host.endpoint contained duplicated logic from the sockerpair implementation and
host.ConnectedEndpoint. Remove host.endpoint in favor of a
host.ConnectedEndpoint wrapped in a socketpair end.
PiperOrigin-RevId: 217240096
Change-Id: I4a3d51e3fe82bdf30e2d0152458b8499ab4c987c
- Change Dirent.Busy => Dirent.isMountPoint. The function body is unchanged,
and it is no longer exported.
- fs.MayDelete now checks that the victim is not the process root. This aligns
with Linux's namei.c:may_delete().
- Fix "is-ancestor" checks to actually compare all ancestors, not just the
parents.
- Fix handling of paths that end in dots, which are handled differently in
Rename vs. Unlink.
PiperOrigin-RevId: 217239274
Change-Id: I7a0eb768e70a1b2915017ce54f7f95cbf8edf1fb
This is a defense-in-depth measure. If the sentry is compromised, this prevents
system call injection to the stubs. There is some complexity with respect to
ptrace and seccomp interactions, so this protection is not really available
for kernel versions < 4.8; this is detected dynamically.
Note that this also solves the vsyscall emulation issue by adding in
appropriate trapping for those system calls. It does mean that a compromised
sentry could theoretically inject these into the stub (ignoring the trap and
resume, thereby allowing execution), but they are harmless.
PiperOrigin-RevId: 216647581
Change-Id: Id06c232cbac1f9489b1803ec97f83097fcba8eb8
Currently, in the face of FileMem fragmentation and a large sendmsg or
recvmsg call, host sockets may pass > 1024 iovecs to the host, which
will immediately cause the host to return EMSGSIZE.
When we detect this case, use a single intermediate buffer to pass to
the kernel, copying to/from the src/dst buffer.
To avoid creating unbounded intermediate buffers, enforce message size
checks and truncation w.r.t. the send buffer size. The same
functionality is added to netstack unix sockets for feature parity.
PiperOrigin-RevId: 216590198
Change-Id: I719a32e71c7b1098d5097f35e6daf7dd5190eff7
Also properly add padding after Procs in the linux.Sysinfo
structure. This will be implicitly padded to 64bits so we
need to do the same.
PiperOrigin-RevId: 216372907
Change-Id: I6eb6a27800da61d8f7b7b6e87bf0391a48fdb475
We accidentally set the wrong maximum. I've also added PATH_MAX and
NAME_MAX to the linux abi package.
PiperOrigin-RevId: 216221311
Change-Id: I44805fcf21508831809692184a0eba4cee469633
- Shared futex objects on shared mappings are represented by Mappable +
offset, analogous to Linux's use of inode + offset. Add type
futex.Key, and change the futex.Manager bucket API to use futex.Keys
instead of addresses.
- Extend the futex.Checker interface to be able to return Keys for
memory mappings. It returns Keys rather than just mappings because
whether the address or the target of the mapping is used in the Key
depends on whether the mapping is MAP_SHARED or MAP_PRIVATE; this
matters because using mapping target for a futex on a MAP_PRIVATE
mapping causes it to stop working across COW-breaking.
- futex.Manager.WaitComplete depends on atomic updates to
futex.Waiter.addr to determine when it has locked the right bucket,
which is much less straightforward for struct futex.Waiter.key. Switch
to an atomically-accessed futex.Waiter.bucket pointer.
- futex.Manager.Wake now needs to take a futex.Checker to resolve
addresses for shared futexes. CLONE_CHILD_CLEARTID requires the exit
path to perform a shared futex wakeup (Linux:
kernel/fork.c:mm_release() => sys_futex(tsk->clear_child_tid,
FUTEX_WAKE, ...)). This is a problem because futexChecker is in the
syscalls/linux package. Move it to kernel.
PiperOrigin-RevId: 216207039
Change-Id: I708d68e2d1f47e526d9afd95e7fed410c84afccf
Terminal support in runsc relies on host tty file descriptors that are imported
into the sandbox. Application tty ioctls are sent directly to the host fd.
However, those host tty ioctls are associated in the host kernel with a host
process (in this case runsc), and the host kernel intercepts job control
characters like ^C and send signals to the host process. Thus, typing ^C into a
"runsc exec" shell will send a SIGINT to the runsc process.
This change makes "runsc exec" handle all signals, and forward them into the
sandbox via the "ContainerSignal" urpc method. Since the "runsc exec" is
associated with a particular container process in the sandbox, the signal must
be associated with the same container process.
One big difficulty is that the signal should not necessarily be sent to the
sandbox process started by "exec", but instead must be sent to the foreground
process group for the tty. For example, we may exec "bash", and from bash call
"sleep 100". A ^C at this point should SIGINT sleep, not bash.
