Commit Graph

4560 Commits

Author SHA1 Message Date
John Baldwin
e0f66ef861 Reorganize the interrupt handling code a bit to make a few things cleaner
and increase flexibility to allow various different approaches to be tried
in the future.
- Split struct ithd up into two pieces.  struct intr_event holds the list
  of interrupt handlers associated with interrupt sources.
  struct intr_thread contains the data relative to an interrupt thread.
  Currently we still provide a 1:1 relationship of events to threads
  with the exception that events only have an associated thread if there
  is at least one threaded interrupt handler attached to the event.  This
  means that on x86 we no longer have 4 bazillion interrupt threads with
  no handlers.  It also means that interrupt events with only INTR_FAST
  handlers no longer have an associated thread either.
- Renamed struct intrhand to struct intr_handler to follow the struct
  intr_foo naming convention.  This did require renaming the powerpc
  MD struct intr_handler to struct ppc_intr_handler.
- INTR_FAST no longer implies INTR_EXCL on all architectures except for
  powerpc.  This means that multiple INTR_FAST handlers can attach to the
  same interrupt and that INTR_FAST and non-INTR_FAST handlers can attach
  to the same interrupt.  Sharing INTR_FAST handlers may not always be
  desirable, but having sio(4) and uhci(4) fight over an IRQ isn't fun
  either.  Drivers can always still use INTR_EXCL to ask for an interrupt
  exclusively.  The way this sharing works is that when an interrupt
  comes in, all the INTR_FAST handlers are executed first, and if any
  threaded handlers exist, the interrupt thread is scheduled afterwards.
  This type of layout also makes it possible to investigate using interrupt
  filters ala OS X where the filter determines whether or not its companion
  threaded handler should run.
- Aside from the INTR_FAST changes above, the impact on MD interrupt code
  is mostly just 's/ithread/intr_event/'.
- A new MI ddb command 'show intrs' walks the list of interrupt events
  dumping their state.  It also has a '/v' verbose switch which dumps
  info about all of the handlers attached to each event.
- We currently don't destroy an interrupt thread when the last threaded
  handler is removed because it would suck for things like ppbus(8)'s
  braindead behavior.  The code is present, though, it is just under
  #if 0 for now.
- Move the code to actually execute the threaded handlers for an interrrupt
  event into a separate function so that ithread_loop() becomes more
  readable.  Previously this code was all in the middle of ithread_loop()
  and indented halfway across the screen.
- Made struct intr_thread private to kern_intr.c and replaced td_ithd
  with a thread private flag TDP_ITHREAD.
- In statclock, check curthread against idlethread directly rather than
  curthread's proc against idlethread's proc. (Not really related to intr
  changes)

Tested on:	alpha, amd64, i386, sparc64
Tested on:	arm, ia64 (older version of patch by cognet and marcel)
2005-10-25 19:48:48 +00:00
Bill Paul
ba3af76df7 Modify the pci_cfgdisable() routine to bring it more in line with
other OSes (Solaris, Linux, VxWorks). It's not necessary to write a 0
to the config address register when using config mechanism 1 to turn
off config access. In fact, it can be downright troublesome, since it
seems to confuse the PCI-PCI bridge in the AMD8111 chipset and cause
it to sporadically botch reads from some devices. This is the cause
of the missing USP ports problem I was experiencing with my Sun Opteron
system.

Also correct the case for mechanism 2: it's only necessary to write
a 0 to the ENABLE port.
2005-10-25 04:53:29 +00:00
John Baldwin
58553b9925 Rename the KDB_STOP_NMI kernel option to STOP_NMI and make it apply to all
IPI_STOP IPIs.
- Change the i386 and amd64 MD IPI code to send an NMI if STOP_NMI is
  enabled if an attempt is made to send an IPI_STOP IPI.  If the kernel
  option is enabled, there is also a sysctl to change the behavior at
  runtime (debug.stop_cpus_with_nmi which defaults to enabled).  This
  includes removing stop_cpus_nmi() and making ipi_nmi_selected() a
  private function for i386 and amd64.
- Fix ipi_all(), ipi_all_but_self(), and ipi_self() on i386 and amd64 to
  properly handle bitmapped IPIs as well as IPI_STOP IPIs when STOP_NMI is
  enabled.
- Fix ipi_nmi_handler() to execute the restart function on the first CPU
  that is restarted making use of atomic_readandclear() rather than
  assuming that the BSP is always included in the set of restarted CPUs.
  Also, the NMI handler didn't clear the function pointer meaning that
  subsequent stop and restarts could execute the function again.
- Define a new macro HAVE_STOPPEDPCBS on i386 and amd64 to control the use
  of stoppedpcbs[] and always enable it for i386 and amd64 instead of
  being dependent on KDB_STOP_NMI.  It works fine in both the NMI and
  non-NMI cases.
2005-10-24 21:04:19 +00:00
John Baldwin
301268b8ca When restarting the BSP during cpu_reset() use a membar to ensure that
the updated cpustop_restartfunc is seen when the BSP resumes execution.
This matches the membar already present in restart_cpus().
2005-10-24 20:53:52 +00:00
John Baldwin
95d84e5461 Use xchg in Xcpustop to close a race and make cpustop_restartfunc truly
one-shot in the SMP case (before using the simple mov / cmp / mov sequence
could allow multiple CPUs to execute the restart function on resume).
2005-10-24 20:52:26 +00:00
John Baldwin
6b1e0d75b0 - Various small whitespace and style nits.
- Use PCPU_GET(cpumask) in preference to 1 << PCPU_GET(cpuid) in a few
  places.
2005-10-24 20:31:04 +00:00
Paul Saab
bbf719c8ba include opt_compat.h to unbreak the build 2005-10-24 00:00:00 +00:00
Ade Lovett
8d228514fb Specifically panic() in the case where pmap_insert_entry() fails to
get a new pv under high system load where the available pv entries
have been exhausted before the pagedaemon has a chance to wake up
to reclaim some.

Prior to this, the NULL pointer dereference ended up causing
secondary panics with rather less than useful resulting tracebacks.

Reviewed by:	alc, jhb
MFC after:	1 week
2005-10-21 19:42:43 +00:00
Jung-uk Kim
7c799f4520 Redo physical/logical CPU count.
Suggested by:	jhb
2005-10-17 23:23:20 +00:00
David Xu
9313eb5537 Micro optimization for context switch. Eliminate code for saving gs.base
and fs.base. We always update pcb.pcb_gsbase and pcb.pcb_fsbase
when user wants to set them, in context switch routine, we only need to
write them into registers, we never have to read them out from registers
when thread is switched away. Since rdmsr is a serialization instruction,
micro benchmark shows it is worthy to do.

