callout is started before kern_setitimer() acquires process mutex, but
looses a race and kern_setitimer() gets the process mutex before the
callout. Then, assuming that new specified struct itimerval has
it_interval zero, but it_value non-zero, the callout, after it starts
executing again, clears p->p_realtimer.it_value, but kern_setitimer()
already rescheduled the callout.
As the result of the race, both p_realtimer is zero, and the callout
is rescheduled. Then, in the exit1(), the exit code sees that it_value
is zero and does not even try to stop the callout. This allows the
struct proc to be reused and eventually the armed callout is
re-initialized. The consequence is the corrupted callwheel tailq.
Use process mutex to interlock the callout start, which fixes the race.
Reported and tested by: pho
Reviewed by: jhb
MFC after: 2 weeks
over the active list. The mount interlock is not enough to guarantee
the validity of the tailq link pointers. The __mnt_vnode_next_active()
and __mnt_vnode_first_active() active lists iterators helper functions
did not provided the neccessary stability for the list, allowing the
iterators to pick garbage.
This was uncovered after the r243599 made the active list iterators
non-nop.
Since a vnode interlock is before the vnode_free_list_mtx, obtain the
vnode ilock in the non-blocking manner when under vnode_free_list_mtx,
and restart iteration after the yield if the lock attempt failed.
Assert that a vnode found on the list is active, and assert that the
helpers return the vnode with interlock owned.
Reported and tested by: pho
MFC after: 1 week
Fix path handling for *at() syscalls.
Before the change directory descriptor was totally ignored,
so the relative path argument was appended to current working
directory path and not to the path provided by descriptor, thus
wrong paths were stored in audit logs.
Now that we use directory descriptor in vfs_lookup, move
AUDIT_ARG_UPATH1() and AUDIT_ARG_UPATH2() calls to the place where
we hold file descriptors table lock, so we are sure paths will
be resolved according to the same directory in audit record and
in actual operation.
Sponsored by: FreeBSD Foundation (auditdistd)
Reviewed by: rwatson
MFC after: 2 weeks
Remove redundant call to AUDIT_ARG_UPATH1().
Path will be remembered by the following NDINIT(AUDITVNODE1) call.
Sponsored by: FreeBSD Foundation (auditdistd)
MFC after: 2 weeks
variable as they may overflow on i386/PAE and i386 with > 2GB RAM.
Use 64bit quad_t instead. It has broader kernel infrastructure support
with TUNABLE_QUAD_FETCH() and qmin/qmax() than other available types.
Pointed out by: alc, bde
kernel memory, whichever is lower. The overall mbuf related memory
limit must be set so that mbufs (and clusters of various sizes)
can't exhaust physical RAM or KVM.
The limit is set to half of the physical RAM or KVM (whichever is
lower) as the baseline. In any normal scenario we want to leave
at least half of the physmem/kvm for other kernel functions and
userspace to prevent it from swapping too easily. Via a tunable
kern.maxmbufmem the limit can be upped to at most 3/4 of physmem/kvm.
At the same time divorce maxfiles from maxusers and set maxfiles to
physpages / 8 with a floor based on maxusers. This way busy servers
can make use of the significantly increased mbuf limits with a much
larger number of open sockets.
Tidy up ordering in init_param2() and check up on some users of
those values calculated here.
Out of the overall mbuf memory limit 2K clusters and 4K (page size)
clusters to get 1/4 each because these are the most heavily used mbuf
sizes. 2K clusters are used for MTU 1500 ethernet inbound packets.
4K clusters are used whenever possible for sends on sockets and thus
outbound packets. The larger cluster sizes of 9K and 16K are limited
to 1/6 of the overall mbuf memory limit. When jumbo MTU's are used
these large clusters will end up only on the inbound path. They are
not used on outbound, there it's still 4K. Yes, that will stay that
way because otherwise we run into lots of complications in the
stack. And it really isn't a problem, so don't make a scene.
Normal mbufs (256B) weren't limited at all previously. This was
problematic as there are certain places in the kernel that on
allocation failure of clusters try to piece together their packet
from smaller mbufs.
The mbuf limit is the number of all other mbuf sizes together plus
some more to allow for standalone mbufs (ACK for example) and to
send off a copy of a cluster. Unfortunately there isn't a way to
set an overall limit for all mbuf memory together as UMA doesn't
support such a limiting.
NB: Every cluster also has an mbuf associated with it.
Two examples on the revised mbuf sizing limits:
1GB KVM:
512MB limit for mbufs
419,430 mbufs
65,536 2K mbuf clusters
32,768 4K mbuf clusters
9,709 9K mbuf clusters
5,461 16K mbuf clusters
16GB RAM:
8GB limit for mbufs
33,554,432 mbufs
1,048,576 2K mbuf clusters
524,288 4K mbuf clusters
155,344 9K mbuf clusters
87,381 16K mbuf clusters
These defaults should be sufficient for even the most demanding
network loads.
MFC after: 1 month
accept queues a new socket/connection may be added to the queue
due to a race on the ACCEPT_LOCK.
The submitted patch is slightly changed in comments, teardown
and locking order and extended with KASSERT's.
Submitted by: Vijay Singh <vijju.singh-at-gmail-dot-com>
Found by: His team.
MFC after: 1 week
is in capability mode.
- Add VN_OPEN_NOCAPCHECK flag for vn_open_cred() to will ne converted into
NOCAPCHECK namei flag.
This functionality will be used to enable core dumps for sandboxed processes.
