Tracepoint argument which extends 'blob_tag' will be interpreted as a
range of byte-sized values. Storage required to serialize such object
is proportional to its size.

I need it to implement storage-fiendly packet capturing using tracing layer.

It could be also used to capture variable length strings. Current
limit (50 chars) is too short for some paths passed to vfs calls. With
variable-length encoding, we could set a more generous limit.

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

If the rcu threads need memory, let them have it, since they will use it
to free even more memory.

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

malloc() must wait for memory, and since page table operations can
allocate memory, it must be able to dip into the reserve pool.  free()
should indicate it is a reclaimer.

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

We already have a facility that to indicate that a thread is a reclaimer
and should be allowed to allocate reserve memory (since that memory will be
used to free memory).  Extend it to allow indicating that a particular
code section is used to free memory, not the entire thread.

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

After the previous patches, when we try to run an executable we cannot
read (e.g., a directory - see issue #94), a "struct error" exception will
be thrown out of osv::run, and nobody will catch it so the user will see
a somewhat-puzzling "uncaught exception" error.

With this patch, we catch the read error exception inside osv::run(), and
when it happens, just return a normal load failure (nullptr). E.g, now
trying to run a directory will result in a normal failure:

   $ scripts/run.py -e /
   OSv v0.07-39-g03feb99
   run_main(): cannot execute /. Powering off.

Fixes #94.

The osv::run() API currently (before this patch, and also after it)
doesn't have any way to say *why* the loading failed - it could have been
that the executable was a directory, that it was not an ELF shared object,
that it was a shared object and didn't have a main - in all cases the
return value is nullptr. In the future this should probably change.

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

read(fileref, ...) and write(fileref, ...), when they notice an error,
currently assert() causing a crash which looks to non-expert users like
an OSv bug. This causes, for example, bug #94, where doing osv::run()
of a directory, instead of an executable, causes such an assertion
failure.

With this patch, these read() and write() will throw an exception
(a struct error) instead of asserting.

This fixes #94, as now the user will see an uncaught exception instead
of buggy-looking assertion failure. In the next patch we'll catch this
exception, so the user won't even see that.

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

No longer used.

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

The bug that caused it to be disabled should be fixed now.

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

Now vma_list_mutex is used to protect against races between ARC buffer
mapping by MMU and eviction by ZFS. The problem is that MMU code calls
into ZFS with vma_list_mutex held, so on that path all ZFS related locks
are taken after vma_list_mutex. An attempt to acquire vma_list_mutex
during ARC buffer eviction, while many of the same ZFS locks are already
held, causes deadlock. It was solved by using trylock() and skipping an
eviction if vma_list_mutex cannot be acquired, but it appears that some
mmapped buffers are destroyed not during eviction, but after writeback and
this destruction cannot be delayed. It calls for locking scheme redesign.

This patch introduce arc_lock that have to be held during access to
read_cache. It prevents simultaneous eviction and mapping. arc_lock should
be the most inner lock held on any code path. Code is change to adhere to
this rule. For that the patch replaces ARC_SHARED_BUF flag by new b_mmaped
field. The reason is that access to b_flags field is guarded by hash_lock
and it is impossible to guaranty same order between hash_lock and arc_lock
on all code paths. Dropping the need for hash_lock is a nice solution.

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

Currently page_allocator return a page to a page mapper and the later
populates a pte with it. Sometimes page allocation and pte population
needs to be appear atomic though. For instance in case of a pagecache
we want to prevent page eviction before pte is populated since page
eviction clears pte, but if allocation and mapping is not atomic pte
can be populated with stale data after eviction. With current approach
very wide scoped lock is needed to guaranty atomicity. Moving pte
population into page_allocator allows for much simpler locking.

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

Current code assumes that for the same file and same offset ZFS will
always return same ARC buffer, but this appears to be not the case.
ZFS may create new ARC buffer while an old one is undergoing writeback.
It means that we need to track mapping between file/offset and mmapped
ARC buffer by ourselves. It's exactly what this patch is about. It adds
new kind of cached page that holds pointers to an ARC buffer and stores
them in new read_cache map.

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

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

All pagecache functions run under vma_list_lock, so no additional
locking is needed.

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

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

Unmap page as soon as possible instead of waiting for max_pages to
accumulate. Will allow to free pages outside of vma_list_mutex in the
feature.

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

Useful for debugging cache related problems.

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

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

sys_read() error should be propagated to an application, but for now
assert here instead of silent memory corruption.

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

rmap will usually contain only one element so using unordered_set for it
is a little bit heavy. boost::variant allow us to use direct pointer in
common case and fall back to unordered_set only when more than one
elements are added.

