[Intel-xe] [PATCH v14 09/10] drm/xe: drop xe_device_mem_access_get() from invalidation_vma

Matthew Auld matthew.auld at intel.com
Mon Jul 17 11:25:12 UTC 2023


Lockdep gives the following splat:

[  594.158863] ffff888140da53f0 (&vm->userptr.notifier_lock){++++}-{3:3}, at: vma_userptr_invalidate+0xeb/0x330 [xe]
[  594.158921]
               but task is already holding lock:
[  594.158926] ffffffff82761940
(mmu_notifier_invalidate_range_start){+.+.}-{0:0}, at: unmap_vmas+0x0/0x1c0
[  594.158941]
               which lock already depends on the new lock.

[  594.158947]
               the existing dependency chain (in reverse order) is:
[  594.158953]
               -> #5 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}:
[  594.158961]        fs_reclaim_acquire+0x68/0xd0
[  594.158969]        __kmem_cache_alloc_node+0x2c/0x1b0
[  594.158975]        kmalloc_node_trace+0x1d/0xb0
[  594.158983]        alloc_worker+0x18/0x50
[  594.158989]        init_rescuer.part.0+0x13/0xa0
[  594.158995]        workqueue_init+0xdf/0x210
[  594.159001]        kernel_init_freeable+0x5c/0x2f0
[  594.159009]        kernel_init+0x11/0x1a0
[  594.159017]        ret_from_fork+0x29/0x50
[  594.159023]
               -> #4 (fs_reclaim){+.+.}-{0:0}:
[  594.159031]        fs_reclaim_acquire+0xa0/0xd0
[  594.159037]        __kmem_cache_alloc_node+0x2c/0x1b0
[  594.159042]        kmalloc_trace+0x20/0xb0
[  594.159048]        acpi_device_add+0x25a/0x3f0
[  594.159056]        acpi_add_single_object+0x387/0x750
[  594.159063]        acpi_bus_check_add+0x108/0x280
[  594.159069]        acpi_bus_scan+0x34/0xf0
[  594.159075]        acpi_scan_init+0xed/0x2b0
[  594.159082]        acpi_init+0x21e/0x520
[  594.159087]        do_one_initcall+0x53/0x260
[  594.159092]        kernel_init_freeable+0x18a/0x2f0
[  594.159099]        kernel_init+0x11/0x1a0
[  594.159105]        ret_from_fork+0x29/0x50
[  594.159110]
               -> #3 (acpi_device_lock){+.+.}-{3:3}:
[  594.159117]        __mutex_lock+0x95/0xd10
[  594.159122]        acpi_enable_wakeup_device_power+0x30/0x120
[  594.159130]        __acpi_device_wakeup_enable+0x34/0x110
[  594.159138]        acpi_pm_set_device_wakeup+0x55/0x140
[  594.159143]        __pci_enable_wake+0x56/0xb0
[  594.159150]        pci_finish_runtime_suspend+0x35/0x80
[  594.159157]        pci_pm_runtime_suspend+0xb5/0x1a0
[  594.159162]        __rpm_callback+0x3c/0x110
[  594.159170]        rpm_callback+0x58/0x70
[  594.159176]        rpm_suspend+0x15c/0x6f0
[  594.159182]        pm_runtime_work+0x9b/0xb0
[  594.159188]        process_one_work+0x263/0x520
[  594.159195]        worker_thread+0x4d/0x3b0
[  594.159200]        kthread+0xeb/0x120
[  594.159206]        ret_from_fork+0x29/0x50
[  594.159211]
               -> #2 (acpi_wakeup_lock){+.+.}-{3:3}:
[  594.159218]        __mutex_lock+0x95/0xd10
[  594.159223]        acpi_pm_set_device_wakeup+0x7a/0x140
[  594.159228]        __pci_enable_wake+0x77/0xb0
[  594.159234]        pci_pm_runtime_resume+0x70/0xd0
[  594.159240]        __rpm_callback+0x3c/0x110
[  594.159246]        rpm_callback+0x58/0x70
[  594.159252]        rpm_resume+0x50d/0x7a0
[  594.159258]        rpm_resume+0x267/0x7a0
[  594.159264]        __pm_runtime_resume+0x45/0x90
[  594.159270]        xe_pm_runtime_resume_and_get+0x12/0x50 [xe]
[  594.159314]        xe_device_mem_access_get+0x97/0xc0 [xe]
[  594.159346]        hw_engines+0x65/0xf0 [xe]
[  594.159380]        seq_read_iter+0x10d/0x4b0
[  594.159385]        seq_read+0x9e/0xd0
[  594.159390]        full_proxy_read+0x4e/0x80
[  594.159396]        vfs_read+0xb6/0x310
[  594.159401]        ksys_read+0x60/0xe0
[  594.159406]        do_syscall_64+0x38/0x90
[  594.159413]        entry_SYSCALL_64_after_hwframe+0x72/0xdc
[  594.159419]
               -> #1 (&xe->mem_access.lock){+.+.}-{3:3}:
[  594.159427]        xe_device_mem_access_get+0x43/0xc0 [xe]
[  594.159457]        xe_gt_tlb_invalidation_vma+0x53/0x190 [xe]
[  594.159490]        invalidation_fence_init+0x1d2/0x2c0 [xe]
[  594.159529]        __xe_pt_unbind_vma+0x151/0x4e0 [xe]
[  594.159564]        vm_bind_ioctl+0x48a/0xae0 [xe]
[  594.159602]        async_op_work_func+0x20c/0x530 [xe]
[  594.159634]        process_one_work+0x263/0x520
[  594.159640]        worker_thread+0x4d/0x3b0
[  594.159646]        kthread+0xeb/0x120
[  594.159650]        ret_from_fork+0x29/0x50
[  594.159655]
               -> #0 (&vm->userptr.notifier_lock){++++}-{3:3}:
[  594.159663]        __lock_acquire+0x16fa/0x2850
[  594.159670]        lock_acquire+0xd2/0x2e0
[  594.159676]        down_write+0x36/0xd0
[  594.159681]        vma_userptr_invalidate+0xeb/0x330 [xe]
[  594.159714]        __mmu_notifier_invalidate_range_start+0x239/0x2a0
[  594.159722]        unmap_vmas+0x1ac/0x1c0
[  594.159727]        unmap_region+0xb5/0x120
[  594.159732]        do_vmi_align_munmap+0x2be/0x430
[  594.159739]        do_vmi_munmap+0xea/0x120
[  594.159744]        __vm_munmap+0x9c/0x160
[  594.159750]        __x64_sys_munmap+0x12/0x20
[  594.159756]        do_syscall_64+0x38/0x90
[  594.159761]        entry_SYSCALL_64_after_hwframe+0x72/0xdc
[  594.159768]
               other info that might help us debug this:

