The ring frequency scaling table tells the PCU to treat certain GPU
frequencies as if they were a given CPU frequency for purposes of
scaling the ring frequency.  Normally the PCU will scale the ring
frequency based on the CPU P-state, but with the table present, it will
also take the GPU frequency into account.

The main downside of keeping the ring frequency high while the CPU is
at a low frequency (or asleep altogether) is increased power
consumption.  But then if you're keeping your GPU busy, you probably
want the extra performance.

v2:
  - add units to debug table header (from Eric)
  - use tsc_khz as a fallback if the cpufreq driver doesn't give us a freq
    (from Chris)
v3:
  - fix comments & debug output
  - remove unneeded force wake get/put
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Tested-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Keith Packard <keithp@keithp.com>

This allows drivers and other code to get the max reported CPU frequency.
Initial use is for scaling ring frequency with GPU frequency in the i915
driver.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Keith Packard <keithp@keithp.com>

Konstantin Belousov pointed out that 4697995b replaced the generic
i915_driver_irq_*install() functions with chipset specific routines
accessible only through driver->irq_*install(). So update the sanity
check in i915_request_wait() to match.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>

The failure is as follows:

1. Userspace gets forcewake lock, lock count >=1
2. GPU hang/reset occurs (forcewake bit is reset)
3. count is now incorrect

The failure can only occur when using the forcewake userspace lock.

This has the unfortunate consequence of messing up the driver as well as
userspace, unless userspace closes the debugfs file, the kernel will
never end up waking the GT since the refcount will be > 1.

The solution is to try to recover the correct forcewake state based on
the refcount. There is a period of time where userspace reads/writes may
occur after the reset, before the GT has been forcewaked. The interface
was never designed to be a perfect solution for userspace reads/writes,
and the kernel portion is fixed by this patch.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Keith Packard <keithp@keithp.com>

When auditing the locking in i915_gem.c (for a prospective change which I
then abandoned), I noticed two places where struct_mutex is not held
across GEM object manipulations that would usually require it.  Since one
is in initial setup and the other in driver unload, I'm guessing the mutex
is not required for either; but post a patch in case it is.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Keith Packard <keithp@keithp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Keith Packard <keithp@keithp.com>

Use the blit ring for submitting flips since the render ring doesn't
generate flip complete interrupts.

Fixes bugs:

	https://bugs.freedesktop.org/show_bug.cgi?id=38362
	https://bugs.freedesktop.org/show_bug.cgi?id=38392
	https://bugs.freedesktop.org/show_bug.cgi?id=38393Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Tested-by: Jian J Zhao <jian.j.zhao@intel.com>
Signed-off-by: Keith Packard <keithp@keithp.com>

This makes things a little clearer and prevents us from running old code
on a new chipset that may not be supported.
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Reviewied-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Keith Packard <keithp@keithp.com>

Even if the object is no longer in the GTT domain, there may still be
a user space mapping which needs to be released.

Without this fix, render-based text (mostly in firefox) would
occasionally get corrupted when the system was under load.
Signed-off-by: Keith Packard <keithp@keithp.com>

The lock must be held for the saving and restoring of VGA state.
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
CC: Alexander Zhaunerchyk <alex.vizor@gmail.com>
CC: Andrey Rahmatullin <wrar@wrar.name>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>

This reverts commit 4a684a41.
Userland has always been required to set the object's domain to GTT
before using it through a GTT mapping, it's not something that the
kernel is supposed to enforce.  (The pagefault support is so that we
can handle multiple mappings without userland having to pin across
them, not so that userland can use GTT after GPU domains without
telling the kernel).

Fixes 19.2% +/- 0.8% (n=6) performance regression in cairo-gl
firefox-talos-gfx on my T420 latop.
Signed-off-by: Keith Packard <keithp@keithp.com>

...we need to apply exactly the same workaround for missing interrupts
from BSD as for the BLT ring, apparently.

