when I reordered events in accept1() to allocate a file descriptor
earlier, I didn't properly update use of goto on exit to unwind for
cases where the file descriptor is now held, but wasn't previously.
The result was that, in the event of accept() on a non-blocking socket,
or in the event of a socket error, a file descriptor would be leaked.
This ended up being non-fatal in many cases, as the file descriptor
would be properly GC'd on process exit, so only showed up for processes
that do a lot of non-blocking accept() calls, and also live for a long
time (such as qmail).
This change updates the use of goto targets to do additional unwinding.
Eyes provided by: Brian Feldman <green@freebsd.org>
Feet, hands provided by: Stefan Ehmann <shoesoft@gmx.net>,
Dimitry Andric <dimitry@andric.com>
Arjan van Leeuwen <avleeuwen@piwebs.com>
is generic to any threading system. This commit does not link this
file to the build yet, nor does it remove these functions from their
current location in kern_thread.c. (that commit coming up after further review)
with an ASUS A7N8X-E motherboard in APIC mode, since storming interrupts
don't repeat immediately. Use DELAY(1) to wait a bit for them to repeat.
This affects all systems. Only delay for the first
(10 * intr_storm_threshold) interrupts (per interrupt handler) so that
this is only a pessimization while warming up. Throttle after calling
the sub-handlers instead of before so that the long delay given by
throttling can be used instead of the DELAY(1) to detect storms after
warming up.
Reduced the throttling period from 1/10 second to 1/hz seconds so that
throttling doesn't destroy performance so much. Interrupts that are
detected as storming are effectively handled by polling at a frequency
of hz Hz. On A7N8X-E's there is another hardware or configuration bug
that makes the throttled frequency closer to 2*hz Hz.
tree, output an empty string instead of "?". This is already what
happened with DEVICE_SYSCTL_LOCATION and DEVICE_SYSCTL_PNPINFO. This
makes the output of "sysctl dev" much nicer (it won't display those
empty sysctls).
Reviewed by: des
size_t and size_t *, respectively. Update callers for the new interface.
This is a better fix for overflows that occurred when dumping segments
larger than 2GB to core files.
called ttyldoptim().
Use this function from all the relevant drivers.
I belive no drivers finger linesw[] directly anymore, paving the way for
locking and refcounting.
class variables in addition to per-device variables. In plain English,
this means that dev.foo0.bar is now called dev.foo.0.bar, and it is
possible to to have dev.foo.bar as well.
double NULL entries signal Witness to stop processing the array of
order entries meaning none of the spin locks are added resulting in
panics on boot.
- Add a missing NULL, NULL terminator to the Slip locks list to keep them
separate from the spin locks.
relationships:
Sockets: filedesc->accept->sellck
Routing: radix node head->rtentry->ifaddr
UDP: udp->udpinp
TCP: tcp->tcpinp
SLIP: slip_mtx->slip sc_mtx
Drop in a place holder section for UNIX domain sockets. Various
sections to be expanded over the next few days.
sched_clock() rather than using callouts. This means we no longer have to
take the load of the callout thread into consideration while balancing and
should make the balancing decisions simpler and more accurate.
Tested on: x86/UP, amd64/SMP
global mutex, accept_mtx, which serializes access to the following
fields across all sockets:
so_qlen so_incqlen so_qstate
so_comp so_incomp so_list
so_head
While providing only coarse granularity, this approach avoids lock
order issues between sockets by avoiding ownership of the fields
by a specific socket and its per-socket mutexes.
While here, rewrite soclose(), sofree(), soaccept(), and
sonewconn() to add assertions, close additional races and address
lock order concerns. In particular:
- Reorganize the optimistic concurrency behavior in accept1() to
always allocate a file descriptor with falloc() so that if we do
find a socket, we don't have to encounter the "Oh, there wasn't
a socket" race that can occur if falloc() sleeps in the current
code, which broke inbound accept() ordering, not to mention
requiring backing out socket state changes in a way that raced
with the protocol level. We may want to add a lockless read of
the queue state if polling of empty queues proves to be important
to optimize.
