Avoid waiting on physical allocations that can't possibly be satisfied

- Change vm_page_reclaim_contig[_domain] to return an errno instead
of a boolean. 0 indicates a successful reclaim, ENOMEM i

Avoid waiting on physical allocations that can't possibly be satisfied

- Change vm_page_reclaim_contig[_domain] to return an errno instead
of a boolean. 0 indicates a successful reclaim, ENOMEM indicates
lack of available memory to reclaim, with any other error (currently
only ERANGE) indicating that reclamation is impossible for the
specified address range. Change all callers to only follow
up with vm_page_wait* in the ENOMEM case.

- Introduce vm_domainset_iter_ignore(), which marks the specified
domain as unavailable for further use by the iterator. Use this
function to ignore domains that can't possibly satisfy a physical
allocation request. Since WAITOK allocations run the iterators
repeatedly, this avoids the possibility of infinitely spinning
in domain iteration if no available domain can satisfy the
allocation request.

PR: 274252
Reported by: kevans
Tested by: kevans
Reviewed by: markj
Differential Revision: https://reviews.freebsd.org/D42706

show more ...

sys: Remove $FreeBSD$: one-line .c pattern

Remove /^[\s*]*__FBSDID\("\$FreeBSD\$"\);?\s*\n/

Convert consumers to vm_page_alloc_noobj_contig()

Remove now-unneeded page zeroing. No functional change intended.

Reviewed by: alc, hselasky, kib
MFC after: 1 week
Sponsored by: The FreeBSD Found

Convert consumers to vm_page_alloc_noobj_contig()

Remove now-unneeded page zeroing. No functional change intended.

Reviewed by: alc, hselasky, kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D32006

show more ...

Convert vm_page_alloc() callers to use vm_page_alloc_noobj().

Remove page zeroing code from consumers and stop specifying
VM_ALLOC_NOOBJ. In a few places, also convert an allocation loop to
simply

Convert vm_page_alloc() callers to use vm_page_alloc_noobj().

Remove page zeroing code from consumers and stop specifying
VM_ALLOC_NOOBJ. In a few places, also convert an allocation loop to
simply use VM_ALLOC_WAITOK.

Similarly, convert vm_page_alloc_domain() callers.

Note that callers are now responsible for assigning the pindex.

Reviewed by: alc, hselasky, kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D31986

show more ...

Merge ^/head r352105 through r352307.

Change synchonization rules for vm_page reference counting.

There are several mechanisms by which a vm_page reference is held,
preventing the page from being freed back to the page allocator. In
pa

Change synchonization rules for vm_page reference counting.

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

show more ...

MFHead @349234

Sponsored by: The FreeBSD Foundation

Replace uses of vm_page_unwire(m, PQ_NONE) with vm_page_unwire_noq(m).

These calls are not the same in general: the former will dequeue the
page if it is enqueued, while the latter will just leave i

Replace uses of vm_page_unwire(m, PQ_NONE) with vm_page_unwire_noq(m).

These calls are not the same in general: the former will dequeue the
page if it is enqueued, while the latter will just leave it alone. But,
all existing uses of the former apply to unmanaged pages, which are
never enqueued in the first place. No functional change intended.

Reviewed by: kib
MFC after: 1 week
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D20470

show more ...

MFHead @348740

Sponsored by: The FreeBSD Foundation

Include eventhandler.h in more compilation units

This was enumerated with exhaustive search for sys/eventhandler.h includes,
cross-referenced against EVENTHANDLER_* usage with the comm(1) utility.

Include eventhandler.h in more compilation units

This was enumerated with exhaustive search for sys/eventhandler.h includes,
cross-referenced against EVENTHANDLER_* usage with the comm(1) utility. Manual
checking was performed to avoid redundant includes in some drivers where a
common os_bsd.h (for example) included sys/eventhandler.h indirectly, but it is
possible some of these are redundant with driver-specific headers in ways I
didn't notice.

(These CUs did not show up as missing eventhandler.h in tinderbox.)

X-MFC-With: r347984

show more ...

Revert drm2 removal.

Revert r338177, r338176, r338175, r338174, r338172

After long consultations with re@, core members and mmacy, revert
these changes. Followup changes will be made to mark them a

Revert drm2 removal.

Revert r338177, r338176, r338175, r338174, r338172

After long consultations with re@, core members and mmacy, revert
these changes. Followup changes will be made to mark them as
deprecated and prent a message about where to find the up-to-date
driver. Followup commits will be made to make this clear in the
installer. Followup commits to reduce POLA in ways we're still
exploring.