See also commit 498e720b
(drm/i915: Fix gen6 (SNB) missed BLT ring interrupts).

Reported-and-tested-by: nkalkhof@web.de
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=38529Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Keith Packard <keithp@keithp.com>

This change got placed in the ironlake path instead of the 9xx path
during a recent code shuffle.
Signed-off-by: Keith Packard <keithp@keithp.com>

Commit 13e12d14 ("vfs: reorganize 'struct inode' layout a bit")
moved things around a bit changed i_state to be unsigned int instead of
unsigned long.  That was to help structure layout for the 64-bit case,
and shrink 'struct inode' a bit (admittedly that only happened when
spinlock debugging was on and i_flags didn't pack with i_lock).

However, Meelis Roos reports that this results in unaligned exceptions
on sprc, and it turns out that the bit-locking primitives that we use
for the I_NEW bit want to use the bitops.  Which want 'unsigned long',
not 'unsigned int'.

We really should fix the bit locking code to not have that kind of
requirement, but that's a much bigger change.  So for now, revert that
field back to 'unsigned long' (but keep the other re-ordering changes
from the commit that caused this).

Andi points out that we have played games with this in 'struct page', so
it's solvable with other hacks too, but since right now the struct inode
size advantage only happens with some rare config options, it's not
worth fighting.

It _would_ be worth fixing the bitlocking code, though.  Especially
since there is no type safety in the bitlocking code (this never caused
any warnings, and worked fine on x86-64, because the bitlocks take a
'void *' and x86-64 doesn't care that deeply about alignment).  So it's
currently a very easy problem to trigger by mistake and never notice.
Reported-by: Meelis Roos <mroos@linux.ee>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

* 'drm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
  drm/radeon/kms/r6xx+: voltage fixes
  drm/nouveau: drop leftover debugging
  drm/radeon: avoid warnings from r600/eg irq handlers on powered off card.
  drm/radeon/kms: add missing param for dce3.2 DP transmitter setup
  drm/radeon/kms/atom: fix duallink on some early DCE3.2 cards
  drm/nouveau: fix assumption that semaphore dmaobj is valid in x-chan sync
  drm/nv50/disp: fix gamma with page flipping overlay turned on
  drm/nouveau/pm: Prevent overflow in nouveau_perf_init()
  drm/nouveau: fix big-endian switch

* 'msm-fix' of git://codeaurora.org/quic/kernel/davidb/linux-msm:
  msm: timer: Fix DGT rate on 8960 and 8660
  msm: timer: compensate for timer shift in msm_read_timer_count
  msm: timer: Fix SMP build error

* 'for-2.6.40' of git://linux-nfs.org/~bfields/linux:
  nfsd4: fix break_lease flags on nfsd open
  nfsd: link returns nfserr_delay when breaking lease
  nfsd: v4 support requires CRYPTO
  nfsd: fix dependency of nfsd on auth_rpcgss

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (40 commits)
  pxa168_eth: fix race in transmit path.
  ipv4, ping: Remove duplicate icmp.h include
  netxen: fix race in skb->len access
  sgi-xp: fix a use after free
  hp100: fix an skb->len race
  netpoll: copy dev name of slaves to struct netpoll
  ipv4: fix multicast losses
  r8169: fix static initializers.
  inet_diag: fix inet_diag_bc_audit()
  gigaset: call module_put before restart of if_open()
  farsync: add module_put to error path in fst_open()
  net: rfs: enable RFS before first data packet is received
  fs_enet: fix freescale FCC ethernet dp buffer alignment
  netdev: bfin_mac: fix memory leak when freeing dma descriptors
  vlan: don't call ndo_vlan_rx_register on hardware that doesn't have vlan support
  caif: Bugfix - XOFF removed channel from caif-mux
  tun: teach the tun/tap driver to support netpoll
  dp83640: drop PHY status frames in the driver.
  dp83640: fix phy status frame event parsing
  phylib: Allow BCM63XX PHY to be selected only on BCM63XX.
  ...

