This allocator uses a binary buddy system with a twist. First and
foremost, this allocator is required to support the implementation of
superpages. As a side effect, it enables a more robust implementation
of contigmalloc(9). Moreover, this reimplementation of
contigmalloc(9) eliminates the acquisition of Giant by
contigmalloc(..., M_NOWAIT, ...).
The twist is that this allocator tries to reduce the number of TLB
misses incurred by accesses through a direct map to small, UMA-managed
objects and page table pages. Roughly speaking, the physical pages
that are allocated for such purposes are clustered together in the
physical address space. The performance benefits vary. In the most
extreme case, a uniprocessor kernel running on an Opteron, I measured
an 18% reduction in system time during a buildworld.
This allocator does not implement page coloring. The reason is that
superpages have much the same effect. The contiguous physical memory
allocation necessary for a superpage is inherently colored.
Finally, the one caveat is that this allocator does not effectively
support prezeroed pages. I hope this is temporary. On i386, this is
a slight pessimization. However, on amd64, the beneficial effects of
the direct-map optimization outweigh the ill effects. I speculate
that this is true in general of machines with a direct map.
Approved by: re
more exposure. The current state of SCTP implementation is
considered to be ready for 32-bit platforms, but still need some
work/testing on 64-bit platforms.
Approved by: re (kensmith)
Discussed with: rrs
making the relevant files standard. This avoids duplication and
makes it easier to override/disable unwanted schemes. Since ARM
doesn't have a DEFAULTS configuration file, leave the source
files for the BSD and MBR partitioning schemes in files.arm for
now.
caches with data caches after writing to memory. This typically
is required to make breakpoints work on ia64 and powerpc. For
those architectures the function is implemented.
- Use sched_throw() rather than replicating the same cpu_throw() code for
each architecture. This also allows the scheduler to use any locking it
may want to.
- Use the thread_lock() rather than sched_lock when preempting.
- The scheduler lock is not required to synchronize release_aps.
Tested by: kris, current@
Tested on: i386, amd64, ULE, 4BSD, libthr, libkse, PREEMPTION, etc.
Discussed with: kris, attilio, kmacy, jhb, julian, bde (small parts each)
- Rename PCPU_LAZY_INC into PCPU_INC
- Add the PCPU_ADD interface which just does an add on the pcpu member
given a specific value.
Note that for most architectures PCPU_INC and PCPU_ADD are not safe.
This is a point that needs some discussions/work in the next days.
Reviewed by: alc, bde
Approved by: jeff (mentor)
Probabilly, a general approach is not the better solution here, so we should
solve the sched_lock protection problems separately.
Requested by: alc
Approved by: jeff (mentor)
handler is wrapped in a couple of functions - a filter wrapper and an
ithread wrapper. In this case (and just in this case), the filter
wrapper could ask the system to schedule the ithread and mask the
interrupt source if the wrapped handler is composed of just an ithread
handler: modify the "old" interrupt code to make it support
this situation, while the "new" interrupt code is already ok.
Discussed with: jhb
used to return PAGE_SIZE without respect to restrictions of a DMA tag.
This affected all of the busdma load functions that use
_bus_dmamap_loader_buffer() as their back-end.
Reviewed by: scottl
in the sun4v source in order to be able to compile the source which
is shared between sparc64 and sun4v just #include the sparc64
version here instead of duplicating it.
This is based on the approach taken by pc98 headers in order to
compile the source shared between i386 and pc98.
iommureg.h (which already began to bitrot) and iommuvar.h from the
sun4v source and adjust some of the source which is shared between
sparc64 and sun4v as appropriate.
vmcnts. This can be used to abstract away pcpu details but also changes
to use atomics for all counters now. This means sched lock is no longer
responsible for protecting counts in the switch routines.
Contributed by: Attilio Rao <attilio@FreeBSD.org>
VM_PHYSSEG_SPARSE depending on whether the physical address space is
densely or sparsely populated with memory. The effect of this
definition is to determine which of two implementations of
vm_page_array and PHYS_TO_VM_PAGE() is used. The legacy
implementation is obtained by defining VM_PHYSSEG_DENSE, and a new
implementation that trades off time for space is obtained by defining
VM_PHYSSEG_SPARSE. For now, all architectures except for ia64 and
sparc64 define VM_PHYSSEG_DENSE. Defining VM_PHYSSEG_SPARSE on ia64
allows the entirety of my Itanium 2's memory to be used. Previously,
only the first 1 GB could be used. Defining VM_PHYSSEG_SPARSE on
sparc64 allows USIIIi-based systems to boot without crashing.
This change is a combination of Nathan Whitehorn's patch and my own
work in perforce.
Discussed with: kmacy, marius, Nathan Whitehorn
PR: 112194
vm.kmem_size_min. Useful when using ZFS to make sure that vm.kmem size will
be at least 256mb (for example) without forcing a particular value via vm.kmem_size.
