not masked during handling of shared PCI interrupts. This resulted in
ASTs sometimes being discarded and softclock interrupts sometimes being
handled prematurely (sometimes = quite often on systems with shared PCI
interrupts, never on other systems).
Debugged by: gibbs and other people at plutotech.com
PR: 6944, maybe 12381
gigabit ethernet adapters. This includes two single port cards
(single mode and multimode fiber) and two dual port cards (also single
mode and multimode fiber). SysKonnect is currently the only
vendor with a dual port gigabit ethernet NIC.
The ports on dual port adapters are treated as separate network
interfaces. Thus, if you have an SK-9844 dual port SX card, you
should have both sk0 and sk1 interfaces attached. Dual port cards
are implemented using two XMAC II chips connected to a single
SysKonnect GEnesis controller. Hence, dual port cards are really
one PCI device, as opposed to two separate PCI devices connected
through a PCI to PCI bridge. Note that SysKonnect's drivers use
the two ports for failover purposes rather that as two separate
interfaces, plus they don't support jumbo frames. This applies to
their Linux driver too. :)
Support is provided for hardware multicast filtering, BPF and
jumbo frames. The SysKonnect cards support TCP checksum offload
however this feature is not currently enabled (hopefully it will
be once we get checksum offload support).
There are still a few things that need to be implemeted, like
the ability to communicate with the on-board LM80 voltage/temperature
monitor, but I wanted to get the driver under CVS control and into
-current so people could bang on it.
A big thanks for SysKonnect for making all their programming info
for these cards (and for their FDDI and token ring cards) available
without NDA (see www.syskonnect.com).
large (1G) memory machine configurations. I was able to run 'dbench 32'
on a 32MB system without bring the machine to a grinding halt.
* buffer cache hash table now dynamically allocated. This will
have no effect on memory consumption for smaller systems and
will help scale the buffer cache for larger systems.
* minor enhancement to pmap_clearbit(). I noticed that
all the calls to it used constant arguments. Making
it an inline allows the constants to propogate to
deeper inlines and should produce better code.
* removal of inherent vfs_ioopt support through the emplacement
of appropriate #ifdef's, with John's permission. If we do not
find a use for it by the end of the year we will remove it entirely.
* removal of getnewbufloops* counters & sysctl's - no longer
necessary for debugging, getnewbuf() is now optimal.
* buffer hash table functions removed from sys/buf.h and localized
to vfs_bio.c
* VFS_BIO_NEED_DIRTYFLUSH flag and support code added
( bwillwrite() ), allowing processes to block when too many dirty
buffers are present in the system.
* removal of a softdep test in bdwrite() that is no longer necessary
now that bdwrite() no longer attempts to flush dirty buffers.
* slight optimization added to bqrelse() - there is no reason
to test for available buffer space on B_DELWRI buffers.
* addition of reverse-scanning code to vfs_bio_awrite().
vfs_bio_awrite() will attempt to locate clusterable areas
in both the forward and reverse direction relative to the
offset of the buffer passed to it. This will probably not
make much of a difference now, but I believe we will start
to rely on it heavily in the future if we decide to shift
some of the burden of the clustering closer to the actual
I/O initiation.
* Removal of the newbufcnt and lastnewbuf counters that Kirk
added. They do not fix any race conditions that haven't already
been fixed by the gbincore() test done after the only call
to getnewbuf(). getnewbuf() is a static, so there is no chance
of it being misused by other modules. ( Unless Kirk can think
of a specific thing that this code fixes. I went through it
very carefully and didn't see anything ).
* removal of VOP_ISLOCKED() check in flushbufqueues(). I do not
think this check is necessary, the buffer should flush properly
whether the vnode is locked or not. ( yes? ).
* removal of extra arguments passed to getnewbuf() that are not
necessary.
* missed cluster_wbuild() that had to be a cluster_wbuild_wb() in
vfs_cluster.c
* vn_write() now calls bwillwrite() *PRIOR* to locking the vnode,
which should greatly aid flushing operations in heavy load
situations - both the pageout and update daemons will be able
to operate more efficiently.
* removal of b_usecount. We may add it back in later but for now
it is useless. Prior implementations of the buffer cache never
had enough buffers for it to be useful, and current implementations
which make more buffers available might not benefit relative to
the amount of sophistication required to implement a b_usecount.
