
|
|
unmount;
|
|
|
|
utimes;
|
|
|
|
utrace;
|
|
|
|
uuidgen;
|
|
|
|
vadvise;
|
|
|
|
wait4;
|
|
|
|
write;
|
|
|
|
writev;
|
|
|
|
|
|
|
|
__error;
|
|
|
|
ftruncate;
|
|
|
|
lseek;
|
|
|
|
mmap;
|
|
|
|
pread;
|
|
|
|
pwrite;
|
|
|
|
truncate;
|
|
|
|
};
|
|
|
|
|
2008-03-31 12:14:04 +00:00
|
|
|
FBSD_1.1 {
|
2009-06-24 21:10:52 +00:00
|
|
|
__semctl;
|
2009-06-15 20:38:55 +00:00
|
|
|
closefrom;
|
2008-04-07 13:53:51 +00:00
|
|
|
cpuset;
|
|
|
|
cpuset_getid;
|
|
|
|
cpuset_setid;
|
|
|
|
cpuset_getaffinity;
|
|
|
|
cpuset_setaffinity;
|
2008-03-31 12:14:04 +00:00
|
|
|
faccessat;
|
|
|
|
fchmodat;
|
|
|
|
fchownat;
|
|
|
|
fexecve;
|
|
|
|
futimesat;
|
2009-04-29 21:14:15 +00:00
|
|
|
jail_get;
|
|
|
|
jail_set;
|
|
|
|
jail_remove;
|
2008-03-31 12:14:04 +00:00
|
|
|
linkat;
|
2009-07-08 15:23:18 +00:00
|
|
|
lpathconf;
|
2008-03-31 12:14:04 +00:00
|
|
|
mkdirat;
|
|
|
|
mkfifoat;
|
2009-06-24 21:10:52 +00:00
|
|
|
msgctl;
|
2008-03-31 12:14:04 +00:00
|
|
|
readlinkat;
|
|
|
|
renameat;
|
Add code to allow the system to handle multiple routing tables.
This particular implementation is designed to be fully backwards compatible
and to be MFC-able to 7.x (and 6.x)
Currently the only protocol that can make use of the multiple tables is IPv4
Similar functionality exists in OpenBSD and Linux.
From my notes:
-----
One thing where FreeBSD has been falling behind, and which by chance I
have some time to work on is "policy based routing", which allows
different
packet streams to be routed by more than just the destination address.
Constraints:
------------
I want to make some form of this available in the 6.x tree
(and by extension 7.x) , but FreeBSD in general needs it so I might as
well do it in -current and back port the portions I need.
One of the ways that this can be done is to have the ability to
instantiate multiple kernel routing tables (which I will now
refer to as "Forwarding Information Bases" or "FIBs" for political
correctness reasons). Which FIB a particular packet uses to make
the next hop decision can be decided by a number of mechanisms.
The policies these mechanisms implement are the "Policies" referred
to in "Policy based routing".
One of the constraints I have if I try to back port this work to
6.x is that it must be implemented as a EXTENSION to the existing
ABIs in 6.x so that third party applications do not need to be
recompiled in timespan of the branch.
This first version will not have some of the bells and whistles that
will come with later versions. It will, for example, be limited to 16
tables in the first commit.
Implementation method, Compatible version. (part 1)
-------------------------------
For this reason I have implemented a "sufficient subset" of a
multiple routing table solution in Perforce, and back-ported it
to 6.x. (also in Perforce though not always caught up with what I
have done in -current/P4). The subset allows a number of FIBs
to be defined at compile time (8 is sufficient for my purposes in 6.x)
and implements the changes needed to allow IPV4 to use them. I have not
done the changes for ipv6 simply because I do not need it, and I do not
have enough knowledge of ipv6 (e.g. neighbor discovery) needed to do it.
Other protocol families are left untouched and should there be
users with proprietary protocol families, they should continue to work
and be oblivious to the existence of the extra FIBs.
To understand how this is done, one must know that the current FIB
code starts everything off with a single dimensional array of
pointers to FIB head structures (One per protocol family), each of
which in turn points to the trie of routes available to that family.
The basic change in the ABI compatible version of the change is to
extent that array to be a 2 dimensional array, so that
instead of protocol family X looking at rt_tables[X] for the
table it needs, it looks at rt_tables[Y][X] when for all
protocol families except ipv4 Y is always 0.
Code that is unaware of the change always just sees the first row
of the table, which of course looks just like the one dimensional
array that existed before.
The entry points rtrequest(), rtalloc(), rtalloc1(), rtalloc_ign()
are all maintained, but refer only to the first row of the array,
so that existing callers in proprietary protocols can continue to
do the "right thing".
Some new entry points are added, for the exclusive use of ipv4 code
called in_rtrequest(), in_rtalloc(), in_rtalloc1() and in_rtalloc_ign(),
which have an extra argument which refers the code to the correct row.
In addition, there are some new entry points (currently called
rtalloc_fib() and friends) that check the Address family being
looked up and call either rtalloc() (and friends) if the protocol
is not IPv4 forcing the action to row 0 or to the appropriate row
if it IS IPv4 (and that info is available). These are for calling
from code that is not specific to any particular protocol. The way
these are implemented would change in the non ABI preserving code
to be added later.
One feature of the first version of the code is that for ipv4,
the interface routes show up automatically on all the FIBs, so
that no matter what FIB you select you always have the basic
direct attached hosts available to you. (rtinit() does this
automatically).
You CAN delete an interface route from one FIB should you want
to but by default it's there. ARP information is also available
in each FIB. It's assumed that the same machine would have the
same MAC address, regardless of which FIB you are using to get
to it.
This brings us as to how the correct FIB is selected for an outgoing
IPV4 packet.
Firstly, all packets have a FIB associated with them. if nothing
has been done to change it, it will be FIB 0. The FIB is changed
in the following ways.
Packets fall into one of a number of classes.
1/ locally generated packets, coming from a socket/PCB.
Such packets select a FIB from a number associated with the
socket/PCB. This in turn is inherited from the process,
but can be changed by a socket option. The process in turn
inherits it on fork. I have written a utility call setfib
that acts a bit like nice..
setfib -3 ping target.example.com # will use fib 3 for ping.
It is an obvious extension to make it a property of a jail
but I have not done so. It can be achieved by combining the setfib and
jail commands.
2/ packets received on an interface for forwarding.
By default these packets would use table 0,
(or possibly a number settable in a sysctl(not yet)).
but prior to routing the firewall can inspect them (see below).
(possibly in the future you may be able to associate a FIB
with packets received on an interface.. An ifconfig arg, but not yet.)
3/ packets inspected by a packet classifier, which can arbitrarily
associate a fib with it on a packet by packet basis.
A fib assigned to a packet by a packet classifier
(such as ipfw) would over-ride a fib associated by
a more default source. (such as cases 1 or 2).
4/ a tcp listen socket associated with a fib will generate
accept sockets that are associated with that same fib.
5/ Packets generated in response to some other packet (e.g. reset
or icmp packets). These should use the FIB associated with the
packet being reponded to.
6/ Packets generated during encapsulation.
gif, tun and other tunnel interfaces will encapsulate using the FIB
that was in effect withthe proces that set up the tunnel.
thus setfib 1 ifconfig gif0 [tunnel instructions]
will set the fib for the tunnel to use to be fib 1.
Routing messages would be associated with their
process, and thus select one FIB or another.
messages from the kernel would be associated with the fib they
refer to and would only be received by a routing socket associated
with that fib. (not yet implemented)
In addition Netstat has been edited to be able to cope with the
fact that the array is now 2 dimensional. (It looks in system
memory using libkvm (!)). Old versions of netstat see only the first FIB.
In addition two sysctls are added to give:
a) the number of FIBs compiled in (active)
b) the default FIB of the calling process.
Early testing experience:
-------------------------
Basically our (IronPort's) appliance does this functionality already
using ipfw fwd but that method has some drawbacks.
For example,
It can't fully simulate a routing table because it can't influence the
socket's choice of local address when a connect() is done.
Testing during the generating of these changes has been
remarkably smooth so far. Multiple tables have co-existed
with no notable side effects, and packets have been routes
accordingly.
ipfw has grown 2 new keywords:
setfib N ip from anay to any
count ip from any to any fib N
In pf there seems to be a requirement to be able to give symbolic names to the
fibs but I do not have that capacity. I am not sure if it is required.
SCTP has interestingly enough built in support for this, called VRFs
in Cisco parlance. it will be interesting to see how that handles it
when it suddenly actually does something.
Where to next:
--------------------
After committing the ABI compatible version and MFCing it, I'd
like to proceed in a forward direction in -current. this will
result in some roto-tilling in the routing code.
Firstly: the current code's idea of having a separate tree per
protocol family, all of the same format, and pointed to by the
1 dimensional array is a bit silly. Especially when one considers that
there is code that makes assumptions about every protocol having the
same internal structures there. Some protocols don't WANT that
sort of structure. (for example the whole idea of a netmask is foreign
to appletalk). This needs to be made opaque to the external code.
My suggested first change is to add routing method pointers to the
'domain' structure, along with information pointing the data.
instead of having an array of pointers to uniform structures,
there would be an array pointing to the 'domain' structures
for each protocol address domain (protocol family),
and the methods this reached would be called. The methods would have
an argument that gives FIB number, but the protocol would be free
to ignore it.
When the ABI can be changed it raises the possibilty of the
addition of a fib entry into the "struct route". Currently,
the structure contains the sockaddr of the desination, and the resulting
fib entry. To make this work fully, one could add a fib number
so that given an address and a fib, one can find the third element, the
fib entry.
Interaction with the ARP layer/ LL layer would need to be
revisited as well. Qing Li has been working on this already.