Approved by: njl (mentor)
Reviewed by: alc
partitioning class that supports multiple schemes. Current
schemes supported are APM (Apple Partition Map) and GPT.
Change all GEOM_APPLE anf GEOM_GPT options into GEOM_PART_APM
and GEOM_PART_GPT (resp).
The ctlreq interface supports verbs to create and destroy
partitioning schemes on a disk; to add, delete and modify
partitions; and to commit or undo changes made.
headers in .S directly rather than getting to their macros through
genassym.c/assym.s so there are less headers genassym.c has to be
kept in sync with.
While at it fix some stytle(9) bugs (indentation, prototype format,
sort headers, etc) and remove trailing whitespace.
may also reflect a Fireplane/Safari or JBus bus (or a virtual bus which
in turn reflects a JBus bus or something like that...).
- In the both the sparc64 and sun4v bus_machdep.c use __FBSDID.
- Spell SBus the official way in comments.
- Replace hardcoded function names (all of which were actually outdated)
in panic and status strings with __func__.
- Fix whitespace nits.
and friends along with all hacks required to implement them. None of
the drivers currently built (as part of GENERIC, LINT or modules) on
sparc64 or sun4v and none of those we might want to use there in
future uses them, AFAICT there actually never was a driver hooked up
to the sparc64 or sun4v build that correctly used these functions
(and it looks like that due to a bug read{b,w,l}()/write{b,w,l}() and
the other functions working on a memory handle never actually worked on
sun4v). All they ever were good for on sparc64 and sun4v was erroneously
dragging in dependencies on isa(4) in drivers like f.e. dpt(4), si(4)
and syscons(4) in source files that supposedly were bus-neutral and
hiding issues with drivers like f.e. ng_bt3c(4) that used these
functions with busses other than isa(4) and therefore couldn't work on
these platforms.
pmap on i386
- check for change in executable status in pmap_enter
- pmap_qenter and pmap_qremove only need to invalidate the range if one
of the pages has been referenced
- remove pmap_kenter/pmap_kremove as they were only used by pmap_qenter
and pmap_qremove
- in pmap_copy don't copy wired bit to destination pmap
- mpte was unused in pmap_enter_object - remove
- pmap_enter_quick_locked is not called on the kernel_pmap, remove check
- move pmap_remove_write specific logic out of tte_clear_phys_bit
- in pmap_protect check for removal of execute bit
- panic in the presence of a wired page in pmap_remove_all
- pmap_zero_range can call hwblkclr if offset is zero and size is PAGE_SIZE
- tte_clear_virt_bit is only used by pmap_change_wiring - thus it can be
greatly simplified
- pmap_invalidate_page need only be called in tte_clear_phys_bit if there
is a match with flags
- lock the pmap in tte_clear_phys_bit so that clearing the page bits is
atomic with invalidating the page
- these changes result in 100s reduction in buildworld from a malloc backed
disk to a malloc backed disk - ~2.5%
usage to conform to that of tl0_trap - the separate code path
for unaligned faults was never getting used (and evidently doesn't
work), so ifdef out for now
- The PCPU usage was to ensure that there were no faults on the stack while
the tte_hash_bucket lock was held - but this can be avoided by making sure
the address on the stack is already referenced.
- PCPU removal obviates the need for critical_{enter, exit}
- rename skip_utrap to tl0_skip_utrap to indicate its use by the fill trap fault handler
- handle a null kstack by switching to the idle threads stack and then going to trap
- correctly handle a unaligned or unmapped stack during a fill trap
- save off some extra data in the pcpu pad in ptl1_panic
- add an assert that PCB is valid in vm_machdep.c
at which the kernel should start allocating physical memory. The primary
purpose of this is to test 64-bit cleanness of the data path by setting
hw.physmemstart=4G so that all physical allocations are above 4GB. AMD64
and i386/PAE could also benefit from having this option.
is already bounded by hw.physmem to calculate phys_avail[] - previously only
real_phys_avail[] was being bound by hw.physmem so we were allocating memory
that wasn't mapped in the direct map
- shuffle memory range following kernel to the beginning of phys_avail
- have the direct area use 256MB pages where possible
- remove dead code from the end of pmap_bootstrap
- have pmap_alloc_contig_pages check all memory ranges in phys_avail before
giving up
- informal benchmarking indicates a ~5% speedup on buildworld
Make part of John Birrell's KSE patch permanent..
Specifically, remove:
Any reference of the ksegrp structure. This feature was
never fully utilised and made things overly complicated.
All code in the scheduler that tried to make threaded programs
fair to unthreaded programs. Libpthread processes will already
do this to some extent and libthr processes already disable it.
Also:
Since this makes such a big change to the scheduler(s), take the opportunity
to rename some structures and elements that had to be moved anyhow.
