MADV_DONTNEED) and madvise(..., MADV_FREE). Specifically, introduce a new
pmap function, pmap_advise(), that operates on a range of virtual addresses
within the specified pmap, allowing for a more efficient implementation of
MADV_DONTNEED and MADV_FREE. Previously, the implementation of
MADV_DONTNEED and MADV_FREE relied on per-page pmap operations, such as
pmap_clear_reference(). Intuitively, the problem with this implementation
is that the pmap-level locks are acquired and released and the page table
traversed repeatedly, once for each resident page in the range
that was specified to madvise(2). A more subtle flaw with the previous
implementation is that pmap_clear_reference() would clear the reference bit
on all mappings to the specified page, not just the mapping in the range
specified to madvise(2).
Since our malloc(3) makes heavy use of madvise(2), this change can have a
measureable impact. For example, the system time for completing a parallel
"buildworld" on a 6-core amd64 machine was reduced by about 1.5% to 2.0%.
Note: This change only contains pmap_advise() implementations for a subset
of our supported architectures. I will commit implementations for the
remaining architectures after further testing. For now, a stub function is
sufficient because of the advisory nature of pmap_advise().
Discussed with: jeff, jhb, kib
Tested by: pho (i386), marcel (ia64)
Sponsored by: EMC / Isilon Storage Division
which is the part of struct vmspace, allocated from UMA_ZONE_NOFREE
zone. Initialize the pmap lock in the vmspace zone init function, and
remove pmap lock initialization and destruction from pmap_pinit() and
pmap_release().
Suggested and reviewed by: alc (previous version)
Tested by: pho
Sponsored by: The FreeBSD Foundation
The flag was mandatory since r209792, where vm_page_grab(9) was
changed to only support the alloc retry semantic.
Suggested and reviewed by: alc
Sponsored by: The FreeBSD Foundation
used by the tools in base systems and with sandboxing more and more tools
the usage should only increase.
Submitted by: Mariusz Zaborski <oshogbo@FreeBSD.org>
Sponsored by: Google Summer of Code 2013
MFC after: 1 month
Unify the 2 concept into a real, minimal, sxlock where the shared
acquisition represent the soft busy and the exclusive acquisition
represent the hard busy.
The old VPO_WANTED mechanism becames the hard-path for this new lock
and it becomes per-page rather than per-object.
The vm_object lock becames an interlock for this functionality:
it can be held in both read or write mode.
However, if the vm_object lock is held in read mode while acquiring
or releasing the busy state, the thread owner cannot make any
assumption on the busy state unless it is also busying it.
Also:
- Add a new flag to directly shared busy pages while vm_page_alloc
and vm_page_grab are being executed. This will be very helpful
once these functions happen under a read object lock.
- Move the swapping sleep into its own per-object flag
The KPI is heavilly changed this is why the version is bumped.
It is very likely that some VM ports users will need to change
their own code.
Sponsored by: EMC / Isilon storage division
Discussed with: alc
Reviewed by: jeff, kib
Tested by: gavin, bapt (older version)
Tested by: pho, scottl
- update powerpc/GENERIC64 as well, suggested by mdf
- update comments so that they make sense after the change, suggested by
jhb
X-MFC after: never (change specific to head)
into threads each processing queue in a single domain. The structure
of the pagedaemons and queues is kept intact, most of the changes come
from the need for code to find an owning page queue for given page,
calculated from the segment containing the page.
The tie between NUMA domain and pagedaemon thread/pagequeue split is
rather arbitrary, the multithreaded daemon could be allowed for the
single-domain machines, or one domain might be split into several page
domains, to further increase concurrency.
Right now, each pagedaemon thread tries to reach the global target,
precalculated at the start of the pass. This is not optimal, since it
could cause excessive page deactivation and freeing. The code should
be changed to re-check the global page deficit state in the loop after
some number of iterations.
The pagedaemons reach the quorum before starting the OOM, since one
thread inability to meet the target is normal for split queues. Only
when all pagedaemons fail to produce enough reusable pages, OOM is
started by single selected thread.
Launder is modified to take into account the segments layout with
regard to the region for which cleaning is performed.
Based on the preliminary patch by jeff, sponsored by EMC / Isilon
Storage Division.
Reviewed by: alc
Tested by: pho
Sponsored by: The FreeBSD Foundation
KDB_TRACE is not an alternative to DDB/etc, they are complementary.
So I do not see any reason to not enable KDB_TRACE by default.
X-MFC after: never (change specific to head)
transparent layering and better fragmentation.