This work was sponsored by Ironport Systems/Cisco
PR:
Reviewed by: several including rwatson, bz and mlair (parts each)
Approved by:
Obtained from: Ironport systems/Cisco
MFC after:
Security:
PR:
Submitted by:
Reviewed by:
Approved by:
Obtained from:
MFC after:
Security:
2008-05-09 23:00:21 +00:00
|
|
|
setfib;
|
2009-06-24 21:10:52 +00:00
|
|
|
shmctl;
|
2008-03-31 12:14:04 +00:00
|
|
|
symlinkat;
|
|
|
|
unlinkat;
|
|
|
|
};
|
|
|
|
|
2011-03-06 08:52:59 +00:00
|
|
|
FBSD_1.2 {
|
2011-03-12 12:10:17 +00:00
|
|
|
cap_enter;
|
|
|
|
cap_getmode;
|
2011-03-06 08:55:36 +00:00
|
|
|
getloginclass;
|
Add experimental support for process descriptors
A "process descriptor" file descriptor is used to manage processes
without using the PID namespace. This is required for Capsicum's
Capability Mode, where the PID namespace is unavailable.
New system calls pdfork(2) and pdkill(2) offer the functional equivalents
of fork(2) and kill(2). pdgetpid(2) allows querying the PID of the remote
process for debugging purposes. The currently-unimplemented pdwait(2) will,
in the future, allow querying rusage/exit status. In the interim, poll(2)
may be used to check (and wait for) process termination.
When a process is referenced by a process descriptor, it does not issue
SIGCHLD to the parent, making it suitable for use in libraries---a common
scenario when using library compartmentalisation from within large
applications (such as web browsers). Some observers may note a similarity
to Mach task ports; process descriptors provide a subset of this behaviour,
but in a UNIX style.
This feature is enabled by "options PROCDESC", but as with several other
Capsicum kernel features, is not enabled by default in GENERIC 9.0.
Reviewed by: jhb, kib
Approved by: re (kib), mentor (rwatson)
Sponsored by: Google Inc
2011-08-18 22:51:30 +00:00
|
|
|
pdfork;
|
|
|
|
pdgetpid;
|
|
|
|
pdkill;
|
2011-04-18 16:32:22 +00:00
|
|
|
posix_fallocate;
|
2011-03-30 18:08:31 +00:00
|
|
|
rctl_get_racct;
|
|
|
|
rctl_get_rules;
|
|
|
|
rctl_get_limits;
|
|
|
|
rctl_add_rule;
|
|
|
|
rctl_remove_rule;
|
2011-03-06 08:55:36 +00:00
|
|
|
setloginclass;
|
2011-03-06 08:52:59 +00:00
|
|
|
};
|
|
|
|
|
2011-11-04 04:02:50 +00:00
|
|
|
FBSD_1.3 {
|
2013-05-01 20:10:21 +00:00
|
|
|
accept4;
|
2013-06-08 13:27:57 +00:00
|
|
|
aio_mlock;
|
2013-03-02 21:11:30 +00:00
|
|
|
bindat;
|
Merge Capsicum overhaul:
- Capability is no longer separate descriptor type. Now every descriptor
has set of its own capability rights.
- The cap_new(2) system call is left, but it is no longer documented and
should not be used in new code.
- The new syscall cap_rights_limit(2) should be used instead of
cap_new(2), which limits capability rights of the given descriptor
without creating a new one.
- The cap_getrights(2) syscall is renamed to cap_rights_get(2).
- If CAP_IOCTL capability right is present we can further reduce allowed
ioctls list with the new cap_ioctls_limit(2) syscall. List of allowed
ioctls can be retrived with cap_ioctls_get(2) syscall.
- If CAP_FCNTL capability right is present we can further reduce fcntls
that can be used with the new cap_fcntls_limit(2) syscall and retrive
them with cap_fcntls_get(2).
- To support ioctl and fcntl white-listing the filedesc structure was
heavly modified.
- The audit subsystem, kdump and procstat tools were updated to
recognize new syscalls.
- Capability rights were revised and eventhough I tried hard to provide
backward API and ABI compatibility there are some incompatible changes
that are described in detail below:
CAP_CREATE old behaviour:
- Allow for openat(2)+O_CREAT.
- Allow for linkat(2).
- Allow for symlinkat(2).
CAP_CREATE new behaviour:
- Allow for openat(2)+O_CREAT.
Added CAP_LINKAT:
- Allow for linkat(2). ABI: Reuses CAP_RMDIR bit.
- Allow to be target for renameat(2).
Added CAP_SYMLINKAT:
- Allow for symlinkat(2).
Removed CAP_DELETE. Old behaviour:
- Allow for unlinkat(2) when removing non-directory object.
- Allow to be source for renameat(2).
Removed CAP_RMDIR. Old behaviour:
- Allow for unlinkat(2) when removing directory.
Added CAP_RENAMEAT:
- Required for source directory for the renameat(2) syscall.
Added CAP_UNLINKAT (effectively it replaces CAP_DELETE and CAP_RMDIR):
- Allow for unlinkat(2) on any object.
- Required if target of renameat(2) exists and will be removed by this
call.
Removed CAP_MAPEXEC.
CAP_MMAP old behaviour:
- Allow for mmap(2) with any combination of PROT_NONE, PROT_READ and
PROT_WRITE.
CAP_MMAP new behaviour:
- Allow for mmap(2)+PROT_NONE.
Added CAP_MMAP_R:
- Allow for mmap(PROT_READ).
Added CAP_MMAP_W:
- Allow for mmap(PROT_WRITE).
Added CAP_MMAP_X:
- Allow for mmap(PROT_EXEC).
Added CAP_MMAP_RW:
- Allow for mmap(PROT_READ | PROT_WRITE).
Added CAP_MMAP_RX:
- Allow for mmap(PROT_READ | PROT_EXEC).
Added CAP_MMAP_WX:
- Allow for mmap(PROT_WRITE | PROT_EXEC).
Added CAP_MMAP_RWX:
- Allow for mmap(PROT_READ | PROT_WRITE | PROT_EXEC).
Renamed CAP_MKDIR to CAP_MKDIRAT.
Renamed CAP_MKFIFO to CAP_MKFIFOAT.
Renamed CAP_MKNODE to CAP_MKNODEAT.
CAP_READ old behaviour:
- Allow pread(2).
- Disallow read(2), readv(2) (if there is no CAP_SEEK).
CAP_READ new behaviour:
- Allow read(2), readv(2).
- Disallow pread(2) (CAP_SEEK was also required).
CAP_WRITE old behaviour:
- Allow pwrite(2).
- Disallow write(2), writev(2) (if there is no CAP_SEEK).
CAP_WRITE new behaviour:
- Allow write(2), writev(2).
- Disallow pwrite(2) (CAP_SEEK was also required).
Added convinient defines:
#define CAP_PREAD (CAP_SEEK | CAP_READ)
#define CAP_PWRITE (CAP_SEEK | CAP_WRITE)
#define CAP_MMAP_R (CAP_MMAP | CAP_SEEK | CAP_READ)
#define CAP_MMAP_W (CAP_MMAP | CAP_SEEK | CAP_WRITE)
#define CAP_MMAP_X (CAP_MMAP | CAP_SEEK | 0x0000000000000008ULL)
#define CAP_MMAP_RW (CAP_MMAP_R | CAP_MMAP_W)
#define CAP_MMAP_RX (CAP_MMAP_R | CAP_MMAP_X)
#define CAP_MMAP_WX (CAP_MMAP_W | CAP_MMAP_X)
#define CAP_MMAP_RWX (CAP_MMAP_R | CAP_MMAP_W | CAP_MMAP_X)
#define CAP_RECV CAP_READ
#define CAP_SEND CAP_WRITE
#define CAP_SOCK_CLIENT \
(CAP_CONNECT | CAP_GETPEERNAME | CAP_GETSOCKNAME | CAP_GETSOCKOPT | \
CAP_PEELOFF | CAP_RECV | CAP_SEND | CAP_SETSOCKOPT | CAP_SHUTDOWN)
#define CAP_SOCK_SERVER \
(CAP_ACCEPT | CAP_BIND | CAP_GETPEERNAME | CAP_GETSOCKNAME | \
CAP_GETSOCKOPT | CAP_LISTEN | CAP_PEELOFF | CAP_RECV | CAP_SEND | \
CAP_SETSOCKOPT | CAP_SHUTDOWN)
Added defines for backward API compatibility:
#define CAP_MAPEXEC CAP_MMAP_X
#define CAP_DELETE CAP_UNLINKAT
#define CAP_MKDIR CAP_MKDIRAT
#define CAP_RMDIR CAP_UNLINKAT
#define CAP_MKFIFO CAP_MKFIFOAT
#define CAP_MKNOD CAP_MKNODAT
#define CAP_SOCK_ALL (CAP_SOCK_CLIENT | CAP_SOCK_SERVER)
Sponsored by: The FreeBSD Foundation
Reviewed by: Christoph Mallon <christoph.mallon@gmx.de>
Many aspects discussed with: rwatson, benl, jonathan
ABI compatibility discussed with: kib
2013-03-02 00:53:12 +00:00
|
|
|
cap_fcntls_get;
|
|
|
|
cap_fcntls_limit;
|
|
|
|
cap_ioctls_get;
|
|
|
|
cap_ioctls_limit;
|
Change the cap_rights_t type from uint64_t to a structure that we can extend
in the future in a backward compatible (API and ABI) way.
The cap_rights_t represents capability rights. We used to use one bit to
represent one right, but we are running out of spare bits. Currently the new
structure provides place for 114 rights (so 50 more than the previous
cap_rights_t), but it is possible to grow the structure to hold at least 285
rights, although we can make it even larger if 285 rights won't be enough.
The structure definition looks like this:
struct cap_rights {
uint64_t cr_rights[CAP_RIGHTS_VERSION + 2];
};
The initial CAP_RIGHTS_VERSION is 0.
The top two bits in the first element of the cr_rights[] array contain total
number of elements in the array - 2. This means if those two bits are equal to
0, we have 2 array elements.
The top two bits in all remaining array elements should be 0.
