as this may cause deadlocks.
This should fix kern/72123.
Discussed with: jhb
Tested by: Nik Azim Azam, Andy Farkas, Flack Man, Aykut KARA
Izzet BESKARDES, Jens Binnewies, Karl Keusgen
Approved by: sam (mentor)
- The MP code no longer knows anything specific about an MP Table.
Instead, the local APIC code adds CPUs via the cpu_add() function when
a local APIC is enumerated by an APIC enumerator.
- Don't divide the argument to mp_bootaddress() by 1024 just so that we
can turn around and mulitply it by 1024 again.
- We no longer panic if SMP is enabled but we are booted on a UP machine.
- init_secondary(), the asm code between init_secondary() and ap_init()
in mpboot.s and ap_init() have all been merged together in C into
init_secondary().
- We now use the cpuid feature bits to determine if we should enable
PSE, PGE, or VME on each AP.
- Due to the change in the implementation of critical sections, acquire
the SMP TLB mutex around a slightly larger chunk of code for TLB
shootdowns.
- Remove some of the debug code from the original SMP implementation
that is no longer used or no longer applies to the new APIC code.
- Use a temporary hack to disable the ACPI module until the SMP code has
been further reorganized to allow ACPI to work as a module again.
- Add a DDB command to dump the interesting contents of the IDT.
as it could be and can do with some more cleanup. Currently its under
options LAZY_SWITCH. What this does is avoid %cr3 reloads for short
context switches that do not involve another user process. ie: we can
take an interrupt, switch to a kthread and return to the user without
explicitly flushing the tlb. However, this isn't as exciting as it could
be, the interrupt overhead is still high and too much blocks on Giant
still. There are some debug sysctls, for stats and for an on/off switch.
The main problem with doing this has been "what if the process that you're
running on exits while we're borrowing its address space?" - in this case
we use an IPI to give it a kick when we're about to reclaim the pmap.
Its not compiled in unless you add the LAZY_SWITCH option. I want to fix a
few more things and get some more feedback before turning it on by default.
This is NOT a replacement for Bosko's lazy interrupt stuff. This was more
meant for the kthread case, while his was for interrupts. Mine helps a
little for interrupts, but his helps a lot more.
The stats are enabled with options SWTCH_OPTIM_STATS - this has been a
pseudo-option for years, I just added a bunch of stuff to it.
One non-trivial change was to select a new thread before calling
cpu_switch() in the first place. This allows us to catch the silly
case of doing a cpu_switch() to the current process. This happens
uncomfortably often. This simplifies a bit of the asm code in cpu_switch
(no longer have to call choosethread() in the middle). This has been
implemented on i386 and (thanks to jake) sparc64. The others will come
soon. This is actually seperate to the lazy switch stuff.
Glanced at by: jake, jhb
This keeps the logical cpu's halted in the idle loop. By default
the logical cpu's are halted at startup. It is also possible to
halt any cpu in the idle loop now using machdep.hlt_cpus.
Examples of how to use this:
machdep.hlt_cpus=1 halt cpu0
machdep.hlt_cpus=2 halt cpu1
machdep.hlt_cpus=4 halt cpu2
machdep.hlt_cpus=3 halt cpu0,cpu1
Reviewed by: jhb, peter
statclock based on profhz when profiling is enabled MD, since most platforms
don't use this anyway. This removes the need for statclock_process, whose
only purpose was to subdivide profhz, and gets the profiling clock running
outside of sched_lock on platforms that implement suswintr.
Also changed the interface for starting and stopping the profiling clock to
do just that, instead of changing the rate of statclock, since they can now
be separate.
Reviewed by: jhb, tmm
Tested on: i386, sparc64
- It actually works this time, honest!
- Fine grained TLB shootdowns for SMP on i386. IPI's are very expensive,
so try and optimize things where possible.
- Introduce ranged shootdowns that can be done as a single IPI.
- PG_G support for i386
- Specific-cpu targeted shootdowns. For example, there is no sense in
globally purging the TLB cache for where we are stealing a page from
the local unshared process on the local cpu. Use pm_active to track
this.
- Add some instrumentation for the tlb shootdown code.
- Rip out SMP code from <machine/cpufunc.h>
- Try and fix some very bogus PG_G and PG_PS interactions that were bad
enough to cause vm86 bios calls to break. vm86 depended on our existing
bugs and this was the cause of the VESA panics last time.
- Fix the silly one-line error that caused the 'panic: bad pte' last time.
- Fix a couple of other silly one-line errors that should have caused more
pain than they did.
Some more work is needed:
- pmap_{zero,copy}_page[_idle]. These can be done without IPI's if we
have a hook in cpu_switch.