- In accept1(), soref() the socket while holding the accept lock
so that the socket cannot be free'd in a race with the protocol
layer. Likewise in netgraph equivilents of the accept1() code.
- In sonewconn(), loop waiting for the queue to be small enough to
insert our new socket once we've committed to inserting it, or
races can occur that cause the incomplete socket queue to
overfill. In the previously implementation, it was sufficient
to simply tested once since calling soabort() didn't release
synchronization permitting another thread to insert a socket as
we discard a previous one.
- In soclose()/sofree()/et al, it is the responsibility of the
caller to remove a socket from the incomplete connection queue
before calling soabort(), which prevents soabort() from having
to walk into the accept socket to release the socket from its
queue, and avoids races when releasing the accept mutex to enter
soabort(), permitting soabort() to avoid lock ordering issues
with the caller.
- Generally cluster accept queue related operations together
throughout these functions in order to facilitate locking.
Annotate new locking in socketvar.h.
descriptors out of fdrop_locked() and into vn_closefile(). This
removes all knowledge of vnodes from fdrop_locked(), since the lock
behavior was specific to vnodes. This also removes the specific
requirement for Giant in fdrop_locked(), it's now only required by
code that it calls into.
Add GIANT_REQUIRED to vn_closefile() since VFS requires Giant.
nextpkt within the m_hdr was not being initialized to NULL for
!M_PKTHDR cases. *Maybe* this will fix weird socket buffer
inconsistency panics, but we'll see.
the socket is on an accept queue of a listen socket. This change
renames the flags to SQ_COMP and SQ_INCOMP, and moves them to a new
state field on the socket, so_qstate, as the locking for these flags
is substantially different for the locking on the remainder of the
flags in so_state.
them to behave the same as if the SS_NBIO socket flag had been set
for this call. The SS_NBIO flag for ordinary sockets is set by
fcntl(fd, F_SETFL, O_NONBLOCK).
Pass the MSG_NBIO flag to the soreceive() and sosend() calls in
fifo_read() and fifo_write() instead of frobbing the SS_NBIO flag
on the underlying socket for each I/O operation. The O_NONBLOCK
flag is a property of the descriptor, and unlike ordinary sockets,
fifos may be referenced by multiple descriptors.
mbuma is an Mbuf & Cluster allocator built on top of a number of
extensions to the UMA framework, all included herein.
Extensions to UMA worth noting:
- Better layering between slab <-> zone caches; introduce
Keg structure which splits off slab cache away from the
zone structure and allows multiple zones to be stacked
on top of a single Keg (single type of slab cache);
perhaps we should look into defining a subset API on
top of the Keg for special use by malloc(9),
for example.
- UMA_ZONE_REFCNT zones can now be added, and reference
counters automagically allocated for them within the end
of the associated slab structures. uma_find_refcnt()
does a kextract to fetch the slab struct reference from
the underlying page, and lookup the corresponding refcnt.
mbuma things worth noting:
- integrates mbuf & cluster allocations with extended UMA
and provides caches for commonly-allocated items; defines
several zones (two primary, one secondary) and two kegs.
- change up certain code paths that always used to do:
m_get() + m_clget() to instead just use m_getcl() and
try to take advantage of the newly defined secondary
Packet zone.
- netstat(1) and systat(1) quickly hacked up to do basic
stat reporting but additional stats work needs to be
done once some other details within UMA have been taken
care of and it becomes clearer to how stats will work
within the modified framework.
From the user perspective, one implication is that the
NMBCLUSTERS compile-time option is no longer used. The
maximum number of clusters is still capped off according
to maxusers, but it can be made unlimited by setting
the kern.ipc.nmbclusters boot-time tunable to zero.
Work should be done to write an appropriate sysctl
handler allowing dynamic tuning of kern.ipc.nmbclusters
at runtime.
Additional things worth noting/known issues (READ):
- One report of 'ips' (ServeRAID) driver acting really
slow in conjunction with mbuma. Need more data.
Latest report is that ips is equally sucking with
and without mbuma.
- Giant leak in NFS code sometimes occurs, can't
reproduce but currently analyzing; brueffer is
able to reproduce but THIS IS NOT an mbuma-specific
problem and currently occurs even WITHOUT mbuma.
