Fix pthread_cond_timedwait to set the absolute timer using a timepoint,
instead of the old s64.

Moreover, now that we have both a wall-clock and monotonic clock, we
can support pthread_condattr_setclock, so this patch also adds this
support. OpenJDK 8, for example, cannot run without this support (it
assumes that if the OS supports CLOCK_MONOTONIC, it can also configure
condition variables to use it).

Unfortunately supporting pthread_condattr_setclock - the only condition-
variable attribute that really exists - grows the pthread condition
variable structure :(

Fixes #168.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Drop the s64 literals _ms, _ns, etc., from <drivers/clock.hh>.
Fix a few places which still use the old literals.

The std:chrono::duration version from <osv/clock.hh> remains -
but remember you need to "using namespace osv::clock::literals"
to use them.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Change alarm() implementation to use the new <osv/clock.hh> APIs and the
monotonic clock.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Delete the sched::thread::sleep_until() function. All users of this
function actually wanted a relative time, not absolute time, and can
use the simpler new sched::thread::sleep() instead.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Switch the timerfd to use std::chrono types, and add support also for the
monotonic clock.

Fixes #142.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Switch the thread scheduler from using the s64 type for durations and
the wall time, to the osv::clock::uptime::duration type (which is
std::chrono::nanoseconds) and monotonic clock.

Also, now that the per-thread CPU-time clock (thread::thread_clock())
returns an std::chrono::duration instead of s64, we no longer need the
fill_ts(s64) variant in libc/time.cc (if we leave it unused, we'll get a
compilation warning).

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Move definitions from <debug.h> to <osv/debug.h> and update includes to
use the latter.

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Reviewed-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Reviewed-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Reviewed-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Vlad Zolotarov <vladz@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

sysinfo() until now was a stub. This patches fills some of the information
we can already provide, namely the uptime in seconds (through the recently
added osv::clock::uptime()), the total and free memory (through the recently
added memory::stats::free()/total() functions), and number of processes
(always 1 on OSv).

This patch also changes a couple of types from unsized names (like "unsigned")
to fixed-sized ones (like "u32"), to match the definition of this structure
on Linux. It won't make any difference on x86_64, but perhaps in some future
architecture it will.

Tested-by: Amnon Heiman <amnon@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Currently, RLIMIT_STACK is 64 KB.  This is too small for the JVM which
limits stack size to RLIMIT_STACK if a VMA range that covers address
found in '__libc_stack_end' in /proc/self/maps.

In preparation for procfs support, switch to pthread_attr_getstacksize()
for RLIMIT_STACK.

Reviewed-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Add pthread_attr_getstacksize() in preparation for fixing RLIMIT_STACK.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Reviewed-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Output to stdout normally goes to file descriptor 1. However, during
early boot, before the console is opened on file descriptor 1, we also
want printf() to work. So this case is specially treated in
libc/stdio/__stdout_write.cc, where in this early case, we used debug_write
directly, instead of write to the file descriptor.

However, recent patches changed debug_write to write to a memory buffer,
instead of to screen (unless "--verbose" option is given to the loader).
This made early printf() break too.

This patch changes __stdout_write to use console::write(), not
debug_write(). To use console::write(), I had to convert that source
file to C++.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Add a type-safe std::chrono interface to the wall-clock time. E.g., use
use osv::clock::wall::now() to get an std::chrono::time_point instead
of clock::get()->time() which returns an s64.

This patch also changes clock_gettime(CLOCK_REALTIME) and gettimeofday()
to use the new osv::clock::wall::now() interface.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Signed-off-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Move alarm cancellation logic to a separate function
cancel_alarm_ll(). This fucntion will be called on
thread destruction to avoid post-mortem alarms.

Also move alarm scheduling logic to a separate function
set_alarm_ll() to make code symmetric.