To handle this, tty files inside the sandbox must keep track of their
foreground process group, which is set/get via ioctls. When an incoming
ContainerSignal urpc comes in, we look up the foreground process group via the
tty file. Unfortunately, this means we have to expose and cache the tty file in
the Loader.
Note that "runsc exec" now handles signals properly, but "runs run" does not.
That will come in a later CL, as this one is complex enough already.
Example:
root@:/usr/local/apache2# sleep 100
^C
root@:/usr/local/apache2# sleep 100
^Z
[1]+ Stopped sleep 100
root@:/usr/local/apache2# fg
sleep 100
^C
root@:/usr/local/apache2#
PiperOrigin-RevId: 215334554
Change-Id: I53cdce39653027908510a5ba8d08c49f9cf24f39
There was a race where we checked task.Parent() != nil, and then later called
task.Parent() again, assuming that it is not nil. If the task is exiting, the
parent may have been set to nil in between the two calls, causing a panic.
This CL changes the code to only call task.Parent() once.
PiperOrigin-RevId: 215274456
Change-Id: Ib5a537312c917773265ec72016014f7bc59a5f59
host.endpoint already has the check, but it is missing from
host.ConnectedEndpoint.
PiperOrigin-RevId: 214962762
Change-Id: I88bb13a5c5871775e4e7bf2608433df8a3d348e6
Previously, if address resolution for UDP or Ping sockets required sending
packets using Write in Transport layer, Resolve would return ErrWouldBlock
and Write would return ErrNoLinkAddress. Meanwhile startAddressResolution
would run in background. Further calls to Write using same address would also
return ErrNoLinkAddress until resolution has been completed successfully.
Since Write is not allowed to block and System Calls need to be
interruptible in System Call layer, the caller to Write is responsible for
blocking upon return of ErrWouldBlock.
Now, when startAddressResolution is called a notification channel for
the completion of the address resolution is returned.
The channel will traverse up to the calling function of Write as well as
ErrNoLinkAddress. Once address resolution is complete (success or not) the
channel is closed. The caller would call Write again to send packets and
check if address resolution was compeleted successfully or not.
Fixesgoogle/gvisor#5
Change-Id: Idafaf31982bee1915ca084da39ae7bd468cebd93
PiperOrigin-RevId: 214962200
We already forward TCSETS and TCSETSW. TCSETSF is roughly equivalent but
discards pending input.
The filters were relaxed to allow host ioctls with TCSETSF argument.
This fixes programs like "passwd" that prevent user input from being displayed
on the terminal.
Before:
root@b8a0240fc836:/# passwd
Enter new UNIX password: 123
Retype new UNIX password: 123
passwd: password updated successfully
After:
root@ae6f5dabe402:/# passwd
Enter new UNIX password:
Retype new UNIX password:
passwd: password updated successfully
PiperOrigin-RevId: 214869788
Change-Id: I31b4d1373c1388f7b51d0f2f45ce40aa8e8b0b58
In order to implement kill --all correctly, the Sentry needs
to track all tasks that belong to a given container. This change
introduces ContainerID to the task, that gets inherited by all
children. 'kill --all' then iterates over all tasks comparing the
ContainerID field to find all processes that need to be signalled.
PiperOrigin-RevId: 214841768
Change-Id: I693b2374be8692d88cc441ef13a0ae34abf73ac6
Old code was returning ID of the thread that created
the child process. It should be returning the ID of
the parent process instead.
PiperOrigin-RevId: 214720910
Change-Id: I95715c535bcf468ecf1ae771cccd04a4cd345b36
If we have an overlay file whose corresponding Dirent is frozen, then we should
not bother calling Readdir on the upper or lower files, since DirentReaddir
will calculate children based on the frozen Dirent tree.
A test was added that fails without this change.
PiperOrigin-RevId: 213531215
Change-Id: I4d6c98f1416541a476a34418f664ba58f936a81d
This makes `runsc wait` behave more like waitpid()/wait4() in that:
- Once a process has run to completion, you can wait on it and get its exit
code.
- Processes not waited on will consume memory (like a zombie process)
PiperOrigin-RevId: 213358916
Change-Id: I5b5eca41ce71eea68e447380df8c38361a4d1558
runApp.execute -> Task.SendSignal -> sendSignalLocked -> sendSignalTimerLocked
-> pendingSignals.enqueue assumes that it owns the arch.SignalInfo returned
from platform.Context.Switch.
On the other hand, ptrace.context.Switch assumes that it owns the returned
SignalInfo and can safely reuse it on the next call to Switch. The KVM platform
always returns a unique SignalInfo.