- Issues in network locking: there is at least one
code path in the rip code where one or more locks
are acquired and we end up in m_prepend() with
M_WAITOK, which causes WITNESS to whine from within
UMA. Current temporary solution: force all UMA
allocations to be M_NOWAIT from within UMA for now
to avoid deadlocks unless WITNESS is defined and we
can determine with certainty that we're not holding
any locks when we're M_WAITOK.
- I've seen at least one weird socketbuffer empty-but-
mbuf-still-attached panic. I don't believe this
to be related to mbuma but please keep your eyes
open, turn on debugging, and capture crash dumps.
This change removes more code than it adds.
A paper is available detailing the change and considering
various performance issues, it was presented at BSDCan2004:
http://www.unixdaemons.com/~bmilekic/netbuf_bmilekic.pdf
Please read the paper for Future Work and implementation
details, as well as credits.
Testing and Debugging:
rwatson,
brueffer,
Ketrien I. Saihr-Kesenchedra,
...
Reviewed by: Lots of people (for different parts)
KERN_PROC_SESSION option which had been previously defined but
never implemented.
PR: bin/65803 (a very tiny piece of the PR)`
Submitted by: Cyrille Lefevre
of not clearing the flags for execv() syscall will result that a new
program runs in KSE thread mode without enabling it.
Submitted by: tjr
Modified by: davidxu
threatened in rev.1.10 of usr.sbin/kgmon/kgmon.c more than 2 years ago.
kgmon has been recovering from the missing initialization for too
long, but the fixup there is ifdefed for i386's and shouldn't be
needed for other arches.
high resolution kernel profiling (options GUPROF. "U" in GUPROF stands
for microseconds resolution, but the resolution is now smaller than 1
nanosecond on multi-GHz machines and the accuracy is heading towards
1 nanosecond too). Arches that support GUPROF must now provide certain
macros for the calibration. GUPROF is now only supported for i386's,
so the absence of the new macros for other arches doesn't break anything
that wasn't already broken. amd64's have uncommitted support for
GUPROF, and sparc64's have support that seems to be complete except
here (there was an #error for non-i386 cases; now there are undefined
macros).
Changed the asms a little:
- declare them as __volatile. They must not be moved, and exporting a
label across asms is technically incorrect, so try harder to stop gcc
moving them.
- don't put the non-clobbered register "bx" in the clobber list. The
clobber lists are still more conservative than necessary.
- drop the non-support for gcc-1. It just gave a better error message,
and this is not useful since compiling with gcc-1 would cause thousands
of worse error messages.
- drop the support for aout.
of kmupetext(). The declaration is misplaced in <machine/profile.h>
since it is not MD and not related to the lowest level of profiling.
It will be moved, but getting it via <sys/gmon.h> already works.
and cannot handle it going away, add an explicit reference to the kobj
class inside each linker class. Without this, a class with no modules
loaded will sit with an idle refcount of 0. Loading and unloading
a module with it causes a 0->1->0 transition which frees the ops table
and causes subsequent loads using that class to explode. Normally, the
"kernel" module will remain forever loaded and prevent this happening, but
if you have more than one linker class active, only one owns the "kernel".
This finishes making modules work for kldload(8) on amd64.
(nobits) tables to simplify some code. Try and shorten some of the very
wide lines. Somewhere along the way, I think I fixed the memory
corruption that caused panics after going multiuser.
elf_reloc() backends for two reasons. First, to support the possibility
of there being two elf linkers in the kernel (eg: amd64), and second, to
pass the relocbase explicitly (for relocating .o format kld files).
is "void *" (it isn't) or that the default promotion of pid_t is int.
Instead, assume that casting "struct foo *" to "void *" and printing the
result with %p is useful, and that all pid_t's are representable as longs.
Fixed some minor style bugs (mainly spelling errors in comments).
removes a specific thread from a sleep queue. sleepq_resume_thread()
resumes scheduling of a thread that has been previously removed from a
sleep queue.
- sleepq_catch_signals() just removes a thread from the queue it was just
added to when a pending signal is found.