Reviewed by: peter, jhb
2005-10-17 23:10:31 +00:00
John Baldwin
05490142bb Another bit of sx(4) removal. 2005-10-17 18:35:57 +00:00
Jung-uk Kim
42fb42a399 Split displaying number of physical and logical cores. 2005-10-17 15:51:28 +00:00
David E. O'Brien
f5dce7aa6e For AMD processors, nullify CPUID.HTT. FreeBSD has no need for the
information it conveys, and it is only confusing people.
This fixes incorrect output in the previous commit.
2005-10-16 08:58:27 +00:00
Jung-uk Kim
25736eb670 Correct few MSR addresses.
PR:		amd64/85852
Submitted by:	Nate Eldredge <nge at cs dot hmc dot edu>
2005-10-15 00:44:56 +00:00
Jung-uk Kim
9c3acb0bc1 - Print number of physical/logical cores and more CPUID info.
- Add newer CPUID definitions for future use.

Many thanks to Mike Tancsa <mike at sentex dot net> for providing test
cases for Intel Pentium D and AMD Athlon 64 X2.

Approved by:	anholt (mentor)
2005-10-14 22:52:01 +00:00
John Baldwin
728ef95410 The signal code is now an int rather than a long, so update debug printfs. 2005-10-14 20:22:57 +00:00
Ruslan Ermilov
6f6b430e2f Sort ath_rate_* entries. Mark ath_rate_sample as the desired algorithm.
Discussed with:	sam
2005-10-14 17:22:28 +00:00
David Xu
9104847f21 1. Change prototype of trapsignal and sendsig to use ksiginfo_t *, most
changes in MD code are trivial, before this change, trapsignal and
   sendsig use discrete parameters, now they uses member fields of
   ksiginfo_t structure. For sendsig, this change allows us to pass
   POSIX realtime signal value to user code.

2. Remove cpu_thread_siginfo, it is no longer needed because we now always
   generate ksiginfo_t data and feed it to libpthread.

3. Add p_sigqueue to proc structure to hold shared signals which were
   blocked by all threads in the proc.

4. Add td_sigqueue to thread structure to hold all signals delivered to
   thread.

5. i386 and amd64 now return POSIX standard si_code, other arches will
   be fixed.

6. In this sigqueue implementation, pending signal set is kept as before,
   an extra siginfo list holds additional siginfo_t data for signals.
   kernel code uses psignal() still behavior as before, it won't be failed
   even under memory pressure, only exception is when deleting a signal,
   we should call sigqueue_delete to remove signal from sigqueue but
   not SIGDELSET. Current there is no kernel code will deliver a signal
   with additional data, so kernel should be as stable as before,
   a ksiginfo can carry more information, for example, allow signal to
   be delivered but throw away siginfo data if memory is not enough.
   SIGKILL and SIGSTOP have fast path in sigqueue_add, because they can
   not be caught or masked.
   The sigqueue() syscall allows user code to queue a signal to target
   process, if resource is unavailable, EAGAIN will be returned as
   specification said.
   Just before thread exits, signal queue memory will be freed by
   sigqueue_flush.
   Current, all signals are allowed to be queued, not only realtime signals.

Earlier patch reviewed by: jhb, deischen
Tested on: i386, amd64
2005-10-14 12:43:47 +00:00
Gleb Smirnoff
9c26aa3c12 Polling is now configured with help of ifconfig(8), not sysctl.
Prodded by:     maxim
2005-10-07 09:23:51 +00:00
Peter Wemm
07f5921b86 Don't set segment registers via ptrace yet. Its not ready. 2005-10-04 23:26:00 +00:00
Gleb Smirnoff
4092996774 Big polling(4) cleanup.
o Axe poll in trap.

o Axe IFF_POLLING flag from if_flags.

o Rework revision 1.21 (Giant removal), in such a way that
  poll_mtx is not dropped during call to polling handler.
  This fixes problem with idle polling.

o Make registration and deregistration from polling in a
  functional way, insted of next tick/interrupt.

o Obsolete kern.polling.enable. Polling is turned on/off
  with ifconfig.

Detailed kern_poll.c changes:
  - Remove polling handler flags, introduced in 1.21. The are not
    needed now.
  - Forget and do not check if_flags, if_capenable and if_drv_flags.
  - Call all registered polling handlers unconditionally.
  - Do not drop poll_mtx, when entering polling handlers.
  - In ether_poll() NET_LOCK_GIANT prior to locking poll_mtx.
  - In netisr_poll() axe the block, where polling code asks drivers
    to unregister.
  - In netisr_poll() and ether_poll() do polling always, if any
    handlers are present.
  - In ether_poll_[de]register() remove a lot of error hiding code. Assert
    that arguments are correct, instead.
  - In ether_poll_[de]register() use standard return values in case of
    error or success.
  - Introduce poll_switch() that is a sysctl handler for kern.polling.enable.
    poll_switch() goes through interface list and enabled/disables polling.
    A message that kern.polling.enable is deprecated is printed.

Detailed driver changes:
  - On attach driver announces IFCAP_POLLING in if_capabilities, but
    not in if_capenable.
  - On detach driver calls ether_poll_deregister() if polling is enabled.
  - In polling handler driver obtains its lock and checks IFF_DRV_RUNNING
    flag. If there is no, then unlocks and returns.
  - In ioctl handler driver checks for IFCAP_POLLING flag requested to
    be set or cleared. Driver first calls ether_poll_[de]register(), then
    obtains driver lock and [dis/en]ables interrupts.
  - In interrupt handler driver checks IFCAP_POLLING flag in if_capenable.
    If present, then returns.This is important to protect from spurious
    interrupts.

Reviewed by:	ru, sam, jhb
2005-10-01 18:56:19 +00:00
Robert Watson
5f419982c2 Back out alpha/alpha/trap.c:1.124, osf1_ioctl.c:1.14, osf1_misc.c:1.57,
osf1_signal.c:1.41, amd64/amd64/trap.c:1.291, linux_socket.c:1.60,
svr4_fcntl.c:1.36, svr4_ioctl.c:1.23, svr4_ipc.c:1.18, svr4_misc.c:1.81,
svr4_signal.c:1.34, svr4_stat.c:1.21, svr4_stream.c:1.55,
svr4_termios.c:1.13, svr4_ttold.c:1.15, svr4_util.h:1.10,
ext2_alloc.c:1.43, i386/i386/trap.c:1.279, vm86.c:1.58,
unaligned.c:1.12, imgact_elf.c:1.164, ffs_alloc.c:1.133:

Now that Giant is acquired in uprintf() and tprintf(), the caller no
longer leads to acquire Giant unless it also holds another mutex that
would generate a lock order reversal when calling into these functions.
Specifically not backed out is the acquisition of Giant in nfs_socket.c
and rpcclnt.c, where local mutexes are held and would otherwise violate
the lock order with Giant.

This aligns this code more with the eventual locking of ttys.