This makes the code a lot more readable.
The ULE scheduler compiles again but I have no idea if it works.
The 4bsd scheduler still reqires a little cleaning and some functions that now do
ALMOST nothing will go away, but I thought I'd do that as a separate commit.
Tested by David Xu, and Dan Eischen using libthr and libpthread.
- create real_phys_avail which includes all memory ranges to be added to the direct map
- merge in nucleus memory to real_phys_avail
- distinguish between tag VA and index VA in tsb_set_tte_real for cases where page_size != index_page_size
- clean up direct map loop
by default for sun4v where it is absolutely required.
This change moves the buffer from struct pcpu to the stack to avoid
using the critical section which created a LOR in a couple of cases
due to interaction with the tty code and kqueue. The LOR can't be
fixed with the critical section and the pcpu buffer can't be used
without the critical section.
Putting the buffer on the stack was my initial solution, but it was
pointed out that the stress on the stack might cause problems
depending on the call path. We don't have a way of creating tests
for those possible cases, so it's best to leave this as an option
for the time being. In time we may get enough data to enable this
option more generally.
retrieval, rather than using pad
- save the fault address in sfar for use by the alignment fixup handler
- mask off the trap number, so the context id doesn't confuse the UT_MAX
comparison
This change fixes alignment fixup handling which is needed for traceroute
to work in spite of its copious unaligned accesses
as this happens much earlier in trap handling.
The fact that we continued to do this when it was no longer necessary caused
breapoint to map to SIGILL as opposed to SIGTRAP :-(.
- "shutdown -r" will reset the system
- "shutdown -h" will power off the system
We don't drop into OFW as newer versions of solaris don't do this either
flags from M_WAITOK to M_NOWAIT. This should not cause any problems
since the calling code appears to properly handle failed allocations.
Discussed with: kmacy
shall retain its CDDL copyright, and thus likely be removed from GENERIC) I have removed the CDDL
from hcall.S because there is zero flexibility in the implementation of hypercalls as they derive
directly from the hypervisor interface which is not copyrighted (ironically the source for the
hypervisor itself is BSD licensed).
It is best to start any bikeshed about this as soon as possible.
Discussed with: bsdimp
switch tsbscratch over to using order of number of pages as opposed to actual number of pages
switch tsb.c over to using wrappers for contig page allocation
wait (time waited to acquire) and hold times for *all* kernel locks. If
the architecture has a system synchronized TSC, the profiling code will
use that - thereby minimizing profiling overhead. Large chunks of profiling
code have been moved out of line, the overhead measured on the T1 for when
it is compiled in but not enabled is < 1%.
Approved by: scottl (standing in for mentor rwatson)
Reviewed by: des and jhb
after the interrupt has been handled. Also move panic_bad_hcall to local to
avoid complaints from the linker on the tinderbox.
Approved by: scottl (substituting for mentor rwatson)
specific privilege names to a broad range of privileges. These may
require some future tweaking.
Sponsored by: nCircle Network Security, Inc.
Obtained from: TrustedBSD Project
Discussed on: arch@
Reviewed (at least in part) by: mlaier, jmg, pjd, bde, ceri,
Alex Lyashkov <umka at sevcity dot net>,
Skip Ford <skip dot ford at verizon dot net>,
Antoine Brodin <antoine dot brodin at laposte dot net>
it as a default.
For the record, the KDTRACE option caused _no_ additional source files
to be compiled in; certainly no CDDL source files. All it did was to
allow existing BSD licensed kernel files to include one or more CDDL
header files.
By removing this from DEFAULTS, the onus is on a kernel builder to add
the option to the kernel config, possibly by including GENERIC and
customising from there. It means that DTrace won't be a feature
available in FreeBSD by default, which is the way I intended it to be.
Without this option, you can't load the dtrace module (which contains
the dtrace device and the DTrace framework). This is equivalent to
requiring an option in a kernel config before you can load the linux
emulation module, for example.
I think it is a mistake to have DTrace ported to FreeBSD, but not
to have it available to everyone, all the time. The only exception
to this is the companies which distribute systems with FreeBSD embedded.
Those companies will customise their systems anyway. The KDTRACE
option was intended for them, and only them.
adds the hooks that DTrace modules register with, and adds a few functions
which have the dtrace_ prefix to allow the DTrace FBT (function boundary
trace) provider to avoid tracing because they are called from the DTtrace
probe context.
Unlike other forms of tracing and debug, DTrace support in the kernel
incurs negligible run-time cost.
I think the only reason why anyone wouldn't want to have kernel support
enabled for DTrace would be due to the license (CDDL) under which DTrace
is released.
and to make user-level trap handlers work
- add new trap entry to trap table to enable fast fetching of floating point trap
context
- remove unused debug code
- map unimplemented floating point trap to SIGFPE
Approved by: scottl (standing in for mentor rwatson)