- sleepq_signal() and sleepq_broadcast() remove threads from a queue,
drop the queue lock, and then resume all the previously removed threads.
This doesn't completely fix the sched_lock <-> sleepq chain LOR, but it
makes it a little better as we no longer call setrunnble() with a sleep
queue lock held meaning if setrunnable() tries to wakeup the swapper we
don't try to lock two sleep queue chains at the same time.
It's not quite correct from a posix Point Of view, but it is a lot better
than what was there before. This will be revisited later
when we decide what form our priority extensions will take. Posix doesn't
specify how a system scope thread can change its priority so you need to
add non-standard extensions to be able to do it..
For now make this slightly non standard to allow it to be done.
Submitted by: Dan Eischen originally, changed by myself.
allocation and deallocation. This flag's principal use is shortly after
allocation. For such cases, clearing the flag is pointless. The only
unusual use of PG_ZERO is in vfs_bio_clrbuf(). However, allocbuf() never
requests a prezeroed page. So, vfs_bio_clrbuf() never sees a prezeroed
page.
Reviewed by: tegge@
synchronization protecting against dynamic load and unload of MAC
policies, and instead simply blocks load and unload. In a static
configuration, this allows you to avoid the synchronization costs
associated with introducing dynamicism.
Obtained from: TrustedBSD Project
Sponsored by: DARPA, McAfee Research
as dependent on binutils features/quirks as the current one. This one
loads plain .o files without having to mess with shared object mode.
This happens to be essential on amd64, because binutils hasn't implemented
all the quirks/features that we need for producing the hack non-PIC shared
objects. As it turned out, .o format isn't all that inconvenient after
all. It looks like the ability to use the same .o files for linking
directly into a static kernel or loading as a module might be worth it.
It is still very much a work-in-progress, but it is almost usable. Other
changes are still needed in order to use it though, these have not been
committed yet. There is still a memory corruption/overrun bug somewhere.
For example, test modules load and work, but the machine explodes a few
minutes later in vm_forkproc() or the like. Notable missing things
include kldxref support, and loader(8) support. I wanted to figure out
a working baseline set of code first.
condition where kse_wakeup() doesn't yet see them in (interruptible)
sleep queues. Also add an upcall check to sleepqueue_catch_signals()
suggested by jhb.
This commit should fix recent mysql hangs.
Reviewed by: jhb, davidxu
Mysql'd by: Robin P. Blanchard <robin.blanchard at gactr uga edu>
jail, which is less restrictive but allows for more flexible
jail usage (for those who are willing to make the sacrifice).
The default is off, but allowing raw sockets within jails can
now be accomplished by tuning security.jail.allow_raw_sockets
to 1.
Turning this on will allow you to use things like ping(8)
or traceroute(8) from within a jail.
The patch being committed is not identical to the patch
in the PR. The committed version is more friendly to
APIs which pjd is working on, so it should integrate
into his work quite nicely. This change has also been
presented and addressed on the freebsd-hackers mailing
list.
Submitted by: Christian S.J. Peron <maneo@bsdpro.com>
PR: kern/65800
sched_ule, in January 2004. Looking at this, "pagezero" is (one of) the
culprit(s). We had no provision for processes with P_NOLOAD set. With
pagezero not running at PRI_ITHD, kseq_load_{add,rem} count pagezero as
another-normal-process, thus the "expected-plus-one" load reported in
the above thread.
Submitted by: Nikos Ntarmos <ntarmos@ceid.upatras.gr>
2. Document that this means that kernel modules must be rebuilt.
3. While I'm here, fix my sorting error in callout.h
Requested by: many [1], scottl [2], bde [3]
the same process as the current thread it makes absolutely
no sense to lock the parent process through the pointer in
said thread.
Submitted by: pho (with minor correction)
Pointy Hat To: mtm
Specifically, we used to enable the source after locking sched_lock
and just before we had already decided to do a context switch.
This meant that an ithread could never process more than one interrupt
per context switch. Enabling earlier in the loop before sched_lock is
acquired allows an ithread to handle multiple interrupts per context
switch if interrupts fire very rapidly. For the case of heavy interrupt
load this can reduce the number of context switches (and thus overhead)
as well as reduce interrupt latency.