The next five bits in all array elements contain array index. Only one bit is
used and bit position in this five-bits range defines array index. This means
there can be at most five array elements in the future.
To define new right the CAPRIGHT() macro must be used. The macro takes two
arguments - an array index and a bit to set, eg.
#define CAP_PDKILL CAPRIGHT(1, 0x0000000000000800ULL)
We still support aliases that combine few rights, but the rights have to belong
to the same array element, eg:
#define CAP_LOOKUP CAPRIGHT(0, 0x0000000000000400ULL)
#define CAP_FCHMOD CAPRIGHT(0, 0x0000000000002000ULL)
#define CAP_FCHMODAT (CAP_FCHMOD | CAP_LOOKUP)
There is new API to manage the new cap_rights_t structure:
cap_rights_t *cap_rights_init(cap_rights_t *rights, ...);
void cap_rights_set(cap_rights_t *rights, ...);
void cap_rights_clear(cap_rights_t *rights, ...);
bool cap_rights_is_set(const cap_rights_t *rights, ...);
bool cap_rights_is_valid(const cap_rights_t *rights);
void cap_rights_merge(cap_rights_t *dst, const cap_rights_t *src);
void cap_rights_remove(cap_rights_t *dst, const cap_rights_t *src);
bool cap_rights_contains(const cap_rights_t *big, const cap_rights_t *little);
Capability rights to the cap_rights_init(), cap_rights_set(),
cap_rights_clear() and cap_rights_is_set() functions are provided by
separating them with commas, eg:
cap_rights_t rights;
cap_rights_init(&rights, CAP_READ, CAP_WRITE, CAP_FSTAT);
There is no need to terminate the list of rights, as those functions are
actually macros that take care of the termination, eg:
#define cap_rights_set(rights, ...) \
__cap_rights_set((rights), __VA_ARGS__, 0ULL)
void __cap_rights_set(cap_rights_t *rights, ...);
Thanks to using one bit as an array index we can assert in those functions that
there are no two rights belonging to different array elements provided
together. For example this is illegal and will be detected, because CAP_LOOKUP
belongs to element 0 and CAP_PDKILL to element 1:
cap_rights_init(&rights, CAP_LOOKUP | CAP_PDKILL);
Providing several rights that belongs to the same array's element this way is
correct, but is not advised. It should only be used for aliases definition.
This commit also breaks compatibility with some existing Capsicum system calls,
but I see no other way to do that. This should be fine as Capsicum is still
experimental and this change is not going to 9.x.
Sponsored by: The FreeBSD Foundation
2013-09-05 00:09:56 +00:00
|
|
|
__cap_rights_get;
|
Merge Capsicum overhaul:
- Capability is no longer separate descriptor type. Now every descriptor
has set of its own capability rights.
- The cap_new(2) system call is left, but it is no longer documented and
should not be used in new code.
- The new syscall cap_rights_limit(2) should be used instead of
cap_new(2), which limits capability rights of the given descriptor
without creating a new one.
- The cap_getrights(2) syscall is renamed to cap_rights_get(2).
- If CAP_IOCTL capability right is present we can further reduce allowed
ioctls list with the new cap_ioctls_limit(2) syscall. List of allowed
ioctls can be retrived with cap_ioctls_get(2) syscall.
- If CAP_FCNTL capability right is present we can further reduce fcntls
that can be used with the new cap_fcntls_limit(2) syscall and retrive
them with cap_fcntls_get(2).
- To support ioctl and fcntl white-listing the filedesc structure was
heavly modified.
- The audit subsystem, kdump and procstat tools were updated to
recognize new syscalls.
- Capability rights were revised and eventhough I tried hard to provide
backward API and ABI compatibility there are some incompatible changes
that are described in detail below:
CAP_CREATE old behaviour:
- Allow for openat(2)+O_CREAT.
- Allow for linkat(2).
- Allow for symlinkat(2).
CAP_CREATE new behaviour:
- Allow for openat(2)+O_CREAT.
Added CAP_LINKAT:
- Allow for linkat(2). ABI: Reuses CAP_RMDIR bit.
- Allow to be target for renameat(2).
Added CAP_SYMLINKAT:
- Allow for symlinkat(2).
Removed CAP_DELETE. Old behaviour:
- Allow for unlinkat(2) when removing non-directory object.
- Allow to be source for renameat(2).
Removed CAP_RMDIR. Old behaviour:
- Allow for unlinkat(2) when removing directory.
Added CAP_RENAMEAT:
- Required for source directory for the renameat(2) syscall.
Added CAP_UNLINKAT (effectively it replaces CAP_DELETE and CAP_RMDIR):
- Allow for unlinkat(2) on any object.
- Required if target of renameat(2) exists and will be removed by this
call.
Removed CAP_MAPEXEC.
CAP_MMAP old behaviour:
- Allow for mmap(2) with any combination of PROT_NONE, PROT_READ and
PROT_WRITE.
CAP_MMAP new behaviour:
- Allow for mmap(2)+PROT_NONE.
Added CAP_MMAP_R:
- Allow for mmap(PROT_READ).
Added CAP_MMAP_W:
- Allow for mmap(PROT_WRITE).
Added CAP_MMAP_X:
- Allow for mmap(PROT_EXEC).
Added CAP_MMAP_RW:
- Allow for mmap(PROT_READ | PROT_WRITE).
Added CAP_MMAP_RX:
- Allow for mmap(PROT_READ | PROT_EXEC).
Added CAP_MMAP_WX:
- Allow for mmap(PROT_WRITE | PROT_EXEC).
Added CAP_MMAP_RWX:
- Allow for mmap(PROT_READ | PROT_WRITE | PROT_EXEC).
Renamed CAP_MKDIR to CAP_MKDIRAT.
Renamed CAP_MKFIFO to CAP_MKFIFOAT.
Renamed CAP_MKNODE to CAP_MKNODEAT.
CAP_READ old behaviour:
- Allow pread(2).
- Disallow read(2), readv(2) (if there is no CAP_SEEK).
CAP_READ new behaviour:
- Allow read(2), readv(2).
- Disallow pread(2) (CAP_SEEK was also required).
CAP_WRITE old behaviour:
- Allow pwrite(2).
- Disallow write(2), writev(2) (if there is no CAP_SEEK).
CAP_WRITE new behaviour:
- Allow write(2), writev(2).
- Disallow pwrite(2) (CAP_SEEK was also required).
Added convinient defines:
#define CAP_PREAD (CAP_SEEK | CAP_READ)
#define CAP_PWRITE (CAP_SEEK | CAP_WRITE)
#define CAP_MMAP_R (CAP_MMAP | CAP_SEEK | CAP_READ)
#define CAP_MMAP_W (CAP_MMAP | CAP_SEEK | CAP_WRITE)
#define CAP_MMAP_X (CAP_MMAP | CAP_SEEK | 0x0000000000000008ULL)
#define CAP_MMAP_RW (CAP_MMAP_R | CAP_MMAP_W)
#define CAP_MMAP_RX (CAP_MMAP_R | CAP_MMAP_X)
#define CAP_MMAP_WX (CAP_MMAP_W | CAP_MMAP_X)
#define CAP_MMAP_RWX (CAP_MMAP_R | CAP_MMAP_W | CAP_MMAP_X)
#define CAP_RECV CAP_READ
#define CAP_SEND CAP_WRITE
#define CAP_SOCK_CLIENT \
(CAP_CONNECT | CAP_GETPEERNAME | CAP_GETSOCKNAME | CAP_GETSOCKOPT | \
CAP_PEELOFF | CAP_RECV | CAP_SEND | CAP_SETSOCKOPT | CAP_SHUTDOWN)
#define CAP_SOCK_SERVER \
(CAP_ACCEPT | CAP_BIND | CAP_GETPEERNAME | CAP_GETSOCKNAME | \
CAP_GETSOCKOPT | CAP_LISTEN | CAP_PEELOFF | CAP_RECV | CAP_SEND | \
CAP_SETSOCKOPT | CAP_SHUTDOWN)
Added defines for backward API compatibility:
#define CAP_MAPEXEC CAP_MMAP_X
#define CAP_DELETE CAP_UNLINKAT
#define CAP_MKDIR CAP_MKDIRAT
#define CAP_RMDIR CAP_UNLINKAT
#define CAP_MKFIFO CAP_MKFIFOAT
#define CAP_MKNOD CAP_MKNODAT
#define CAP_SOCK_ALL (CAP_SOCK_CLIENT | CAP_SOCK_SERVER)
Sponsored by: The FreeBSD Foundation
Reviewed by: Christoph Mallon <christoph.mallon@gmx.de>
Many aspects discussed with: rwatson, benl, jonathan
ABI compatibility discussed with: kib
2013-03-02 00:53:12 +00:00
|
|
|
cap_rights_limit;
|
2013-03-02 00:11:27 +00:00
|
|
|
cap_sandboxed;
|
2013-03-21 22:59:01 +00:00
|
|
|
chflagsat;
|
2012-08-17 02:26:31 +00:00
|
|
|
clock_getcpuclockid2;
|
2013-03-02 21:11:30 +00:00
|
|
|
connectat;
|
2012-07-10 08:31:28 +00:00
|
|
|
ffclock_getcounter;
|
|
|
|
ffclock_getestimate;
|
|
|
|
ffclock_setestimate;
|
2013-05-01 22:42:42 +00:00
|
|
|
pipe2;
|
2011-11-04 04:02:50 +00:00
|
|
|
posix_fadvise;
|
2013-09-19 18:53:42 +00:00
|
|
|
procctl;
|
2012-11-13 12:55:52 +00:00
|
|
|
wait6;
|
2011-11-04 04:02:50 +00:00
|
|
|
};
|
|
|
|
|
2014-11-13 05:26:14 +00:00
|
|
|
FBSD_1.4 {
|
2015-01-23 21:07:08 +00:00
|
|
|
futimens;
|
2014-11-13 05:26:14 +00:00
|
|
|
ppoll;
|
2015-01-23 21:07:08 +00:00
|
|
|
utimensat;
|
Add an initial NUMA affinity/policy configuration for threads and processes.