Signed-off-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

The code "file_ts" converting a std::chrono::duration into a struct timespec,
was unnecessarily constrained to take as input a std::chrono::nanoseconds,
whereas it can actually work with durations of any resolution (the
duration_cast will convert it to the correct units), so this patch makes
this generalization which, I think, makes the code clearer.

At first I decided to move this general function into <osv/clock.hh> and
make it a bit more friendly (returning a timespec, instead of writing into
one), but at the end, I decided not to move it. typespec is a dangerous
type because though it does specify the clock's resolution (always
nanoseconds) it doesn't specify the clock's epoch, so one can make mistakes
like calling clock_gettime(CLOCK_MONOTONIC), and pass the returned timespec
to pthread_cond_timedwait, which expects CLOCK_REALTIME not CLOCK_MONOTONIC.
So we should avoid timespec whenever we can, and I don't think we'll need
the fill_ts() function anywhere outside time.cc.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

We are currently only answering requests for CLOCK_REALTIME, but we could
easily handle:

    * CLOCK_REALTIME_COARSE, which is effective the same as CLOCK_REALTIME
      but faster. In our case, all time sources are equally fast
    * CLOCK_PROCESS_CPUTIME_ID and CLOCK_THREAD_CPUTIME_ID, since we can
      easily get runtimes for our threads and publish that.

Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

This patch starts to solve both issue #142 ("Support MONOTONIC_CLOCK")
and issue #81 (use <chrono> for time).

First, it adds an uptime() function to the "clock" interface, and
implements it for kvm/xen/hpet by returning the system time from which
we subtract the system time at boot (but not adding any correction
for wallclock).

Second, it adds a new std::chrono-based interface to this clock, in
a new header file <osv/clock.hh>. Instead of the old-style
clock::get()->uptime(), one should prefer osv::clock::uptime::now().
This returns a std::chrono::time_point which is type-safe, in the
sense that: 1. It knows what its epoch is (i.e., that it belongs to
osv::clock::uptime), and 2. It knows what its units are (nanoseconds).
This allows the compiler to prevent a user from confusing measurements
from this clock with those from other clocks, or making mistakes in
its units.

Third, this patch implements clock_gettime(MONOTONIC_CLOCK), using
the new osv::clock::uptime::now().

Note that though the new osv::clock::uptime is almost identical to
std::chrono::steady_clock, they should not be confused. The former is
actually OSv's implementation of the latter: steady_clock is implemented
by the C++11 standard library using the Posix clock_gettime, and that
is implemented (in this patch) using osv::clock::uptime.

With this patch, we're *not* done with either issues #142 or #81.
For issue #142, i.e., for supporting MONOTONIC_CLOCK in timerfd, we
need OSv's timers to work on uptime(), not on clock::get()->time().
For issue #81, we should add a osv::clock::wall type too (similar to
what clock::get()->time() does today, but more correctly), and use either
osv::clock::wall or osv::clock::uptime everywhere that
clock::get()->time() is currently used in the code.
clock::get()->time() should be removed.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

The current implementation of memmove is a PITA (I mean the bread, of course)
to decode if a fault happens. We have very little control of where exactly in
the code the fault happens, therefore it is difficult to reason about it. This
patch implements memmove in terms of memcpy + memcpy_backwards.

For those, we can have specific fixups in the possible fault sites, that will
allow us to decode the faults with ease.

Note that originally, the only reason why the first branch was not a memcpy is
that we would like to handle alignment. Since our implementation of memcpy is
fast enough, we can just ignore that and we will end up being even faster.

Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

In his review of timerfd.cc, Avi asked that I simplify the implementation
by having a single "timerfd" object (instead of two I had - timerfd_file
and timerfd_object), and by using a single mutex instead of the complex
combination of mutexes and atomic variable.

This new version indeed does this. It should be easier to understand this
code, and it is 30 lines shorter.

The performance of this code is slightly inferior to the previous one -
in particular poll() now locks and unlocks a mutex - but this should be
negligible in practice.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

This patch implements a simplified version of pthread_getcpuclockid
that should be enough for our needs.