- The IPI handlers need some cleanup. I have a bogus %ds load that can
be avoided.
- APTD handling is rather bogus and appears to be a large source of
global TLB IPI shootdowns for no really good reason.
I see speedups of between 1.5% and ~4% on buildworlds in a while 1 loop.
I expect to see a bigger difference when there is significant pageout
activity or the system otherwise has memory shortages.
I have backed out a few optimizations that I had been using over the last
few days in order to be a little more conservative. I'll revisit these
again over the next few days as the dust settles.
New option: DISABLE_PG_G - In case I missed something.
not removing tabs before "__P((", and not outdenting continuation lines
to preserve non-KNF lining up of code with parentheses. Switch to KNF
formatting and/or rewrap the whole prototype in some cases.
There is some unresolved badness that has been eluding me, particularly
affecting uniprocessor kernels. Turning off PG_G helped (which is a bad
sign) but didn't solve it entirely. Userland programs still crashed.
on for a while:
- fine grained TLB shootdown for SMP on i386
- ranged TLB shootdowns.. eg: specify a range of pages to shoot down with
a single IPI, since the IPI is very expensive. Adjust some callers
that used to trigger this inside tight loops to do a ranged shootdown
at the end instead.
- PG_G support for SMP on i386 (options ENABLE_PG_G)
- defer PG_G activation till after we decide what we are going to do with
PSE and the 4MB pages at the start of the kernel. This should solve
some rumored strangeness about stale PG_G entries getting stuck
underneath the 4MB pages.
- add some instrumentation for the fine TLB shootdown
- convert some asm instruction wrappers from functions to inlines. gcc
seems to do a fair bit better with this.
- [temporarily!] pessimize the tlb shootdown IPI handlers. I will fix
this again shortly.
This has been working fairly well for me for a while, but I have tweaked
it again prior to commit since my last major testing round. The only
outstanding problem that I know of is PG_G related, which is why there
is an option for it (not on by default for SMP). I have seen a world
speedups by a few percent (as much as 4 or 5% in one case) but I have
*not* accurately measured this - I am a bit sceptical of these numbers.
- Axe inlvtlb_ok as it was completely redundant with smp_active.
- Remove references to non-existent variable and non-existent file
in i386/include/smp.h.
- Don't perform initializations local to each CPU while holding the
ap boot lock on i386 while an AP bootstraps itself.
- Reorganize the AP startup code some to unify the latter half of the
functions to bring an AP up. Eventually this might be broken out into
a MI function in subr_smp.c.
been made machine independent and various other adjustments have been made
to support Alpha SMP.
- It splits the per-process portions of hardclock() and statclock() off
into hardclock_process() and statclock_process() respectively. hardclock()
and statclock() call the *_process() functions for the current process so
that UP systems will run as before. For SMP systems, it is simply necessary
to ensure that all other processors execute the *_process() functions when the
main clock functions are triggered on one CPU by an interrupt. For the alpha
4100, clock interrupts are delievered in a staggered broadcast fashion, so
we simply call hardclock/statclock on the boot CPU and call the *_process()
functions on the secondaries. For x86, we call statclock and hardclock as
usual and then call forward_hardclock/statclock in the MD code to send an IPI
to cause the AP's to execute forwared_hardclock/statclock which then call the
*_process() functions.
- forward_signal() and forward_roundrobin() have been reworked to be MI and to
involve less hackery. Now the cpu doing the forward sets any flags, etc. and
sends a very simple IPI_AST to the other cpu(s). AST IPIs now just basically
return so that they can execute ast() and don't bother with setting the
astpending or needresched flags themselves. This also removes the loop in
forward_signal() as sched_lock closes the race condition that the loop worked
around.
- need_resched(), resched_wanted() and clear_resched() have been changed to take
a process to act on rather than assuming curproc so that they can be used to
implement forward_roundrobin() as described above.
- Various other SMP variables have been moved to a MI subr_smp.c and a new
header sys/smp.h declares MI SMP variables and API's. The IPI API's from
machine/ipl.h have moved to machine/smp.h which is included by sys/smp.h.
- The globaldata_register() and globaldata_find() functions as well as the
SLIST of globaldata structures has become MI and moved into subr_smp.c.
Also, the globaldata list is only available if SMP support is compiled in.
Reviewed by: jake, peter
Looked over by: eivind
mpapic.c. This gives us the benefit of C type checking. These functions
are not called in any critical paths and are not used by the interrupt
routines.
Also, while here, run up to 32 interrupt sources on APIC systems.
Normalize INTREN/INTRDIS so they are the same on both UP and SMP systems
rather than sometimes a macro, and sometimes a function.