This is based on work done by jeff@ and jhb@, as well as the numa.diff
patch that has been circulating when someone asks for first-touch NUMA
on -10 or -11.
* Introduce a simple set of VM policy and iterator types.
* tie the policy types into the vm_phys path for now, mirroring how
the initial first-touch allocation work was enabled.
* add syscalls to control changing thread and process defaults.
* add a global NUMA VM domain policy.
* implement a simple cascade policy order - if a thread policy exists, use it;
if a process policy exists, use it; use the default policy.
* processes inherit policies from their parent processes, threads inherit
policies from their parent threads.
* add a simple tool (numactl) to query and modify default thread/process
policities.
* add documentation for the new syscalls, for numa and for numactl.
* re-enable first touch NUMA again by default, as now policies can be
set in a variety of methods.
This is only relevant for very specific workloads.
This doesn't pretend to be a final NUMA solution.
The previous defaults in -HEAD (with MAXMEMDOM set) can be achieved by
'sysctl vm.default_policy=rr'.
This is only relevant if MAXMEMDOM is set to something other than 1.
Ie, if you're using GENERIC or a modified kernel with non-NUMA, then
this is a glorified no-op for you.
Thank you to Norse Corp for giving me access to rather large
(for FreeBSD!) NUMA machines in order to develop and verify this.
Thank you to Dell for providing me with dual socket sandybridge
and westmere v3 hardware to do NUMA development with.
Thank you to Scott Long at Netflix for providing me with access
to the two-socket, four-domain haswell v3 hardware.
Thank you to Peter Holm for running the stress testing suite
against the NUMA branch during various stages of development!
Tested:
* MIPS (regression testing; non-NUMA)
* i386 (regression testing; non-NUMA GENERIC)
* amd64 (regression testing; non-NUMA GENERIC)
* westmere, 2 socket (thankyou norse!)
* sandy bridge, 2 socket (thankyou dell!)
* ivy bridge, 2 socket (thankyou norse!)
* westmere-EX, 4 socket / 1TB RAM (thankyou norse!)
* haswell, 2 socket (thankyou norse!)
* haswell v3, 2 socket (thankyou dell)
* haswell v3, 2x18 core (thankyou scott long / netflix!)
* Peter Holm ran a stress test suite on this work and found one
issue, but has not been able to verify it (it doesn't look NUMA
related, and he only saw it once over many testing runs.)
* I've tested bhyve instances running in fixed NUMA domains and cpusets;
all seems to work correctly.
Verified:
* intel-pcm - pcm-numa.x and pcm-memory.x, whilst selecting different
NUMA policies for processes under test.
Review:
This was reviewed through phabricator (https://reviews.freebsd.org/D2559)
as well as privately and via emails to freebsd-arch@. The git history
with specific attributes is available at https://github.com/erikarn/freebsd/
in the NUMA branch (https://github.com/erikarn/freebsd/compare/local/adrian_numa_policy).
This has been reviewed by a number of people (stas, rpaulo, kib, ngie,
wblock) but not achieved a clear consensus. My hope is that with further
exposure and testing more functionality can be implemented and evaluated.
Notes:
* The VM doesn't handle unbalanced domains very well, and if you have an overly
unbalanced memory setup whilst under high memory pressure, VM page allocation
may fail leading to a kernel panic. This was a problem in the past, but it's
much more easily triggered now with these tools.
* This work only controls the path through vm_phys; it doesn't yet strongly/predictably
affect contigmalloc, KVA placement, UMA, etc. So, driver placement of memory
isn't really guaranteed in any way. That's next on my plate.
Sponsored by: Norse Corp, Inc.; Dell
2015-07-11 15:21:37 +00:00
|
|
|
numa_setaffinity;
|
|
|
|
numa_getaffinity;
|
2016-01-29 14:12:12 +00:00
|
|
|
sendmmsg;
|
|
|
|
recvmmsg;
|
2014-11-13 05:26:14 +00:00
|
|
|
};
|
|
|
|
|
2016-08-15 19:08:51 +00:00
|
|
|
FBSD_1.5 {
|
2017-03-20 03:47:15 +00:00
|
|
|
clock_nanosleep;
|
|
|
|
fdatasync;
|
Commit the 64-bit inode project.
Extend the ino_t, dev_t, nlink_t types to 64-bit ints. Modify
struct dirent layout to add d_off, increase the size of d_fileno
to 64-bits, increase the size of d_namlen to 16-bits, and change
the required alignment. Increase struct statfs f_mntfromname[] and
f_mntonname[] array length MNAMELEN to 1024.
ABI breakage is mitigated by providing compatibility using versioned
symbols, ingenious use of the existing padding in structures, and
by employing other tricks. Unfortunately, not everything can be
fixed, especially outside the base system. For instance, third-party
APIs which pass struct stat around are broken in backward and
forward incompatible ways.
Kinfo sysctl MIBs ABI is changed in backward-compatible way, but
there is no general mechanism to handle other sysctl MIBS which
return structures where the layout has changed. It was considered
that the breakage is either in the management interfaces, where we
usually allow ABI slip, or is not important.
Struct xvnode changed layout, no compat shims are provided.
For struct xtty, dev_t tty device member was reduced to uint32_t.
It was decided that keeping ABI compat in this case is more useful
than reporting 64-bit dev_t, for the sake of pstat.
Update note: strictly follow the instructions in UPDATING. Build
and install the new kernel with COMPAT_FREEBSD11 option enabled,
then reboot, and only then install new world.
Credits: The 64-bit inode project, also known as ino64, started life
many years ago as a project by Gleb Kurtsou (gleb). Kirk McKusick
(mckusick) then picked up and updated the patch, and acted as a
flag-waver. Feedback, suggestions, and discussions were carried
by Ed Maste (emaste), John Baldwin (jhb), Jilles Tjoelker (jilles),
and Rick Macklem (rmacklem). Kris Moore (kris) performed an initial
ports investigation followed by an exp-run by Antoine Brodin (antoine).
Essential and all-embracing testing was done by Peter Holm (pho).
The heavy lifting of coordinating all these efforts and bringing the
project to completion were done by Konstantin Belousov (kib).
Sponsored by: The FreeBSD Foundation (emaste, kib)
Differential revision: https://reviews.freebsd.org/D10439
2017-05-23 09:29:05 +00:00
|
|
|
fhstat;
|
|
|
|
fhstatfs;
|
|
|
|
fstat;
|
|
|
|
fstatat;
|
|
|
|
fstatfs;
|
|
|
|
getdents;
|
|
|
|
getdirentries;
|
|
|
|
getfsstat;
|
2018-03-21 01:15:45 +00:00
|
|
|
getrandom;
|
Add abstime kqueue(2) timers and expand struct kevent members.
This change implements NOTE_ABSTIME flag for EVFILT_TIMER, which
specifies that the data field contains absolute time to fire the
event.
To make this useful, data member of the struct kevent must be extended
to 64bit. Using the opportunity, I also added ext members. This
changes struct kevent almost to Apple struct kevent64, except I did
not changed type of ident and udata, the later would cause serious API
incompatibilities.
The type of ident was kept uintptr_t since EVFILT_AIO returns a
pointer in this field, and e.g. CHERI is sensitive to the type
(discussed with brooks, jhb).
Unlike Apple kevent64, symbol versioning allows us to claim ABI
compatibility and still name the new syscall kevent(2). Compat shims
are provided for both host native and compat32.
Requested by: bapt
Reviewed by: bapt, brooks, ngie (previous version)
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D11025
2017-06-17 00:57:26 +00:00
|
|
|
kevent;
|
Commit the 64-bit inode project.
Extend the ino_t, dev_t, nlink_t types to 64-bit ints. Modify
struct dirent layout to add d_off, increase the size of d_fileno
to 64-bits, increase the size of d_namlen to 16-bits, and change
the required alignment. Increase struct statfs f_mntfromname[] and
f_mntonname[] array length MNAMELEN to 1024.
ABI breakage is mitigated by providing compatibility using versioned
symbols, ingenious use of the existing padding in structures, and
by employing other tricks. Unfortunately, not everything can be
fixed, especially outside the base system. For instance, third-party
APIs which pass struct stat around are broken in backward and
forward incompatible ways.
Kinfo sysctl MIBs ABI is changed in backward-compatible way, but
there is no general mechanism to handle other sysctl MIBS which
return structures where the layout has changed. It was considered
that the breakage is either in the management interfaces, where we
usually allow ABI slip, or is not important.
Struct xvnode changed layout, no compat shims are provided.
For struct xtty, dev_t tty device member was reduced to uint32_t.
It was decided that keeping ABI compat in this case is more useful
than reporting 64-bit dev_t, for the sake of pstat.
Update note: strictly follow the instructions in UPDATING. Build
and install the new kernel with COMPAT_FREEBSD11 option enabled,
then reboot, and only then install new world.
Credits: The 64-bit inode project, also known as ino64, started life
many years ago as a project by Gleb Kurtsou (gleb). Kirk McKusick
(mckusick) then picked up and updated the patch, and acted as a
flag-waver. Feedback, suggestions, and discussions were carried
by Ed Maste (emaste), John Baldwin (jhb), Jilles Tjoelker (jilles),
and Rick Macklem (rmacklem). Kris Moore (kris) performed an initial
ports investigation followed by an exp-run by Antoine Brodin (antoine).
Essential and all-embracing testing was done by Peter Holm (pho).
The heavy lifting of coordinating all these efforts and bringing the
project to completion were done by Konstantin Belousov (kib).