[  594.159773] Chain exists of:
                 &vm->userptr.notifier_lock --> fs_reclaim -->
mmu_notifier_invalidate_range_start

[  594.159785]  Possible unsafe locking scenario:

[  594.159790]        CPU0                    CPU1
[  594.159794]        ----                    ----
[  594.159797]   lock(mmu_notifier_invalidate_range_start);
[  594.159802]                                lock(fs_reclaim);
[  594.159808]
lock(mmu_notifier_invalidate_range_start);
[  594.159814]   lock(&vm->userptr.notifier_lock);
[  594.159819]

The VM should be holding a mem_access.ref so this looks like it should
be a false positive and we can just drop the explicit mem_access in
xe_gt_tlb_invalidation().  The GGTT invalidation path also takes care to
hold mem_access.ref so should be fine there also, and we already assert
that we hold access.ref for the GuC communication underneath.

Signed-off-by: Matthew Auld <matthew.auld at intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
Cc: Thomas Hellström <thomas.hellstrom at linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost at intel.com>
---
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index e2b85559257c..cad0ade595ec 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -248,7 +248,7 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
 	struct xe_device *xe = gt_to_xe(gt);
 #define MAX_TLB_INVALIDATION_LEN	7
 	u32 action[MAX_TLB_INVALIDATION_LEN];
-	int len = 0, ret;
+	int len = 0;
 
 	XE_BUG_ON(!vma);
 
@@ -302,11 +302,7 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
 
 	XE_BUG_ON(len > MAX_TLB_INVALIDATION_LEN);
 
-	xe_device_mem_access_get(xe);
-	ret = send_tlb_invalidation(&gt->uc.guc, fence, action, len);
-	xe_device_mem_access_put(xe);
-
-	return ret;
+	return send_tlb_invalidation(&gt->uc.guc, fence, action, len);
 }
 
 /**
-- 
2.41.0



More information about the Intel-xe mailing list