Suggested by:	bde
2005-09-28 07:03:03 +00:00
Peter Wemm
d176c062c9 I believe the stack underflows during early development that caused me to
add spare padding at the beginning of the pcb are long gone.  Remove the
padding fields.
2005-09-27 21:11:35 +00:00
Peter Wemm
1acc225f91 Kill pcb_rflags. It served no purpose.
Reported by:  bde
2005-09-27 21:10:10 +00:00
Peter Wemm
98df9e0010 Fix a minor nit that has been bugging me for a while. Fix the obvious
cases of using a 64 bit operation to zero a register.  32 bit opcodes are
smaller and supposedly faster, and clear the upper 32 bits for free.
2005-09-27 18:32:46 +00:00
Peter Wemm
901b68c185 Add a bare minimum (but wrong) R_X86_64_JMP_SLOT relocation type for
kernel modules.  We actually need to include any addends and the symbol
offset value, but for gcc/binutils didn't set it anywhere I've found on
'cc -fpic -shared' kernel modules.
2005-09-27 18:18:23 +00:00
Peter Wemm
04bc142a09 Don't report Maxmem as 'real memory'. It is really the highest address
available and can give the wrong impression when there are memory holes.
Report the total amount of usable memory that we detected instead of the
highest address.
2005-09-27 18:15:57 +00:00
Peter Wemm
686447adcc MFi386: If we take a trap with interrupts disabled while in a critical
section, don't enable them if we're servicing an NMI.
2005-09-27 18:13:07 +00:00
Peter Wemm
458d22f302 Don't let the upper bits of %dr6/%dr7 get set.
Submitted by:  Nate Eldredge <neldredge@math.ucsd.edu>
2005-09-27 18:10:26 +00:00
Peter Wemm
add121a476 Implement 32 bit getcontext/setcontext/swapcontext on amd64. I've added
stubs for ia64 to keep it compiling.  These are used by 32 bit apps such
as gdb.
2005-09-27 18:04:20 +00:00
John Baldwin
3c2bc2bf26 Add a new atomic_fetchadd() primitive that atomically adds a value to a
variable and returns the previous value of the variable.

Tested on:	i386, alpha, sparc64, arm (cognet)
Reviewed by:	arch@
Submitted by:	cognet (arm)
MFC after:	1 week
2005-09-27 17:39:11 +00:00
Poul-Henning Kamp
57489b8657 __RMAN_RESOURCE_VISIBLE is not actually needed. 2005-09-25 20:03:41 +00:00
Stephan Uphoff
2a988f7cb5 Fix the "fpudna: fpcurthread == curthread XXX times" problem.
Tested by: kris@
Reviewed by:	peter@
MFC after:	3 days
2005-09-22 15:46:21 +00:00
Robert Watson
84d2b7df26 Add GIANT_REQUIRED and WITNESS sleep warnings to uprintf() and tprintf(),
as they both interact with the tty code (!MPSAFE) and may sleep if the
tty buffer is full (per comment).

Modify all consumers of uprintf() and tprintf() to hold Giant around
calls into these functions.  In most cases, this means adding an
acquisition of Giant immediately around the function.  In some cases
(nfs_timer()), it means acquiring Giant higher up in the callout.

With these changes, UFS no longer panics on SMP when either blocks are
exhausted or inodes are exhausted under load due to races in the tty
code when running without Giant.

NB: Some reduction in calls to uprintf() in the svr4 code is probably
desirable.

NB: In the case of nfs_timer(), calling uprintf() while holding a mutex,
or even in a callout at all, is a bad idea, and will generate warnings
and potential upset.  This needs to be fixed, but was a problem before
this change.

NB: uprintf()/tprintf() sleeping is generally a bad ideas, as is having
non-MPSAFE tty code.

MFC after:	1 week
2005-09-19 16:51:43 +00:00
Christian S.J. Peron
33cdc78d01 Introduce a kernel config for the Mandatory Access Control framework.
This kernel config briefly describes some of the major MAC policies
available on FreeBSD. The hope is that this will raise the awareness
about MAC and get more people interested.

Discussed with:	scottl
2005-09-18 03:15:36 +00:00
Warner Losh
62061bf002 MFi386: pci attribute allocation fixes. 2005-09-18 01:42:43 +00:00
John Baldwin
80d52f16da Stop using the '+' constraint modifier with inline assembly. The '+'
constraint is actually only allowed for register operands.  Instead, use
separate input and output memory constraints.

Education from:	alc
Reviewed by:	alc
Tested on:	i386, alpha
MFC after:	1 week
2005-09-15 19:31:22 +00:00
David E. O'Brien
2a191126de Canonize the include of acpi.h. 2005-09-11 18:39:03 +00:00
Marcel Moolenaar
216e80c2ba Move the prototypes of db_md_set_watchpoint(), db_md_clr_watchpoint()
and db_md_list_watchpoints() to ddb/ddb.h.
2005-09-10 03:01:25 +00:00
Scott Long
dc8540a9a0 Hook up the hptmv driver for amd64.
MFC After: 3 days
2005-09-08 03:29:18 +00:00
Alan Cox
3be99ffc1a Eliminate unnecessary TLB invalidations by pmap_enter(). Specifically,
eliminate TLB invalidations when permissions are relaxed, such as when a
read-only mapping is changed to a read/write mapping.  Additionally,
eliminate TLB invalidations when bits that are ignored by the hardware,
such as PG_W ("wired mapping"), are changed.

Reviewed by:	tegge
2005-09-04 19:06:27 +00:00
Alan Cox
ba8bca610c Pass a value of type vm_prot_t to pmap_enter_quick() so that it determine
whether the mapping should permit execute access.
2005-09-03 18:20:20 +00:00
Joseph Koshy
7ef5ed2bb1 - Special-case NMI handling on the AMD64.
On entry or exit from the kernel the 'alltraps' and 'doreti' code
  used taken by normal traps disables interrupts to protect the
  critical sections where it is setting up %gs.

  This protection is insufficient in the presence of NMIs since NMIs
  can be taken even when the processor has disabled normal interrupts.
  Thus the NMI handler needs to actually read MSR_GBASE on entry to
  the kernel to determine whether a swap of %gs using 'swapgs' is
  needed.  However, reads of MSRs are expensive and integrating this
  check into the 'alltraps'/'doreti' path would penalize normal
  interrupts.

- Teach DDB about the 'nmi_calltrap' symbol.

Reviewed by:	bde, peter (older versions of this change)
2005-08-27 16:03:40 +00:00
Alan Cox
8c190069a2 Remedy the following three problems:
1. The amd64 pmap, unlike the i386 pmap, maintains a reference count
   for each page directory (PD) page.  However, in the transformation
   of the i386 pmap into the amd64 pmap, operations, such as
   pmap_copy() and pmap_object_init_pt(), that create 2MB "superpage"
   mappings by setting the PG_PS bit in a PD entry were not modified
   to adjust the underlying PD page's reference count.  Consequently,
   superpage mappings could disappear prematurely.