Sponsored by: The FreeBSD Foundation (emaste, kib)
Differential revision: https://reviews.freebsd.org/D10439
2017-05-23 09:29:05 +00:00
|
|
|
lstat;
|
|
|
|
mknod;
|
|
|
|
mknodat;
|
|
|
|
stat;
|
|
|
|
statfs;
|
2018-01-12 22:48:23 +00:00
|
|
|
cpuset_getdomain;
|
|
|
|
cpuset_setdomain;
|
2016-08-15 19:08:51 +00:00
|
|
|
};
|
|
|
|
|
2018-12-07 15:17:29 +00:00
|
|
|
FBSD_1.6 {
|
2019-09-03 04:16:30 +00:00
|
|
|
__sysctlbyname;
|
2021-01-02 23:34:20 +00:00
|
|
|
aio_readv;
|
|
|
|
aio_writev;
|
2020-04-12 21:23:19 +00:00
|
|
|
close_range;
|
2019-07-25 06:05:49 +00:00
|
|
|
copy_file_range;
|
2018-12-07 15:17:29 +00:00
|
|
|
fhlink;
|
|
|
|
fhlinkat;
|
|
|
|
fhreadlink;
|
|
|
|
getfhat;
|
2019-04-06 09:34:26 +00:00
|
|
|
funlinkat;
|
2019-09-25 18:03:18 +00:00
|
|
|
memfd_create;
|
2020-09-09 22:20:36 +00:00
|
|
|
shm_create_largepage;
|
2019-09-26 15:32:28 +00:00
|
|
|
shm_rename;
|
2018-12-07 15:17:29 +00:00
|
|
|
};
|
|
|
|
|
2021-08-02 09:50:32 +00:00
|
|
|
FBSD_1.7 {
|
2021-09-02 13:07:08 +00:00
|
|
|
_Fork;
|
2021-08-05 15:20:42 +00:00
|
|
|
fspacectl;
|
2023-03-31 22:27:00 +00:00
|
|
|
kqueuex;
|
2021-12-08 21:04:57 +00:00
|
|
|
swapoff;
|
2021-08-02 09:50:32 +00:00
|
|
|
};
|
|
|
|
|
2007-04-29 14:05:22 +00:00
|
|
|
FBSDprivate_1.0 {
|
2006-03-13 00:53:21 +00:00
|
|
|
___acl_aclcheck_fd;
|
|
|
|
__sys___acl_aclcheck_fd;
|
|
|
|
___acl_aclcheck_file;
|
|
|
|
__sys___acl_aclcheck_file;
|
|
|
|
___acl_aclcheck_link;
|
|
|
|
__sys___acl_aclcheck_link;
|
|
|
|
___acl_delete_fd;
|
|
|
|
__sys___acl_delete_fd;
|
|
|
|
___acl_delete_file;
|
|
|
|
__sys___acl_delete_file;
|
|
|
|
___acl_delete_link;
|
|
|
|
__sys___acl_delete_link;
|
|
|
|
___acl_get_fd;
|
|
|
|
__sys___acl_get_fd;
|
|
|
|
___acl_get_file;
|
|
|
|
__sys___acl_get_file;
|
|
|
|
___acl_get_link;
|
|
|
|
__sys___acl_get_link;
|
|
|
|
___acl_set_fd;
|
|
|
|
__sys___acl_set_fd;
|
|
|
|
___acl_set_file;
|
|
|
|
__sys___acl_set_file;
|
|
|
|
___acl_set_link;
|
|
|
|
__sys___acl_set_link;
|
|
|
|
___getcwd;
|
|
|
|
__sys___getcwd;
|
|
|
|
___mac_execve;
|
|
|
|
__sys___mac_execve;
|
|
|
|
___mac_get_fd;
|
|
|
|
__sys___mac_get_fd;
|
|
|
|
___mac_get_file;
|
|
|
|
__sys___mac_get_file;
|
|
|
|
___mac_get_link;
|
|
|
|
__sys___mac_get_link;
|
|
|
|
___mac_get_pid;
|
|
|
|
__sys___mac_get_pid;
|
|
|
|
___mac_get_proc;
|
|
|
|
__sys___mac_get_proc;
|
|
|
|
___mac_set_fd;
|
|
|
|
__sys___mac_set_fd;
|
|
|
|
___mac_set_file;
|
|
|
|
__sys___mac_set_file;
|
|
|
|
___mac_set_link;
|
|
|
|
__sys___mac_set_link;
|
|
|
|
___mac_set_proc;
|
|
|
|
__sys___mac_set_proc;
|
|
|
|
___semctl;
|
|
|
|
__sys___semctl;
|
|
|
|
___setugid;
|
|
|
|
__sys___setugid;
|
|
|
|
___syscall;
|
|
|
|
__sys___syscall;
|
|
|
|
___sysctl;
|
|
|
|
__sys___sysctl;
|
|
|
|
__umtx_op;
|
|
|
|
__sys__umtx_op;
|
|
|
|
_abort2;
|
|
|
|
__sys_abort2;
|
|
|
|
_accept;
|
|
|
|
__sys_accept;
|
2013-05-01 20:10:21 +00:00
|
|
|
_accept4;
|
|
|
|
__sys_accept4;
|
2006-03-13 00:53:21 +00:00
|
|
|
_access;
|
|
|
|
__sys_access;
|
|
|
|
_acct;
|
|
|
|
__sys_acct;
|
|
|
|
_adjtime;
|
|
|
|
__sys_adjtime;
|
|
|
|
__sys_aio_cancel;
|
|
|
|
__sys_aio_error;
|
2006-07-23 13:08:54 +00:00
|
|
|
__sys_aio_fsync;
|
2006-03-13 00:53:21 +00:00
|
|
|
__sys_aio_read;
|
2021-08-22 11:34:07 +00:00
|
|
|
__sys_aio_readv;
|
2006-03-13 00:53:21 +00:00
|
|
|
__sys_aio_return;
|
|
|
|
__sys_aio_suspend;
|
|
|
|
__sys_aio_waitcomplete;
|
|
|
|
__sys_aio_write;
|
2021-08-22 11:34:07 +00:00
|
|
|
__sys_aio_writev;
|
2006-03-13 00:53:21 +00:00
|
|
|
_audit;
|
|
|
|
__sys_audit;
|
|
|
|
_auditctl;
|
|
|
|
__sys_auditctl;
|
|
|
|
_auditon;
|
|
|
|
__sys_auditon;
|
|
|
|
_bind;
|
|
|
|
__sys_bind;
|
|
|
|
_chdir;
|
|
|
|
__sys_chdir;
|
|
|
|
_chflags;
|
|
|
|
__sys_chflags;
|
|
|
|
_chmod;
|
|
|
|
__sys_chmod;
|
|
|
|
_chown;
|
|
|
|
__sys_chown;
|
|
|
|
_chroot;
|
|
|
|
__sys_chroot;
|
2012-08-17 02:26:31 +00:00
|
|
|
_clock_getcpuclockid2;
|
|
|
|
__sys_clock_getcpuclockid2;
|
2006-03-13 00:53:21 +00:00
|
|
|
_clock_getres;
|
|
|
|
__sys_clock_getres;
|
|
|
|
_clock_gettime;
|
|
|
|
__sys_clock_gettime;
|
2017-03-19 00:51:12 +00:00
|
|
|
__sys_clock_nanosleep;
|
2006-03-13 00:53:21 +00:00
|
|
|
_clock_settime;
|
|
|
|
__sys_clock_settime;
|
|
|
|
_close;
|
|
|
|
__sys_close;
|
|
|
|
_connect;
|
|
|
|
__sys_connect;
|
2008-07-11 15:17:06 +00:00
|
|
|
_cpuset;
|
Add cpuset, an api for thread to cpu binding and cpu resource grouping
and assignment.
- Add a reference to a struct cpuset in each thread that is inherited from
the thread that created it.
- Release the reference when the thread is destroyed.
- Add prototypes for syscalls and macros for manipulating cpusets in
sys/cpuset.h
- Add syscalls to create, get, and set new numbered cpusets:
cpuset(), cpuset_{get,set}id()
- Add syscalls for getting and setting affinity masks for cpusets or
individual threads: cpuid_{get,set}affinity()
- Add types for the 'level' and 'which' parameters for the cpuset. This
will permit expansion of the api to cover cpu masks for other objects
identifiable with an id_t integer. For example, IRQs and Jails may be
coming soon.
- The root set 0 contains all valid cpus. All thread initially belong to
cpuset 1. This permits migrating all threads off of certain cpus to
reserve them for special applications.
Sponsored by: Nokia
Discussed with: arch, rwatson, brooks, davidxu, deischen
Reviewed by: antoine
2008-03-02 07:39:22 +00:00
|
|
|
__sys_cpuset;
|
2008-07-11 15:17:06 +00:00
|
|
|
_cpuset_getid;
|
Add cpuset, an api for thread to cpu binding and cpu resource grouping
and assignment.
- Add a reference to a struct cpuset in each thread that is inherited from
the thread that created it.
- Release the reference when the thread is destroyed.
- Add prototypes for syscalls and macros for manipulating cpusets in
sys/cpuset.h
- Add syscalls to create, get, and set new numbered cpusets:
cpuset(), cpuset_{get,set}id()
- Add syscalls for getting and setting affinity masks for cpusets or
individual threads: cpuid_{get,set}affinity()
- Add types for the 'level' and 'which' parameters for the cpuset. This
will permit expansion of the api to cover cpu masks for other objects
identifiable with an id_t integer. For example, IRQs and Jails may be
coming soon.
- The root set 0 contains all valid cpus. All thread initially belong to
cpuset 1. This permits migrating all threads off of certain cpus to
reserve them for special applications.
Sponsored by: Nokia
Discussed with: arch, rwatson, brooks, davidxu, deischen
Reviewed by: antoine
2008-03-02 07:39:22 +00:00
|
|
|
__sys_cpuset_getid;
|
2008-07-11 15:17:06 +00:00
|
|
|
_cpuset_setid;
|
Add cpuset, an api for thread to cpu binding and cpu resource grouping
and assignment.
