Commit graph

286,663 commits

Author SHA1 Message Date
Ben Skeggs
591b06d73b drm/nouveau/tmr: calibrate for ns timestamps on init
We previously assumed (incorrectly a lot of the time) that PTIMER would
be programmed at a frequency which'd give its 64-bit timestamps in
nanoseconds.

By programming PTIMER ourselves, we avoid this problem.

Reviewed-by: Martin Peres <martin.peres@ensi-bourges.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:04:36 +10:00
Ben Skeggs
16cd399c65 drm/nvc0/gr: unblacklist nvcf acceleration
Reported to be working.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:04:32 +10:00
Ben Skeggs
0b3b5579e1 drm/nouveau: don't complain for disabled timingset entries
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:04:29 +10:00
Ben Skeggs
e425e0b339 drm/nvc0/gr: copy GPC mpart config from PFFB
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:04:15 +10:00
Ben Skeggs
aa6500964c drm/nvc0/vram: support non-uniform memory size per controller
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:04:11 +10:00
Ben Skeggs
3c23a7b8bc drm/nvc0/gr: add support for nvcf chipset
untested, written from a trace, accel disabled by default until it is

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:04:06 +10:00
Ben Skeggs
a12036ba2c drm/nouveau: allow a nouveau_mm to be created with holes
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:04:00 +10:00
Ben Skeggs
987eec10dd drm/nouveau: embed nouveau_mm
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:03:56 +10:00
Ben Skeggs
52d073318a drm/nv31/mpeg: support for a single class3174 user
Uncertain if/how the hw does multiple PMPEG channels, supporting one is
better than none however.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:03:44 +10:00
Ben Skeggs
323dcac552 drm/nouveau: rename nv40_mpeg to nv31_mpeg
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:03:38 +10:00
Ben Skeggs
9698b9a680 drm/nvc0/pm: more complete parsing of clock domains
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:03:34 +10:00
Ben Skeggs
354d0781e5 drm/nvc0/pm: initial implementation of clocks_get()
Not too certain on memory clock yet, but it gets the right numbers for
each perflvl on my NVC0.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:03:16 +10:00
Ben Skeggs
d0f67a48f4 drm/nva3/pm: idle graphics engine before changing clocks
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:02:53 +10:00
Ben Skeggs
78e2933d07 drm/nouveau: add function to wait until a callback returns true
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:02:50 +10:00
Ben Skeggs
95f0de3a0a drm/nv50/gr: insert set/clr of a ctxprog flag at start/end of ctxprog
The set will be replaced with a wait on the same flag by a subsequent
commit in order to halt a ctxprog's execution temporarily.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:02:46 +10:00
Ben Skeggs
cec2a270db drm/nva3/pm: tidy and add some comments here and there
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:02:40 +10:00
Ben Skeggs
4fd2847e9b drm/nva3/pm: parse/reclock vdec/41a0 clocks
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:02:36 +10:00
Ben Skeggs
ca94a71fc4 drm/nva3/pm: rewrite clock_set, and switch to new interfaces
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:51 +10:00
Ben Skeggs
77e7da6814 drm/nouveau/pm: add hooks to get/set *all* clocks at once
This is probably better than having to tell the common code about all the
clocks that exist on every chipset.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:45 +10:00
Ben Skeggs
3b0582d31d drm/nva3/pm: rewrite clock readback functions, far more correct now
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:41 +10:00
Ben Skeggs
03ce8d9e63 drm/nouveau/pm: some fermi chipsets still use volt 0x30
Fun, fun.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:37 +10:00
Ben Skeggs
da1dc4cfec drm/nouveau/pm: allow voltage-only perflvl set, enable nvc0
Okay, my card didn't blow up.  Lets turn it on!

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:30 +10:00
Ben Skeggs
3c71c2330b drm/nvc0/pm: enable voltage_get
I don't have a terribly good reason for not enabling voltage_set too, but,
lets wait and see.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:25 +10:00
Ben Skeggs
93dccbedeb drm/nouveau/pm: show any info we can manage to glean on current perflvl
Previously wouldn't show detected voltage if we couldn't figure out the
clock frequencies..

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:21 +10:00
Ben Skeggs
3b5565ddfd drm/nouveau/pm: add support for parsing perflvl voltage on fermi chips
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:14 +10:00
Ben Skeggs
a31214ef3e drm/nouveau/pm: add yet another vid gpio tag
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:11 +10:00
Ben Skeggs
f60dfb996c drm/nouveau/pm: initial attempt at parsing volt 0x40
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:06 +10:00
Ben Skeggs
c3450239c7 drm/nouveau/pm: store voltage in microvolts
Instead of 10s of millivolts, to match fermi vbios.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2011-09-20 16:01:02 +10:00
Benjamin Herrenschmidt
55190f8878 powerpc: Add skeleton PowerNV platform
This adds a skeletton for the new Power "Non Virtualized"
platform which will be used by machines supporting running
without an hypervisor, for example in order to run KVM.