- Normalize functions that allocate memory to use kmem_*
- Those that allocate address space are named kva_*
- Those that operate on maps are named kmap_*
- Implement recursive allocation handling for kmem_arena in vmem.
Reviewed by: alc
Tested by: pho
Sponsored by: EMC / Isilon Storage Division
to get the semantics when setting the PMAP right. Prior to r251782, the
latter already used implicit acquire semantics, which - currently - means
to not employ additional explicit memory barriers under the hood (see also
r225889).
* Make Yarrow an optional kernel component -- enabled by "YARROW_RNG" option.
The files sha2.c, hash.c, randomdev_soft.c and yarrow.c comprise yarrow.
* random(4) device doesn't really depend on rijndael-*. Yarrow, however, does.
* Add random_adaptors.[ch] which is basically a store of random_adaptor's.
random_adaptor is basically an adapter that plugs in to random(4).
random_adaptor can only be plugged in to random(4) very early in bootup.
Unplugging random_adaptor from random(4) is not supported, and is probably a
bad idea anyway, due to potential loss of entropy pools.
We currently have 3 random_adaptors:
+ yarrow
+ rdrand (ivy.c)
+ nehemeiah
* Remove platform dependent logic from probe.c, and move it into
corresponding registration routines of each random_adaptor provider.
probe.c doesn't do anything other than picking a specific random_adaptor
from a list of registered ones.
* If the kernel doesn't have any random_adaptor adapters present then the
creation of /dev/random is postponed until next random_adaptor is kldload'ed.
* Fix randomdev_soft.c to refer to its own random_adaptor, instead of a
system wide one.
Submitted by: arthurmesh@gmail.com, obrien
Obtained from: Juniper Networks
Reviewed by: obrien
Issues were noted by Bruce Evans and are present on all architectures.
On i386, a counter fetch should use atomic read of 64bit value,
otherwise carry from the increment on other CPU could be lost for the
given fetch, making error of 2^32. If 64bit read (cmpxchg8b) is not
available on the machine, it cannot be SMP and it is enough to disable
preemption around read to avoid the split read.
On x86 the counter increment is not atomic on purpose, which makes it
possible for the store of the incremented result to override just
zeroed per-cpu slot. The effect would be a counter going off by
arbitrary value after zeroing. Perform the counter zeroing on the
same processor which does the increments, making the operations
mutually exclusive. On i386, same as for the fetching, if the
cmpxchg8b is not available, machine is not SMP and we disable
preemption for zeroing.
PowerPC64 is treated the same as amd64.
For other architectures, the changes made to allow the compilation to
succeed, without fixing the issues with zeroing or fetching. It
should be possible to handle them by using the 64bit loads and stores
atomic WRT preemption (assuming the architectures also converted from
using critical sections to proper asm). If architecture does not
provide the facility, using global (spin) mutex would be non-optimal
but working solution.
Noted by: bde
Sponsored by: The FreeBSD Foundation
The atomic_load() and atomic_store() macros conflict with the equally
named macros from <stdatomic.h>. Remove them, as they are only used to
implement functions that are not present on any of the other
architectures.
o Relax locking assertions for pmap_enter_object() and add them also
to architectures that currently don't have any
o Introduce VM_OBJECT_LOCK_DOWNGRADE() which is basically a downgrade
operation on the per-object rwlock
o Use all the mechanisms above to make vm_map_pmap_enter() to work
mostl of the times only with readlocks.
Sponsored by: EMC / Isilon storage division
Reviewed by: alc
order to match the MAXCPU concept. The change should also be useful
for consolidation and consistency.
Sponsored by: EMC / Isilon storage division
Obtained from: jeff
Reviewed by: alc
and kern.cam.ctl.disable tunable; those were introduced as a workaround
to make it possible to boot GENERIC on low memory machines.
With ctl(4) being built as a module and automatically loaded by ctladm(8),
this makes CTL work out of the box.
Reviewed by: ken
Sponsored by: FreeBSD Foundation
Introduce counter(9) API, that implements fast and raceless counters,
provided (but not limited to) for gathering of statistical data.
See http://lists.freebsd.org/pipermail/freebsd-arch/2013-April/014204.html
for more details.
In collaboration with: kib
Reviewed by: luigi
Tested by: ae, ray
Sponsored by: Nginx, Inc.
most kernels before FreeBSD 9.0. Remove such modules and respective kernel
options: atadisk, ataraid, atapicd, atapifd, atapist, atapicam. Remove the
atacontrol utility and some man pages. Remove useless now options ATA_CAM.