- Add a reference to a struct cpuset in each thread that is inherited from
the thread that created it.
- Release the reference when the thread is destroyed.
- Add prototypes for syscalls and macros for manipulating cpusets in
sys/cpuset.h
- Add syscalls to create, get, and set new numbered cpusets:
cpuset(), cpuset_{get,set}id()
- Add syscalls for getting and setting affinity masks for cpusets or
individual threads: cpuid_{get,set}affinity()
- Add types for the 'level' and 'which' parameters for the cpuset. This
will permit expansion of the api to cover cpu masks for other objects
identifiable with an id_t integer. For example, IRQs and Jails may be
coming soon.
- The root set 0 contains all valid cpus. All thread initially belong to
cpuset 1. This permits migrating all threads off of certain cpus to
reserve them for special applications.
Sponsored by: Nokia
Discussed with: arch, rwatson, brooks, davidxu, deischen
Reviewed by: antoine
2008-03-02 07:39:22 +00:00
|
|
|
__sys_cpuset_setid;
|
2008-07-11 15:17:06 +00:00
|
|
|
_cpuset_getaffinity;
|
Add cpuset, an api for thread to cpu binding and cpu resource grouping
and assignment.
- Add a reference to a struct cpuset in each thread that is inherited from
the thread that created it.
- Release the reference when the thread is destroyed.
- Add prototypes for syscalls and macros for manipulating cpusets in
sys/cpuset.h
- Add syscalls to create, get, and set new numbered cpusets:
cpuset(), cpuset_{get,set}id()
- Add syscalls for getting and setting affinity masks for cpusets or
individual threads: cpuid_{get,set}affinity()
- Add types for the 'level' and 'which' parameters for the cpuset. This
will permit expansion of the api to cover cpu masks for other objects
identifiable with an id_t integer. For example, IRQs and Jails may be
coming soon.
- The root set 0 contains all valid cpus. All thread initially belong to
cpuset 1. This permits migrating all threads off of certain cpus to
reserve them for special applications.
Sponsored by: Nokia
Discussed with: arch, rwatson, brooks, davidxu, deischen
Reviewed by: antoine
2008-03-02 07:39:22 +00:00
|
|
|
__sys_cpuset_getaffinity;
|
2008-07-11 15:17:06 +00:00
|
|
|
_cpuset_setaffinity;
|
Add cpuset, an api for thread to cpu binding and cpu resource grouping
and assignment.
- Add a reference to a struct cpuset in each thread that is inherited from
the thread that created it.
- Release the reference when the thread is destroyed.
- Add prototypes for syscalls and macros for manipulating cpusets in
sys/cpuset.h
- Add syscalls to create, get, and set new numbered cpusets:
cpuset(), cpuset_{get,set}id()
- Add syscalls for getting and setting affinity masks for cpusets or
individual threads: cpuid_{get,set}affinity()
- Add types for the 'level' and 'which' parameters for the cpuset. This
will permit expansion of the api to cover cpu masks for other objects
identifiable with an id_t integer. For example, IRQs and Jails may be
coming soon.
- The root set 0 contains all valid cpus. All thread initially belong to
cpuset 1. This permits migrating all threads off of certain cpus to
reserve them for special applications.
Sponsored by: Nokia
Discussed with: arch, rwatson, brooks, davidxu, deischen
Reviewed by: antoine
2008-03-02 07:39:22 +00:00
|
|
|
__sys_cpuset_setaffinity;
|
2006-03-13 00:53:21 +00:00
|
|
|
_dup;
|
|
|
|
__sys_dup;
|
|
|
|
_dup2;
|
|
|
|
__sys_dup2;
|
|
|
|
_eaccess;
|
|
|
|
__sys_eaccess;
|
|
|
|
_execve;
|
|
|
|
__sys_execve;
|
|
|
|
_extattr_delete_fd;
|
|
|
|
__sys_extattr_delete_fd;
|
|
|
|
_extattr_delete_file;
|
|
|
|
__sys_extattr_delete_file;
|
|
|
|
_extattr_delete_link;
|
|
|
|
__sys_extattr_delete_link;
|
|
|
|
_extattr_get_fd;
|
|
|
|
__sys_extattr_get_fd;
|
|
|
|
_extattr_get_file;
|
|
|
|
__sys_extattr_get_file;
|
|
|
|
_extattr_get_link;
|
|
|
|
__sys_extattr_get_link;
|
|
|
|
_extattr_list_fd;
|
|
|
|
__sys_extattr_list_fd;
|
|
|
|
_extattr_list_file;
|
|
|
|
__sys_extattr_list_file;
|
|
|
|
_extattr_list_link;
|
|
|
|
__sys_extattr_list_link;
|
|
|
|
_extattr_set_fd;
|
|
|
|
__sys_extattr_set_fd;
|
|
|
|
_extattr_set_file;
|
|
|
|
__sys_extattr_set_file;
|
|
|
|
_extattr_set_link;
|
|
|
|
__sys_extattr_set_link;
|
|
|
|
_extattrctl;
|
|
|
|
__sys_extattrctl;
|
Add a way to manage thread signal mask using shared word, instead of syscall.
A new syscall sigfastblock(2) is added which registers a uint32_t
variable as containing the count of blocks for signal delivery. Its
content is read by kernel on each syscall entry and on AST processing,
non-zero count of blocks is interpreted same as the signal mask
blocking all signals.
The biggest downside of the feature that I see is that memory
corruption that affects the registered fast sigblock location, would
cause quite strange application misbehavior. For instance, the process
would be immune to ^C (but killable by SIGKILL).
With consumers (rtld and libthr added), benchmarks do not show a
slow-down of the syscalls in micro-measurements, and macro benchmarks
like buildworld do not demonstrate a difference. Part of the reason is
that buildworld time is dominated by compiler, and clang already links
to libthr. On the other hand, small utilities typically used by shell
scripts have the total number of syscalls cut by half.
The syscall is not exported from the stable libc version namespace on
purpose. It is intended to be used only by our C runtime
implementation internals.
Tested by: pho
Disscussed with: cem, emaste, jilles
Sponsored by: The FreeBSD Foundation
Differential revision: https://reviews.freebsd.org/D12773
2020-02-09 11:53:12 +00:00
|
|
|
__sys_sigfastblock;
|
2006-03-13 00:53:21 +00:00
|
|
|
_fchdir;
|
|
|
|
__sys_fchdir;
|
|
|
|
_fchflags;
|
|
|
|
__sys_fchflags;
|
|
|
|
_fchmod;
|
|
|
|
__sys_fchmod;
|
|
|
|
_fchown;
|
|
|
|
__sys_fchown;
|
|
|
|
_fcntl;
|
|
|
|
__sys_fcntl;
|
2008-05-30 14:47:42 +00:00
|
|
|
__fcntl_compat;
|
2006-03-13 00:53:21 +00:00
|
|
|
_fhopen;
|
|
|
|
__sys_fhopen;
|
|
|
|
_fhstat;
|
|
|
|
__sys_fhstat;
|
|
|
|
_fhstatfs;
|
|
|
|
__sys_fhstatfs;
|
|
|
|
_flock;
|
|
|
|
__sys_flock;
|
|
|
|
_fork;
|
|
|
|
__sys_fork;
|
|
|
|
_fpathconf;
|
|
|
|
__sys_fpathconf;
|
|
|
|
_fstat;
|
|
|
|
__sys_fstat;
|
|
|
|
_fstatfs;
|
|
|
|
__sys_fstatfs;
|
|
|
|
_fsync;
|
|
|
|
__sys_fsync;
|
2016-08-15 19:08:51 +00:00
|
|
|
_fdatasync;
|
|
|
|
__sys_fdatasync;
|
2006-03-13 00:53:21 +00:00
|
|
|
_futimes;
|
|
|
|
__sys_futimes;
|
|
|
|
_getaudit;
|
|
|
|
__sys_getaudit;
|
|
|
|
_getaudit_addr;
|
|
|
|
__sys_getaudit_addr;
|
|
|
|
_getauid;
|
|
|
|