- Now that we can handle multiple interrupts per context switch, add simple
interrupt storm protection to threaded interrupts. If X number of
consecutive interrupts are triggered before the itherad voluntarily
yields to another thread, then the interrupt thread will sleep with the
associated interrupt source disabled (masked) for 1/10th of a second.
The default value of X is 500, but it can be tweaked via the tunable/
sysctl hw.intr_storm_threshold. If an interrupt storm is detected, then
a message is output to the kernel console on the first occurrence per
interrupt thread. Interrupt storm protection can be disabled completely
by setting this value to 0. There is no scientific reasoning for the
1/10th of a second or 500 interrupts values, so they may require tweaking
at some point in the future.
Tested by: rwatson (an earlier version w/o the storm protection)
Tested by: mux (reportedly made a machine with two PCI interrupts
storming usable rather than hard locked)
Reviewed by: imp
unconditionally initialize the mbuf header even if cluster allocation
failed, which could result in a NULL pointer dereference in low-memory
conditions.
PR: kern/65548
Submitted by: Stephan Uphoff <ups@tree.com>
a LOR against sleepq. Fix the comment, and fix ptracestop() to pick up
sched_lock after stop() rather than before.
Reported by: Scott Sipe <cscotts@mindspring.com>
Reviewed by: rwatson, jhb
side effect of that change caused headers to not be sent if a 0 byte
file was passed to sendfile. This change fixes that behavior, allowing
sendfile to send out the headers even with a 0 byte file again.
Noticed by: Dirk Engling
equal to the process ID) is still present when we dump a core. It
already may have been destroyed. In that case we would end up
dereferencing a NULL pointer, so specifically test for that as well.
Reported & tested by: Dan Nelson <dnelson@allantgroup.com>
Remove spurious whitespace, add indent protection, fix punctuation,
remove initialization of static variables to zero, put wakeup_ctr
and wakeup_needed in the correct order. (reported by bde)
This doesn't fix all the style bugs I introduced, but the remaining
style bugs make it easier for me to understand what I did here.
a callout, and use the new callout_drain API to make sure that a callout
has finished before we deallocate memory it is using.
PR: kern/64121
Discussed with: gallatin
callout_stop(), except that if the callout being stopped is currently
in progress, it blocks attempts to reset the callout and waits until the
callout is completed before it returns.
This makes it possible to clean up callout-using code safely, e.g.,
without potentially freeing memory which is still being used by a callout.
Reviewed by: mux, gallatin, rwatson, jhb
count is protected by the mutex that protects the condition, so the count
does not require any extra locking or atomic operations. It serves as an
optimization to avoid calling into the sleepqueue code at all if there are
no waiters.
Note that the count can get temporarily out of sync when threads sleeping
on a condition variable time out or are aborted. However, it doesn't hurt
to call the sleepqueue code for either a signal or a broadcast when there
are no waiters, and the count is never out of sync in the opposite
direction unless we have more than INT_MAX sleeping threads.
to awaken all waiters when a contested mutex is released instead of just
the highest priority waiter. If the various threads are awakened in
sequence then each thread may acquire and release the lock in question
without contention resulting in fewer expensive unlock and lock
operations. This old behavior of waking just the highest priority is
still used if this option is specified. Making the algorithm conditional
on a kernel option will allows us to benchmark both cases later and
determine which one should be used by default.
Requested by: tanimura-san
more consistent with other APIs. sleepq and cv's use signal/broadcast, and
msleep uses wakeup_one/wakeup. Prior to this turnstiles were using a
signal/wakeup mixture.
- don't say what a small subset of the options includes are for.
- don't mark up functions which use all their args with /* ARGSUSED */.
The markup should have been removed when the unused retval parameter
was removed.
- don't comment on what routine suser() checks do. Removed nearby
excessive vertical whitespace.
SCHED_INTERACT_MAX was used where SCHED_SLP_RUN_MAX was needed. This was
causing the interactivity scaler to lose history at a more dramatic rate
than intended.
in the process. This is required for proper debugging of corefiles
created by 1:1 or M:N threaded processes. Add an XXX comment where
we should actually call a function that dumps MD specific notes.
