lock object (and thus off of each mutex and sx lock):
- Rename the all_locks list to pending_locks and only put locks initialized
before SI_SUB_WITNESS on the list so that the SI_SUB_WITNESS can add them
to witness once it starts up.
- Now that pending_locks is only used during early startup, change it from
a TAILQ to an STAILQ. This removes a pointer from the STAILQ_ENTRY in
struct lock_object.
- Since the pending_locks list is only used during the single-threaded
early boot it no longer needs to be protected by a mutex, so remove
all_mtx.
- Since the lo_list member of struct lock_object is now only used during
early boot before witness is running, collapse lo_list and lo_witness
into a union. This shaves the second pointer off of struct lock_object.
- Axe lock_cur_cnt and lock_max_cnt.
With these changes, struct mtx shrinks from 36 to 28 bytes on 32-bit
platforms and from 72 to 56 bytes on 64-bit platforms. Note that this
commit will completely and utterly destroy the kernel ABI, so no MFC.
Tested on: alpha, amd64, i386, sparc64
sosend(). Robert accidentally changed the snderr() macro to jump to the
out label which assumes the lock is already released rather than the
release label which drops the lock in his previous change to sosend().
This should fix the recent panics about returning from write(2) with the
socket lock held and the most recent LOR on current@.
process as over the limit when its time is >= to the limit rather than >
the limit. Technically, if p->p_rux.rux_runtime.sec == p->p_pcpulimit
and p->p_rux.rux_runtime.frac == 0, the process hasn't exceeded the limit
yet. However, having the fraction exactly equal to 0 is rather rare, and
it is not worth the overhead to handle that edge case. With just the >
comparison, the process would have to exceed its limit by almost a second
before it was killed.
PR: kern/83192
Submitted by: Maciej Zawadzinski mzawadzinski at gmail dot com
Reviewed by: bde
MFC after: 1 week
chains and copying in mbufs from the body of the send logic, creating
a new function sosend_copyin(). This changes makes sosend() almost
readable, and will allow the same logic to be used by tailored socket
send routines.
MFC after: 1 month
Reviewed by: andre, glebius
application wishes to request high precision time stamps be returned:
Alias Existing
CLOCK_REALTIME_PRECISE CLOCK_REALTIME
CLOCK_MONOTONIC_PRECISE CLOCK_MONOTONIC
CLOCK_UPTIME_PRECISE CLOCK_UPTIME
Add experimental low-precision clockid_t names corresponding to these
clocks, but implemented using cached timestamps in kernel rather than
a full time counter query. This offers a minimum update rate of 1/HZ,
but in practice will often be more frequent due to the frequency of
time stamping in the kernel:
New clockid_t name Approximates existing clockid_t
CLOCK_REALTIME_FAST CLOCK_REALTIME
CLOCK_MONOTONIC_FAST CLOCK_MONOTONIC
CLOCK_UPTIME_FAST CLOCK_UPTIME
Add one additional new clockid_t, CLOCK_SECOND, which returns the
current second without performing a full time counter query or cache
lookup overhead to make sure the cached timestamp is stable. This is
intended to support very low granularity consumers, such as time(3).
The names, visibility, and implementation of the above are subject
to change, and will not be MFC'd any time soon. The goal is to
expose lower quality time measurement to applications willing to
sacrifice accuracy in performance critical paths, such as when taking
time stamps for the purpose of rescheduling select() and poll()
timeouts. Future changes might include retrofitting the time counter
infrastructure to allow the "fast" time query mechanisms to use a
different time counter, rather than a cached time counter (i.e.,
TSC).
NOTE: With different underlying time mechanisms exposed, using
different time query mechanisms in the same application may result in
relative non-monoticity or the appearance of clock stalling for a
single clockid_t, as a cached time stamp queried after a precision
time stamp lookup may be "before" the time returned by the earlier
live time counter query.
directly. We need to copyin() the strings in the iovec before
we can strcmp() them. Also, when we want to send the errmsg back
to userspace, we need to copyout()/copystr() the string.
Add a small helper function vfs_getopt_pos() which takes in the
name of an option, and returns the array index of the name in the iovec,
or -1 if not found. This allows us to locate an option in
the iovec without actually manipulating the iovec members. directly via
strcmp().
Noticed by: kris on sparc64
connection queue for a new connection. It was removing connections
from the wrong list.