2. pmap_object_init_pt() could crash or corrupt memory if either the
   virtual address range being mapped crosses a 1GB boundary in the
   virtual address space or nothing is mapped in the 1GB area.

3. When pmap_allocpte() destroys a 2MB "superpage" mapping it does not
   reduce the pmap's resident count accordingly.  It should.  (This
   bug is inherited from i386.)

Discussed with: peter
Reviewed by:    tegge
2005-08-26 05:18:46 +00:00
Stephan Uphoff
0e7bd54c71 NMI handler should not enable interrupts.
Tested by: kris@
MFC after:	3 weeks
2005-08-25 20:33:43 +00:00
Alan Cox
7380c1acb5 Pass the PDE from pmap_remove() to pmap_remove_page() so that the latter
procedure doesn't have to recompute it.
2005-08-22 20:02:40 +00:00
Alan Cox
2c15852e1e Change pmap_extract() and pmap_extract_and_hold() to use PG_FRAME rather
than ~PDRMASK to extract the physical address of a superpage from a PDE.
The use of ~PDRMASK is problematic if the PDE has PG_NX set.  Specifically,
the PG_NX bit will be included in the physical address if ~PDRMASK is used.

Reviewed by:	peter
2005-08-22 07:23:51 +00:00
Alan Cox
8b78b3dc58 Introduce pmap_pml4e_to_pdpe() and pmap_pdpe_to_pde() and use them to avoid
recomputation of the pml4e and pdpe in pmap_copy(), pmap_protect(), and
pmap_remove().
2005-08-20 18:37:34 +00:00
Stefan Farfeleder
a1f85d7f83 Move MINSIGSTKSZ from <machine/signal.h> to <machine/_limits.h> and rename
it to __MINSIGSTKSZ.  Define MINSIGSTKSZ in <sys/signal.h>.

This is done in order to use MINSIGSTKSZ for the macro PTHREAD_STACK_MIN
in <pthread.h> (soon <limits.h>) without having to include the whole
<sys/signal.h> header.

Discussed with:		bde
2005-08-20 16:44:41 +00:00
Pawel Jakub Dawidek
a95452ee8d Avoid code duplication and implement bitcount32() function in systm.h only.
Reviewed by:	cperciva
MFC after:	3 days
2005-08-19 22:10:19 +00:00
Alan Cox
eb3d4a39fd Correct a performance bug in revision 1.462. The effect of the bug is to
execute the outer loop in procedures such as pmap_protect() many more times
than necessary.

Reviewed by:	tegge
2005-08-19 07:25:40 +00:00
John Baldwin
5d2f4de5da Add aliases for atomic operations on 64-bit integers just like other
64-bit platforms.

MFC after:	1 week
2005-08-18 14:36:47 +00:00
Alan Cox
96e5109430 Simplify the page table page reference counting by pmap_enter()'s change of
mapping case.

Eliminate a stale comment from pmap_enter().

Reviewed by:	tegge
2005-08-14 20:02:50 +00:00
Alan Cox
50b334506f Eliminate unneeded diagnostic code.
Eliminate an unused #include.  (Kernel stack allocation and deallocation
long ago migrated to the machine-independent code.)
2005-08-11 23:38:02 +00:00
Alan Cox
b69dd0fda6 Eliminate unneeded diagnostic code.
Reviewed by:	tegge
2005-08-11 17:43:28 +00:00
Alan Cox
8e7a85fac9 Decouple the unrefing of a page table page from the removal of a pv entry.
In other words, change pmap_remove_entry() such that it no longer unrefs
the page table page.  Now, it only removes the pv entry.

Reviewed by:	tegge
2005-08-11 02:22:55 +00:00
Alan Cox
5f2c46d5ed When support for 2MB/4MB pages was added in revision 1.148 an error was
made in pmap_protect(): The pmap's resident count should not be reduced
unless mappings are removed.

The errant change to the pmap's resident count could result in a later
pmap_remove() failing to remove any mappings if the errant change has set
the pmap's resident count to zero.
2005-08-07 22:00:47 +00:00
Jeff Roberson
d0f5f62d8b - Add support for saving stack traces and displaying them via printf(9)
and KTR.

Contributed by:		Antoine Brodin <antoine.brodin@laposte.net>
Concept code from:	Neal Fachan <neal@isilon.com>
2005-08-03 04:33:48 +00:00
Jeff Roberson
bb2fd058ce - Improve the definition of INKERNEL() to include the DMAP area and the
proper start of the kernel area.

Discussed with:	peter
2005-08-03 04:21:51 +00:00
John Baldwin
813a5e14ec Move MODULE_DEPEND() statements for SYSVIPC dependencies to linux_ipc.c
so that they aren't duplicated 3 times and are also in the same file as
the code that depends on the SYSVIPC modules.
2005-07-29 19:40:39 +00:00
Maxime Henrion
5a29706504 Add back ed(4) in amd64 GENERIC. It now works nicely and since those
chips are commonly found, it makes sense to have it in GENERIC.  This
is a candidate for a RELENG_6 MFC.

Approved by;	peter
Requested by:	pav
Tested by:	pav
2005-07-24 17:55:57 +00:00
Ruslan Ermilov
c5bf476aa9 Fallout from the previous revision: lnc isn't quite ready for amd64 yet. 2005-07-22 16:02:40 +00:00
David E. O'Brien
b8b77732ff Fix $FreeBSD$. 2005-07-22 04:03:25 +00:00
Peter Wemm
9e76f9ad3f Like on i386, bypass lock prefix for atomic ops on !SMP kernels. 2005-07-21 22:35:02 +00:00
Peter Wemm
4bf21bfef9 MFi386: add vpd driver (vital product data.. model & serial numbers etc) 2005-07-21 21:57:31 +00:00
Peter Wemm
6ec2971397 Add the ed driver for lint building. The PCI instances are still useful.
In theory, there are no isa slots on any amd64/em64t systems, but it
doesn't hurt to keep these tiny fragments compiling.
2005-07-21 21:55:11 +00:00
Peter Wemm
84d7e08229 Actually create the double fault stack page for AP cpus so that we have a
chance of getting a working double fault instead of converting it to an
instant triple fault reset.
2005-07-21 21:46:09 +00:00
Poul-Henning Kamp
636d90fc5c Make the facility for recognizing BIOS-signatures more general
and return a printable representation.

This fixes recognition of the PC Engines WRAP and improves the
recognition of the Soekris boards (Bios version can now be
seen in the dmesg output for instance).

Also, add watchdog support for PCM-582x platforms.