No objections: current@, stable@
MFC after: never
uart(4) allocates send and receiver buffers in attach() before it calls
the low-level driver's attach routine. Many low-level drivers set the
fifo sizes in their attach routine, which is too late. Other drivers set
them in the probe() routine, so that they're available when uart(4)
allocates buffers. This fixes the ones that were setting the values too
late by moving the code to probe().
do not map the b_pages pages into buffer_map KVA. The use of the
unmapped buffers eliminate the need to perform TLB shootdown for
mapping on the buffer creation and reuse, greatly reducing the amount
of IPIs for shootdown on big-SMP machines and eliminating up to 25-30%
of the system time on i/o intensive workloads.
The unmapped buffer should be explicitely requested by the GB_UNMAPPED
flag by the consumer. For unmapped buffer, no KVA reservation is
performed at all. The consumer might request unmapped buffer which
does have a KVA reserve, to manually map it without recursing into
buffer cache and blocking, with the GB_KVAALLOC flag.
When the mapped buffer is requested and unmapped buffer already
exists, the cache performs an upgrade, possibly reusing the KVA
reservation.
Unmapped buffer is translated into unmapped bio in g_vfs_strategy().
Unmapped bio carry a pointer to the vm_page_t array, offset and length
instead of the data pointer. The provider which processes the bio
should explicitely specify a readiness to accept unmapped bio,
otherwise g_down geom thread performs the transient upgrade of the bio
request by mapping the pages into the new bio_transient_map KVA
submap.
The bio_transient_map submap claims up to 10% of the buffer map, and
the total buffer_map + bio_transient_map KVA usage stays the
same. Still, it could be manually tuned by kern.bio_transient_maxcnt
tunable, in the units of the transient mappings. Eventually, the
bio_transient_map could be removed after all geom classes and drivers
can accept unmapped i/o requests.
Unmapped support can be turned off by the vfs.unmapped_buf_allowed
tunable, disabling which makes the buffer (or cluster) creation
requests to ignore GB_UNMAPPED and GB_KVAALLOC flags. Unmapped
buffers are only enabled by default on the architectures where
pmap_copy_page() was implemented and tested.
In the rework, filesystem metadata is not the subject to maxbufspace
limit anymore. Since the metadata buffers are always mapped, the
buffers still have to fit into the buffer map, which provides a
reasonable (but practically unreachable) upper bound on it. The
non-metadata buffer allocations, both mapped and unmapped, is
accounted against maxbufspace, as before. Effectively, this means that
the maxbufspace is forced on mapped and unmapped buffers separately.
The pre-patch bufspace limiting code did not worked, because
buffer_map fragmentation does not allow the limit to be reached.
By Jeff Roberson request, the getnewbuf() function was split into
smaller single-purpose functions.
Sponsored by: The FreeBSD Foundation
Discussed with: jeff (previous version)
Tested by: pho, scottl (previous version), jhb, bf
MFC after: 2 weeks
pages around, taking array of vm_page_t both for source and
destination. Starting offsets and total transfer size are specified.
The function implements optimal algorithm for copying using the
platform-specific optimizations. For instance, on the architectures
were the direct map is available, no transient mappings are created,
for i386 the per-cpu ephemeral page frame is used. The code was
typically borrowed from the pmap_copy_page() for the same
architecture.
Only i386/amd64, powerpc aim and arm/arm-v6 implementations were
tested at the time of commit. High-level code, not committed yet to
the tree, ensures that the use of the function is only allowed after
explicit enablement.
For sparc64, the existing code has known issues and a stab is added
instead, to allow the kernel linking.
Sponsored by: The FreeBSD Foundation
Tested by: pho (i386, amd64), scottl (amd64), ian (arm and arm-v6)
MFC after: 2 weeks
future further optimizations where the vm_object lock will be held
in read mode most of the time the page cache resident pool of pages
are accessed for reading purposes.
The change is mostly mechanical but few notes are reported:
* The KPI changes as follow:
- VM_OBJECT_LOCK() -> VM_OBJECT_WLOCK()
- VM_OBJECT_TRYLOCK() -> VM_OBJECT_TRYWLOCK()
- VM_OBJECT_UNLOCK() -> VM_OBJECT_WUNLOCK()
- VM_OBJECT_LOCK_ASSERT(MA_OWNED) -> VM_OBJECT_ASSERT_WLOCKED()
(in order to avoid visibility of implementation details)
- The read-mode operations are added:
VM_OBJECT_RLOCK(), VM_OBJECT_TRYRLOCK(), VM_OBJECT_RUNLOCK(),
VM_OBJECT_ASSERT_RLOCKED(), VM_OBJECT_ASSERT_LOCKED()
* The vm/vm_pager.h namespace pollution avoidance (forcing requiring
sys/mutex.h in consumers directly to cater its inlining functions
using VM_OBJECT_LOCK()) imposes that all the vm/vm_pager.h
consumers now must include also sys/rwlock.h.
