There was once good reasons for wanting the drm to be able to use M2MF etc
on user channels, but they're not relevant anymore.  For the general
buffer move case, we've already lost by transferring between vram/sysmem
already so the context switching overhead is minimal in comparison.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Due to a race it was possible for a fence to be destroyed while another
thread was trying to synchronise with it.  If this happened in the fallback
non-semaphore path, it lead to the following oops due to fence->channel
being NULL.

BUG: unable to handle kernel NULL pointer dereference at   (null)
IP: [<fa9632ce>] nouveau_fence_update+0xe/0xe0 [nouveau]
*pde = a649c067
SMP
Modules linked in: fuse nouveau(O) ttm(O) drm_kms_helper(O) drm(O) mxm_wmi video wmi netconsole configfs lockd bnep bluetooth rfkill ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 nf_conntrack_ipv4 nf_defrag_ipv4 xt_state nf_conntrack ip6table_filter ip6_tables snd_hda_codec_realtek snd_hda_intel snd_hda_cobinfmt_misc uinput ata_generic pata_acpi pata_aet2c_algo_bit i2c_core [last unloaded: wmi]

Pid: 2255, comm: gnome-shell Tainted: G           O 3.2.0-0.rc5.git0.1.fc17.i686 #1 System manufacturer System Product Name/M2A-VM
EIP: 0060:[<fa9632ce>] EFLAGS: 00010296 CPU: 1
EIP is at nouveau_fence_update+0xe/0xe0 [nouveau]
EAX: 00000000 EBX: ddfc6dd0 ECX: dd111580 EDX: 00000000
ESI: 00003e80 EDI: dd111580 EBP: dd121d00 ESP: dd121ce8
 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
Process gnome-shell (pid: 2255, ti=dd120000 task=dd111580 task.ti=dd120000)
Stack:
 7dc86c76 00000000 00003e80 ddfc6dd0 00003e80 dd111580 dd121d0c fa96371f
 00000000 dd121d3c fa963773 dd111580 01000246 000ec53d 00000000 ddfc6dd0
 00001f40 00000000 ddfc6dd0 00000010 dc7df840 dd121d6c fa9639a0 00000000
Call Trace:
 [<fa96371f>] __nouveau_fence_signalled+0x1f/0x30 [nouveau]
 [<fa963773>] __nouveau_fence_wait+0x43/0xd0 [nouveau]
 [<fa9639a0>] nouveau_fence_sync+0x1a0/0x1c0 [nouveau]
 [<fa964046>] validate_list+0x176/0x300 [nouveau]
 [<f7d9c9c0>] ? ttm_bo_mem_put+0x30/0x30 [ttm]
 [<fa964b8a>] nouveau_gem_ioctl_pushbuf+0x48a/0xfd0 [nouveau]
 [<c0406481>] ? die+0x31/0x80
 [<f7c93d98>] drm_ioctl+0x388/0x490 [drm]
 [<c0406481>] ? die+0x31/0x80
 [<fa964700>] ? nouveau_gem_ioctl_new+0x150/0x150 [nouveau]
 [<c0635c7b>] ? file_has_perm+0xcb/0xe0
 [<f7c93a10>] ? drm_copy_field+0x80/0x80 [drm]
 [<c0564f56>] do_vfs_ioctl+0x86/0x5b0
 [<c0406481>] ? die+0x31/0x80
 [<c0635f22>] ? selinux_file_ioctl+0x62/0x130
 [<c0554f30>] ? fget_light+0x30/0x340
 [<c05654ef>] sys_ioctl+0x6f/0x80
 [<c099e3a4>] syscall_call+0x7/0xb
 [<c0406481>] ? die+0x31/0x80
 [<c0406481>] ? die+0x31/0x80
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>
Cc: stable@vger.kernel.org

This reverts commit dfadbbdb.

Further upstream discussion between Marek and Thomas decided this wasn't
fully baked and needed further work, so revert it before it hits mainline.
Signed-off-by: NDave Airlie <airlied@redhat.com>

Sometimes we want to know whether a buffer is busy and wait for it (bo_wait).
However, sometimes it would be more useful to be able to query whether
a buffer is busy and being either read or written, and wait until it's stopped
being either read or written. The point of this is to be able to avoid
unnecessary waiting, e.g. if a GPU has written something to a buffer and is now
reading that buffer, and a CPU wants to map that buffer for read, it needs to
only wait for the last write. If there were no write, there wouldn't be any
waiting needed.

This, or course, requires user space drivers to send read/write flags
with each relocation (like we have read/write domains in radeon, so we can
actually use those for something useful now).