Submitted by:	Adrian Steinmann <ast@marabu.ch>
Slightly changed by:	phk
PR:	81360
2005-07-21 09:48:37 +00:00
Jung-uk Kim
a52daa5fd2 Fix smbios(4) and add support for amd64
Approved by:	anholt (mentor)
2005-07-21 00:18:28 +00:00
Eric Anholt
af088425f7 Add the latest r300 code from r300.sf.net. This is based on the patch supplied
by Vladimir Dergachev for inclusion in DRM CVS, with minor modifications for
FreeBSD CVS and the appropriate license from Nicolai Haehnle on r300_reg.h.
Fixes hangs when using r300.sf.net userland, tested on a Radeon 9600 on amd64.
2005-07-20 21:10:57 +00:00
John Baldwin
122eceef61 Convert the atomic_ptr() operations over to operating on uintptr_t
variables rather than void * variables.  This makes it easier and simpler
to get asm constraints and volatile keywords correct.

MFC after:	3 days
Tested on:	i386, alpha, sparc64
Compiled on:	ia64, powerpc, amd64
Kernel toolchain busted on:	arm
2005-07-15 18:17:59 +00:00
Ken Smith
22e59cec3b Add recently invented COMPAT_FREEBSD5 option.
MFC after:	3 days
2005-07-14 15:39:06 +00:00
John Baldwin
ac5ee935dd Regen. 2005-07-13 20:35:09 +00:00
John Baldwin
8683e7fdc1 Make a pass through all the compat ABIs sychronizing the MP safe flags
with the master syscall table as well as marking several ABI wrapper
functions safe.

MFC after:	1 week
2005-07-13 20:32:42 +00:00
John Baldwin
db015a9153 Fixup some more fallout from the lapic/i8254 changes:
- Make sure timer0_max_count is set to a correct value in the lapic case.
- Revert i8254_restore() to explicitly reprogram timer 0 rather than
  calling set_timer_freq() to do it.  set_timer_freq() only reprograms
  the counter if the max count changes which it never does on resume.  This
  unbreaks suspend/resume for several people.

Tested by:	marks, others
Reviewed by:	bde
MFC after:	3 days
2005-07-13 15:43:21 +00:00
David Xu
740fd64d65 Validate if the value written into {FS,GS}.base is a canonical
address, writting non-canonical address can cause kernel a panic,
by restricting base values to 0..VM_MAXUSER_ADDRESS, ensuring
only canonical values get written to the registers.

Reviewed by: peter, Josepha Koshy < joseph.koshy at gmail dot com >
Approved by: re (scottl)
2005-07-10 23:31:11 +00:00
John Baldwin
48281036d7 Some cleanups and tweaks to some of the atomic.h files in preparation for
further changes and fixes in the future:
- Use aliases via macros rather than duplicated inlines wherever possible.
- Move all the aliases to the bottom of these files and the inline
  functions to the top.
- Add various comments.
- On alpha, drop atomic_{load_acq,store_rel}_{8,char,16,short}().
- On i386 and amd64, don't duplicate the extern declarations for functions
  in the two non-inline cases (KLD_MODULE and compiler doesn't do inlines),
  instead, consolidate those two cases.
- Some whitespace fixes.

Approved by:	re (scottl)
2005-07-09 12:38:53 +00:00
John Baldwin
623b1a868e Remove a || 1 that crept into the i8254 commit and was subsequently
copied and pasted.  I had actually tested without this change in my
trees as had the other testers.

Reported by:	bde, Rostislav Krasny rosti dot bsd at gmail dot com
Approved by:	re (scottl)
Pointy hat to:	jhb
2005-07-05 20:13:12 +00:00
Andrew Thompson
2fcb030ad5 Check the alignment of the IP header before passing the packet up to the
packet filter. This would cause a panic on architectures that require strict
alignment such as sparc64 (tier1) and ia64/ppc (tier2).

This adds two new macros that check the alignment, these are compile time
dependent on __NO_STRICT_ALIGNMENT which is set for i386 and amd64 where
alignment isn't need so the cost is avoided.

 IP_HDR_ALIGNED_P()
 IP6_HDR_ALIGNED_P()

Move bridge_ip_checkbasic()/bridge_ip6_checkbasic() up so that the alignment
is checked for ipfw and dummynet too.

PR:		ia64/81284
Obtained from:	NetBSD
Approved by:	re (dwhite), mlaier (mentor)
2005-07-02 23:13:31 +00:00
Marcel Moolenaar
5116398a06 Fix a buglet that was present in the ia64 code and that got inherited
by amd64 and i386: For buffered writes we collect data and write it
out a ${DEV_BSIZE}-sized block at a time. The fragsz variable is used
to keep track of how much data we have collected in the buffer so far
and it's reset to zero immediately after writing a block to the dump
device.
When the last, possibly partially filled buffer is flushed, we didn't
reset fragsz to 0 and as such would stop reflecting reality. Since we
currently only need to do buffered writes once, this isn't a problem.
However, when kernel dumps are made by hand (say by callling doadump
from within DDB), the improperly cleared state from the first call to
dumpsys causes the next call to dumpsys to create an invalid code file.
This change resets fragsz after flushing the partially filled buffer so
that it fixes the two problems at once.

Approved by: re (scottl)
2005-07-02 19:57:31 +00:00
Peter Wemm
27e11adbbb MFi386: r1.221: use simple timecounter that is aware of irq0 being off.
Approved by:  re
2005-07-01 20:13:19 +00:00
Peter Wemm
62919d788b Jumbo-commit to enhance 32 bit application support on 64 bit kernels.
This is good enough to be able to run a RELENG_4 gdb binary against
a RELENG_4 application, along with various other tools (eg: 4.x gcore).
We use this at work.

ia32_reg.[ch]: handle the 32 bit register file format, used by ptrace,
	procfs and core dumps.
procfs_*regs.c: vary the format of proc/XXX/*regs depending on the client
	and target application.
procfs_map.c: Don't print a 64 bit value to 32 bit consumers, or their
	sscanf fails.  They expect an unsigned long.
imgact_elf.c: produce a valid 32 bit coredump for 32 bit apps.
sys_process.c: handle 32 bit consumers debugging 32 bit targets.  Note
	that 64 bit consumers can still debug 32 bit targets.

IA64 has got stubs for ia32_reg.c.

Known limitations: a 5.x/6.x gdb uses get/setcontext(), which isn't
implemented in the 32/64 wrapper yet.  We also make a tiny patch to
gdb pacify it over conflicting formats of ld-elf.so.1.

Approved by:	re
2005-06-30 07:49:22 +00:00
Peter Wemm
80a110932e Sync i386->amd64.
* Add ichwd (The Intel EM64T folks have an ICH)
* Cosmetic comment syncs
* Merge cpufreq change over to NOTES
* add pbio (it compiles, but isn't useful since no boxes have ISA slots)
* copy ath settings (note: wlan disabled here since its in global NOTES)
* copy profiling, including fixing a previous i386->amd64 merge typo.