Reviewed by: jhb, jakeb
include:
* Mutual exclusion is used instead of spl*(). See mutex(9). (Note: The
alpha port is still in transition and currently uses both.)
* Per-CPU idle processes.
* Interrupts are run in their own separate kernel threads and can be
preempted (i386 only).
Partially contributed by: BSDi (BSD/OS)
Submissions by (at least): cp, dfr, dillon, grog, jake, jhb, sheldonh
Don't allow cpu entries in the MP table to contain APIC IDs out of range.
Don't write outside array boundaries if an IO APIC entry in the MP table
contains an APIC ID out of range.
Assign APIC IDs for all IO APICs according to section 3.6.6 in the
Intel MP spec:
- If the current APIC ID on an IO APIC doesn't conflict with other
IO APICs or CPUs, that APIC ID should be used. The copy of the MP
table must be updated if the corresponding APIC ID in the MP table
is different.
- If the current APIC ID was in conflict with other units, the
corresponding APIC ID specified in the MP table is checked for conflict.
- If a conflict is still found then fall back to using a new unique ID.
The copy of the MP table must be updated.
- IDs out of range is considered to be in conflict.
During these operations, the IO_TO_ID array cannot be used, since any
conflict would have caused information loss. The array is then corrected,
since all APIC ID conflicts should have been resolved.
PR: 20312, 18919
Further experimentation showed that some Dell 2450 machines with the
prevention kludge installed still got T_RESERVED traps. CPU interrupt
vector 0x7A was observed to be triggered. This might have been the
bitwise OR of two different vectors sent from each of the IOAPICs at
the same time.
IOAPIC #0: 0x68 --> irq 8: RTC timer interrupt
IOAPIC #1: 0x32 --> irq 18: scsi host adapter or network interface
----
0x7a --> T_RESERVED
Both IOAPICs had ID 0.
Appendix B.3 in the MP spec indicates that the operating system is
responsible for assigning unique IDs to the IOAPICs.
The enclosed patch programs the IOAPIC IDs according to the IOAPIC
entries in the MP table.
Submitted by: tegge
the low level interrupt handler number should be used. Change
setup_apic_irq_mapping() to allocate low level interrupt handler X (Xintr${X})
for any ISA interrupt X mentioned in the MP table.
Remove an assumption in the driver for the system clock (clock.c) that
interrupts mentioned in the MP table as delivered to IOAPIC #0 intpin Y
is handled by low level interrupt handler Y (Xintr${Y}) but don't assume
that low level interrupt handler 0 (Xintr0) is used.
Don't allocate two low level interrupt handlers for the system clock.
Reviewed by: NOKUBI Hirotaka <hnokubi@yyy.or.jp>
is an application space macro and the applications are supposed to be free
to use it as they please (but cannot). This is consistant with the other
BSD's who made this change quite some time ago. More commits to come.
the caller to specify a function to be guarded between an entry and exit
barrier, as well as pre- and post-barrier functions.
The primary use for this function is synchronised update of per-cpu private
data. The implementation is almost (but not quite) MI; with a better
mechanism for masking per-CPU interrupts it could probably be hoisted.
Reviewed by: peter (partially)
- %fs register is added to trapframe and saved/restored upon kernel entry/exit.
- Per-cpu pages are no longer mapped at the same virtual address.
- Each cpu now has a separate gdt selector table. A new segment selector
is added to point to per-cpu pages, per-cpu global variables are now
accessed through this new selector (%fs). The selectors in gdt table are
rearranged for cache line optimization.
- fask_vfork is now on as default for both UP and SMP.
- Some aio code cleanup.
Reviewed by: Alan Cox <alc@cs.rice.edu>
John Dyson <dyson@iquest.net>
Julian Elischer <julian@whistel.com>
Bruce Evans <bde@zeta.org.au>
David Greenman <dg@root.com>
and use this when masking/unmasking interrupts.
Maintain a mapping from (iopaic number, int pin) tuple to irq number,
and use this when configuring devices and programming the ioapics.
Previous code assumed that irq number was equal to int pin number, and
that the ioapic number was 0.
Don't let an AP enter _cpu_switch before all local apics are initialized.
update of cpu usage as shown by top when one process is cpu bound
(no system calls) while the system is otherwise idle (except for top).
Don't attempt to switch to the BSP in boot(). If the system was idle when
an interrupt caused a panic, this won't work. Instead, switch to the BSP
in cpu_reset.
Remove some spurious forward_statclock/forward_hardclock warnings.
- Attempt to handle PCI devices where the interrupt is
an ISA/EISA interrupt according to the mp table.
- Attempt to handle multiple IO APIC pins connected to
the same PCI or ISA/EISA interrupt source. Print a
warning if this happens, since performance is suboptimal.
