drivers/gpu/drm/scheduler/sched_main.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

New commits:
commit be32b28967f485382fa663556811bc2ed7c4e539
Merge: 3dd924190fe9 bafaf67c42f4
Author: Kevin Brace <kevinbr...@bracecomputerlab.com>
Date:   Mon Oct 10 18:38:22 2022 -0500

    Merge tag 'drm-next-2022-10-07-1' of git://anongit.freedesktop.org/drm/drm 
into drm-next-6.1
    
    drm fix for 6.1-rc1
    
    sched:
    - revert patch causing oopses

commit bafaf67c42f4b547bf4fb329ac6dcb28b05de15e
Author: Dave Airlie <airl...@redhat.com>
Date:   Fri Oct 7 12:40:50 2022 +1000

    Revert "drm/sched: Use parent fence instead of finished"
    
    This reverts commit e4dc45b1848bc6bcac31eb1b4ccdd7f6718b3c86.
    
    This is causing instability on Linus' desktop, and I'm seeing
    oops with VK CTS runs.
    
    netconsole got me the following oops:
    [ 1234.778760] BUG: kernel NULL pointer dereference, address: 
0000000000000088
    [ 1234.778782] #PF: supervisor read access in kernel mode
    [ 1234.778787] #PF: error_code(0x0000) - not-present page
    [ 1234.778791] PGD 0 P4D 0
    [ 1234.778798] Oops: 0000 [#1] PREEMPT SMP NOPTI
    [ 1234.778803] CPU: 7 PID: 805 Comm: systemd-journal Not tainted 6.0.0+ #2
    [ 1234.778809] Hardware name: System manufacturer System Product
    Name/PRIME X370-PRO, BIOS 5603 07/28/2020
    [ 1234.778813] RIP: 0010:drm_sched_job_done.isra.0+0xc/0x140 [gpu_sched]
    [ 1234.778828] Code: aa 0f 1d ce e9 57 ff ff ff 48 89 d7 e8 9d 8f 3f
    ce e9 4a ff ff ff 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 54 55 53
    48 89 fb <48> 8b af 88 00 00 00 f0 ff 8d f0 00 00 00 48 8b 85 80 01 00
    00 f0
    [ 1234.778834] RSP: 0000:ffffabe680380de0 EFLAGS: 00010087
    [ 1234.778839] RAX: ffffffffc04e9230 RBX: 0000000000000000 RCX: 
0000000000000018
    [ 1234.778897] RDX: 00000ba278e8977a RSI: ffff953fb288b460 RDI: 
0000000000000000
    [ 1234.778901] RBP: ffff953fb288b598 R08: 00000000000000e0 R09: 
ffff953fbd98b808
    [ 1234.778905] R10: 0000000000000000 R11: ffffabe680380ff8 R12: 
ffffabe680380e00
    [ 1234.778908] R13: 0000000000000001 R14: 00000000ffffffff R15: 
ffff953fbd9ec458
    [ 1234.778912] FS:  00007f35e7008580(0000) GS:ffff95428ebc0000(0000)
    knlGS:0000000000000000
    [ 1234.778916] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    [ 1234.778919] CR2: 0000000000000088 CR3: 000000010147c000 CR4: 
00000000003506e0
    [ 1234.778924] Call Trace:
    [ 1234.778981]  <IRQ>
    [ 1234.778989]  dma_fence_signal_timestamp_locked+0x6a/0xe0
    [ 1234.778999]  dma_fence_signal+0x2c/0x50
    [ 1234.779005]  amdgpu_fence_process+0xc8/0x140 [amdgpu]
    [ 1234.779234]  sdma_v3_0_process_trap_irq+0x70/0x80 [amdgpu]
    [ 1234.779395]  amdgpu_irq_dispatch+0xa9/0x1d0 [amdgpu]
    [ 1234.779609]  amdgpu_ih_process+0x80/0x100 [amdgpu]
    [ 1234.779783]  amdgpu_irq_handler+0x1f/0x60 [amdgpu]
    [ 1234.779940]  __handle_irq_event_percpu+0x46/0x190
    [ 1234.779946]  handle_irq_event+0x34/0x70
    [ 1234.779949]  handle_edge_irq+0x9f/0x240
    [ 1234.779954]  __common_interrupt+0x66/0x100
    [ 1234.779960]  common_interrupt+0xa0/0xc0
    [ 1234.779965]  </IRQ>
    [ 1234.779968]  <TASK>
    [ 1234.779971]  asm_common_interrupt+0x22/0x40
    [ 1234.779976] RIP: 0010:finish_mkwrite_fault+0x22/0x110
    [ 1234.779981] Code: 1f 84 00 00 00 00 00 90 0f 1f 44 00 00 41 55 41
    54 55 48 89 fd 53 48 8b 07 f6 40 50 08 0f 84 eb 00 00 00 48 8b 45 30
    48 8b 18 <48> 89 df e8 66 bd ff ff 48 85 c0 74 0d 48 89 c2 83 e2 01 48
    83 ea
    [ 1234.779985] RSP: 0000:ffffabe680bcfd78 EFLAGS: 00000202
    
    Revert it for now and figure it out later.
    
    Signed-off-by: Dave Airlie <airl...@redhat.com>

diff --git a/drivers/gpu/drm/scheduler/sched_main.c 
b/drivers/gpu/drm/scheduler/sched_main.c
index 4f2395d1a791..e5a4ecde0063 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -829,7 +829,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
        job = list_first_entry_or_null(&sched->pending_list,
                                       struct drm_sched_job, list);
 
-       if (job && dma_fence_is_signaled(job->s_fence->parent)) {
+       if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
                /* remove job from pending_list */
                list_del_init(&job->list);
 
@@ -841,7 +841,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 
                if (next) {
                        next->s_fence->scheduled.timestamp =
-                               job->s_fence->parent->timestamp;
+                               job->s_fence->finished.timestamp;
                        /* start TO timer for next job */
                        drm_sched_start_timeout(sched);
                }

Reply via email to