linux/drivers/gpu/drm/i915/i915_gem_evict.c
Daniel Vetter b93dab6e9d drm/i915: More vma fixups around unbind/destroy
The important bugfix here is that we must not unlink the vma when
we keep it around as a placeholder for the execbuf code. Since then we
won't find it again when execbuf gets interrupt and restarted and
create a 2nd vma. And since the code as-is isn't fit yet to deal with
more than one vma, hilarity ensues.

Specifically the dma map/unmap of the sg table isn't adjusted for
multiple vmas yet and will blow up like this:

BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
IP: [<ffffffffa008fb37>] i915_gem_gtt_finish_object+0x73/0xc8 [i915]
PGD 56bb5067 PUD ad3dd067 PMD 0
Oops: 0000 [#1] SMP
Modules linked in: tcp_lp ppdev parport_pc lp parport ipv6 dm_mod dcdbas snd_hda_codec_hdmi pcspkr snd_hda_codec_realtek serio_raw i2c_i801 iTCO_wdt iTCO_vendor_support snd_hda_intel snd_hda_codec lpc_ich snd_hwdep mfd_core snd_pcm snd_page_alloc snd_timer snd soundcore acpi_cpufreq i915 video button drm_kms_helper drm mperf freq_table
CPU: 1 PID: 16650 Comm: fbo-maxsize Not tainted 3.11.0-rc4_nightlytop_d93f59_debug_20130814_+ #6957
Hardware name: Dell Inc. OptiPlex 9010/03JR84, BIOS A01 05/04/2012
task: ffff8800563b3f00 ti: ffff88004bdf4000 task.ti: ffff88004bdf4000
RIP: 0010:[<ffffffffa008fb37>]  [<ffffffffa008fb37>] i915_gem_gtt_finish_object+0x73/0xc8 [i915]
RSP: 0018:ffff88004bdf5958  EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff8801135e0000 RCX: ffff8800ad3bf8e0
RDX: ffff8800ad3bf8e0 RSI: 0000000000000000 RDI: ffff8801007ee780
RBP: ffff88004bdf5978 R08: ffff8800ad3bf8e0 R09: 0000000000000000
R10: ffffffff86ca1810 R11: ffff880036a17101 R12: ffff8801007ee780
R13: 0000000000018001 R14: ffff880118c4e000 R15: ffff8801007ee780
FS:  00007f401a0ce740(0000) GS:ffff88011e280000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000008 CR3: 000000005635c000 CR4: 00000000001407e0
Stack:
 ffff8801007ee780 ffff88005c253180 0000000000018000 ffff8801135e0000
 ffff88004bdf59a8 ffffffffa0088e55 0000000000000011 ffff8801007eec00
 0000000000018000 ffff880036a17101 ffff88004bdf5a08 ffffffffa0089026
Call Trace:
 [<ffffffffa0088e55>] i915_vma_unbind+0xdf/0x1ab [i915]
 [<ffffffffa0089026>] __i915_gem_shrink+0x105/0x177 [i915]
 [<ffffffffa0089452>] i915_gem_object_get_pages_gtt+0x108/0x309 [i915]
 [<ffffffffa0085ba9>] i915_gem_object_get_pages+0x61/0x90 [i915]
 [<ffffffffa008f22b>] ? gen6_ppgtt_insert_entries+0x103/0x125 [i915]
 [<ffffffffa008a113>] i915_gem_object_pin+0x1fa/0x5df [i915]
 [<ffffffffa008cdfe>] i915_gem_execbuffer_reserve_object.isra.6+0x8d/0x1bc [i915]
 [<ffffffffa008d156>] i915_gem_execbuffer_reserve+0x229/0x367 [i915]
 [<ffffffffa008dbf6>] i915_gem_do_execbuffer.isra.12+0x4dc/0xf3a [i915]
 [<ffffffff810fc823>] ? might_fault+0x40/0x90
 [<ffffffffa008eb89>] i915_gem_execbuffer2+0x187/0x222 [i915]
 [<ffffffffa000971c>] drm_ioctl+0x308/0x442 [drm]
 [<ffffffffa008ea02>] ? i915_gem_execbuffer+0x3ae/0x3ae [i915]
 [<ffffffff817db156>] ? __do_page_fault+0x3dd/0x481
 [<ffffffff8112fdba>] vfs_ioctl+0x26/0x39
 [<ffffffff811306a2>] do_vfs_ioctl+0x40e/0x451
 [<ffffffff817deda7>] ? sysret_check+0x1b/0x56
 [<ffffffff8113073c>] SyS_ioctl+0x57/0x87
 [<ffffffff8135bbfe>] ? trace_hardirqs_on_thunk+0x3a/0x3f
 [<ffffffff817ded82>] system_call_fastpath+0x16/0x1b
Code: 48 c7 c6 84 30 0e a0 31 c0 e8 d0 e9 f7 ff bf c6 a7 00 00 e8 07 af 2c e1 41 f6 84 24 03 01 00 00 10 75 44 49 8b 84 24 08 01 00 00 <8b> 50 08 48 8b 30 49 8b 86 b0 04 00 00 48 89 c7 48 81 c7 98 00
RIP  [<ffffffffa008fb37>] i915_gem_gtt_finish_object+0x73/0xc8 [i915]
 RSP <ffff88004bdf5958>
CR2: 0000000000000008