These machines will be using a new firmware called OPAL
for which the support will be provided by later patches.

The PowerNV platform is intended to be also usable under
the BML environment used internally for early CPU bringup
which is why the code also supports using RTAS instead of
OPAL in various places.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:25 +10:00
Benjamin Herrenschmidt
e550592e68 powerpc/powernv: Don't clobber r9 in relative_toc()
With OPAL, r8 and r9 will be used to pass the OPAL base and entry
for debugging purposes (those informations are also in the
device-tree). We don't want to clobber those registers that
early.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:24 +10:00
Benjamin Herrenschmidt
781fb7a3e4 powerpc/pci: Call pcie_bus_configure_settings()
This new function is used to properly setup the PCI Express Max Payload Size
(and in some circumstances Max Read Request Size).

Some systems will not operate properly if these aren't set correctly and
the firmware doesn't always do it.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:24 +10:00
Benjamin Herrenschmidt
fb82b83970 powerpc/smp: More generic support for "soft hotplug"
This adds more generic support for doing CPU hotplug with a simple
idle loop and no actual reset of the processors. The generic
smp_generic_kick_cpu() does the hotplug bringup trick if the PACA
shows that the CPU has already been started at boot and we provide
an accessor for the CPU state.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:24 +10:00
Benjamin Herrenschmidt
b8bb922c68 powerpc/udbg: Fix Kconfig entry for avoiding 44x early debug with KVM
It was preventing the global early debug selection whenever KVM was enabled
instead of only preventing the 440 specific one.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:24 +10:00
Brian King
ac07a4a57f hvcs: Ensure page aligned partner info buffer
The Power platform requires the partner info buffer to be page aligned
otherwise it will fail the partner info hcall with H_PARAMETER. Switch
from using kmalloc to allocate this buffer to __get_free_page to ensure
page alignment.

Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:24 +10:00
Anton Blanchard
8bdafa39a4 powerpc: Fix deadlock in icswx code
The icswx code introduced an A-B B-A deadlock:

     CPU0                    CPU1
     ----                    ----
lock(&anon_vma->mutex);
                             lock(&mm->mmap_sem);
                             lock(&anon_vma->mutex);
lock(&mm->mmap_sem);

Instead of using the mmap_sem to keep mm_users constant, take the
page table spinlock.

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: <stable@kernel.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:23 +10:00
Anton Blanchard
a11940978b powerpc: Fix oops when echoing bad values to /sys/devices/system/memory/probe
If we echo an address the hypervisor doesn't like to
/sys/devices/system/memory/probe we oops the box:

# echo 0x10000000000 > /sys/devices/system/memory/probe

kernel BUG at arch/powerpc/mm/hash_utils_64.c:541!

The backtrace is:

create_section_mapping
arch_add_memory
add_memory
memory_probe_store
sysdev_class_store
sysfs_write_file
vfs_write
SyS_write

In create_section_mapping we BUG if htab_bolt_mapping returned
an error. A better approach is to return an error which will
propagate back to userspace.

Rerunning the test with this patch applied:

# echo 0x10000000000 > /sys/devices/system/memory/probe
-bash: echo: write error: Invalid argument

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: stable@kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:23 +10:00
Anton Blanchard
dfbe93a222 powerpc: Coding style cleanups
While converting code to use for_each_node_by_type I noticed a
number of coding style issues.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:23 +10:00
Anton Blanchard
94db7c5e14 powerpc: Use for_each_node_by_type instead of open coding it
Use for_each_node_by_type instead of open coding it.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:23 +10:00
Anton Blanchard
6083184269 powerpc/numa: Remove double of_node_put in hot_add_node_scn_to_nid
During memory hotplug testing, I got the following warning:

ERROR: Bad of_node_put() on /memory@0

of_node_release
kref_put
of_node_put
of_find_node_by_type
hot_add_node_scn_to_nid
hot_add_scn_to_nid
memory_add_physaddr_to_nid
...

of_find_node_by_type() loop does the of_node_put for us so we only
need the handle the case where we terminate the loop early.

As suggested by Stephen Rothwell we can do the of_node_put
unconditionally outside of the loop since of_node_put handles a
NULL argument fine.

Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: stable@kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:22 +10:00
Anton Blanchard
e377bc5d49 powerpc/numa: Remove duplicate RECLAIM_DISTANCE definition
We have two identical definitions of RECLAIM_DISTANCE, looks like
the patch got applied twice. Remove one.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:22 +10:00
Anton Blanchard
7bebcf0925 powerpc/numa: Disable NEWIDLE balancing at node level
On big POWER7 boxes we see large amounts of CPU time in system
processes like workqueue and watchdog kernel threads.

We currently rebalance the entire machine each time a task goes
idle and this is very expensive on large machines. Disable newidle
balancing at the node level and rely on the scheduler tick to
rebalance across nodes.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:22 +10:00
Anton Blanchard
d4761ad2ef powerpc/numa: Increase SD_NODES_PER_DOMAIN to 32.
The largest POWER7 boxes have 32 nodes. SD_NODES_PER_DOMAIN groups
nodes into chunks of 16 and adds a global balancing domain
(SD_ALLNODES) above it.

