This is derived from alpha/microtime.c and i386/tsc_microtime.c,
and will share with both ports.
This should fix PR port-sparc64/18452.
(approved by martin)
walking the page tables whenever this information is needed.
Add an option PMAP_COUNT_DEBUG to assert the new counts and the
page table walk agree.
The old solution had very bad performance impact, for example
by the high CPU load when running top(1).
Thanks to Simon Burge for pointing at the cause of the problem and
to Valeriy E. Ushakov for optimizing my simple minded assembler code.
port: T_IDIV0 is the hardware trap generated on integer division by
zero, T_DIV0 is the software trap used to signal the same event.
This makes 32 bit kernels able to run sparc code with the v7 multiply/
divide library.
Spotted by Valeriy E. Ushakov.
- The MD netbsd32_machdep.h header now defines the 32-bit pointer type
instead of using u_int32_t everywhere,
- The MD netbsd32_machdep.h header now defines a macro (at least on
current implementations) which converts a 32-bit pointer to its 64-bit
equivalent,
- Change the MI code to utilise the above two items in all the right places,
- Implement netbsd32___sigaction_sigtramp().
Tested on Sparc64 by Matt Green.
UPA is just a physical incarnation of our mainbus0.
Evidence:
- There can only be one!
- The firmware node coresponding to it is the root of the OF tree
So: remove the unused (and uncompilable) upa.c, remove upavar.h after
moving the only declaration used from it to autoconf.h.
- use struct vm_page_md for attaching pv entries to struct vm_page
- change pseg_set()'s return value to indicate whether the spare page
was used as an L2 or L3 PTP.
- use a pool for pv entries instead of malloc().
- put PTPs on a list attached to the pmap so we can free them
more efficiently (by just walking the list) in pmap_destroy().
- use the new pmap_remove_all() interface to avoid flushing the cache and TLB
for each pmap_remove() that's done as we are tearing down an address space.
- in pmap_enter(), handle replacing an existing mapping more efficiently
than just calling pmap_remove() on it. also, skip flushing the
TSB and TLB if there was no previous mapping, since there can't be
anything we need to flush. also, preload the TSB if we're pre-setting
the mod/ref bits.
- allocate hardware contexts like the MIPS pmap:
allocate them all sequentially without reuse, then once we run out
just invalidate all user TLB entries and flush the entire L1 dcache.
- fix pmap_extract() for the case where the va is not page-aligned and
nothing is mapped there.
- fix calculation of TSB size. it was comparing physmem (which is
in units of pages) to constants that only make sense if they are
in units of bytes.
- avoid sleeping in pmap_enter(), instead let the caller do it.
- use pmap_kenter_pa() instead of pmap_enter() where appropriate.
- remove code to handle impossible cases in various functions.
- tweak asm code to pipeline a little better.
- remove many unnecessary spls and membars.
- lots of code cleanup.
- no doubt other stuff that I've forgotten.
the result of all this is that a fork+exit microbenchmark is 34% faster
and a fork+exec+exit microbenchmark is 28% faster.
This merge changes the device switch tables from static array to
dynamically generated by config(8).
- All device switches is defined as a constant structure in device drivers.
- The new grammer ``device-major'' is introduced to ``files''.
device-major <prefix> char <num> [block <num>] [<rules>]
- All device major numbers must be listed up in port dependent majors.<arch>
by using this grammer.
- Added the new naming convention.
The name of the device switch must be <prefix>_[bc]devsw for auto-generation
of device switch tables.
- The backward compatibility of loading block/character device
switch by LKM framework is broken. This is necessary to convert
from block/character device major to device name in runtime and vice versa.
- The restriction to assign device major by LKM is completely removed.
We don't need to reserve LKM entries for dynamic loading of device switch.
- In compile time, device major numbers list is packed into the kernel and
the LKM framework will refer it to assign device major number dynamically.
counters. These counters do not exist on all CPUs, but where they
do exist, can be used for counting events such as dcache misses that
would otherwise be difficult or impossible to instrument by code
inspection or hardware simulation.
pmc(9) is meant to be a general interface. Initially, the Intel XScale
counters are the only ones supported.
very difficult to get out of sync. add bootinfo.h and promlib.h
(using the same method) so that sparc64 headers can build sparc
stand (not yet finished.)
* struct sigacts gets a new sigact_sigdesc structure, which has the
sigaction and the trampoline/version. Version 0 means "legacy kernel
provided trampoline". Other versions are coordinated with machine-
dependent code in libc.
* sigaction1() grows two more arguments -- the trampoline pointer and
the trampoline version.
* A new __sigaction_sigtramp() system call is provided to register a
trampoline along with a signal handler.
* The handler is no longer passed to sensig() functions. Instead,
sendsig() looks up the handler by peeking in the sigacts for the
process getting the signal (since it has to look in there for the
trampoline anyway).
* Native sendsig() functions now select the appropriate trampoline and
its arguments based on the trampoline version in the sigacts.
Changes to libc to use the new facility will be checked in later. Kernel
version not bumped; we will ride the 1.6C bump made recently.