Reviewed-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

This is not a documented behavior but glibc's dlopen behaves this way.

Spotted when debugging assertion failure when java is started with a
debugger, we try to read elf header from "/" on dlopen("", ...):

Assertion failed: data.uio_resid == 0 (osv/fs/fs.cc: read: 27)

Signed-off-by: Tomasz Grabiec <tgrabiec@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Each implementation of "struct file" needs to implement 8 different file
operations. Most special file implementations, such as pipe, socketpair,
epoll and timerfd, don't support many of these operations. We had in
unsupported.h functions that can be reused for the unsupported operation,
but this resulted in a lot of ugly boiler-plate code.

Instead, this patch switches to a cleaner, more C++-like, method:
It defines a new "file" subclass, called "special_file", which implements
all file operations except close(), with a default implementation identical
to the old unsupported.h implementations.

The files of pipe(), socketpair(), timerfd() and epoll_create() now inherit
from special_file, and only override the file operations they really want
to implement.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Avi Kivity <avi@cloudius-systems.com>

Right now most of mmap related functions have the same bug related to vma
locking: they validate mapping under vma lock then release the lock
and do actual vma operation, but since between validation and operation
the mapping can go away it is incorrect. This patch fixes this by doing
validation and operation under the same lock.

Signed-off-by: Gleb Natapov <gleb@cloudius-systems.com>
Signed-off-by: Avi Kivity <avi@cloudius-systems.com>

mprotect(PROT_WRITE) on a file opened as read only should fail,
but current mprotect() implementation is missing the check. The patch
implements it.

Signed-off-by: Gleb Natapov <gleb@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

getgrgid_r(3) is needed when querying file attributes from Java (see
java.nio.file.Files.readAttributes()).
This is needed for long format (-l) flag of ls.

getgrgid_r also requires sysconf(_SC_GETGR_R_SIZE_MAX)

Signed-off-by: Or Cohen <orc@fewbytes.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

We use sched::thread::attr to pass parameters to sched::thread creation,
i.e., create a thread with non-default stack parameters, pinned to a
particular CPU, or a detached thread.

Previously we had constructors taking many combinations of stack size
(integer), pinned cpu (cpu*) and detached (boolean), and doing "the
right thing". However, this makes the code hard to read (what does
attr(4096) specify?) and the constructors hard to expand with new
parameters.

Replace the attr() constructors with the so-called "named parameter"
idiom: attr now only has a null constructor attr(), and one modifies
it with calls to pin(cpu*), detach(), or stack(size).

For example,
    attr()                                  // default attributes
    attr().pin(sched::cpus[0])              // pin to cpu 0
    attr().stack(4096).pin(sched::cpus[0])  // pin and non-default stack
    and so on.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Avi Kivity <avi@cloudius-systems.com>

This patch implements the Linux's timerfd_*() system calls, declared in
<sys/timerfd.h>. These define a file descriptor, usable for read() or
poll() and friends, which becomes readable when a timer expires.

This aspires to be a full implementation of timerfd, with all the intricate
details explained in timerfd_create(2).

timerfd was added to Linux five years ago (Linux 2.6.25). Boost's asio,
in particular, uses this feature if it thinks it is available.

Fixes #129.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

mprotect() should fails with ENOMEM if it is called on non mapped
virtual address, but this check is done by mmu::ismapped().

Signed-off-by: Gleb Natapov <gleb@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

af_local.h declares a couple of functions implemented in af_local.cc.
There is no reason for pipe.cc to include it.

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

This patch changes backtrace() to use the _Unwind_* facilities provided
by the GCC runtime (libgcc_eh.a), instead of the separate libunwind.a.

After this patch, we don't use libunwind.a in OSv any more, and it can
be removed (see issue #83).

Signed-off-by: Nadav Har'El <nyh@cloudius-systems.com>
Signed-off-by: Avi Kivity <avi@cloudius-systems.com>