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

Write permission should not be granted to ptes that has no write
permission because they are COW, but currently there is no way to
distinguish between write protection due to vma permission and write
protection due to COW. Use bit reserved for software use in pte as a
marker for COW ptes and check it during permission changes.

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

Mapping page as dirty saves CPU from doing additional memory access to
write out dirty bit when access will succeed.

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

Posix allows read() on directories in some filesystems. However, Linux
always returns EISDIR in this case, so because we're emulating Linux,
so should we, for every filesystem. All our filesystems except ZFS
(e.g., ramfs) already return EISDIR when reading a directory, but ZFS
doesn't, so this patch adds the missing check in ZFS.

This patch is related to issue #94: the first step to fixing #94 is to
return the right error when reading a directory.

This patch also adds a test case, which can be compiled both on OSv and
Linux, to verify they both have the same behavior. Before the patch, the
test succeeded on Linux but failed on OSv when the directory is on ZFS.

Instead of fixing zfs_read like I do in this patch, I could have also fixed
sys_read() in vfs_syscalls.cc which is the top layer of all read()
operations, and I could have done there
   (fp->f_dentry && fp->f_dentry->d_vnode->v_type == VDIR) {
      return EISDIR;
   }
to cover all the filesystems. I decided not to do that, because all
filesystems except ZFS already have this check, and because the lower
layers like zfs_read() already have more natural access to d_vnode.

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>

txq_encap decrements txq.avail for each mbuf, so we need to increment same number here.

Reviewed-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
Signed-off-by: Takuya ASADA <syuu@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

This patch implements a version of flock that only performs error checking.
It assumes any valid operation succeeds, since we are using a single-process
model.

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

The jemalloc memory allocator will make intense use of MADV_DONTNEED to flush
pages it is no longer using. Respect that advice.

Let's keep returning -1 for the remaining cases so we don't fool anybody

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

MongoDB wants it. In general, I am providing the information that is easy
to get, and ignoring the ones which are not - with the exception of process
count, that seemed easy enough to implement.

This is the kind of thing Mongo does with it:

2014-04-15T09:54:12.322+0000 [clientcursormon] mem (MB) res:670160 virt:25212
2014-04-15T09:54:12.323+0000 [clientcursormon]  mapped (incl journal view):160
2014-04-15T09:54:12.324+0000 [clientcursormon]  connections:0

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

This is one of the statistics that shows up in /proc/self/stat under Linux, but
this is generally interesting for applications. Since we don't have kernel mode
and userspace mode, it is very hard to differentiate between "time spent in
userspace" and "kernel time spent on behalf of the process". Therefore, we will
present system time as always 0. If we wanted, we could at least differentiate
clearly osv-specific threads as system time, but there is no need to go through
the trouble now.

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

It will be used for procfs compatibility. Applications may want to know how much
memory is potentially available through mmap mappings (not necessarily allocated).

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

The current code does not allow ioctls on unix sockets, but real world
applications - nginx in my example will issue them. I am starting by
implementing FIONBIO to set blocking/nonblocking mode.

I notice here that we already have a flag in the read and write functions, and
they seem to handle that flag: the internal pipe_buffer implementation does
check and act on it.

So let's just flip it.

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>

First of all, we need the symbol. But so far it is fine returning EINVAL to
everybody except for PR_SET_DUMPABLE. There are situations (see man prctl) in
which this flag is automatically cleared. Some programs (nginx here) will then
proceed to set it to make sure it is on. The flag itself is meanginless to us,
since we are not producing per-thread coredumps, and when we do dump, we will
dump regardless of this. But we need the call to suceed.

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>

empty implementation will suit us.

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

Nadav says:
The clock() function is stubbed. We can easily implement it by calling
clock_gettime(CLOCK_PROCESS_CPUTIME_ID).

Closes #275.

Reviewed-by: Glauber Costa <glommer@cloudius-systems.com>
Signed-off-by: Raphael S. Carvalho <raphaelsc@cloudius-systems.com>
Signed-off-by: Pekka Enberg <penberg@cloudius-systems.com>

Compile tst-mmap.so with "-z now", so that symbols are resolved at load
time instead of when needed.

The problem was that tst-mmap uses wait_until, which runs the functions
sched::thread::wait() and sched::thread::stop_wait() while preemption is
disabled. In about 1 in 10 runs of tst-mmap.so, this caused an assertion-
failure crash (symbol resolution caused sleeping while preemption is disabled).

Fixes #256.

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

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

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

Same as we currently have for AS, show that value as unlimited.

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>

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

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

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