__sys_getauid;
|
|
|
|
_getcontext;
|
|
|
|
__sys_getcontext;
|
|
|
|
_getdirentries;
|
|
|
|
__sys_getdirentries;
|
|
|
|
_getdtablesize;
|
|
|
|
__sys_getdtablesize;
|
|
|
|
_getegid;
|
|
|
|
__sys_getegid;
|
|
|
|
_geteuid;
|
|
|
|
__sys_geteuid;
|
|
|
|
_getfh;
|
|
|
|
__sys_getfh;
|
|
|
|
_getfsstat;
|
|
|
|
__sys_getfsstat;
|
|
|
|
_getgid;
|
|
|
|
__sys_getgid;
|
|
|
|
_getgroups;
|
|
|
|
__sys_getgroups;
|
|
|
|
_getitimer;
|
|
|
|
__sys_getitimer;
|
|
|
|
_getpeername;
|
|
|
|
__sys_getpeername;
|
|
|
|
_getpgid;
|
|
|
|
__sys_getpgid;
|
|
|
|
_getpgrp;
|
|
|
|
__sys_getpgrp;
|
|
|
|
_getpid;
|
|
|
|
__sys_getpid;
|
|
|
|
_getppid;
|
|
|
|
__sys_getppid;
|
|
|
|
_getpriority;
|
|
|
|
__sys_getpriority;
|
|
|
|
_getresgid;
|
|
|
|
__sys_getresgid;
|
|
|
|
_getresuid;
|
|
|
|
__sys_getresuid;
|
|
|
|
_getrlimit;
|
|
|
|
__sys_getrlimit;
|
|
|
|
_getrusage;
|
|
|
|
__sys_getrusage;
|
|
|
|
_getsid;
|
|
|
|
__sys_getsid;
|
|
|
|
_getsockname;
|
|
|
|
__sys_getsockname;
|
|
|
|
_getsockopt;
|
|
|
|
__sys_getsockopt;
|
|
|
|
_gettimeofday;
|
|
|
|
__sys_gettimeofday;
|
|
|
|
_getuid;
|
|
|
|
__sys_getuid;
|
|
|
|
_ioctl;
|
|
|
|
__sys_ioctl;
|
|
|
|
_issetugid;
|
|
|
|
__sys_issetugid;
|
|
|
|
_jail;
|
|
|
|
__sys_jail;
|
|
|
|
_jail_attach;
|
|
|
|
__sys_jail_attach;
|
|
|
|
_kenv;
|
|
|
|
__sys_kenv;
|
|
|
|
_kevent;
|
|
|
|
__sys_kevent;
|
|
|
|
_kill;
|
|
|
|
__sys_kill;
|
|
|
|
_kldfind;
|
|
|
|
__sys_kldfind;
|
|
|
|
_kldfirstmod;
|
|
|
|
__sys_kldfirstmod;
|
|
|
|
_kldload;
|
|
|
|
__sys_kldload;
|
|
|
|
_kldnext;
|
|
|
|
__sys_kldnext;
|
|
|
|
_kldstat;
|
|
|
|
__sys_kldstat;
|
|
|
|
_kldsym;
|
|
|
|
__sys_kldsym;
|
|
|
|
_kldunload;
|
|
|
|
__sys_kldunload;
|
|
|
|
_kldunloadf;
|
|
|
|
__sys_kldunloadf;
|
|
|
|
_kmq_notify;
|
|
|
|
__sys_kmq_notify;
|
|
|
|
_kmq_open;
|
|
|
|
__sys_kmq_open;
|
|
|
|
_kmq_setattr;
|
|
|
|
__sys_kmq_setattr;
|
|
|
|
_kmq_timedreceive;
|
|
|
|
__sys_kmq_timedreceive;
|
|
|
|
_kmq_timedsend;
|
|
|
|
__sys_kmq_timedsend;
|
|
|
|
_kmq_unlink;
|
|
|
|
__sys_kmq_unlink;
|
|
|
|
_kqueue;
|
|
|
|
__sys_kqueue;
|
|
|
|
_ksem_close;
|
|
|
|
__sys_ksem_close;
|
|
|
|
_ksem_destroy;
|
|
|
|
__sys_ksem_destroy;
|
|
|
|
_ksem_getvalue;
|
|
|
|
__sys_ksem_getvalue;
|
|
|
|
_ksem_init;
|
|
|
|
__sys_ksem_init;
|
|
|
|
_ksem_open;
|
|
|
|
__sys_ksem_open;
|
|
|
|
_ksem_post;
|
|
|
|
__sys_ksem_post;
|
|
|
|
_ksem_timedwait;
|
|
|
|
__sys_ksem_timedwait;
|
|
|
|
_ksem_trywait;
|
|
|
|
__sys_ksem_trywait;
|
|
|
|
_ksem_unlink;
|
|
|
|
__sys_ksem_unlink;
|
|
|
|
_ksem_wait;
|
|
|
|
__sys_ksem_wait;
|
|
|
|
_ktrace;
|
|
|
|
__sys_ktrace;
|
|
|
|
_lchflags;
|
|
|
|
__sys_lchflags;
|
|
|
|
_lchmod;
|
|
|
|
__sys_lchmod;
|
|
|
|
_lchown;
|
|
|
|
__sys_lchown;
|
|
|
|
_lgetfh;
|
|
|
|
__sys_lgetfh;
|
|
|
|
_link;
|
|
|
|
__sys_link;
|
|
|
|
__sys_lio_listio;
|
|
|
|
_listen;
|
|
|
|
__sys_listen;
|
|
|
|
_lutimes;
|
|
|
|
__sys_lutimes;
|
|
|
|
_mac_syscall;
|
|
|
|
__sys_mac_syscall;
|
|
|
|
_madvise;
|
|
|
|
__sys_madvise;
|
|
|
|
_mincore;
|
|
|
|
__sys_mincore;
|
|
|
|
_minherit;
|
|
|
|
__sys_minherit;
|
|
|
|
_mkdir;
|
|
|
|
__sys_mkdir;
|
|
|
|
_mkfifo;
|
|
|
|
__sys_mkfifo;
|
|
|
|
_mknod;
|
|
|
|
__sys_mknod;
|
|
|
|
_mlock;
|
|
|
|
__sys_mlock;
|
|
|
|
_mlockall;
|
|
|
|
__sys_mlockall;
|
2021-09-09 10:46:53 +00:00
|
|
|
_mmap;
|
|
|
|
__sys_mmap;
|
2006-03-13 00:53:21 +00:00
|
|
|
_modfind;
|
|
|
|
__sys_modfind;
|
|
|
|
_modfnext;
|
|
|
|
__sys_modfnext;
|
|
|
|
_modnext;
|
|
|
|
__sys_modnext;
|
|
|
|
_modstat;
|
|
|
|
__sys_modstat;
|
|
|
|
_mount;
|
|
|
|
__sys_mount;
|
|
|
|
_mprotect;
|
|
|
|
__sys_mprotect;
|
|
|
|
_msgctl;
|
|
|
|
__sys_msgctl;
|
|
|
|
_msgget;
|
|
|
|
__sys_msgget;
|
|
|
|
_msgrcv;
|
|
|
|
__sys_msgrcv;
|
|
|
|
_msgsnd;
|
|
|
|
__sys_msgsnd;
|
|
|
|
_msgsys;
|
|
|
|
__sys_msgsys;
|
|
|
|
_msync;
|
|
|
|
__sys_msync;
|
|
|
|
_munlock;
|
|
|
|
__sys_munlock;
|
|
|
|
_munlockall;
|
|
|
|
__sys_munlockall;
|
|
|
|
_munmap;
|
|
|
|
__sys_munmap;
|
|
|
|
_nanosleep;
|
|
|
|
__sys_nanosleep;
|
|
|
|
_nfssvc;
|
|
|
|
__sys_nfssvc;
|
|
|
|
_nmount;
|
|
|
|
__sys_nmount;
|
|
|
|
_ntp_adjtime;
|
|
|
|
__sys_ntp_adjtime;
|
|
|
|
_ntp_gettime;
|
|
|
|
__sys_ntp_gettime;
|
|
|
|
_open;
|
|
|
|
__sys_open;
|
2009-10-11 20:19:45 +00:00
|
|
|
_openat;
|
|
|
|
__sys_openat;
|
2006-03-13 00:53:21 +00:00
|
|
|
_pathconf;
|
|
|
|
__sys_pathconf;
|
2021-01-10 19:22:49 +00:00
|
|
|
__sys_pdfork;
|
2006-03-13 00:53:21 +00:00
|
|
|
_pipe;
|
|
|
|
__sys_pipe;
|
|
|
|
_poll;
|
|
|
|
__sys_poll;
|
2014-11-13 05:26:14 +00:00
|
|
|
_ppoll;
|
|
|
|
__sys_ppoll;
|
2006-03-13 00:53:21 +00:00
|
|
|
_preadv;
|
|
|
|
__sys_preadv;
|
2013-09-19 18:53:42 +00:00
|
|
|
_procctl;
|
|
|
|
__sys_procctl;
|
2006-03-13 00:53:21 +00:00
|
|
|
_profil;
|
|
|
|
__sys_profil;
|
2009-10-27 10:55:34 +00:00
|
|
|
_pselect;
|
|
|
|
__sys_pselect;
|
2006-03-13 00:53:21 +00:00
|
|
|
_ptrace;
|
|
|
|
__sys_ptrace;
|
|
|
|
_pwritev;
|
|
|
|
__sys_pwritev;
|
|
|
|
_quotactl;
|
|
|
|
__sys_quotactl;
|
|
|
|
_read;
|
|
|
|
__sys_read;
|
|
|
|
_readlink;
|
|
|
|
__sys_readlink;
|
|
|
|
_readv;
|
|
|
|
__sys_readv;
|
|
|
|
_reboot;
|
|
|
|
__sys_reboot;
|
|
|
|
_recvfrom;
|
|
|
|
__sys_recvfrom;
|
|
|
|
_recvmsg;
|
|
|
|
__sys_recvmsg;
|
|
|
|
_rename;
|
|
|
|
__sys_rename;
|
|
|
|
_revoke;
|
|
|
|
__sys_revoke;
|
|
|
|
_rfork;
|
|
|
|
__sys_rfork;
|
|
|
|
_rmdir;
|
|
|
|
__sys_rmdir;
|
|
|
|
_rtprio;
|
|
|
|
__sys_rtprio;
|
2006-09-21 04:22:46 +00:00
|
|
|
_rtprio_thread;
|
|
|
|
__sys_rtprio_thread;
|
2006-03-13 00:53:21 +00:00
|
|
|
_sched_get_priority_max;
|
|
|
|
__sys_sched_get_priority_max;
|
|
|
|
_sched_get_priority_min;
|
|
|
|
__sys_sched_get_priority_min;
|
|
|
|
_sched_getparam;
|
|
|
|
__sys_sched_getparam;
|
|
|
|
_sched_getscheduler;
|
|
|
|
__sys_sched_getscheduler;
|
|
|
|
_sched_rr_get_interval;
|
|
|
|
__sys_sched_rr_get_interval;
|
|
|
|
_sched_setparam;
|
|
|
|
__sys_sched_setparam;
|
|
|
|
_sched_setscheduler;
|
|
|
|
__sys_sched_setscheduler;
|
|
|
|
_sched_yield;
|
|
|
|
__sys_sched_yield;
|
|
|
|
_select;
|
|
|
|
__sys_select;
|
|
|
|
_semget;
|
|
|
|
__sys_semget;
|
|
|
|
_semop;
|
|
|
|
__sys_semop;
|
|
|
|
_semsys;
|
|
|
|
__sys_semsys;
|
|
|
|
_sendfile;
|
|
|
|
__sys_sendfile;
|
|
|
|
_sendmsg;
|
|
|
|
__sys_sendmsg;
|
|
|
|
_sendto;
|
|
|
|
__sys_sendto;
|
|
|
|
_setaudit;
|
|
|
|
__sys_setaudit;
|
|
|
|
_setaudit_addr;
|
|
|
|
__sys_setaudit_addr;
|
|
|
|
_setauid;
|
|
|
|
__sys_setauid;
|
|
|
|
_setcontext;
|
|
|
|
__sys_setcontext;
|
|
|
|
_setegid;
|
|
|
|
__sys_setegid;
|
|
|
|
_seteuid;
|
|