Now how this patch works:

The read/write flags should passed to ttm_validate_buffer. TTM maintains
separate sync objects of the last read and write for each buffer, in addition
to the sync object of the last use of a buffer. ttm_bo_wait then operates
with one the sync objects.
Signed-off-by: NMarek Olšák <maraeo@gmail.com>
Reviewed-by: NJerome Glisse <jglisse@redhat.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Signed-off-by: NMarcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

GPU virtual addresses are constant now so this should never be getting hit
anyway and userspace shouldn't break from them being ignored.

This is being done in preference to teaching the code how to deal with BOs
that exist at different virtual addresses within separate VMs.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Userspace hasn't passed us a channel_hint for a long long time now, and
there isn't actually a need to do so anymore anyway.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Removes the need to disable IRQs to lookup channel struct on every pushbuf
ioctl, among others.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NJan Engelhardt <jengelh@medozas.de>
Signed-off-by: NDave Airlie <airlied@redhat.com>

When "buffer in list" check does not pass, don't free validation lists - they were
not initialized yet.

Fixes this oops:

[drm] nouveau 0000:02:00.0: push 105 buffer not in list
BUG: unable to handle kernel NULL pointer dereference at 000000000000057c
IP: [<ffffffff81236aa4>] do_raw_spin_lock+0x14/0x13c
PGD 1ac6cb067 PUD 1aaa52067 PMD 0
CPU 0
Modules linked in: nouveau ttm drm_kms_helper snd_hda_codec_realtek snd_hda_intel snd_hda_codec

Pid: 6265, comm: OilRush_x86 Not tainted 2.6.38-rc6-nv+ #632 System manufacturer System Product Name/P6T SE
RIP: 0010:[<ffffffff81236aa4>]  [<ffffffff81236aa4>] do_raw_spin_lock+0x14/0x13c
(...)
Process OilRush_x86 (pid: 6265, threadinfo ffff8801a6aee000, task ffff8801a26c0000)
 0000000000000000 ffff8801ac74c618 0000000000000000 0000000000000578
 0000000000000000 ffff8801ac74c618 0000000000000000 ffff8801bd9d0000
 [<ffffffff81417f78>] _raw_spin_lock+0x1e/0x22
 [<ffffffffa00a2746>] nouveau_bo_fence+0x2e/0x60 [nouveau]
 [<ffffffffa00a540b>] validate_fini_list+0x35/0xeb [nouveau]
 [<ffffffffa00a54d3>] validate_fini+0x12/0x31 [nouveau]
 [<ffffffffa00a6386>] nouveau_gem_ioctl_pushbuf+0xe94/0xf6b [nouveau]
 [<ffffffff8141ac56>] ? sub_preempt_count+0x9e/0xb2
 [<ffffffff81417e94>] ? _raw_spin_unlock_irqrestore+0x30/0x4d
 [<ffffffff8105dea2>] ? __wake_up+0x3f/0x48
 [<ffffffff812aebb4>] drm_ioctl+0x289/0x361
 [<ffffffff8141ac56>] ? sub_preempt_count+0x9e/0xb2
 [<ffffffffa00a54f2>] ? nouveau_gem_ioctl_pushbuf+0x0/0xf6b [nouveau]
 [<ffffffff8141ac56>] ? sub_preempt_count+0x9e/0xb2
 [<ffffffffa010caa2>] nouveau_compat_ioctl+0x16/0x1c [nouveau]
 [<ffffffff81142c0d>] compat_sys_ioctl+0x1c8/0x12d7
 [<ffffffff814179ca>] ? trace_hardirqs_off_thunk+0x3a/0x6c
 [<ffffffff81058099>] sysenter_dispatch+0x7/0x30
 [<ffffffff8141798e>] ? trace_hardirqs_on_thunk+0x3a/0x3c
RIP  [<ffffffff81236aa4>] do_raw_spin_lock+0x14/0x13c
 RSP <ffff8801a6aefb88>
---[ end trace 0014d5d93e6147e1 ]---

Additionally, don't call validate_fini twice in case of validation failure.
Signed-off-by: NMarcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: NMaarten Maathuis <madman2003@gmail.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Upcoming patches are going to enable full support for buffers that keep
a constant GPU virtual address whenever they're validated for use by
the GPU.

In order for this to work properly while keeping support for large pages,
we need to know if it's ever going to be possible for a buffer to end
up in GART, and if so, disable large pages for the buffer's VMA.

This is a new restriction that's not present in earlier kernel's, but
should not break userspace as the current code never attempts to validate
buffers into a memtype other than it was created with.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

'mappable' isn't really used at all, nor is it necessary anymore as the
bo code is capable of moving buffers to mappable vram as required.