NULL for root PCI busses. For busses behind a bridge, it points to
a persistent copy of the bridge's pcitag_t. This can be very useful
for machine-dependent PCI bus enumeration code.
* Implement a machine-dependent pci_enumerate_bus() for sparc64 which
uses OFW device nodes to enumerate the bus. When a PCI bus that is
behind a bridge is attached, pci_attach_hook() allocates a new PCI
chipset tag for the new bus and sets it's "curnode" to the OFW node
of the bridge. This is used as a starting point when enumerating
that bus. Root busses get the OFW node of the host bridge (psycho).
* Garbage-collect "ofpci" and "ofppb" from the sparc64 port.
bus_space_handle_t now holds an address and two ASIs, one for normal accesses
and one for streaming accesses. This allows to map individual handles
different ways, so some can use MMU bypass accesses and others use virtual
addresses. bus_space_map() will now create handles that use bypass accesses
unles BUS_SPACE_MAP_LINEAR is passed in. So only pass in BUS_SPACE_MAP_LINEAR
if you absolutely *need* to use bus_space_vaddr(). This removes at least one
extra level of indirection and should reduce TLB misses.
32-bit kernels have problems accessing 64-bit addresses, so they always use
virtual addresses.
Be consistant in the way that MSIZE, MCLSHIFT, MCLBYTES and NMBCLUSTERS
are defined.
Remove old VM constants from cesfic port.
Bump MSIZE to 256 on mipsco (the only one that wasn't already 256).
- Add alignment-safe double and float unions.
- Use the above for the __infinity and __nan constants on all
architectures that use the standard ieee754 representation of
those constants.
- Add a single copy of various ieee754 math functions (frexp, isinf,
isnan, ldexp and modf) that had numerous duplicates among the
arch-specific directories.
- Use the above functions on all architectures where the generic C
versions where used. Architectures that had local assembly
routines are untouched (for those functions only).
- Make the 32-bit SPARC profile support work with the GCC 2.95.3
SPARC ELF compiler, which uses a different name for mcount.
- Make the 64-bit SPARC profile support header look more like the 32-bit
SPARC header (no functional change -- 64-bit SPARC already used the
correct mcount name).
This will allow improvements to the pmaps so that they can more easily defer expensive operations, eg tlb/cache flush, til the last possible moment.
Currently this is a no-op on most platforms, so they should see no difference.
Reviewed by Jason.
Note: DEBUG checks will not allow accesses to the hole between
text and data segments, so you may need to update programs that
use libkvm before relocating the start of kernel data.
* rename sigcontext.sc_tstate to sc_psr, since this is how it is known to
the 32-bit API, and also used for;
* don't try to squeeze the tstate into it, just emulate the ICC bits.
Per discussion with Eduardo.
each vm_page structure. Add a VM_MDPAGE_INIT() macro to init this
data when pages are initialized by UVM. These macros are mandatory,
but ports may #define them to nothing if they are not needed/used.
This deprecates struct pmap_physseg. As a transitional measure,
allow a port to #define PMAP_PHYSSEG so that it can continue to
use it until its pmap is converted to use VM_MDPAGE_MEMBERS.
Use all this stuff to eliminate a lot of extra work in the Alpha
pmap module (it's smaller and faster now). Changes to other pmap
modules will follow.
to <sys/types.h> and <sys/stdint.h>.
* Add a new C99 <stdint.h> header, which provides integer types of
explicit width, related limits and integer constant macros.
* Extend <inttypes.h> to provide <stdint.h> definitions and format
macros for printf() and scanf().
* Add C99 strtoimax() and strtoumax() functions.
* Use the latter within scanf().
* Add C99 %j, %t and %z printf()/scanf() conversions for
intmax_t, pointer-type and size_t arguments.
call overhead is incurred as we start sprinkling pmap_update() calls
throughout the source tree (no pmaps currently defer operations, but
we are adding the infrastructure to allow them to do so).
and use appropriately
- create more helper macros:
. cdev__xyz_init(c,n), such as cdev__ocri_init() for
/* open, close, read, ioctl */, etc.
. cdev__xRy_init(c,n), where nullop is used instead of enodev to dummy out
method `R' and the comments now read /* xxx (read) yyy */ instead
. cdev__xyz_t_init(c,n,t) - as per cdev__xyz_init, but sets d_type = t
as well
- use seltrue instead of dev_noimpl(poll,*), as (IIRC) cdevsw.d_poll should
always DTRT WRT returning a valid result. (a few devices previously
incorrectly returned ENODEV)
- use dev_noimpl(stop,enodev) instead of dev_noimpl(stop,nullop) if tty
== 0, because it doesn't matter if dev_type_stop isn't implemented in that
case, and it allows the use of the cdev__xyz_init macros. certain ports
(sparc,sparc64,x68k) used the nullop method for dev_type_stop in a few
drivers, whereas everything else uses enodev
- ensure that the comments are accurate WRT the behaviour of a given entry
and place the definition in <machine/types.h>. This can now be used
as a flag to indicate whether or not <machine/intr.h> can be included
to get the generic soft interrupt API.