|
|
__sys_seteuid;
|
|
|
|
_setgid;
|
|
|
|
__sys_setgid;
|
|
|
|
_setgroups;
|
|
|
|
__sys_setgroups;
|
|
|
|
_setitimer;
|
|
|
|
__sys_setitimer;
|
|
|
|
_setlogin;
|
|
|
|
__sys_setlogin;
|
|
|
|
_setpgid;
|
|
|
|
__sys_setpgid;
|
|
|
|
_setpriority;
|
|
|
|
__sys_setpriority;
|
|
|
|
_setregid;
|
|
|
|
__sys_setregid;
|
|
|
|
_setresgid;
|
|
|
|
__sys_setresgid;
|
|
|
|
_setresuid;
|
|
|
|
__sys_setresuid;
|
|
|
|
_setreuid;
|
|
|
|
__sys_setreuid;
|
|
|
|
_setrlimit;
|
|
|
|
__sys_setrlimit;
|
|
|
|
_setsid;
|
|
|
|
__sys_setsid;
|
|
|
|
_setsockopt;
|
|
|
|
__sys_setsockopt;
|
|
|
|
_settimeofday;
|
|
|
|
__sys_settimeofday;
|
|
|
|
_setuid;
|
|
|
|
__sys_setuid;
|
2009-04-02 15:53:29 +00:00
|
|
|
_shm_open;
|
|
|
|
__sys_shm_open;
|
2020-09-09 22:20:36 +00:00
|
|
|
__sys_shm_open2;
|
2009-04-02 15:53:29 +00:00
|
|
|
_shm_unlink;
|
|
|
|
__sys_shm_unlink;
|
2006-03-13 00:53:21 +00:00
|
|
|
_shmat;
|
|
|
|
__sys_shmat;
|
|
|
|
_shmctl;
|
|
|
|
__sys_shmctl;
|
|
|
|
_shmdt;
|
|
|
|
__sys_shmdt;
|
|
|
|
_shmget;
|
|
|
|
__sys_shmget;
|
|
|
|
_shmsys;
|
|
|
|
__sys_shmsys;
|
|
|
|
_shutdown;
|
|
|
|
__sys_shutdown;
|
|
|
|
_sigaction;
|
|
|
|
__sys_sigaction;
|
|
|
|
_sigaltstack;
|
|
|
|
__sys_sigaltstack;
|
|
|
|
_sigpending;
|
|
|
|
__sys_sigpending;
|
|
|
|
_sigprocmask;
|
|
|
|
__sys_sigprocmask;
|
|
|
|
_sigqueue;
|
|
|
|
__sys_sigqueue;
|
|
|
|
_sigreturn;
|
|
|
|
__sys_sigreturn;
|
|
|
|
_sigsuspend;
|
|
|
|
__sys_sigsuspend;
|
|
|
|
_sigtimedwait;
|
|
|
|
__sys_sigtimedwait;
|
|
|
|
_sigwait;
|
2010-09-10 01:47:37 +00:00
|
|
|
__sigwait;
|
2006-03-13 00:53:21 +00:00
|
|
|
__sys_sigwait;
|
|
|
|
_sigwaitinfo;
|
|
|
|
__sys_sigwaitinfo;
|
|
|
|
_socket;
|
|
|
|
__sys_socket;
|
|
|
|
_socketpair;
|
|
|
|
__sys_socketpair;
|
|
|
|
_statfs;
|
|
|
|
__sys_statfs;
|
|
|
|
_swapcontext;
|
|
|
|
__sys_swapcontext;
|
|
|
|
_swapoff;
|
|
|
|
__sys_swapoff;
|
|
|
|
_swapon;
|
|
|
|
__sys_swapon;
|
|
|
|
_symlink;
|
|
|
|
__sys_symlink;
|
|
|
|
_sync;
|
|
|
|
__sys_sync;
|
|
|
|
_sysarch;
|
|
|
|
__sys_sysarch;
|
|
|
|
_syscall;
|
|
|
|
__sys_syscall;
|
|
|
|
_thr_create;
|
|
|
|
__sys_thr_create;
|
|
|
|
_thr_exit;
|
|
|
|
__sys_thr_exit;
|
|
|
|
_thr_kill;
|
|
|
|
__sys_thr_kill;
|
2007-08-22 01:56:35 +00:00
|
|
|
_thr_kill2;
|
|
|
|
__sys_thr_kill2;
|
2006-03-13 00:53:21 +00:00
|
|
|
_thr_new;
|
|
|
|
__sys_thr_new;
|
|
|
|
_thr_self;
|
|
|
|
__sys_thr_self;
|
|
|
|
_thr_set_name;
|
|
|
|
__sys_thr_set_name;
|
|
|
|
_thr_suspend;
|
|
|
|
__sys_thr_suspend;
|
|
|
|
_thr_wake;
|
|
|
|
__sys_thr_wake;
|
|
|
|
_ktimer_create;
|
|
|
|
__sys_ktimer_create;
|
|
|
|
_ktimer_delete;
|
|
|
|
__sys_ktimer_delete;
|
|
|
|
_ktimer_getoverrun;
|
|
|
|
__sys_ktimer_getoverrun;
|
|
|
|
_ktimer_gettime;
|
|
|
|
__sys_ktimer_gettime;
|
|
|
|
_ktimer_settime;
|
|
|
|
__sys_ktimer_settime;
|
|
|
|
_umask;
|
|
|
|
__sys_umask;
|
|
|
|
_undelete;
|
|
|
|
__sys_undelete;
|
|
|
|
_unlink;
|
|
|
|
__sys_unlink;
|
|
|
|
_unmount;
|
|
|
|
__sys_unmount;
|
|
|
|
_utimes;
|
|
|
|
__sys_utimes;
|
|
|
|
_utrace;
|
|
|
|
__sys_utrace;
|
|
|
|
_uuidgen;
|
|
|
|
__sys_uuidgen;
|
|
|
|
_wait4;
|
|
|
|
__sys_wait4;
|
2012-11-13 12:55:52 +00:00
|
|
|
_wait6;
|
|
|
|
__sys_wait6;
|
2006-03-13 00:53:21 +00:00
|
|
|
_write;
|
|
|
|
__sys_write;
|
|
|
|
_writev;
|
|
|
|
__sys_writev;
|
2015-01-05 01:06:54 +00:00
|
|
|
__set_error_selector;
|
2008-03-26 15:23:12 +00:00
|
|
|
nlm_syscall;
|
Implement support for RPCSEC_GSS authentication to both the NFS client
and server. This replaces the RPC implementation of the NFS client and
server with the newer RPC implementation originally developed
(actually ported from the userland sunrpc code) to support the NFS
Lock Manager. I have tested this code extensively and I believe it is
stable and that performance is at least equal to the legacy RPC
implementation.
The NFS code currently contains support for both the new RPC
implementation and the older legacy implementation inherited from the
original NFS codebase. The default is to use the new implementation -
add the NFS_LEGACYRPC option to fall back to the old code. When I
merge this support back to RELENG_7, I will probably change this so
that users have to 'opt in' to get the new code.
To use RPCSEC_GSS on either client or server, you must build a kernel
which includes the KGSSAPI option and the crypto device. On the
userland side, you must build at least a new libc, mountd, mount_nfs
and gssd. You must install new versions of /etc/rc.d/gssd and
/etc/rc.d/nfsd and add 'gssd_enable=YES' to /etc/rc.conf.
As long as gssd is running, you should be able to mount an NFS
filesystem from a server that requires RPCSEC_GSS authentication. The
mount itself can happen without any kerberos credentials but all
access to the filesystem will be denied unless the accessing user has
a valid ticket file in the standard place (/tmp/krb5cc_<uid>). There
is currently no support for situations where the ticket file is in a
different place, such as when the user logged in via SSH and has
delegated credentials from that login. This restriction is also
present in Solaris and Linux. In theory, we could improve this in
future, possibly using Brooks Davis' implementation of variant
symlinks.
Supporting RPCSEC_GSS on a server is nearly as simple. You must create
service creds for the server in the form 'nfs/<fqdn>@<REALM>' and
install them in /etc/krb5.keytab. The standard heimdal utility ktutil
makes this fairly easy. After the service creds have been created, you
can add a '-sec=krb5' option to /etc/exports and restart both mountd
and nfsd.
The only other difference an administrator should notice is that nfsd
doesn't fork to create service threads any more. In normal operation,
there will be two nfsd processes, one in userland waiting for TCP
connections and one in the kernel handling requests. The latter
process will create as many kthreads as required - these should be
visible via 'top -H'. The code has some support for varying the number
of service threads according to load but initially at least, nfsd uses
a fixed number of threads according to the value supplied to its '-n'
option.
Sponsored by: Isilon Systems
MFC after: 1 month
2008-11-03 10:38:00 +00:00
|
|
|
gssd_syscall;
|
2015-01-03 18:38:46 +00:00
|
|
|
__libc_interposing_slot;
|
|
|
|
__libc_sigwait;
|
2018-01-12 22:48:23 +00:00
|
|
|
_cpuset_getdomain;
|
|
|
|
__sys_cpuset_getdomain;
|
|
|
|
_cpuset_setdomain;
|
|
|
|
__sys_cpuset_setdomain;
|
2020-05-28 21:26:26 +00:00
|
|
|
rpctls_syscall;
|
2006-03-13 00:53:21 +00:00
|
|
|
};
|