Straight LRU should work just as well, especially when most things
are VMIO backed. I expect that (even though John will not like
this assumption) directories will become VMIO backed some point soon.
Submitted by: Matthew Dillon <dillon@backplane.com>
Reviewed by: Kirk McKusick <mckusick@mckusick.com>
than a review, this was a nice puzzle.
This is supposed to be binary and source compatible with older
applications that access the old FreeBSD-style three arguments to a
signal handler.
Except those applications that access hidden signal handler arguments
bejond the documented third one. If you have applications that do,
please let me know so that we take the opportunity to provide the
functionality they need in a documented manner.
Also except application that use 'struct sigframe' directly. You need
to recompile gdb and doscmd. `make world` is recommended.
Example program that demonstrates how SA_SIGINFO and old-style FreeBSD
handlers (with their three args) may be used in the same process is at
http://www3.cons.org/tmp/fbsd-siginfo.c
Programs that use the old FreeBSD-style three arguments are easy to
change to SA_SIGINFO (although they don't need to, since the old style
will still work):
Old args to signal handler:
void handler_sn(int sig, int code, struct sigcontext *scp)
New args:
void handler_si(int sig, siginfo_t *si, void *third)
where:
old:code == new:second->si_code
old:scp == &(new:si->si_scp) /* Passed by value! */
The latter is also pointed to by new:third, but accessing via
si->si_scp is preferred because it is type-save.
FreeBSD implementation notes:
- This is just the framework to make the interface POSIX compatible.
For now, no additional functionality is provided. This is supposed
to happen now, starting with floating point values.
- We don't use 'sigcontext_t.si_value' for now (POSIX meant it for
realtime-related values).
- Documentation will be updated when new functionality is added and
the exact arguments passed are determined. The comments in
sys/signal.h are meant to be useful.
Reviewed by: BDE
into uipc_mbuf.c. This reduces three sets of identical tunable code to
one set, and puts the initialisation with the mbuf code proper.
Make NMBUFs tunable as well.
Move the nmbclusters sysctl here as well.
Move the initialisation of maxsockets from param.c to uipc_socket2.c,
next to its corresponding sysctl.
Use the new tunable macros for the kern.vm.kmem.size tunable (this should have
been in a separate commit, whoops).
print_AMD_info(), L2 internal cache is shown, as are AMD's special CPUID
infos:
CPU: AMD-K6(tm) 3D processor (350.81-MHz 586-class CPU)
Origin = "AuthenticAMD" Id = 0x58c Stepping=12
Features=0x8021bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8,PGE,MMX>
AMD Features=0x808029bf<FPU,VME,DE,PSE,TSC,MSR,MCE,CX8,SYSCALL,PGE,MMX,3DNow!>
PR: kern/12512
Submitted by: Louis A. Mamakos <louie@TransSys.COM>
frames (or just insane received packet lengths generated due to errors
reading from the NIC's internal buffers). Anything too large to fit
safely into an mbuf cluster buffer is discarded and an error logged.
I have not observed this problem with my own cards, but on user has
reported it and adding the sanity test seems reasonable in any case.
Problem noted and patch provided by: Per Andersson <per@cdg.chalmers.se>
we will never use more memory than this value (if specified), but will always
check memory for validity up to this amount.
Get rid of the speculative_mprobe option; the memory amount can now be
specified by hw.physmem.
QUEUE_AGE, QUEUE_LRU, and QUEUE_EMPTY we instead have QUEUE_CLEAN,
QUEUE_DIRTY, QUEUE_EMPTY, and QUEUE_EMPTYKVA. With this patch clean
and dirty buffers have been separated. Empty buffers with KVM
assignments have been separated from truely empty buffers. getnewbuf()
has been rewritten and now operates in a 100% optimal fashion. That is,
it is able to find precisely the right kind of buffer it needs to
allocate a new buffer, defragment KVM, or to free-up an existing buffer
when the buffer cache is full (which is a steady-state situation for
the buffer cache).
Buffer flushing has been reorganized. Previously buffers were flushed
in the context of whatever process hit the conditions forcing buffer
flushing to occur. This resulted in processes blocking on conditions
unrelated to what they were doing. This also resulted in inappropriate
VFS stacking chains due to multiple processes getting stuck trying to
flush dirty buffers or due to a single process getting into a situation
where it might attempt to flush buffers recursively - a situation that
was only partially fixed in prior commits. We have added a new daemon
called the buf_daemon which is responsible for flushing dirty buffers
when the number of dirty buffers exceeds the vfs.hidirtybuffers limit.