It's anticipated that after the freeze, this will be removed in
13-current (with the residual of the drm2 code copied to
sys/arm/dev/drm2 for the TEGRA port's use w/o the intel or
radeon drivers).

Due to the impending freeze, there was no formal core vote for
this. I've been talking to different core members all day, as well as
Matt Macey and Glen Barber. Nobody is completely happy, all are
grudgingly going along with this. Work is in progress to mitigate
the negative effects as much as possible.

Requested by: re@ (gjb, rgrimes)

show more ...

vm_wait() rework.

Make vm_wait() take the vm_object argument which specifies the domain
set to wait for the min condition pass. If there is no object
associated with the wait, use curthread' policy

vm_wait() rework.

Make vm_wait() take the vm_object argument which specifies the domain
set to wait for the min condition pass. If there is no object
associated with the wait, use curthread' policy domainset. The
mechanics of the wait in vm_wait() and vm_wait_domain() is supplied by
the new helper vm_wait_doms(), which directly takes the bitmask of the
domains to wait for passing min condition.

Eliminate pagedaemon_wait(). vm_domain_clear() handles the same
operations.

Eliminate VM_WAIT and VM_WAITPFAULT macros, the direct functions calls
are enough.

Eliminate several control state variables from vm_domain, unneeded
after the vm_wait() conversion.

Scetched and reviewed by: jeff
Tested by: pho
Sponsored by: The FreeBSD Foundation, Mellanox Technologies
Differential revision: https://reviews.freebsd.org/D14384

show more ...

Merge ^/head r318380 through r318559.

Don't bother enqueuing a page immediately before freeing it.

No functional change intended.

MFC after: 1 week

MFH r289384-r293170

Sponsored by: The FreeBSD Foundation

MFH @r292599

This includes the pluggable TCP framework and other chnages to the
netstack to track for VNET stability.

Security: The FreeBSD Foundation

Introduce a new mechanism for relocating virtual pages to a new physical
address and use this mechanism when:

1. kmem_alloc_{attr,contig}() can't find suitable free pages in the physical
memory a

Introduce a new mechanism for relocating virtual pages to a new physical
address and use this mechanism when:

1. kmem_alloc_{attr,contig}() can't find suitable free pages in the physical
memory allocator's free page lists. This replaces the long-standing
approach of scanning the inactive and inactive queues, converting clean
pages into PG_CACHED pages and laundering dirty pages. In contrast, the
new mechanism does not use PG_CACHED pages nor does it trigger a large
number of I/O operations.

2. on 32-bit MIPS processors, uma_small_alloc() and the pmap can't find
free pages in the physical memory allocator's free page lists that are
covered by the direct map. Tested by: adrian

3. ttm_bo_global_init() and ttm_vm_page_alloc_dma32() can't find suitable
free pages in the physical memory allocator's free page lists.

In the coming months, I expect that this new mechanism will be applied in
other places. For example, balloon drivers should use relocation to
minimize fragmentation of the guest physical address space.

Make vm_phys_alloc_contig() a little smarter (and more efficient in some
cases). Specifically, use vm_phys_segs[] earlier to avoid scanning free
page lists that can't possibly contain suitable pages.

Reviewed by: kib, markj
Glanced at: jhb
Discussed with: jeff
Sponsored by: EMC / Isilon Storage Division
Differential Revision: https://reviews.freebsd.org/D4444

show more ...

Catch up with HEAD (r280229-r284686).

Merge ^/head r284188 through r284643.

Merge from head@274131

ttm_vm_page_alloc: use vm_page_alloc for pages without dma32 restriction

This change re-organizes code a little bit to extract common pieces
of ttm_alloc_new_pages() and ttm_get_pages() into dedicat

ttm_vm_page_alloc: use vm_page_alloc for pages without dma32 restriction

This change re-organizes code a little bit to extract common pieces
of ttm_alloc_new_pages() and ttm_get_pages() into dedicated functions.
Also, for requests without address restrictions regular vm_page_alloc()
is used.
Lastly, when vm_page_alloc_contig() fails we call VM_WAIT before calling
vm_pageout_grow_cache() to ensure that there is enough free pages at all.

Reviewed by: kib
MFC after: 15 days

show more ...

Merge sync of head

Merge from HEAD

Merge ^/head r278110 through r278223.

If the vm_page_alloc_contig() failed in the ttm page allocators, do
what other callers of vm_page_alloc_contig() do, retry after
vm_pageout_grow_cache().

Sponsored by: The FreeBSD Foundation