Re: [PATCH v4 09/33] drm/xe: Add SVM init / close / fini to faulting VMs

["Ghimiray, Himal Prasad" <himal.prasad.ghimiray@xxxxxxxxx>]

On 30-01-2025 01:21, Matthew Brost wrote:
> Add SVM init / close / fini to faulting VMs. Minimual implementation
> acting as a placeholder for follow on patches.
>
> v2:
>   - Add close function
> v3:
>   - Better commit message (Thomas)
>   - Kernel doc (Thomas)
>   - Update chunk array to be unsigned long (Thomas)
>   - Use new drm_gpusvm.h header location (Thomas)
>   - Newlines between functions in xe_svm.h (Thomas)
>   - Call drm_gpusvm_driver_set_lock in init (Thomas)
>
> Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
> ---
>   drivers/gpu/drm/xe/Makefile      |  1 +
>   drivers/gpu/drm/xe/xe_svm.c      | 73 ++++++++++++++++++++++++++++++++
>   drivers/gpu/drm/xe/xe_svm.h      | 17 ++++++++
>   drivers/gpu/drm/xe/xe_vm.c       | 12 ++++++
>   drivers/gpu/drm/xe/xe_vm_types.h |  7 +++
>   5 files changed, 110 insertions(+)
>   create mode 100644 drivers/gpu/drm/xe/xe_svm.c
>   create mode 100644 drivers/gpu/drm/xe/xe_svm.h
>
> diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
> index 328aff36831b..a078a8895ec5 100644
> --- a/drivers/gpu/drm/xe/Makefile
> +++ b/drivers/gpu/drm/xe/Makefile
> @@ -97,6 +97,7 @@ xe-y += xe_bb.o \
>   	xe_sched_job.o \
>   	xe_step.o \
>   	xe_survivability_mode.o \
> +	xe_svm.o \
>   	xe_sync.o \
>   	xe_tile.o \
>   	xe_tile_sysfs.o \
> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> new file mode 100644
> index 000000000000..79da859f02b1
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_svm.c
> @@ -0,0 +1,73 @@
> +// SPDX-License-Identifier: MIT
> +/*
> + * Copyright © 2024 Intel Corporation
> + */
> +
> +#include "xe_svm.h"
> +#include "xe_vm.h"
> +#include "xe_vm_types.h"
> +
> +static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
> +			      struct drm_gpusvm_notifier *notifier,
> +			      const struct mmu_notifier_range *mmu_range)
> +{
> +	/* TODO: Implement */
> +}
> +
> +static const struct drm_gpusvm_ops gpusvm_ops = {
> +	.invalidate = xe_svm_invalidate,
> +};
> +
> +static const unsigned long fault_chunk_sizes[] = {
> +	SZ_2M,
> +	SZ_64K,
> +	SZ_4K,
> +};
> +
> +/**
> + * xe_svm_init() - SVM initialize
> + * @vm: The VM.
> + *
> + * Initialize SVM state which is embedded within the VM.
> + *
> + * Return: 0 on success, negative error code on error.
> + */
> +int xe_svm_init(struct xe_vm *vm)
> +{
> +	int err;
> +
> +	err = drm_gpusvm_init(&vm->svm.gpusvm, "Xe SVM", &vm->xe->drm,
> +			      current->mm, NULL, 0, vm->size,
> +			      SZ_512M, &gpusvm_ops, fault_chunk_sizes,
> +			      ARRAY_SIZE(fault_chunk_sizes));
> +	if (err)
> +		return err;
> +
> +	drm_gpusvm_driver_set_lock(&vm->svm.gpusvm, &vm->lock);
> +
> +	return 0;
> +}
> +
> +/**
> + * xe_svm_close() - SVM close
> + * @vm: The VM.
> + *