Submitted by: Paul Mikesell
Sponsored by: Isilon Systems
MFC after: 1 week
When all file systems have a time stamp of zero, which is the case
for example when the root file system is on a read-only medium, we
ended up not calling inittodr() at all. A potential uncleanliness
existed as well. If multiple file systems had a non-zero time stamp,
we would call inittodr() multiple times. While this should not be
harmful, it's definitely not ideal.
Fix both issues by iterating over the mounted file systems to find
the largest time stamp and call inittodr() exactly once with that
time stamp. This could of course be a zero time stamp if none of the
mounted file systems have a non-zero time stamp. In that case the
annoying errors mentioned in the commit log for revision 1.186 still
haven't been avoided. The bottom line is that inittodr() should not
complain when it gets a time base of zero. At the time of this
commit only alpha seems to have that problem.
Reported by: Dario Freni (saturnero at freesbie dot org)
MFC after: 1 week
is called. It looks like there are lots of different mount flags checked
in vfs_domount(), so we need to do the parsing for these particular
mount flags earlier on. The new flags parsed are:
async, force, multilabel, noasync, noatime, noclusterr, noclusterw,
noexec, nosuid, nosymfollow, snapshot, suiddir, sync, union.
Existing code which uses mount() to mount UFS filesystems is not
affected, but new code which uses nmount() to mount UFS filesystems
should behave better.
in, and if so, set MNT_UPDATE filesystem flag.
vfs_nmount() calls vfs_domount(), and there is special logic
inside vfs_domount() if MNT_UPDATE is set. This is very important
when we want to do an update mount of the root filesystem, using nmount().
execute a ET_DYN binary (shared object).
This does not make much sense, but some linux scripts expect to be able to
execute /lib/ld-linux.so.2 (ldd comes to mind).
The sysctl defaults to 0.
MFC after: 3 days
currently present is minor and offers no real semantic issues, it also
doesn't make sense since an earlier lockless check has already
occurred. Also hold the mutex longer, over a manipulation of
per-process ktrace state, which requires synchronization.
MFC after: 1 month
Pointed out by: jhb
reliability when tracing fast-moving processes or writing traces to
slow file systems by avoiding unbounded queueuing and dropped records.
Record loss was previously possible when the global pool of records
become depleted as a result of record generation outstripping record
commit, which occurred quickly in many common situations.
These changes partially restore the 4.x model of committing ktrace
records at the point of trace generation (synchronous), but maintain
the 5.x deferred record commit behavior (asynchronous) for situations
where entering VFS and sleeping is not possible (i.e., in the
scheduler). Records are now queued per-process as opposed to
globally, with processes responsible for committing records from their
own context as required.
- Eliminate the ktrace worker thread and global record queue, as they
are no longer used. Keep the global free record list, as records
are still used.
- Add a per-process record queue, which will hold any asynchronously
generated records, such as from context switches. This replaces the
global queue as the place to submit asynchronous records to.
- When a record is committed asynchronously, simply queue it to the
process.
- When a record is committed synchronously, first drain any pending
per-process records in order to maintain ordering as best we can.
Currently ordering between competing threads is provided via a global
ktrace_sx, but a per-process flag or lock may be desirable in the
future.
- When a process returns to user space following a system call, trap,
signal delivery, etc, flush any pending records.
- When a process exits, flush any pending records.
- Assert on process tear-down that there are no pending records.
- Slightly abstract the notion of being "in ktrace", which is used to
prevent the recursive generation of records, as well as generating
traces for ktrace events.
Future work here might look at changing the set of events marked for
synchronous and asynchronous record generation, re-balancing queue
depth, timeliness of commit to disk, and so on. I.e., performing a
drain every (n) records.
MFC after: 1 month
Discussed with: jhb
Requested by: Marc Olzheim <marcolz at stack dot nl>
happiness, as well as correct other bugs:
- Replace notion of current and saved accounting credential/vnode with a
single credential/vnode and an acct_suspended flag. This simplifies the
accounting logic substantially.
- Replace acct_mtx with acct_sx, a sleepable lock held exclusively during
reconfiguration and space polling, but shared during log entry
generation. This avoids holding a mutex over sleepable VFS operations.
- Hold the sx lock over the duration of the I/O so that the vnode I/O
cannot occur after vnode close, which could occur previously if
accounting was disabled as a process exited.
