[PATCH v2] drm/xe: Add config control for svm flush work
Matthew Brost
matthew.brost at intel.com
Fri May 2 17:09:03 UTC 2025
On Fri, May 02, 2025 at 05:00:52PM +0000, Shuicheng Lin wrote:
> Without CONFIG_DRM_XE_GPUSVM set, GPU SVM is not initialized thus below
> warning pops. Refine the flush work code to be controlled by the config
> to avoid below warning:
> "
> [ 453.132028] ------------[ cut here ]------------
> [ 453.132527] WARNING: CPU: 9 PID: 4491 at kernel/workqueue.c:4205 __flush_work+0x379/0x3a0
> [ 453.133355] Modules linked in: xe drm_ttm_helper ttm gpu_sched drm_buddy drm_suballoc_helper drm_gpuvm drm_exec
> [ 453.134352] CPU: 9 UID: 0 PID: 4491 Comm: xe_exec_mix_mod Tainted: G U W 6.15.0-rc3+ #7 PREEMPT(full)
> [ 453.135405] Tainted: [U]=USER, [W]=WARN
> ...
> [ 453.136921] RIP: 0010:__flush_work+0x379/0x3a0
> [ 453.137417] Code: 8b 45 00 48 8b 55 08 89 c7 48 c1 e8 04 83 e7 08 83 e0 0f 83 cf 02 89 c6 48 0f ba 6d 00 03 e9 d5 fe ff ff 0f 0b e9 db fd ff ff <0f> 0b 45 31 e4 e9 d1 fd ff ff 0f 0b e9 03 ff ff ff 0f 0b e9 d6 fe
> [ 453.139250] RSP: 0018:ffffc90000c67b18 EFLAGS: 00010246
> [ 453.139782] RAX: 0000000000000000 RBX: ffff888108a24000 RCX: 0000000000002000
> [ 453.140521] RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff8881016d61c8
> [ 453.141253] RBP: ffff8881016d61c8 R08: 0000000000000000 R09: 0000000000000000
> [ 453.141985] R10: 0000000000000000 R11: 0000000008a24000 R12: 0000000000000001
> [ 453.142709] R13: 0000000000000002 R14: 0000000000000000 R15: ffff888107db8c00
> [ 453.143450] FS: 00007f44853d4c80(0000) GS:ffff8882f469b000(0000) knlGS:0000000000000000
> [ 453.144276] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 453.144853] CR2: 00007f4487629228 CR3: 00000001016aa000 CR4: 00000000000406f0
> [ 453.145594] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> [ 453.146320] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> [ 453.147061] Call Trace:
> [ 453.147336] <TASK>
> [ 453.147579] ? tick_nohz_tick_stopped+0xd/0x30
> [ 453.148067] ? xas_load+0x9/0xb0
> [ 453.148435] ? xa_load+0x6f/0xb0
> [ 453.148781] __xe_vm_bind_ioctl+0xbd5/0x1500 [xe]
> [ 453.149338] ? dev_printk_emit+0x48/0x70
> [ 453.149762] ? _dev_printk+0x57/0x80
> [ 453.150148] ? drm_ioctl+0x17c/0x440
> [ 453.150544] ? __drm_dev_vprintk+0x36/0x90
> [ 453.150983] ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
> [ 453.151575] ? drm_ioctl_kernel+0x9f/0xf0
> [ 453.151998] ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
> [ 453.152560] drm_ioctl_kernel+0x9f/0xf0
> [ 453.152968] drm_ioctl+0x20f/0x440
> [ 453.153332] ? __pfx_xe_vm_bind_ioctl+0x10/0x10 [xe]
> [ 453.153893] ? ioctl_has_perm.constprop.0.isra.0+0xae/0x100
> [ 453.154489] ? memory_bm_test_bit+0x5/0x60
> [ 453.154935] xe_drm_ioctl+0x47/0x70 [xe]
> [ 453.155419] __x64_sys_ioctl+0x8d/0xc0
> [ 453.155824] do_syscall_64+0x47/0x110
> [ 453.156228] entry_SYSCALL_64_after_hwframe+0x76/0x7e
> "
>
> v2 (Matt):
> refine commit message to have more details
> add Fixes tag
> move the code to xe_svm.h which already have the config
> remove a blank line per codestyle suggestion
>
> Fixes: 63f6e480d115 ("drm/xe: Add SVM garbage collector")
> Cc: Matthew Brost <matthew.brost at intel.com>
Reviewed-by: Matthew Brost <matthew.brost at intel.com>
> Signed-off-by: Shuicheng Lin <shuicheng.lin at intel.com>
> ---
> drivers/gpu/drm/xe/xe_svm.c | 13 ++++++++++++-
> drivers/gpu/drm/xe/xe_svm.h | 6 ++++++
> drivers/gpu/drm/xe/xe_vm.c | 3 +--
> 3 files changed, 19 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> index 890f6b2f40e9..d25f02c8d7fc 100644
> --- a/drivers/gpu/drm/xe/xe_svm.c
> +++ b/drivers/gpu/drm/xe/xe_svm.c
> @@ -726,7 +726,6 @@ static int xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
> }
> #endif
>
> -
> /**
> * xe_svm_handle_pagefault() - SVM handle page fault
> * @vm: The VM.
> @@ -966,3 +965,15 @@ int xe_devm_add(struct xe_tile *tile, struct xe_vram_region *vr)
> return 0;
> }
> #endif
> +
> +/**
> + * xe_svm_flush() - SVM flush
> + * @vm: The VM.
> + *
> + * Flush all SVM actions.
> + */
> +void xe_svm_flush(struct xe_vm *vm)
> +{
> + if (xe_vm_in_fault_mode(vm))
> + flush_work(&vm->svm.garbage_collector.work);
> +}
> diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
> index 3d441eb1f7ea..2881af1e60b2 100644
> --- a/drivers/gpu/drm/xe/xe_svm.h
> +++ b/drivers/gpu/drm/xe/xe_svm.h
> @@ -96,6 +96,8 @@ static inline bool xe_svm_range_has_dma_mapping(struct xe_svm_range *range)
> #define xe_svm_notifier_unlock(vm__) \
> drm_gpusvm_notifier_unlock(&(vm__)->svm.gpusvm)
>
> +void xe_svm_flush(struct xe_vm *vm);
> +
> #else
> #include <linux/interval_tree.h>
>
> @@ -180,5 +182,9 @@ static inline void xe_svm_notifier_lock(struct xe_vm *vm)
> static inline void xe_svm_notifier_unlock(struct xe_vm *vm)
> {
> }
> +
> +static inline void xe_svm_flush(struct xe_vm *vm)
> +{
> +}
> #endif
> #endif
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index 2a9d58a4471c..91a0570abb16 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -3419,8 +3419,7 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
> }
>
> /* Ensure all UNMAPs visible */
> - if (xe_vm_in_fault_mode(vm))
> - flush_work(&vm->svm.garbage_collector.work);
> + xe_svm_flush(vm);
>
> err = down_write_killable(&vm->lock);
> if (err)
> --
> 2.25.1
>
More information about the Intel-xe
mailing list