* zfs requires a quite convoluted fix to include FreeBSD rwlocks into
the compat layer because the name clash between FreeBSD and solaris
versions must be avoided.
At this purpose zfs redefines the vm_object locking functions
directly, isolating the FreeBSD components in specific compat stubs.
The KPI results heavilly broken by this commit. Thirdy part ports must
be updated accordingly (I can think off-hand of VirtualBox, for example).
Sponsored by: EMC / Isilon storage division
Reviewed by: jeff
Reviewed by: pjd (ZFS specific review)
Discussed with: alc
Tested by: pho
Turn on the CTL disable tunable by default.
This will allow GENERIC configurations to boot on small memory boxes, but
not require end users who want to use CTL to recompile their kernel. They
can simply set kern.cam.ctl.disable=0 in loader.conf.
interrupt shutdown handlers into filters. Shutdown_nice(9) acquires a sleep
lock, which filters shouldn't do. It also seems that kern_reboot(9) still
may require Giant to be hold.
- Correct an incorrect argument to shutdown_nice(9).
Submitted by: bde
interrupt shutdown handlers into filters. Shutdown_nice(9) acquires a sleep
lock, which filters shouldn't do. It also seems that kern_reboot(9) still
may require Giant to be hold.
Submitted by: bde
an interrupt filter (some other drivers in the tree do the same). So
change the overtemperature and power fail interrupts from handlers in order
to code and get rid of a !INTR_MPSAFE handlers.
- Mark unused parameters as such.
- Use NULL instead of 0 for pointers.
MFC after: 1 week
fail interrupt handler, there seems to be either a broken batch of them
or a tendency to develop a defect which causes this interrupt to fire
inadvertedly. Given that apart from this problem these machines work
just fine, add a tunable allowing the setup of the power fail interrupt
to be disabled.
While at it, remove the DEBUGGER_ON_POWERFAIL compile time option and
make that behavior also selectable via the newly added tunable.
- Apparently, it's no longer a problem to call shutdown_nice(9) from within
an interrupt filter (some other drivers in the tree do the same). So
change the power fail interrupt from an handler in order to simplify the
code and get rid of a !INTR_MPSAFE handler.
- Use NULL instead of 0 for pointers.
MFC after: 1 week
- Use NULL instead of 0 for pointers.
- Let ofw_pcib_probe() return BUS_PROBE_DEFAULT instead of 0 so specialized
PCI-PCI-bridge drivers may attach instead.
- Add WARs for PLX Technology PEX 8114 bridges and PEX 8532 switches.
Ideally, these should live in MI code but at least for the latter we're
missing the necessary infrastructure there.
MFC after: 1 week
Switch eventtimers(9) from using struct bintime to sbintime_t.
Even before this not a single driver really supported full dynamic range of
struct bintime even in theory, not speaking about practical inexpediency.
This change legitimates the status quo and cleans up the code.
VM_OBJECT_LOCKED() macro is only used to implement a custom version
of lock assertions right now (which likely spread out thanks to
copy and paste).
Remove it and implement actual assertions.
Sponsored by: EMC / Isilon storage division
Reviewed by: alc
Tested by: pho
every architecture's busdma_machdep.c. It is done by unifying the
bus_dmamap_load_buffer() routines so that they may be called from MI
code. The MD busdma is then given a chance to do any final processing
in the complete() callback.
The cam changes unify the bus_dmamap_load* handling in cam drivers.
The arm and mips implementations are updated to track virtual
addresses for sync(). Previously this was done in a type specific
way. Now it is done in a generic way by recording the list of
virtuals in the map.
Submitted by: jeff (sponsored by EMC/Isilon)
Reviewed by: kan (previous version), scottl,
mjacob (isp(4), no objections for target mode changes)
Discussed with: ian (arm changes)
Tested by: marius (sparc64), mips (jmallet), isci(4) on x86 (jharris),
amd64 (Fabian Keil <freebsd-listen@fabiankeil.de>)
reading registers from other CPUs. As it turns out, the hardware doesn't
really like concurrent IPI'ing causing adverse effects. Also the thought
deadlock when using this spin lock here and the targeted CPU(s) are also
holding or in case of nested locks can't actually happen. This is due to
the fact that on sparc64, spinlock_enter() only raises the PIL but doesn't
disable interrupts completely. Thus direct cross calls as used for the
register reading (and all other MD IPI needs) still will be executed by
the targeted CPU(s) in that case.
MFC after: 3 days