Reviewed by: rwatson
Obtained from: WHEEL Systems
MFC after: 2 weeks
to himself. For example abort(3) at first tries to do kill(getpid(), SIGABRT)
which was failing in capability mode, so the code was failing back to exit(1).
Reviewed by: rwatson
Obtained from: WHEEL Systems
MFC after: 2 weeks
There has not been any complaints about the default behavior, so there
is no need to keep a knob that enables the worse alternative.
Now that the hard-stopping of other CPUs is the only behavior, the panic_cpu
spinlock-like logic can be dropped, because only a single CPU is
supposed to win stop_cpus_hard(other_cpus) race and proceed past that
call.
MFC after: 1 month
the unix domain sockets to the next tick, coalescing the serial calls
until the collection fires. The thought is that more work for the
collector could arise in the near time, allowing to clean more and not
spend too much CPU on repeated collection when there is no garbage.
Currently the collection task is fired immediately upon unix domain
socket close if there are any rights in flight, which caused excessive
CPU usage and too long blocking of the threads waiting for
unp_list_lock and unp_link_rwlock in write mode.
Robert noted that it would be nice if we could find some heuristic by
which we decide whether to run GC a bit more quickly. E.g., if the
number of UNIX domain sockets is close to its resource limit, but not
quite.
Reported and tested by: Markus Gebert <markus.gebert@hostpoint.ch>
Reviewed by: rwatson
MFC after: 2 weeks
taskqueue_enqueue_timeout(). Do not rearm the callout if it is
already armed and the ticks is negative. Otherwise rearm it to fire
in abs(ticks) ticks in the future.
The intended use is to call taskqueue_enqueue_timeout() for the given
timeout_task with the same negative ticks argument. As result, the
task is scheduled to execute not further than abs(ticks) ticks in
future, and the consequent enqueues are coalesced until the already
scheduled task is finished.
Reviewed by: rwatson
Tested by: Markus Gebert <markus.gebert@hostpoint.ch>
MFC after: 2 weeks
then:
- assume the lock is held in exclusive mode and remove a moot check
about the lock acquisition.
- in the destructor remove !MPSAFE specific chunk.
Reviewed by: kib
MFC after: 2 weeks
Also remove the checks from vop_lookup_pre and vop_lookup_post, which
are now completely redundant (before this change they were partially
redundant).
Discussed with: kib
MFC after: 10 days
zombie list for the pid. This allows several kern.proc sysctls to
report useful information for zombies.
Hold the allproc_lock around all searches instead of relocking it.
Remove private pfind_locked() from the new nfs client code.
Requested and reviewed by: pjd
Tested by: pho
MFC after: 3 weeks
here is race between decaying the resource usage in containers, and updating
per-process usage; basically, the former may cause per-container usage
to get smaller than per-process usage.
Submitted by: Rudo Tomori
- Implement a function to ensure that all preempted threads have switched
back out at least once. Use this to make sure there are no stale
references to the old ktr_buf or the lock profiling buffers before
updating them.
Reviewed by: marius (sparc64 parts), attilio (earlier patch)
Sponsored by: EMC / Isilon Storage Division
pgrp2 was used only for debugging, but pgrp2 = pgfind(..) was present in compiled code even for kernels without INVARIANTS
Approved by: trasz (mentor)
MFC after: 1 week
designator to select a process which is waited for. The system call
optionally returns siginfo_t which would be otherwise provided to
SIGCHLD handler, as well as extended structure accounting for child
and cumulative grandchild resource usage.
Allow to get the current rusage information for non-exited processes
as well, similar to Solaris.
The explicit WEXITED flag is required to wait for exited processes,
allowing for more fine-grained control of the events the waiter is
interested in.
Fix the handling of siginfo for WNOWAIT option for all wait*(2)
family, by not removing the queued signal state.
PR: standards/170346
Submitted by: "Jukka A. Ukkonen" <jau@iki.fi>
MFC after: 1 month
- Do not try to steal load from other CPUs if there was no contest switches
on this CPU (i.e. it was idle all the time and woke up just for bus mastering
or TLB shutdown). If current CPU was idle, then it is quite unlikely that some
other CPU has load to steal. Under high I/O rate, when TLB shutdowns cause
numerous CPU wakeups, on 24-CPU system load stealing code may consume up to
25% of all CPU time without giving any benefits.
- Change code that implements spinning for load to restart spin in case of
context switch. Previous code periodically called cpu_idle() even under
high interrupt/context switch rate.
- Rise spinning threshold to 10KHz, where it gives at least some effect
that may worth consumed power.
Reviewed by: jeff@
Some hooks are added to clamp down maxusers and nmbclusters for
small address space systems.
VM_MAX_AUTOTUNE_MAXUSERS - the max maxusers that will be autotuned based on
physical memory.
VM_MAX_AUTOTUNE_NMBCLUSTERS - max nmbclusters based on physical memory.
These are set to the old values on i386 to preserve the clamping that was
being done to all arches.
Another macro VM_AUTOTUNE_NMBCLUSTERS is provided to allow an override
for the calculation on a MD basis. Currently no arch defines this.
Reviewed by: peter
MFC after: 2 weeks
to further reduce latency for threads in this queue. This should help
as threads transition from realtime to timeshare. The latency is
bound to a max of sched_slice until we have more than sched_slice / 6
threads runnable. Then the min slice is allotted to all threads and
latency becomes (nthreads - 1) * min_slice.
Discussed with: mav