Approved by:	re (blanket i386 <-> amd64 sync/convergence)
2005-06-30 05:33:26 +00:00
Peter Wemm
2bdfd0d814 Add a special-case handler for general protection faults. It appears to
be possible to get the swapgs state reversed if doreti traps during
the iretq.  Attempt to handle this.  load_gs() might need special
handling too.  Running the kernel with the user's TLS and the
kernel's PCPU space interchanged would be bad(TM).

Discovered as a result of a conversation with:  bde
Approved by:  re
2005-06-30 00:26:54 +00:00
Peter Wemm
f0c6706de9 Move the KDB_STOP_NMI option from opt_global.h to opt_kdb.h
Approved by:	re
2005-06-29 23:23:16 +00:00
Peter Wemm
235a54de9d Switch AMD64 and i386 platforms to using ELF as their kernel crash
dump format.  The key reason to do this is so that we can dump sparse
address space.  For example, we need to be able to skip the PCI hole
just below the 4GB boundary.  Trying to destructively dump MMIO device
registers is Really Bad(TM).  The frequent result of trying to do a
crash dump on a machine with 4GB or more ram was ugly (lockup or reboot).

This code has been taken directly from the IA64 dump_machdep.c code,
with just a few (mostly minor) mods.

Introduce a dump_avail[] array in the machdep.c code so that we have a
source of truth for what memory is present in a machine that needs to be
dumped.  We can't use phys_avail[] because all sorts of things slice
memory out of it that we really need to dump.  eg: the vm page array
and the dmesg buffer.  dump_avail[] is pretty much an unmolested version
of phys_avail[].  It does have Maxmem correction.

Bump the i386 and amd64 dump format to version 2, but nothing actually
uses this.  amd64 was actually using the i386 dump version number.

libkvm support to follow.

Approved by:	re
2005-06-29 22:28:46 +00:00
John Baldwin
014693eb89 Increase MAXCPU to 16 in SMP kernels so that APIC IDs from 0 to 15 are
allowed for CPUs.

Tested by:	amd64 at cybernetwork dot org
Approved by:	re (scottl)
MFC after:	1 week
2005-06-29 15:13:25 +00:00
Stephan Uphoff
769c6708cb Disable the interrupts in trap_fatal before calling kdb_trap.
(required now that critical sections no longer block interrupts)

Reviewed by:	jhb@
Approved by:	re (scottl)
Tested by:	kris@,glebius@
2005-06-25 22:14:42 +00:00
John Baldwin
de1c01ad37 Correct the amount of data to allocate in these local copies of
exec_copyin_strings() to catch up to rev 1.266 of kern_exec.c.  This fixes
panics on amd64 with compat binaries since exec_free_args() was freeing
more memory than these functions were allocating and the mismatch could
cause memory to be freed out from under other concurrent execs.

Approved by:	re (scottl)
2005-06-24 17:41:28 +00:00
Peter Wemm
46007a41da Various trivial comment fixes
Approved by: re
2005-06-24 00:45:01 +00:00
Peter Wemm
e973a7af90 Eliminate a source of 'trap xx with interrupts disabled'. I was jumping to
the wrong backend code and neglecting to re-enable interrupts after the
stack prep.

Approved by:  re
2005-06-24 00:38:36 +00:00
Peter Wemm
a202ff9ebf MFi386: 1.258: Minor cleanups
Approved by:  re (blanket i386<->amd64 sync)
2005-06-24 00:29:53 +00:00
Peter Wemm
4da0d332f4 Move HWPMC_HOOKS into its own opt_hwpmc_hooks.h file. It doesn't merit
being in opt_global.h and forcing a global recompile when only a few files
reference it.

Approved by:  re
2005-06-24 00:16:57 +00:00
David E. O'Brien
c3e0dfa1f8 Add .cvsignore files just like in sys/<arch>/compiled, this keeps CVS from
questing kernel config files not in CVS.

Approved by:	re(kensmith)
2005-06-20 16:52:59 +00:00
Stephan Uphoff
7452bc4957 Move IPI_PREEMPTION option from global NOTES file to i386+amd64 specific
NOTES files.

Approved by:	re (scottl)
2005-06-14 14:21:25 +00:00
Alan Cox
1c245ae7d1 Introduce a procedure, pmap_page_init(), that initializes the
vm_page's machine-dependent fields.  Use this function in
vm_pageq_add_new_page() so that the vm_page's machine-dependent and
machine-independent fields are initialized at the same time.

Remove code from pmap_init() for initializing the vm_page's
machine-dependent fields.

Remove stale comments from pmap_init().

Eliminate the Boolean variable pmap_initialized from the alpha, amd64,
i386, and ia64 pmap implementations.  Its use is no longer required
because of the above changes and earlier changes that result in physical
memory that is being mapped at initialization time being mapped without
pv entries.

Tested by: cognet, kensmith, marcel
2005-06-10 03:33:36 +00:00
Joseph Koshy
f263522a45 MFP4:
- Implement sampling modes and logging support in hwpmc(4).

- Separate MI and MD parts of hwpmc(4) and allow sharing of
  PMC implementations across different architectures.
  Add support for P4 (EMT64) style PMCs to the amd64 code.

- New pmcstat(8) options: -E (exit time counts) -W (counts
  every context switch), -R (print log file).

- pmc(3) API changes, improve our ability to keep ABI compatibility
  in the future.  Add more 'alias' names for commonly used events.

- bug fixes & documentation.
2005-06-09 19:45:09 +00:00
Stephan Uphoff
6097174e4d Add IPI support for preempting a thread on another CPU.
MFC after:	3 weeks
2005-06-09 18:23:54 +00:00
Maxim Sobolev
ded18ff2ab Regen after addition of linux_getpriority wrapper.
PR:		kern/81951
Submitted by:	Andriy Gapon <avg@icyb.net.ua>
MFC after:	1 week
2005-06-08 20:47:30 +00:00
Maxim Sobolev
bc165ab0fe Properly convert FreeBSD priority values into Linux values in the
getpriority(2) syscall.

PR:		kern/81951
Submitted by:	Andriy Gapon <avg@icyb.net.ua>
2005-06-08 20:41:28 +00:00
Robert Watson
3984b2328c Rebuild generated system call definition files following the addition of
the audit event field to the syscalls.master file format.

Submitted by:	wsalamon
Obtained from:	TrustedBSD Project
2005-05-30 15:20:21 +00:00
Robert Watson
f3596e3370 Introduce a new field in the syscalls.master file format to hold the
audit event identifier associated with each system call, which will
be stored by makesyscalls.sh in the sy_auevent field of struct sysent.
For now, default the audit identifier on all system calls to AUE_NULL,
but in the near future, other BSM event identifiers will be used.  The
mapping of system calls to event identifiers is many:one due to
multiple system calls that map to the same end functionality across
compatibility wrappers, ABI wrappers, etc.