As a consequence we need to change the "only one vma for now" check in
vma_unbind - since vma_destroy isn't always called the obj->vma_list
might not be empty. Instead check that the vma list is singular at the
beginning of vma_unbind. This is also more symmetric with bind_to_vm.

This fixes the igt/gem_evict_everything|alignment testcases.

v2:
- Add a paranoid WARN to mark_free in the eviction code to make sure
  we never try to evict a vma used by the execbuf code right now.
- Move the check for a temporary execbuf vma into vma_destroy -
  otherwise the failure path cleanup in bind_to_vm will blow up.

Our first attempting at fixing this was

commit 1be81a2f2cfd8789a627401d470423358fba2d76
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date:   Tue Aug 20 12:56:40 2013 +0100

    drm/i915: Don't destroy the vma placeholder during execbuffer reservation

Squash with this when merging!

v3: Improvements suggested in Chris' review:
- Move the WARN_ON in vma_destroy that checks for vmas with an drm_mm
  allocation before the early return.
- Bail out if we hit the WARN in mark_free to hopefully make the
  kernel survive for long enough to capture it.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ben Widawsky <ben@bwidawsk.net>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68298
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68171
Tested-by: lu hua <huax.lu@intel.com> (v2)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-09-04 17:34:42 +02:00

198 lines
5.8 KiB
C

/*
* Copyright © 2008-2010 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*
* Authors:
* Eric Anholt <eric@anholt.net>
* Chris Wilson <chris@chris-wilson.co.uuk>
*
*/
#include <drm/drmP.h>
#include "i915_drv.h"
#include <drm/i915_drm.h>
#include "i915_trace.h"
static bool
mark_free(struct i915_vma *vma, struct list_head *unwind)
{
if (vma->obj->pin_count)
return false;
if (WARN_ON(!list_empty(&vma->exec_list)))
return false;
list_add(&vma->exec_list, unwind);
return drm_mm_scan_add_block(&vma->node);
}
int
i915_gem_evict_something(struct drm_device *dev, struct i915_address_space *vm,
int min_size, unsigned alignment, unsigned cache_level,
bool mappable, bool nonblocking)
{
drm_i915_private_t *dev_priv = dev->dev_private;
struct list_head eviction_list, unwind_list;
struct i915_vma *vma;
int ret = 0;
trace_i915_gem_evict(dev, min_size, alignment, mappable);
/*
* The goal is to evict objects and amalgamate space in LRU order.
* The oldest idle objects reside on the inactive list, which is in
* retirement order. The next objects to retire are those on the (per
* ring) active list that do not have an outstanding flush. Once the
* hardware reports completion (the seqno is updated after the
* batchbuffer has been finished) the clean buffer objects would
* be retired to the inactive list. Any dirty objects would be added
* to the tail of the flushing list. So after processing the clean
* active objects we need to emit a MI_FLUSH to retire the flushing
* list, hence the retirement order of the flushing list is in