- Write the accounting log entry with Giant conditionally acquired based
on the file system where the log is stored. Previously, the accounting
code relied on the caller acquiring Giant.
- Acquire Giant conditionally in the accounting callout based on the file
system where the accounting log is stored. Run the callout MPSAFE.
- Expose acct_suspended via a read-only sysctl so it is possibly to
programmatically determine whether accounting is suspended or not without
attempting to parse logs.
- Check both acct_vp and acct_suspended lock-free before entering the
accounting sx lock in acct().
- When accounting is disabled due to a VBAD vnode (i.e., forceable unmount),
generate a log message indicating accounting has been disabled.
- Correct a long-standing bug in how free space is calculated and compared
to the required space: generate and compare signed results, not unsigned
results, or negative free space will cause accounting to not be suspended
when required, or worse, incorrectly resumed once negative free space is
reached.
MFC after: 2 weeks
socket file descriptor garbage collection code, which is intended to
detect and clear cycles of orphaned file descriptors that are "in-flight"
in a socket when that socket is closed before they are received. The
algorithm present was both run at poor times (resulting in recursion and
reentrance), and also buggy in the presence of parallelism. In order to
fix these problems, make the following changes:
- When there are in-flight sockets and a UNIX domain socket is destroyed,
asynchronously schedule the garbage collector, rather than running it
synchronously in the current context. This avoids lock order issues
when the garbage collection code reenters the UNIX domain socket code,
avoiding lock order reversals, deadlocks, etc. Run the code
asynchronously in a task queue.
- In the garbage collector, when skipping file descriptors that have
entered a closing state (i.e., have f_count == 0), re-test the FDEFER
flag, and decrement unp_defer. As file descriptors can now transition
to a closed state, while the garbage collector is running, it is no
longer the case that unp_defer will remain an accurate count of
deferred sockets in the mark portion of the GC algorithm. Otherwise,
the garbage collector will loop waiting waiting for unp_defer to reach
zero, which it will never do as it is skipping file descriptors that
were marked in an earlier pass, but now closed.
- Acquire the UNIX domain socket subsystem lock in unp_discard() when
modifying the unp_rights counter, or a read/write race is risked with
other threads also manipulating the counter.
While here:
- Remove #if 0'd code regarding acquiring the socket buffer sleep lock in
the garbage collector, this is not required as we are able to use the
socket buffer receive lock to protect scanning the receive buffer for
in-flight file descriptors on the socket buffer.
- Annotate that the description of the garbage collector implementation
is increasingly inaccurate and needs to be updated.
- Add counters of the number of deferred garbage collections and recycled
file descriptors. This will be removed and is here temporarily for
debugging purposes.
With these changes in place, the unp_passfd regression test now appears
to be passed consistently on UP and SMP systems for extended runs,
whereas before it hung quickly or panicked, depending on which bug was
triggered.
Reported by: Philip Kizer <pckizer at nostrum dot com>
MFC after: 2 weeks
state about each open file, and identify the first process in the process
table that references the file. This is helpful in debugging leaks of
file descriptors.
MFC after: 1 week
The PR and patch have the details. The ultimate fix requires architectural
changes and clarifications to the VFS API, but this will prevent the system
from panicking when someone does "ls /dev" while running in a shell under the
linuxulator.
This issue affects HEAD and RELENG_6 only.
PR: 88249
Submitted by: "Devon H. O'Dell" <dodell@ixsystems.com>
MFC after: 3 days
with the file descriptor. When a file descriptor is closed as a result
of garbage collecting a UNIX domain socket, the file descriptor will
not have any associated thread, so the logic to identify advisory locks
held by that thread is not appropriate. Check the thread for NULL to
avoid this scenario. Expand an existing comment to say a bit more about
this.
MFC after: 1 week
thread context. While it doesn't matter too much at the moment, in
the future we could be back in the same boat if/when more restrictions
are placed (or enforced) in a SWI.
Suggested by: njl, bde, jhb, scottl
in the hardware interrupt context (even if it is likely just an
ithread). We don't document that suspend/resume routines are run from
such a context and some of the things that happen in those routines
aren't interrupt safe. Since there's no real need to run from that
context, this restores assumptions that suspend routines have made.
This fixes Thierry Herbelot's 'Trying to sleep while sleeping is
prohibited' problem.