'no_vm' isn't necessary anymore either, any places that don't want to be
mapped into a GPU address space should allocate the VRAM directly instead.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

NVC0 will be able to share some of nv50's paths this way.  This also makes
it the card-specific vram code responsible for deciding if a given set
of tile_flags is valid, rather than duplicating the allowed types in
nv50_vram.c and nouveau_gem.c
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

This will be used later to fixup bo.offset with a buffer's fixed GPU
virtual address.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

nv0x-nv4x should be mostly fine, nv50 doesn't work yet.
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

nouveau_fence_* functions are not type safe, which could lead to bugs.
Additionally every use of nouveau_fence_unref had to cast struct
nouveau_fence to void **.
Fix it by renaming old functions and creating static inline functions with
new prototypes. We still need old functions, because we pass function
pointers to ttm.
As we are wrapping functions, drop unused "void *arg" parameter where possible.
Signed-off-by: NMarcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

No other driver uses this, and userspace should be responsible for handling
locking between them if they share BOs.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

The bo lock used only to protect the bo sync object members, and since it
is a per bo lock, fencing a buffer list will see a lot of locks and unlocks.
Replace it with a per-device lock that protects the sync object members on
*all* bos. Reading and setting these members will always be very quick, so
the risc of heavy lock contention is microscopic. Note that waiting for
sync objects will always take place outside of this lock.

The bo device fence lock will eventually be replaced with a seqlock /
rcu mechanism so we can determine that a bo is idle under a
rcu / read seqlock.

However this change will allow us to batch fencing and unreserving of
buffers with a minimal amount of locking.
Signed-off-by: NThomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: NJerome Glisse <j.glisse@gmail.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

This will be needed for Z compression and to take smarter placement
decisions.
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Acked-by: NBen Skeggs <bskeggs@redhat.com>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Mainly to make room for inter-channel sync.
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

There were lots of places being inconsistent since handle count
looked like a kref but it really wasn't.

Fix this my just making handle count an atomic on the object,
and have it increase the normal object kref.

Now i915/radeon/nouveau drivers can drop the normal reference on
userspace object creation, and have the handle hold it.

This patch fixes a memory leak or corruption on unload, because
the driver had no way of knowing if a handle had been actually
added for this object, and the fbcon object needed to know this
to clean itself up properly.
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDave Airlie <airlied@redhat.com>

We don't need it and it can lead to lock order inversions with respect
to drm_global_mutex, potentially causing dead locks.
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

If we keep hold of the mutex here, the process which currently holds the
buffer object will never be able to release it, causing a deadlock.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

The "return" command is buggy on the original nv20, it jumps back to
the caller address as expected, but it doesn't clear the subroutine
active bit making the subsequent pushbuf calls fail with a "stack"
overflow.
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

When VRAM is running out it's possible that the client's push buffers get
evicted to main memory.  When they're validated back in, the GPU may
be used for the copy back to VRAM, but the existing synchronisation code
only deals with inter-channel sync, not sync between PFIFO and PGRAPH on
the same channel.  This leads to PFIFO fetching from command buffers that
haven't quite been copied by PGRAPH yet.

This patch marks push buffers as so, and forces any GPU-assisted buffer
moves to be done on a different channel, which triggers the correct
synchronisation to happen before we submit them.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

This is consistent with trying to access a filename that not exist
within a directory which is a good analogy here. The main reason for the
change is that it is easy to confuse the error code of EBADF as an
performing an ioctl on an invalid file descriptor (rather than an
unknown object).
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Nouveau will no longer load at all if card initialisation fails, so all
these checks are unnecessary.
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

When drivers embed the core gem object into their own structures,
they'll have to do this. Temporarily this results in an ugly

kfree(gem_obj);

in every gem driver.
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: NEric Anholt <eric@anholt.net>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Previously we were filling it the same as "placements", but in some
cases there're valid alternatives that we were ignoring completely.
Keeping a back-up memory type helps on several low-mem situations.
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>

There is case where we want to be able to wait only for the
GPU while not waiting for other buffer to be unreserved. This
patch split the no_wait argument all the way down in the whole
ttm path so that upper level can decide on what to wait on or
not.

[airlied: squashed these 4 for bisectability reasons.]
drm/radeon/kms: update to TTM no_wait splitted argument
drm/nouveau: update to TTM no_wait splitted argument
drm/vmwgfx: update to TTM no_wait splitted argument
[vmwgfx patch: Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>]
Signed-off-by: NJerome Glisse <jglisse@redhat.com>
Acked-by: NThomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: NDave Airlie <airlied@redhat.com>

Found by sparse.
Signed-off-by: NLuca Barbieri <luca@luca-barbieri.com>
Signed-off-by: NFrancisco Jerez <currojerez@riseup.net>
Signed-off-by: NBen Skeggs <bskeggs@redhat.com>