This becomes a problem when the returned signal is not immediately delivered,
allowing a future signal in Switch to change the previous pending SignalInfo.
This is noticeable in #38 when external SIGINTs are delivered from the PTY
slave FD. Note that the ptrace stubs are in the same process group as the
sentry, so they are eligible to receive the PTY signals. This should probably
change, but is not the only possible cause of this bug.
Updates #38
Original change by newmanwang <wcs1011@gmail.com>, updated by Michael Pratt
<mpratt@google.com>.
Change-Id: I5383840272309df70a29f67b25e8221f933622cd
PiperOrigin-RevId: 213071072
Linux permits hard-linking if the target is owned by the user OR the target has
Read+Write permission.
PiperOrigin-RevId: 213024613
Change-Id: If642066317b568b99084edd33ee4e8822ec9cbb3
The old kernel version, such as 4.4, only support 255 vcpus.
While gvisor is ran on these kernels, it could panic because the
vcpu id and vcpu number beyond max_vcpus.
Use ioctl(vmfd, _KVM_CHECK_EXTENSION, _KVM_CAP_MAX_VCPUS) to get max
vcpus number dynamically.
Change-Id: I50dd859a11b1c2cea854a8e27d4bf11a411aa45c
PiperOrigin-RevId: 212929704
Netstack needs to be portable, so this seems to be preferable to using raw
system calls.
PiperOrigin-RevId: 212917409
Change-Id: I7b2073e7db4b4bf75300717ca23aea4c15be944c
The contract in ExecArgs says that a reference on ExecArgs.Root must be held
for the lifetime of the struct, but the caller is free to drop the ref after
that.
As a result, proc.Exec must take an additional ref on Root when it constructs
the CreateProcessArgs, since that holds a pointer to Root as well. That ref is
dropped in CreateProcess.
PiperOrigin-RevId: 212828348
Change-Id: I7f44a612f337ff51a02b873b8a845d3119408707
This is different from the existing -pid-file flag, which saves a host pid.
PiperOrigin-RevId: 212713968
Change-Id: I2c486de8dd5cfd9b923fb0970165ef7c5fc597f0
We were previously openining the platform device (i.e. /dev/kvm) inside the
platfrom constructor (i.e. kvm.New). This requires that we have RW access to
the platform device when constructing the platform.
However, now that the runsc sandbox process runs as user "nobody", it is not
able to open the platform device.
This CL changes the kvm constructor to take the platform device FD, rather than
opening the device file itself. The device file is opened outside of the
sandbox and passed to the sandbox process.
PiperOrigin-RevId: 212505804
Change-Id: I427e1d9de5eb84c84f19d513356e1bb148a52910
We must use a context.Context with a Root Dirent that corresponds to the
container's chroot. Previously we were using the root context, which does not
have a chroot.
Getting the correct context required refactoring some of the path-lookup code.
We can't lookup the path without a context.Context, which requires
kernel.CreateProcArgs, which we only get inside control.Execute. So we have to
do the path lookup much later than we previously were.
PiperOrigin-RevId: 212064734
Change-Id: I84a5cfadacb21fd9c3ab9c393f7e308a40b9b537
This allows applications to verify they are running with gVisor. It
also helps debugging when running with a mix of container runtimes.
Closes#54
PiperOrigin-RevId: 212059457
Change-Id: I51d9595ee742b58c1f83f3902ab2e2ecbd5cedec
Before destroying the Kernel, we disable signal forwarding,
relinquishing control to the Go runtime. External signals that arrive
after disabling forwarding but before the sandbox exits thus may use
runtime.raise (i.e., tkill(2)) and violate the syscall filters.
Adjust forwardSignals to handle signals received after disabling
forwarding the same way they are handled before starting forwarding.
i.e., by implementing the standard Go runtime behavior using tgkill(2)
instead of tkill(2).
This also makes the stop callback block until forwarding actually stops.
This isn't required to avoid tkill(2) but is a saner interface.
PiperOrigin-RevId: 211995946
Change-Id: I3585841644409260eec23435cf65681ad41f5f03
It was always returning the MountNamespace root, which may be different from
the process Root if the process is in a chroot environment.
PiperOrigin-RevId: 211862181
Change-Id: I63bfeb610e2b0affa9fdbdd8147eba3c39014480
Ian Gudger
Nicolas Lacasse
Zhaozhong Ni
Kevin Krakauer
Adin Scannell
Michael Pratt
Brian Geffon
Jamie Liu
Sepehr Raissian
Fabricio Voznika
newmanwang
Chenggang
Rahat Mahmood