Copy stable/10@r272459 to releng/10.1 as part of
the 10.1-RELEASE process.

Approved by: re (implicit)
Sponsored by: The FreeBSD Foundation

drm/i915: Add HW context support

This feature is required by Mesa 9.2+. Without this, a GL application
crashes with the following message:
# glxinfo
name of display: :0.0
Gen6+ requires Kernel 3.6 or later.
Assertion failed: (ctx->Version > 0), function handle_first_current,
file ../../src/mesa/main/context.c, line 1498.
Abort (core dumped)

Now, Mesa 10.2.4 and 10.3-rc3 works fine:
# glxinfo
name of display: :0
display: :0 screen: 0
direct rendering: Yes
...
OpenGL renderer string: Mesa DRI Intel(R) 965GM
OpenGL version string: 2.1 Mesa 10.2.4
...

The code was imported from Linux 3.8.13.

This an MFC of r271705.

Approved by: re (glebius)
Reviewed by: kib@
Tested by: kwm@, danfe@, Henry Hu,
Lundberg, Johannes <johannes@brilliantservice.co.jp>,
Johannes Dieterich <dieterich.joh@gmail.com>,
Lutz Bichler <lutz.bichler@gmail.com>,
Relnotes: yes

MFC r265102:
Fix two cases of recursive acquisitions of the vm object lock, only
possible in rare failure situations.

Copy head (r256279) to stable/10 as part of the 10.0-RELEASE cycle.

Approved by: re (implicit)
Sponsored by: The FreeBSD Foundation

Add a mmap flag (MAP_32BIT) on 64-bit platforms to request that a mapping use
an address in the first 2GB of the process's address space. This flag should
have the same semantics as the same flag on Linux.

To facilitate this, add a new parameter to vm_map_find() that specifies an
optional maximum virtual address. While here, fix several callers of
vm_map_find() to use a VMFS_* constant for the findspace argument instead of
TRUE and FALSE.

Reviewed by: alc
Approved by: re (kib)

Correct atomic operations in i915.

Remove the deprecated VM_ALLOC_RETRY flag for the vm_page_grab(9).
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

On all the architectures, avoid to preallocate the physical memory
for nodes used in vm_radix.
On architectures supporting direct mapping, also avoid to pre-allocate
the KVA for such nodes.

In order to do so make the operations derived from vm_radix_insert()
to fail and handle all the deriving failure of those.

vm_radix-wise introduce a new function called vm_radix_replace(),
which can replace a leaf node, already present, with a new one,
and take into account the possibility, during vm_radix_insert()
allocation, that the operations on the radix trie can recurse.
This means that if operations in vm_radix_insert() recursed
vm_radix_insert() will start from scratch again.

Sponsored by: EMC / Isilon storage division
Reviewed by: alc (older version)
Reviewed by: jeff
Tested by: pho, scottl

The soft and hard busy mechanism rely on the vm object lock to work.
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

Use the right name for the vm_map_find(9) flag to specify shared
mapping. The MAP_SHARED and MAP_INHERIT_SHARE values are identical.

Noted by: alc
MFC after: 3 days

Be more aggressive in using superpages in all mappings of objects:
- Add a new address space allocation method (VMFS_OPTIMAL_SPACE) for
vm_map_find() that will try to alter the alignment of a mapping to match
any existing superpage mappings of the object being mapped. If no
suitable address range is found with the necessary alignment,
vm_map_find() will fall back to using the simple first-fit strategy
(VMFS_ANY_SPACE).
- Change mmap() without MAP_FIXED, shmat(), and the GEM mapping ioctl to
use VMFS_OPTIMAL_SPACE instead of VMFS_ANY_SPACE.

Reviewed by: alc (earlier version)
MFC after: 2 weeks

Since the gem pagefault handler relocks the vm object lock, other
thread might fault on the same GTT offset meantime and instantiate the
mapping. Recheck that the mgt device object still does not have a
page at the current offset after relocking, and return a possibly
installed page.

Reported by: Oleg Sidorkin <osidorkin@gmail.com>
Sponsored by: The FreeBSD Foundation
MFC after: 2 weeks

Remove stray empty line.

MFC after: 3 days

Don't busy the page unless we are likely to release the object lock.

Reviewed by: kib
Sponsored by: EMC / Isilon Storage Division

The vm_page lock is not needed around the call to vm_page_insert().

Submitted by: alc
MFC after: 1 week

Switch the vm_object mutex to be a rwlock. This will enable in the
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

Use right size when freeing unneeded GTT mapping.

MFC after: 3 days

A small simplification to i915_gem_pager_fault().

Reviewed by: kib

Add the code for new Intel GPU driver, which supports GEM, KMS and
works with new generations of GPUs (IronLake, SandyBridge and
supposedly IvyBridge).

The driver is not connected to the build yet.

Sponsored by: The FreeBSD Foundation
MFC after: 1 week