Convert all remaining references to that field to "ref_count" and update
comments accordingly. No functional change intended.
Reviewed by: alc, kib
Sponsored by: Intel, Netflix
Differential Revision: https://reviews.freebsd.org/D21768
There are several mechanisms by which a vm_page reference is held,
preventing the page from being freed back to the page allocator. In
particular, holding the page's object lock is sufficient to prevent the
page from being freed; holding the busy lock or a wiring is sufficent as
well. These references are protected by the page lock, which must
therefore be acquired for many per-page operations. This results in
false sharing since the page locks are external to the vm_page
structures themselves and each lock protects multiple structures.
Transition to using an atomically updated per-page reference counter.
The object's reference is counted using a flag bit in the counter. A
second flag bit is used to atomically block new references via
pmap_extract_and_hold() while removing managed mappings of a page.
Thus, the reference count of a page is guaranteed not to increase if the
page is unbusied, unmapped, and the object's write lock is held. As
a consequence of this, the page lock no longer protects a page's
identity; operations which move pages between objects are now
synchronized solely by the objects' locks.
The vm_page_wire() and vm_page_unwire() KPIs are changed. The former
requires that either the object lock or the busy lock is held. The
latter no longer has a return value and may free the page if it releases
the last reference to that page. vm_page_unwire_noq() behaves the same
as before; the caller is responsible for checking its return value and
freeing or enqueuing the page as appropriate. vm_page_wire_mapped() is
introduced for use in pmap_extract_and_hold(). It fails if the page is
concurrently being unmapped, typically triggering a fallback to the
fault handler. vm_page_wire() no longer requires the page lock and
vm_page_unwire() now internally acquires the page lock when releasing
the last wiring of a page (since the page lock still protects a page's
queue state). In particular, synchronization details are no longer
leaked into the caller.
The change excises the page lock from several frequently executed code
paths. In particular, vm_object_terminate() no longer bounces between
page locks as it releases an object's pages, and direct I/O and
sendfile(SF_NOCACHE) completions no longer require the page lock. In
these latter cases we now get linear scalability in the common scenario
where different threads are operating on different files.
__FreeBSD_version is bumped. The DRM ports have been updated to
accomodate the KPI changes.
Reviewed by: jeff (earlier version)
Tested by: gallatin (earlier version), pho
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20486
error in the function hypercall_memfree(), where the wrong arena was being
passed to kmem_free().
Introduce a per-page flag, VPO_KMEM_EXEC, to mark physical pages that are
mapped in kmem with execute permissions. Use this flag to determine which
arena the kmem virtual addresses are returned to.
Eliminate UMA_SLAB_KRWX. The introduction of VPO_KMEM_EXEC makes it
redundant.
Update the nearby comment for UMA_SLAB_KERNEL.
Reviewed by: kib, markj
Discussed with: jeff
Approved by: re (marius)
Differential Revision: https://reviews.freebsd.org/D16845
Mainly focus on files that use BSD 2-Clause license, however the tool I
was using misidentified many licenses so this was mostly a manual - error
prone - task.
The Software Package Data Exchange (SPDX) group provides a specification
to make it easier for automated tools to detect and summarize well known
opensource licenses. We are gradually adopting the specification, noting
that the tags are considered only advisory and do not, in any way,
superceed or replace the license texts.
rounddown2 tends to produce longer lines than the original code
and when the code has a high indentation level it was not really
advantageous to do the replacement.
This tries to strike a balance between readability using the macros
and flexibility of having the expressions, so not everything is
converted.
The i915 video driver doesn't depend on agp(4) anymore for Sandybridge
and later GPUs. Therefore, there is no need to attach agp(4) to those
devices.
While here, fix `agp_i965_res_spec` to include the aperture base for
GEN4 and GEN5.
Reviewed by: kib
Approved by: kib
Differential Revision: https://reviews.freebsd.org/D5586
This update brings initial support for Haswell GPUs.
Tested by: Many users of FreeBSD, PC-BSD and HardenedBSD
Relnotes: yes
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D5554
IGP may declare subclass as either VGA-compatible, or non-VGA. The
difference is that in the later case, IGP does not claim VGA cycles.