If we bump SD_NODES_PER_DOMAIN to 32, then we avoid this extra
level of balancing on our largest boxes.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:22 +10:00
Anton Blanchard
590e4d8571 sched: Allow SD_NODES_PER_DOMAIN to be overridden
We want to override the default value of SD_NODES_PER_DOMAIN on ppc64,
so move it into linux/topology.h.

Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:21 +10:00
Anton Blanchard
a200d8e446 powerpc/numa: Enable SD_WAKE_AFFINE in node definition
When chasing a performance issue on ppc64, I noticed tasks
communicating via a pipe would often end up on different nodes.

It turns out SD_WAKE_AFFINE is not set in our node defition. Commit
9fcd18c9e6 (sched: re-tune balancing) enabled SD_WAKE_AFFINE
in the node definition for x86 and we need a similar change for
ppc64.

I used lmbench lat_ctx and perf bench pipe to verify this fix. Each
benchmark was run 10 times and the average taken.

lmbench lat_ctx:

before:  66565 ops/sec
after:  204700 ops/sec

3.1x faster

perf bench pipe:

before: 5.6570 usecs
after:  1.3470 usecs

4.2x faster

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-09-20 15:53:21 +10:00
Benjamin Herrenschmidt
1cce058b29 Merge remote-tracking branch 'origin/master' into next
(Merge in order to get the PCIe mps/mrss code fixes)
2011-09-20 15:52:38 +10:00
Shirish Pargaonkar
cfbd6f84c2 cifs: Fix broken sec=ntlmv2/i sec option (try #2)
Fix sec=ntlmv2/i authentication option during mount of Samba shares.

cifs client was coding ntlmv2 response incorrectly.
All that is needed in temp as specified in MS-NLMP seciton 3.3.2

"Define ComputeResponse(NegFlg, ResponseKeyNT, ResponseKeyLM,
CHALLENGE_MESSAGE.ServerChallenge, ClientChallenge, Time, ServerName)

as
Set temp to ConcatenationOf(Responserversion, HiResponserversion,
Z(6), Time, ClientChallenge, Z(4), ServerName, Z(4)"

is MsvAvNbDomainName.

For sec=ntlmsspi, build_av_pair is not used, a blob is plucked from
type 2 response sent by the server to use in authentication.

I tested sec=ntlmv2/i and sec=ntlmssp/i mount options against
Samba (3.6) and Windows - XP, 2003 Server and 7.
They all worked.

Signed-off-by: Shirish Pargaonkar <shirishpargaonkar@gmail.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
2011-09-19 21:16:58 -05:00
Steve French
c9c7fa0064 Fix the conflict between rwpidforward and rw mount options
Both these options are started with "rw" - that's why the first one
isn't switched on even if it is specified. Fix this by adding a length
check for "rw" option check.

Cc: <stable@kernel.org>
Signed-off-by: Pavel Shilovsky <piastry@etersoft.ru>
Signed-off-by: Steve French <sfrench@us.ibm.com>
2011-09-19 21:16:20 -05:00
Pavel Shilovsky
5b980b0121 CIFS: Fix ERR_PTR dereference in cifs_get_root
move it to the beginning of the loop.

Signed-off-by: Pavel Shilovsky <piastryyy@gmail.com>
Reviewed-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
2011-09-19 21:15:03 -05:00
Jeff Layton
9438fabb73 cifs: fix possible memory corruption in CIFSFindNext
The name_len variable in CIFSFindNext is a signed int that gets set to
the resume_name_len in the cifs_search_info. The resume_name_len however
is unsigned and for some infolevels is populated directly from a 32 bit
value sent by the server.

If the server sends a very large value for this, then that value could
look negative when converted to a signed int. That would make that
value pass the PATH_MAX check later in CIFSFindNext. The name_len would
then be used as a length value for a memcpy. It would then be treated
as unsigned again, and the memcpy scribbles over a ton of memory.

Fix this by making the name_len an unsigned value in CIFSFindNext.

Cc: <stable@kernel.org>
Reported-by: Darren Lavender <dcl@hppine99.gbr.hp.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>
2011-09-19 21:14:40 -05:00
Keith Packard
7cd015a0a3 drm/i915: Enable dither whenever display bpc < frame buffer bpc
We want to enable dithering on any pipe where the frame buffer has
more color resolution than the output device.

The previous code was incorrectly clamping the frame buffer bpc to the
display bpc, effectively disabling dithering all of the time as the
computed frame buffer bpc would never be larger than the display bpc.

Signed-off-by: Keith Packard <keithp@keithp.com>
Reported-by: Oliver Hartkopp <socketcan@hartkopp.net>
Tested-by: Oliver Hartkopp <socketcan@hartkopp.net>
2011-09-19 18:02:51 -07:00