drm/amdgpu: Fix userq ttm_bo_pin and ttm_bo_unpin lockdep warnings

The ttm_bo_pin and ttm_bo_unpin warnings are resolved by moving the
doorbell bo reserve up before pin/unpin.

WARNING: CPU: 11 PID: 1818 at drivers/gpu/drm/ttm/ttm_bo.c:592 ttm_bo_pin+0x1f6/0x270 [ttm]
[  +0.000277] CPU: 11 UID: 1000 PID: 1818 Comm: Xwayland Tainted: G        W          6.12.0+ #15
[  +0.000006] Tainted: [W]=WARN
[  +0.000004] Hardware name: ASUS System Product Name/TUF GAMING B650-PLUS, BIOS 3072 12/20/2024
[  +0.000004] RIP: 0010:ttm_bo_pin+0x1f6/0x270 [ttm]
[  +0.000005] RSP: 0018:ffff88846ca879d0 EFLAGS: 00010246
[  +0.000007] RAX: 0000000000000000 RBX: ffff88810b7ca848 RCX: 0000000000000000
[  +0.000004] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[  +0.000005] RBP: ffff88846ca879e8 R08: 0000000000000000 R09: 0000000000000000
[  +0.000004] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88810b7ca848
[  +0.000004] R13: ffff88846c666250 R14: 1ffff1108d950f44 R15: ffff88846ca87aa0
[  +0.000005] FS:  00007c45ff436d00(0000) GS:ffff888409580000(0000) knlGS:0000000000000000
[  +0.000004] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  +0.000005] CR2: 00005b0c142a60e0 CR3: 000000012ce5a000 CR4: 0000000000f50ef0
[  +0.000004] PKRU: 55555554
[  +0.000004] Call Trace:
[  +0.000004]  <TASK>
[  +0.000005]  ? show_regs+0x6c/0x80
[  +0.000007]  ? __warn+0xd2/0x2d0
[  +0.000007]  ? ttm_bo_pin+0x1f6/0x270 [ttm]
[  +0.000031]  ? report_bug+0x282/0x2f0
[  +0.000012]  ? handle_bug+0x6e/0xc0
[  +0.000007]  ? exc_invalid_op+0x18/0x50
[  +0.000007]  ? asm_exc_invalid_op+0x1b/0x20
[  +0.000017]  ? ttm_bo_pin+0x1f6/0x270 [ttm]
[  +0.000014]  amdgpu_bo_pin+0x365/0x9d0 [amdgpu]
[  +0.000191]  ? __pfx_amdgpu_bo_pin+0x10/0x10 [amdgpu]
[  +0.000185]  ? drm_gem_object_lookup+0x81/0xc0
[  +0.000008]  ? kasan_save_alloc_info+0x37/0x60
[  +0.000007]  ? __kasan_kmalloc+0xc3/0xd0
[  +0.000013]  amdgpu_userqueue_get_doorbell_index+0xee/0x5f0 [amdgpu]
[  +0.000209]  amdgpu_userq_ioctl+0x6b4/0xd40 [amdgpu]
[  +0.000193]  ? __pfx_amdgpu_userq_ioctl+0x10/0x10 [amdgpu]
[  +0.000211]  ? lock_acquire+0x7c/0xc0
[  +0.000006]  ? drm_dev_enter+0x51/0x190
[  +0.000015]  drm_ioctl_kernel+0x18b/0x330
[  +0.000007]  ? __pfx_amdgpu_userq_ioctl+0x10/0x10 [amdgpu]
[  +0.000190]  ? __pfx_drm_ioctl_kernel+0x10/0x10
[  +0.000005]  ? lock_acquire+0x7c/0xc0
[  +0.000009]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? __kasan_check_write+0x14/0x30
[  +0.000005]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000011]  drm_ioctl+0x589/0xd00
[  +0.000005]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000006]  ? __pfx_amdgpu_userq_ioctl+0x10/0x10 [amdgpu]
[  +0.000194]  ? __pfx_drm_ioctl+0x10/0x10
[  +0.000006]  ? __pm_runtime_resume+0x80/0x110
[  +0.000021]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? trace_hardirqs_on+0x53/0x60
[  +0.000005]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? _raw_spin_unlock_irqrestore+0x51/0x80
[  +0.000013]  amdgpu_drm_ioctl+0xd2/0x1c0 [amdgpu]
[  +0.000185]  __x64_sys_ioctl+0x13a/0x1c0
[  +0.000010]  x64_sys_call+0x11ad/0x25f0
[  +0.000007]  do_syscall_64+0x91/0x180
[  +0.000007]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? irqentry_exit+0x77/0xb0
[  +0.000005]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? exc_page_fault+0x93/0x150
[  +0.000009]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000005] RIP: 0033:0x7c45ff924ded
[  +0.000005] RSP: 002b:00007ffff7167810 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[  +0.000008] RAX: ffffffffffffffda RBX: 00000000c0486456 RCX: 00007c45ff924ded
[  +0.000004] RDX: 00007ffff7167870 RSI: 00000000c0486456 RDI: 000000000000000b
[  +0.000004] RBP: 00007ffff7167860 R08: ffff800100000000 R09: 0000000000010000
[  +0.000005] R10: 00007ffff7167950 R11: 0000000000000246 R12: 00005b0c2a51bc48
[  +0.000004] R13: 000000000000000b R14: 0000000000000000 R15: 00007ffff7167950
[  +0.000022]  </TASK>
[  +0.000004] irq event stamp: 80693
[  +0.000004] hardirqs last  enabled at (80699): [<ffffffff86a693a9>] __up_console_sem+0x79/0xa0
[  +0.000005] hardirqs last disabled at (80704): [<ffffffff86a6938e>] __up_console_sem+0x5e/0xa0
[  +0.000005] softirqs last  enabled at (80390): [<ffffffff8687377e>] __irq_exit_rcu+0x17e/0x1d0
[  +0.000005] softirqs last disabled at (80385): [<ffffffff8687377e>] __irq_exit_rcu+0x17e/0x1d0
[  +0.000006] ---[ end trace 0000000000000000 ]---
------------------------------------------------------------------------------------------------------