* advance of the dirty objects on the active lists.
*
* The retirement sequence is thus:
* 1. Inactive objects (already retired)
* 2. Clean active objects
* 3. Flushing list
* 4. Dirty active objects.
*
* On each list, the oldest objects lie at the HEAD with the freshest
* object on the TAIL.
*/
INIT_LIST_HEAD(&unwind_list);
if (mappable) {
BUG_ON(!i915_is_ggtt(vm));
drm_mm_init_scan_with_range(&vm->mm, min_size,
alignment, cache_level, 0,
dev_priv->gtt.mappable_end);
} else
drm_mm_init_scan(&vm->mm, min_size, alignment, cache_level);
/* First see if there is a large enough contiguous idle region... */
list_for_each_entry(vma, &vm->inactive_list, mm_list) {
if (mark_free(vma, &unwind_list))
goto found;
}
if (nonblocking)
goto none;
/* Now merge in the soon-to-be-expired objects... */
list_for_each_entry(vma, &vm->active_list, mm_list) {
if (mark_free(vma, &unwind_list))
goto found;
}
none:
/* Nothing found, clean up and bail out! */
while (!list_empty(&unwind_list)) {
vma = list_first_entry(&unwind_list,
struct i915_vma,
exec_list);
ret = drm_mm_scan_remove_block(&vma->node);
BUG_ON(ret);
list_del_init(&vma->exec_list);
}
/* We expect the caller to unpin, evict all and try again, or give up.
* So calling i915_gem_evict_everything() is unnecessary.
*/
return -ENOSPC;
found:
/* drm_mm doesn't allow any other other operations while
* scanning, therefore store to be evicted objects on a
* temporary list. */
INIT_LIST_HEAD(&eviction_list);
while (!list_empty(&unwind_list)) {
vma = list_first_entry(&unwind_list,
struct i915_vma,
exec_list);
if (drm_mm_scan_remove_block(&vma->node)) {
list_move(&vma->exec_list, &eviction_list);
drm_gem_object_reference(&vma->obj->base);
continue;
}
list_del_init(&vma->exec_list);
}
/* Unbinding will emit any required flushes */
while (!list_empty(&eviction_list)) {
struct drm_gem_object *obj;
vma = list_first_entry(&eviction_list,
struct i915_vma,
exec_list);
obj = &vma->obj->base;
list_del_init(&vma->exec_list);
if (ret == 0)
ret = i915_vma_unbind(vma);
drm_gem_object_unreference(obj);
}
return ret;
}
int
i915_gem_evict_everything(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
struct i915_address_space *vm;
struct i915_vma *vma, *next;
bool lists_empty = true;
int ret;
list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
lists_empty = (list_empty(&vm->inactive_list) &&
list_empty(&vm->active_list));
if (!lists_empty)
lists_empty = false;
}
if (lists_empty)
return -ENOSPC;
trace_i915_gem_evict_everything(dev);
/* The gpu_idle will flush everything in the write domain to the
* active list. Then we must move everything off the active list
* with retire requests.
*/
ret = i915_gpu_idle(dev);
if (ret)
return ret;
i915_gem_retire_requests(dev);
/* Having flushed everything, unbind() should never raise an error */
list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
list_for_each_entry_safe(vma, next, &vm->inactive_list, mm_list)
if (vma->obj->pin_count == 0)
WARN_ON(i915_vma_unbind(vma));
}
return 0;
}