This daemon attempts to dynamically adjust the rate at which dirty buffers
are flushed such that getnewbuf() calls (almost) never block.
The number of nbufs and amount of buffer space is now scaled past the
8MB limit that was previously imposed for systems with over 64MB of
memory, and the vfs.{lo,hi}dirtybuffers limits have been relaxed
somewhat. The number of physical buffers has been increased with the
intention that we will manage physical I/O differently in the future.
reassignbuf previously attempted to keep the dirtyblkhd list sorted which
could result in non-deterministic operation under certain conditions,
such as when a large number of dirty buffers are being managed. This
algorithm has been changed. reassignbuf now keeps buffers locally sorted
if it can do so cheaply, and otherwise gives up and adds buffers to
the head of the dirtyblkhd list. The new algorithm is deterministic but
not perfect. The new algorithm greatly reduces problems that previously
occured when write_behind was turned off in the system.
The P_FLSINPROG proc->p_flag bit has been replaced by the more descriptive
P_BUFEXHAUST bit. This bit allows processes working with filesystem
buffers to use available emergency reserves. Normal processes do not set
this bit and are not allowed to dig into emergency reserves. The purpose
of this bit is to avoid low-memory deadlocks.
A small race condition was fixed in getpbuf() in vm/vm_pager.c.
Submitted by: Matthew Dillon <dillon@apollo.backplane.com>
Reviewed by: Kirk McKusick <mckusick@mckusick.com>
behavior slightly.
If machine/bus.h is included, but neither bus_memio.h nor bus_pio.h
are included, then behave as if both were included.
This won't change existing drivers, all of which include one or more
of bus_{p,mem}io.h, but will allow drivers from other systems to come
over with fewer changes. I freely admit that this might not be
optimal for some drivers, but those drivers can be optimized for
FreeBSD after the initial bringup happens.
Without the change, there is a bug that preclude drivers from
compiling with strange warning/errors.
I've been running this here for a while now w/o ill effects.
Reviewed by: gibbs
Not objected to by: bde, arch@ list.
On the VAX, it used to be used for special compilation to avoid the
optimizer which would mess with memory mapped devices etc. These days
we use 'volatile'.
- The kernel environment variable 'hw.physmem' can be used to set the
amount of physical memory space, based at 0, that FreeBSD will use.
Any memory detected over this limit is ignored. Documentation for
this is available under 'help set tunables' in the loader.
- In the case where system memory size can't be accurately determined,
hw.physmem is used as a best-guess memory size, but speculative
probing will be used to determine actual memory size if any of the
guesses or hints are 16M or more.
- If RB_VERBOSE, we list the memory regions as we test them.
- The compile-time option MAXMEM supplies a default value for
'hw.physmem'.
specified in the kernel config file - but setting options MAXMEM works
exactly the same. Userconfig overrides of this have not worked for
ages.
Also, change the getenv for the loader override to hw.physmem based on a
prior suggestion from Mike Smith. I think he still wants to change this
some, but this shouldn't get in his way. This is a forced setting of
the memory size, not a "cap". We probably should have a plain 'maxmem'
variable as well which does do a cap, without loosing the bios memory
configuration data.
memory size. If somebody wants to change the name, fine - I used this
since it's consistant with the config variable it replaces.
This is intended to replace the npx0 msize hack (which no longer works).
SYSINIT_KT() etc (which is a static, compile-time procedure), use a
NetBSD-style kthread_create() interface. kproc_start is still available
as a SYSINIT() hook. This allowed simplification of chunks of the
sysinit code in the process. This kthread_create() is our old kproc_start
internals, with the SYSINIT_KT fork hooks grafted in and tweaked to work
the same as the NetBSD one.
One thing I'd like to do shortly is get rid of nfsiod as a user initiated
process. It makes sense for the nfs client code to create them on the
fly as needed up to a user settable limit. This means that nfsiod
doesn't need to be in /sbin and is always "available". This is a fair bit
easier to do outside of the SYSINIT_KT() framework.
surrounding critical sections that consist of (1) a single read or
(2) a single locked RMW operation.
(Thanks to thomma@slip.net (Tamiji Homma) for helping to test
these changes.)