Submitted by:	wsalamon
Obtained from:	TrustedBSD Project
2005-05-30 15:09:18 +00:00
Joseph Koshy
36c0fd9d0f Kernel hooks to support PMC sampling modes.
Reviewed by:	alc
2005-05-30 06:29:29 +00:00
Marcel Moolenaar
470cd51ee6 Create nexus in configure_first() instead of in configure(). This
makes sure that sysinit tasks that run after configure_first(),
but before configure() have a nexus to hang devices off.
2005-05-29 23:44:22 +00:00
Jens Schweikhardt
1d91c0f538 Chop a '>' in a feature name (RSVD2>) that snuck in;
this now balances the <> flags displayed at boot, e.g. without this
Features2=0x41d<SSE3,RSVD2>,MON,DS_CPL,CNTX-ID>

MFC after:	1 week
2005-05-29 17:43:24 +00:00
Yoshihiro Takahashi
d4fcf3cba5 Remove bus_{mem,p}io.h and related code for a micro-optimization on i386
and amd64.  The optimization is a trivial on recent machines.

Reviewed by:	-arch (imp, marcel, dfr)
2005-05-29 04:42:30 +00:00
Yoshihiro Takahashi
f7965374d4 Change the spkr_set_pitch() function to a macro to fix low level profiling. 2005-05-28 13:40:27 +00:00
Damien Bergamini
0b090f4153 Add new ral(4) and ural(4) drivers.
Approved by:	silby (mentor)
2005-05-24 16:48:07 +00:00
David E. O'Brien
dc156a91f9 Sync the style of these two files. 2005-05-23 17:36:54 +00:00
Peter Wemm
ea5d76835f Fix some of the problems Bruce observed with this code. 2005-05-22 23:28:17 +00:00
Peter Wemm
b2e960125c MFi386: set PMC vector 2005-05-22 16:32:02 +00:00
Peter Wemm
1eb6f02e7a MFi386: remove comment 2005-05-22 16:31:32 +00:00
Peter Wemm
c592ba5f3f For non-profiling kernels, there were two symbols assigned to the same
address.  One was alltraps_with_regs_pushed, the other was calltrap.

When the stack tracer walks up, it looks for magic symbol names to
determine how to parse non-standard stack frames, such as a trapframe.
It was looking for "calltrap".  Which of the two symbols you got depended
on things like Phase of moon, etc.  If you were unlucky, you got a
garbage stack trace for things like 'debug.trace_on_panic', which would
completely hide the actual source of the problem.
2005-05-21 00:02:12 +00:00
David E. O'Brien
c8dddf0d55 Adjust the start_ap delay to match i386. 2005-05-20 16:25:08 +00:00
David E. O'Brien
5d12ba1ff7 Fix mismerge in rev 1.226: wait 5 seconds as the comment documents,
not .5 seconds.
2005-05-20 16:23:15 +00:00
Yoshihiro Takahashi
b22bf66063 - Move bus dependent defines to {isa,cbus}_dmareg.h.
- Use isa/isareg.h rather than <arch>/isa/isa.h.

Tested on: i386, pc98
2005-05-14 10:14:56 +00:00
Yoshihiro Takahashi
24072ca35b - Move timerreg.h to <arch>/include and split i8253 specific defines into
i8253reg.h, and add some defines to control a speaker.
- Move PPI related defines from i386/isa/spkr.c into ppireg.h and use them.
- Move IO_{PPI,TIMER} defines into ppireg.h and timerreg.h respectively.
- Use isa/isareg.h rather than <arch>/isa/isa.h.

Tested on: i386, pc98
2005-05-14 09:10:02 +00:00
Jacques Vidrine
032e56ae9b Default hyperthreading on in -CURRENT. No seatbelts in CURRENT (^_^)
Requested by:	peter, jhb
2005-05-13 00:57:04 +00:00
Jacques Vidrine
f6108b6158 Add a knob for disabling/enabling HTT, "machdep.hyperthreading_allowed".
Default off due to information disclosure on multi-user systems.

Submitted by:	cperciva
Reviewed by:	jhb
2005-05-13 00:10:56 +00:00
Yoshihiro Takahashi
d6c331a30d Remove unused IO_NPX* defines. 2005-05-12 12:36:31 +00:00
Peter Wemm
fa37873521 Remove unused (besides being initialized) variable. 2005-05-05 18:19:53 +00:00
David Xu
89af2d4283 Turn on PCB_FULLCTX in set_regs to fully restore context
set by debugger.
2005-05-04 22:26:40 +00:00
Doug White
fdc9713bf7 Implement an alternate method to stop CPUs when entering DDB. Normally we use
a regular IPI vector, but this vector is blocked when interrupts are disabled.
With "options KDB_STOP_NMI" and debug.kdb.stop_cpus_with_nmi set, KDB will
send an NMI to each CPU instead. The code also has a context-stuffing
feature which helps ddb extract the state of processes running on the
stopped CPUs.

KDB_STOP_NMI is only useful with SMP and complains if SMP is not defined.
This feature only applies to i386 and amd64 at the moment, but could be
used on other architectures with the appropriate MD bits.

Submitted by:	ups
2005-04-30 20:01:00 +00:00
Scott Long
379ad24369 Remove the ACPI_MAX_THREADS option. 2005-04-25 19:59:09 +00:00
David Xu
21fc316430 Change cpu_set_kse_upcall to more generic style, so we can reuse it
in other codes. Add cpu_set_user_tls, use it to tweak user register
and setup user TLS. I ever wanted to merge it into cpu_set_kse_upcall,
but since cpu_set_kse_upcall is also used by M:N threads which may
not need this feature, so I wrote a separated cpu_set_user_tls.
2005-04-23 02:32:32 +00:00
Marcel Moolenaar
d47cce3ec8 Revert previous commit: The hwpmc(4) driver compiles on all platforms. 2005-04-20 22:19:51 +00:00
Paul Saab
8cb038b4b2 Don't enter the debugger if KDB_UNATTENDED is set or if
debug.debugger_on_panic=0.

MFC after:	2 weeks
2005-04-20 20:52:46 +00:00
Marcel Moolenaar
76b6d954f0 o Reverse the inclusion chain from MD->MI to MI->MD by removing the
inclusion of <sys/pmc.h> and depending on being included from
   that header file.
o  Include any MD specific header files that otherwise need to be
   included from MI files.

Ok'd: jkoshy@
2005-04-20 20:22:33 +00:00
Warner Losh
f13ea502b5 Move this to the specific architectures that are supported. #ifdef foo
in sys/pmc.h precludes it from working on !i386, !amd64.  When that changes,
it can be moved back into conf/NOTES.
2005-04-19 22:16:46 +00:00
Joseph Koshy
ebccf1e3a6 Bring a working snapshot of hwpmc(4), its associated libraries, userland utilities
and documentation into -CURRENT.