Other than that, the device functions normally, and agp_i810 should
attach to it.
Sponsored by: The FreeBSD Foundation
MFC after: 1 week
on my part about north bridge/GPU pci ids and use of aperture.
Leave the agp_intel.c out of static compilation on amd64, it makes the
things consistent with agp.ko.
Pointed out by: tijl
Sponsored by: The FreeBSD Foundation
MFC after: 13 days
875. This intersects with the agp_i810.c, which supports all Intels
from i810 to Core i5/7. Both agp_intel.c and agp_i810.c are compiled
into kernel when device agp is specified in config, and agp_i810
attach seems to be selected by chance due to linking order.
Strip support for 810 and later from agp_intel.c. Since 440-class
chipsets do not support any long-mode capable CPUs, remove agp_intel.c
from amd64 kernel file list. Note that agp_intel.c is not compiled
into agp.ko on amd64 already.
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks
updating the GTT and flushing the AGP TLB by storing the GTT in
write-combining memory.
On x86 flushing the AGP TLB is done by an I/O operation or a store to a
MMIO register in uncacheable memory. Both cases imply that WC buffers are
flushed so no memory barriers are needed.
On powerpc there is no WC memory type. It maps to uncacheable memory and
two stores to uncacheable memory, such as to the GTT and then to an MMIO
register, are strongly ordered, so no memory barriers are needed either.
MFC after: 1 month
the queue where to enqueue pages that are going to be unwired.
- Add stronger checks to the enqueue/dequeue for the pagequeues when
adding and removing pages to them.
Of course, for unmanaged pages the queue parameter of vm_page_unwire() will
be ignored, just as the active parameter today.
This makes adding new pagequeues quicker.
This change effectively modifies the KPI. __FreeBSD_version will be,
however, bumped just when the full cache of free pages will be
evicted.
Sponsored by: EMC / Isilon storage division
Reviewed by: alc
Tested by: pho
shifts into the sign bit. Instead use (1U << 31) which gets the
expected result.
This fix is not ideal as it assumes a 32 bit int, but does fix the issue
for most cases.
A similar change was made in OpenBSD.
Discussed with: -arch, rdivacky
Reviewed by: cperciva
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
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
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
flush wait on the Gen2 chipsets. Confirmed by the inspection of the
Linux agp code.
Submitted by: Taku YAMAMOTO <taku@tackymt.homeip.net>
MFC after: 2 weeks
to pull vm_param.h was removed. Other big dependency of vm_page.h on
vm_param.h are PA_LOCK* definitions, which are only needed for
in-kernel code, because modules use KBI-safe functions to lock the
pages.
Stop including vm_param.h into vm_page.h. Include vm_param.h
explicitely for the kernel code which needs it.
Suggested and reviewed by: alc
MFC after: 2 weeks
Don't use Maxmem when the amount of memory is meant. Use realmem instead.
Maxmem is not only a MD variable, it represents the highest physical memory
address in use. On systems where memory is sparsely layed-out the highest
memory address and the amount of memory are not interchangeable. Scaling the
AGP aperture based on the actual amount of memory (= realmem) rather than
the available memory (= physmem) makes sure there's consistent behaviour
across architectures.
agp_i810.c:
While arguably the use of Maxmem can be considered correct, replace its use
with realmem anyway. agp_i810.c is specific to amd64, i386 & pc98, which
have a dense physical memory layout. Avoiding Maxmem here is done with an
eye on copy-n-paste behaviour in general and to avoid confusion caused by
using realmem in agp.c and Maxmem in agp_i810.c.
In both cases, remove the inclusion of md_var.h
operations required by GEMified i915.ko. It also attaches to SandyBridge
and IvyBridge CPU northbridges now.
Sponsored by: The FreeBSD Foundation
MFC after: 1 month
scope of the object lock in agp_i810.c. (In this specific case, the scope
of the object lock shouldn't matter, but I don't want to create a bad
example that might be copied to a case where it did matter.)
Reviewed by: kib