An example of a MD specific note is the NT_PRXFPREG note for SSE
registers.
Since BFD creates non-annotated pseudo-sections for the first PRSTATUS
and FPREGSET notes (non-annotated in the sense that the name of the
section does not contain the pid/tid), make sure those sections describe
the initial thread of the process (i.e. the thread which tid equals the
pid). This is not strictly necessary, but makes sure that tools that use
the non-annotated section names will not change behaviour due to this
change.
The practical upshot of this all is that one can see the threads in
the debugger when looking at a corefile. For 1:1 threading this means
that *all* threads are visible.
is twofold:
1. When a 1:1 or M:N threaded process dumps core, we need to put the
register state of each of its kernel threads in the core file.
This can only be done by differentiating the pid field in the
respective note. For this we need the tid.
2. When thread support is present for remote debugging the kernel
with gdb(1), threads need to be identified by an integer due to
limitations in the remote protocol. This requires having a tid.
To minimize the impact of having thread IDs, threads that are created
as part of a fork (i.e. the initial thread in a process) will inherit
the process ID (i.e. tid=pid). Subsequent threads will have IDs larger
than PID_MAX to avoid interference with the pid allocation algorithm.
The assignment of tids is handled by thread_new_tid().
The thread ID allocation algorithm has been written with 3 assumptions
in mind:
1. IDs need to be created as fast a possible,
2. Reuse of IDs may happen instantaneously,
3. Someone else will write a better algorithm.
- ptrace_single_step() is no longer called with the proc lock held, so
don't try to unlock it and then relock it.
- Push Giant down into proc_rwmem() instead of forcing all the consumers
(including Alpha breakpoint support) to explicitly wrap calls to
proc_rwmem() with Giant.
Tested by: kensmith
not quite well by me - if kern.ps_argsopen was set to 0, users weren't
permitted to see arguments of even own processes.
But kern.ps_argsopen is going away, so just remove this check and leave
security checks for p_cansee() function.
declaration. Observe that initialization in declaration is
frequently incompatible with locking, not just a bad idea
due to style(9).
Submitted by: bde
and consume that interface in portalfs and fifofs instead. In the
new world order, unp_connect2() assumes that the unpcb mutex is
held, whereas uipc_connect2() validates that the passed sockets are
UNIX domain sockets, then grabs the mutex.
NB: the portalfs and fifofs code gets down and dirty with UNIX domain
sockets. Maybe this is a bad thing.
stuff was here (NFS) was fixed by Alfred in November. The only remaining
consumer of the stub functions was umapfs, which is horribly horribly
broken. It has missed out on about the last 5 years worth of maintenence
that was done on nullfs (from which umapfs is derived). It needs major
work to bring it up to date with the vnode locking protocol. umapfs really
needs to find a caretaker to bring it into the 21st century.
Functions GC'ed:
vop_noislocked, vop_nolock, vop_nounlock, vop_sharedlock.
instead of ephemeral mappings using pmap_qenter() by the writer. The
writer is still, however, responsible for wiring the pages, just not
mapping them. Consequently, the allocation of KVA for the direct case is
unnecessary. Remove it and the sysctls limiting it, i.e.,
kern.ipc.maxpipekvawired and kern.ipc.amountpipekvawired. The number
of temporarily wired pages is still, however, limited by
kern.ipc.maxpipekva.
Note: On platforms lacking a direct virtual-to-physical mapping,
uiomove_fromphys() uses sf_bufs to cache ephemeral mappings. Thus,
the number of available sf_bufs can influence the performance of pipes
on platforms such i386. Surprisingly, I saw the greatest gain from this
change on such a machine: lmbench's pipe bandwidth result increased from
~1050MB/s to ~1850MB/s on my 2.4GHz, 400MHz FSB P4 Xeon.
long as there are still explicit uses of int, whether in types or
in function names (such as atomic_set_int() in sched_ule.c), we can
not change cpumask_t to be anything other than u_int. See also the
commit log for sys/sys/types.h, revision 1.84.