Bump FreeBSD_version.

Reviewed by:	alc, jhb (kernel changes)
2005-04-19 04:01:25 +00:00
Warner Losh
06db52b609 Break out the definition of bus_space_{tag,handle}_t and a few other types
into _bus.h to help with name space polution from including all of bus.h.
In a few days, I'll commit changes to the MI code to take advantage of thse
sepration (after I've made sure that these changes don't break anything in
the main tree, I've tested in my trees, but you never know...).

Suggested by: bde (in 2002 or 2003 I think)
Reviewed in principle by: jhb
2005-04-18 21:45:34 +00:00
Eric Anholt
b8aa843c63 Update to DRM CVS as of 2005-04-12, bringing many changes:
- Split core DRM routines back into their own module, rather than using the
  nasty templated system like before.
- Development-class R300 support in radeon driver (requires userland pieces, of
  course).
- Mach64 driver (haven't tested in a while -- my mach64s no longer fit in the
  testbox).  Covers Rage Pros, Rage Mobility P/M, Rage XL, and some others.
- i915 driver files, which just need to get drm_drv.c fixed to allow attachment
  to the drmsub device.  Covers i830 through i915 integrated graphics.
- savage driver files, which should require minimal changes to work.  Covers the
  Savage3D, Savage IX/MX, Savage 4, ProSavage.
- Support for color and texture tiling and HyperZ features of Radeon.

Thanks to:	scottl (much p4 handholding)
		Jung-uk Kim (helpful prodding)
PR:		[1] kern/76879, [2] kern/72548
Submitted by:	[1] Alex, lesha at intercaf dot ru
		[2] Shaun Jurrens, shaun at shamz dot net
2005-04-16 03:44:47 +00:00
Peter Wemm
ae692d88c4 MFi386: sync rtc code - don't setup an interrupt handler for irq0 when
the lapic timer is active.  Don't enable periodic interrupts unless we are
using them.  Replace spl protection with a spinlock.
2005-04-15 18:46:53 +00:00
Peter Wemm
e137a5d63a MFi386: remove NO_MIXED_MODE 2005-04-15 18:45:07 +00:00
Peter Wemm
ba5f6b61da MFi386: use the lapic timer for UP systems that are using the apic so that
IRQ0 and mixed mode isn't a problem anymore.  This removes mixed mode
support because nothing is left that uses it.
2005-04-15 18:44:53 +00:00
Peter Wemm
0501844603 MFi386: use c99 types 2005-04-15 18:41:32 +00:00
Peter Wemm
7234adbe8e Show that I can actually count. 2005-04-15 18:39:31 +00:00
Peter Wemm
2fc8e0f037 MFi386: track bus.h changes (unsplit bus_${machine}.h) 2005-04-15 18:38:59 +00:00
Peter Wemm
fe8b8bf778 Implement 32-bit compatable fsbase/gsbase methods so that we can run
(newer) unmodified static i386 binaries again.
2005-04-14 16:57:58 +00:00
John Baldwin
33b5f5b7e0 Always use the local APIC timer, even on UP machines. 2005-04-14 05:56:17 +00:00
Eric Anholt
354096a348 Follow i386's suit and include AGP support in the generic kernel. 2005-04-13 06:00:07 +00:00
John Baldwin
aa9aa68d2f Use PCPU_LAZY_INC() for cnt.v_{intr,trap,syscalls} rather than atomic
operations in some places and simple non-per CPU math in others.
2005-04-12 23:18:54 +00:00
John Baldwin
181897f05f The memory operands to fldcw and ldmxcsr are inputs, not outputs. 2005-04-12 23:12:00 +00:00
Alan Cox
16f571bd18 Align the entry point to assembly language functions to a 16-byte boundary.
(The Opteron's instruction fetcher reads instructions from the L1 cache in
16-byte, aligned packets.)
2005-04-10 20:49:21 +00:00
Alan Cox
fb41e04787 Eliminate a conditional branch and as a side-effect eliminate a branch to
a return instruction.  (The latter is discouraged by the Opteron
optimization manual because it disables branch prediction for the return
instruction.)

Reviewed by: bde
2005-04-10 18:12:07 +00:00
David E. O'Brien
6ab95de3a3 'apic' isn't optional on amd64, so don't speak as if it is. 2005-04-08 20:24:45 +00:00
Colin Percival
d0b183c937 Fully initialize the required TSS fields so that the io permission
bitmap is set correctly.

Patch from:	peter
Security:	FreeBSD-SA-05:03.amd64
2005-04-06 01:05:51 +00:00
John Baldwin
0d49a5c910 Fix a change in a debug printf I missed in an earlier commit. 2005-04-05 15:28:06 +00:00
John Baldwin
c6a37e8413 Divorce critical sections from spinlocks. Critical sections as denoted by
critical_enter() and critical_exit() are now solely a mechanism for
deferring kernel preemptions.  They no longer have any affect on
interrupts.  This means that standalone critical sections are now very
cheap as they are simply unlocked integer increments and decrements for the
common case.

Spin mutexes now use a separate KPI implemented in MD code: spinlock_enter()
and spinlock_exit().  This KPI is responsible for providing whatever MD
guarantees are needed to ensure that a thread holding a spin lock won't
be preempted by any other code that will try to lock the same lock.  For
now all archs continue to block interrupts in a "spinlock section" as they
did formerly in all critical sections.  Note that I've also taken this
opportunity to push a few things into MD code rather than MI.  For example,
critical_fork_exit() no longer exists.  Instead, MD code ensures that new
threads have the correct state when they are created.  Also, we no longer
try to fixup the idlethreads for APs in MI code.  Instead, each arch sets
the initial curthread and adjusts the state of the idle thread it borrows
in order to perform the initial context switch.

This change is largely a big NOP, but the cleaner separation it provides
will allow for more efficient alternative locking schemes in other parts
of the kernel (bare critical sections rather than per-CPU spin mutexes
for per-CPU data for example).

Reviewed by:	grehan, cognet, arch@, others
Tested on:	i386, alpha, sparc64, powerpc, arm, possibly more
2005-04-04 21:53:56 +00:00
Alexander Leidinger
3df129097b The file machine/ieeefp.h needs sys/cdefs.h on amd64 and i386 after my
compiler features tests. This is ok, since machine/ieeefp.h is an internal
interface. But floatingpoint.h is a public interface and some ports use it,
so include sys/cdefs.h in the amd64 and i386 version of floatingpoint.h.

Note: some architectures don't provide recursive inclusion protection in
floatingpoint.h, namely alpha and ia64. Except for this part and now the
include of sys/cdefs.h, all those files are equal (from a compiler POV),
so they could be moved to only one version in src/include/.

Approved by:	joerg
2005-04-02 17:31:42 +00:00