> + * Close SVM state (i.e., stop and flush all SVM actions).
> + */
> +void xe_svm_close(struct xe_vm *vm)
> +{
> +	xe_assert(vm->xe, xe_vm_is_closed(vm));
> +}
> +
> +/**
> + * xe_svm_fini() - SVM finalize
> + * @vm: The VM.
> + *
> + * Finalize SVM state which is embedded within the VM.
> + */
> +void xe_svm_fini(struct xe_vm *vm)
> +{
> +	xe_assert(vm->xe, xe_vm_is_closed(vm));
> +
> +	drm_gpusvm_fini(&vm->svm.gpusvm);
> +}
> diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
> new file mode 100644
> index 000000000000..49cfd938aa17
> --- /dev/null
> +++ b/drivers/gpu/drm/xe/xe_svm.h
> @@ -0,0 +1,17 @@
> +/* SPDX-License-Identifier: MIT */
> +/*
> + * Copyright © 2024 Intel Corporation
> + */
> +
> +#ifndef _XE_SVM_H_
> +#define _XE_SVM_H_
> +
> +struct xe_vm;
> +
> +int xe_svm_init(struct xe_vm *vm);
> +
> +void xe_svm_fini(struct xe_vm *vm);
> +
> +void xe_svm_close(struct xe_vm *vm);
> +
> +#endif
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index dff10dfa9c69..bc34e6738c8c 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -34,6 +34,7 @@
>   #include "xe_preempt_fence.h"
>   #include "xe_pt.h"
>   #include "xe_res_cursor.h"
> +#include "xe_svm.h"
>   #include "xe_sync.h"
>   #include "xe_trace_bo.h"
>   #include "xe_wa.h"
> @@ -1504,6 +1505,12 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
>   		}
>   	}
>   
> +	if (flags & XE_VM_FLAG_FAULT_MODE) {
> +		err = xe_svm_init(vm);
> +		if (err)
> +			goto err_close;
> +	}
> +
>   	if (number_tiles > 1)
>   		vm->composite_fence_ctx = dma_fence_context_alloc(1);
>   
> @@ -1549,6 +1556,8 @@ void xe_vm_close_and_put(struct xe_vm *vm)
>   	xe_vm_close(vm);
>   	if (xe_vm_in_preempt_fence_mode(vm))
>   		flush_work(&vm->preempt.rebind_work);
> +	if (xe_vm_in_fault_mode(vm))
> +		xe_svm_close(vm);
>   
>   	down_write(&vm->lock);
>   	for_each_tile(tile, xe, id) {
> @@ -1617,6 +1626,9 @@ void xe_vm_close_and_put(struct xe_vm *vm)
>   		xe_vma_destroy_unlocked(vma);
>   	}
>   
> +	if (xe_vm_in_fault_mode(vm))
> +		xe_svm_fini(vm);
> +
>   	up_write(&vm->lock);
>   
>   	down_write(&xe->usm.lock);
> diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
> index f6855e4fb9e6..aa075d5e7a3f 100644
> --- a/drivers/gpu/drm/xe/xe_vm_types.h
> +++ b/drivers/gpu/drm/xe/xe_vm_types.h
> @@ -6,6 +6,7 @@
>   #ifndef _XE_VM_TYPES_H_
>   #define _XE_VM_TYPES_H_
>   
> +#include <drm/drm_gpusvm.h>
>   #include <drm/drm_gpuvm.h>
>   
>   #include <linux/dma-resv.h>
> @@ -140,6 +141,12 @@ struct xe_vm {
>   	/** @gpuvm: base GPUVM used to track VMAs */
>   	struct drm_gpuvm gpuvm;
>   
> +	/** @svm: Shared virtual memory state */
> +	struct {
> +		/** @svm.gpusvm: base GPUSVM used to track fault allocations */
> +		struct drm_gpusvm gpusvm;
> +	} svm;
> +

LGTM
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@xxxxxxxxx>

>   	struct xe_device *xe;
>   
>   	/* exec queue used for (un)binding vma's */