[  +0.000006] WARNING: CPU: 10 PID: 1818 at drivers/gpu/drm/ttm/ttm_bo.c:611 ttm_bo_unpin+0x21f/0x2c0 [ttm]
[  +0.000280] CPU: 10 UID: 1000 PID: 1818 Comm: Xwayland Tainted: G        W          6.12.0+ #15
[  +0.000006] Tainted: [W]=WARN
[  +0.000004] Hardware name: ASUS System Product Name/TUF GAMING B650-PLUS, BIOS 3072 12/20/2024
[  +0.000004] RIP: 0010:ttm_bo_unpin+0x21f/0x2c0 [ttm]
[  +0.000005] RSP: 0018:ffff88846ca87888 EFLAGS: 00010246
[  +0.000007] RAX: 0000000000000000 RBX: ffff88810b7ca848 RCX: 0000000000000000
[  +0.000005] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
[  +0.000004] RBP: ffff88846ca878a0 R08: 0000000000000000 R09: 0000000000000000
[  +0.000004] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888164e90050
[  +0.000005] R13: ffff88846c666200 R14: 0000000000000001 R15: ffff888168402d28
[  +0.000004] FS:  00007c45ff436d00(0000) GS:ffff888409500000(0000) knlGS:0000000000000000
[  +0.000005] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  +0.000004] CR2: 00007c45f7373b20 CR3: 000000012ce5a000 CR4: 0000000000f50ef0
[  +0.000005] PKRU: 55555554
[  +0.000004] Call Trace:
[  +0.000004]  <TASK>
[  +0.000005]  ? show_regs+0x6c/0x80
[  +0.000008]  ? __warn+0xd2/0x2d0
[  +0.000007]  ? ttm_bo_unpin+0x21f/0x2c0 [ttm]
[  +0.000012]  ? report_bug+0x282/0x2f0
[  +0.000013]  ? handle_bug+0x6e/0xc0
[  +0.000006]  ? exc_invalid_op+0x18/0x50
[  +0.000008]  ? asm_exc_invalid_op+0x1b/0x20
[  +0.000017]  ? ttm_bo_unpin+0x21f/0x2c0 [ttm]
[  +0.000011]  ? ttm_bo_unpin+0x217/0x2c0 [ttm]
[  +0.000011]  amdgpu_bo_unpin+0x45/0x250 [amdgpu]
[  +0.000216]  amdgpu_userq_ioctl+0x2c3/0xd40 [amdgpu]
[  +0.000226]  ? drm_dev_exit+0x2d/0x60
[  +0.000010]  ? __pfx_amdgpu_userq_ioctl+0x10/0x10 [amdgpu]
[  +0.000201]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? lock_acquire+0x7c/0xc0
[  +0.000006]  ? drm_dev_enter+0x51/0x190
[  +0.000015]  drm_ioctl_kernel+0x18b/0x330
[  +0.000007]  ? __pfx_amdgpu_userq_ioctl+0x10/0x10 [amdgpu]
[  +0.000188]  ? __pfx_drm_ioctl_kernel+0x10/0x10
[  +0.000006]  ? lock_acquire+0x7c/0xc0
[  +0.000008]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? __kasan_check_write+0x14/0x30
[  +0.000006]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000010]  drm_ioctl+0x589/0xd00
[  +0.000005]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000006]  ? __pfx_amdgpu_userq_ioctl+0x10/0x10 [amdgpu]
[  +0.000211]  ? __pfx_drm_ioctl+0x10/0x10
[  +0.000006]  ? __pm_runtime_resume+0x80/0x110
[  +0.000020]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000006]  ? trace_hardirqs_on+0x53/0x60
[  +0.000005]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? _raw_spin_unlock_irqrestore+0x51/0x80
[  +0.000013]  amdgpu_drm_ioctl+0xd2/0x1c0 [amdgpu]
[  +0.000186]  __x64_sys_ioctl+0x13a/0x1c0
[  +0.000010]  x64_sys_call+0x11ad/0x25f0
[  +0.000007]  do_syscall_64+0x91/0x180
[  +0.000007]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? do_syscall_64+0x9d/0x180
[  +0.000007]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000010]  ? __pfx___rseq_handle_notify_resume+0x10/0x10
[  +0.000005]  ? __pfx_blkcg_maybe_throttle_current+0x10/0x10
[  +0.000013]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000009]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000008]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? syscall_exit_to_user_mode+0x95/0x260
[  +0.000008]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? do_syscall_64+0x9d/0x180
[  +0.000007]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? do_syscall_64+0x9d/0x180
[  +0.000011]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000010]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000009]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000008]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? irqentry_exit_to_user_mode+0x8b/0x260
[  +0.000007]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000006]  ? irqentry_exit+0x77/0xb0
[  +0.000004]  ? srso_alias_return_thunk+0x5/0xfbef5
[  +0.000005]  ? exc_page_fault+0x93/0x150
[  +0.000010]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  +0.000005] RIP: 0033:0x7c45ff924ded
[  +0.000005] RSP: 002b:00007ffff7168790 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[  +0.000008] RAX: ffffffffffffffda RBX: 00000000c0486456 RCX: 00007c45ff924ded
[  +0.000005] RDX: 00007ffff71687f0 RSI: 00000000c0486456 RDI: 000000000000000b
[  +0.000004] RBP: 00007ffff71687e0 R08: 00005b0c2a49b010 R09: 0000000000000007
[  +0.000004] R10: 00005b0c2a4d7140 R11: 0000000000000246 R12: 000000000000000b
[  +0.000004] R13: 00007c45ff19e5cc R14: 00005b0c2a51c538 R15: 00005b0c2a51bbd8
[  +0.000022]  </TASK>
[  +0.000005] irq event stamp: 87419
[  +0.000004] hardirqs last  enabled at (87425): [<ffffffff86a693a9>] __up_console_sem+0x79/0xa0
[  +0.000005] hardirqs last disabled at (87430): [<ffffffff86a6938e>] __up_console_sem+0x5e/0xa0
[  +0.000005] softirqs last  enabled at (87058): [<ffffffff8687377e>] __irq_exit_rcu+0x17e/0x1d0
[  +0.000006] softirqs last disabled at (87053): [<ffffffff8687377e>] __irq_exit_rcu+0x17e/0x1d0
[  +0.000005] ---[ end trace 0000000000000000 ]---

Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
index 9d1f185a815e814c13fa38bc33c5722e6946decd..80401a37af77ac11d77cb89ac063b1e97929240e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
@@ -240,17 +240,17 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
        db_obj->obj = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
        drm_gem_object_put(gobj);
 
-       /* Pin the BO before generating the index, unpin in queue destroy */
-       r = amdgpu_bo_pin(db_obj->obj, AMDGPU_GEM_DOMAIN_DOORBELL);
+       r = amdgpu_bo_reserve(db_obj->obj, true);
        if (r) {
                drm_file_err(uq_mgr->file, "[Usermode queues] Failed to pin doorbell object\n");
                goto unref_bo;
        }
 
-       r = amdgpu_bo_reserve(db_obj->obj, true);
+       /* Pin the BO before generating the index, unpin in queue destroy */
+       r = amdgpu_bo_pin(db_obj->obj, AMDGPU_GEM_DOMAIN_DOORBELL);
        if (r) {
                drm_file_err(uq_mgr->file, "[Usermode queues] Failed to pin doorbell object\n");
-               goto unpin_bo;
+               goto unresv_bo;
        }
 
        switch (db_info->queue_type) {
@@ -286,7 +286,8 @@ amdgpu_userq_get_doorbell_index(struct amdgpu_userq_mgr *uq_mgr,
 
 unpin_bo:
        amdgpu_bo_unpin(db_obj->obj);
-
+unresv_bo:
+       amdgpu_bo_unreserve(db_obj->obj);
 unref_bo:
        amdgpu_bo_unref(&db_obj->obj);
        return r;
@@ -311,9 +312,13 @@ amdgpu_userq_destroy(struct drm_file *filp, int queue_id)
                return -EINVAL;
        }
        amdgpu_userq_wait_for_last_fence(uq_mgr, queue);
-       r = amdgpu_userq_unmap_helper(uq_mgr, queue);
-       amdgpu_bo_unpin(queue->db_obj.obj);
+       r = amdgpu_bo_reserve(queue->db_obj.obj, true);
+       if (!r) {
+               amdgpu_bo_unpin(queue->db_obj.obj);
+               amdgpu_bo_unreserve(queue->db_obj.obj);
+       }
        amdgpu_bo_unref(&queue->db_obj.obj);
+       r = amdgpu_userq_unmap_helper(uq_mgr, queue);
        amdgpu_userq_cleanup(uq_mgr, queue, queue_id);
        mutex_unlock(&uq_mgr->userq_mutex);