This workaround is only used for PCI devices.
With these two workarounds, the -SMP kernel is capable of running on
my Asus P/I-P65UP5 motherboard when version 1.4 of the MP table is disabled.
has been some bitrot and incorrect assumptions in the vfs_bio code. These
problems have manifest themselves worse on NFS type filesystems, but can
still affect local filesystems under certain circumstances. Most of
the problems have involved mmap consistancy, and as a side-effect broke
the vfs.ioopt code. This code might have been committed seperately, but
almost everything is interrelated.
1) Allow (pmap_object_init_pt) prefaulting of buffer-busy pages that
are fully valid.
2) Rather than deactivating erroneously read initial (header) pages in
kern_exec, we now free them.
3) Fix the rundown of non-VMIO buffers that are in an inconsistent
(missing vp) state.
4) Fix the disassociation of pages from buffers in brelse. The previous
code had rotted and was faulty in a couple of important circumstances.
5) Remove a gratuitious buffer wakeup in vfs_vmio_release.
6) Remove a crufty and currently unused cluster mechanism for VBLK
files in vfs_bio_awrite. When the code is functional, I'll add back
a cleaner version.
7) The page busy count wakeups assocated with the buffer cache usage were
incorrectly cleaned up in a previous commit by me. Revert to the
original, correct version, but with a cleaner implementation.
8) The cluster read code now tries to keep data associated with buffers
more aggressively (without breaking the heuristics) when it is presumed
that the read data (buffers) will be soon needed.
9) Change to filesystem lockmgr locks so that they use LK_NOPAUSE. The
delay loop waiting is not useful for filesystem locks, due to the
length of the time intervals.
10) Correct and clean-up spec_getpages.
11) Implement a fully functional nfs_getpages, nfs_putpages.
12) Fix nfs_write so that modifications are coherent with the NFS data on
the server disk (at least as well as NFS seems to allow.)
13) Properly support MS_INVALIDATE on NFS.
14) Properly pass down MS_INVALIDATE to lower levels of the VM code from
vm_map_clean.
15) Better support the notion of pages being busy but valid, so that
fewer in-transit waits occur. (use p->busy more for pageouts instead
of PG_BUSY.) Since the page is fully valid, it is still usable for
reads.
16) It is possible (in error) for cached pages to be busy. Make the
page allocation code handle that case correctly. (It should probably
be a printf or panic, but I want the system to handle coding errors
robustly. I'll probably add a printf.)
17) Correct the design and usage of vm_page_sleep. It didn't handle
consistancy problems very well, so make the design a little less
lofty. After vm_page_sleep, if it ever blocked, it is still important
to relookup the page (if the object generation count changed), and
verify it's status (always.)
18) In vm_pageout.c, vm_pageout_clean had rotted, so clean that up.
19) Push the page busy for writes and VM_PROT_READ into vm_pageout_flush.
20) Fix vm_pager_put_pages and it's descendents to support an int flag
instead of a boolean, so that we can pass down the invalidate bit.
interrupts are masked, and EOI is sent iff the corresponding ISR bit
is set in the local apic. If the CPU cannot obtain the interrupt
service lock (currently the global kernel lock) the interrupt is
forwarded to the CPU holding that lock.
Clock interrupts now have higher priority than other slow interrupts.
the signal handling latency for cpu-bound processes that performs very
few system calls.
The IPI for forcing an additional software trap is no longer dependent upon
BETTER_CLOCK being defined.
Add a simplelock to deal with disable_intr()/enable_intr() as used in UP kernel.
UP kernel expects that this is enough to guarantee exclusive access to
regions of code bracketed by these 2 functions.
Add a simplelock to bracket clock accesses in clock.c: clock_lock.
Help from: Bruce Evans <bde@zeta.org.au>
- We now have enough per-cpu idle context, the real idle loop has been
revived (cpu's halt now with nothing to do).
- Some preliminary support for running some operations outside the
global lock (eg: zeroing "free but not yet zeroed pages") is present
but appears to cause problems. Off by default.
- the smp_active sysctl now behaves differently. It's merely a 'true/false'
option. Setting smp_active to zero causes the AP's to halt in the idle
loop and stop scheduling processes.
- bootstrap is a lot safer. Instead of sharing a statically compiled in
stack a number of times (which has caused lots of problems) and then
abandoning it, we use the idle context to boot the AP's directly. This
should help >2 cpu support since the bootlock stuff was in doubt.
- print physical apic id in traps.. helps identify private pages getting
out of sync. (You don't want to know how much hair I tore out with this!)
More cleanup to follow, this is more of a checkpoint than a
'finished' thing.