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  devcgroup_inode_permission: take "is it a device node" checks to inlined wrapper
  fix comment in generic_permission()
  kill obsolete comment for follow_down()
  proc_sys_permission() is OK in RCU mode
  reiserfs_permission() doesn't need to bail out in RCU mode
  proc_fd_permission() is doesn't need to bail out in RCU mode
  nilfs2_permission() doesn't need to bail out in RCU mode
  logfs doesn't need ->permission() at all
  coda_ioctl_permission() is safe in RCU mode
  cifs_permission() doesn't need to bail out in RCU mode
  bad_inode_permission() is safe from RCU mode
  ubifs: dereferencing an ERR_PTR in ubifs_mount()

0xff01 is not an actual voltage value, but a flag
for the driver.  If the power state as that value,
skip setting the voltage.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

The DGT runs at 27 MHz divided by 4 on 8660 and 8960.
Signed-off-by: Stephen Boyd <sboyd@codeaurora.org>
Signed-off-by: David Brown <davidb@codeaurora.org>

Because the socket buffer is freed in the completion interrupt, it is not
safe to access it after submitting it to the hardware.

Cc: stable@kernel.org
Cc: Sachin Sanap <ssanap@marvell.com>
Cc: Zhangfei Gao <zgao6@marvell.com>
Cc: Philip Rakity <prakity@marvell.com>
Signed-off-by: Richard Cochran <richard.cochran@omicron.at>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Remove the duplicate inclusion of net/icmp.h from net/ipv4/ping.c
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

As soon as skb is given to hardware, TX completion can free skb under
us.
Therefore, we should update dev stats before kicking the device.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Amit Kumar Salecha <amit.salecha@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

* 'stable/bug.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen/setup: Fix for incorrect xen_extra_mem_start.
  xen: When calling power_off, don't call the halt function.
  xen: Fix compile warning when CONFIG_SMP is not defined.
  xen: support CONFIG_MAXSMP
  xen: partially revert "xen: set max_pfn_mapped to the last pfn mapped"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
  Input: sh_keysc - 8x8 MODE_6 fix
  Input: omap-keypad - add missing input_sync()
  Input: evdev - try to wake up readers only if we have full packet
  Input: properly assign return value of clamp() macro.

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
  Btrfs: avoid delayed metadata items during commits
  btrfs: fix uninitialized return value
  btrfs: fix wrong reservation when doing delayed inode operations
  btrfs: Remove unused sysfs code
  btrfs: fix dereference of ERR_PTR value
  Btrfs: fix relocation races
  Btrfs: set no_trans_join after trying to expand the transaction
  Btrfs: protect the pending_snapshots list with trans_lock
  Btrfs: fix path leakage on subvol deletion
  Btrfs: drop the delalloc_bytes check in shrink_delalloc
  Btrfs: check the return value from set_anon_super

* 'kvm-updates/3.0' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Fix register corruption in pvclock_scale_delta
  KVM: MMU: fix opposite condition in mapping_level_dirty_bitmap
  KVM: VMX: do not overwrite uptodate vcpu->arch.cr3 on KVM_SET_SREGS
  KVM: MMU: Fix build warnings in walk_addr_generic()

inode_permission() calls devcgroup_inode_permission() and almost all such
calls are _not_ for device nodes; let's at least keep the common path
straight...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

CAP_DAC_OVERRIDE is enough for MAY_EXEC on directory, even if
no exec bits are set.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

nothing blocking there, since all instances of sysctl
->permissions() method are non-blocking - both of them,
that is.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

nothing blocking other than generic_permission() (and
check_acl callback does bail out in RCU mode).
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

nothing blocking except generic_permission()
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

Nothing blocking except for generic_permission().  Which will DTRT.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

... and never did, what with its ->permission() being what we do by default
when ->permission is NULL...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>