Re: [PATCH v2 07/29] drm/xe: Add SVM init / close / fini to faulting VMs

[Matthew Brost <matthew.brost@intel.com>]

On Tue, Nov 19, 2024 at 01:13:26PM +0100, Thomas Hellström wrote:
> On Tue, 2024-10-15 at 20:24 -0700, Matthew Brost wrote:
> > Add SVM init / close / fini to faulting VMs. Minimual implementation.
> > 
> > v2:
> >  - Add close function
> > 
> > Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> > ---
> >  drivers/gpu/drm/xe/Makefile      |  1 +
> >  drivers/gpu/drm/xe/xe_svm.c      | 46
> > ++++++++++++++++++++++++++++++++
> >  drivers/gpu/drm/xe/xe_svm.h      | 15 +++++++++++
> >  drivers/gpu/drm/xe/xe_vm.c       | 12 +++++++++
> >  drivers/gpu/drm/xe/xe_vm_types.h |  7 +++++
> >  5 files changed, 81 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 8d991d4a92a5..c3e85bcfd4d1 100644
> > --- a/drivers/gpu/drm/xe/Makefile
> > +++ b/drivers/gpu/drm/xe/Makefile
> > @@ -96,6 +96,7 @@ xe-y += drm_gpusvm.o \
> >  	xe_sa.o \
> >  	xe_sched_job.o \
> >  	xe_step.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..57b740367843
> > --- /dev/null
> > +++ b/drivers/gpu/drm/xe/xe_svm.c
> > @@ -0,0 +1,46 @@
> > +// SPDX-License-Identifier: MIT
> > +/*
> > + * Copyright © 2024 Intel Corporation
> > + */
> > +
> > +#include "drm_gpusvm.h"
> > +
> > +#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 u64 fault_chunk_sizes[] = {
> > +	SZ_2M,
> > +	SZ_64K,
> > +	SZ_4K,
> > +};
> > +
> > +int xe_svm_init(struct xe_vm *vm)
> Kerneldoc + other undocumented extern funcs
> 

This whole series going to be missing kernel doc aside from GPUSVM.
Aware of the issue, will fixup all kernel doc in next rev.

Matt

> > +{
> > +	return 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));
> > +}
> > +
> > +void xe_svm_close(struct xe_vm *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..979f2322eeba
> > --- /dev/null
> > +++ b/drivers/gpu/drm/xe/xe_svm.h
> > @@ -0,0 +1,15 @@
> > +/* 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 0d887fb9de59..b11fb0ac9520 100644
> > --- a/drivers/gpu/drm/xe/xe_vm.c
> > +++ b/drivers/gpu/drm/xe/xe_vm.c
> > @@ -35,6 +35,7 @@
> >  #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"
> > @@ -1503,6 +1504,12 @@ 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);
> >  
> > @@ -1548,6 +1555,8 @@ 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) {
> > @@ -1616,6 +1625,9 @@ 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 1764781c376b..bd1c0e368238 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_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;
> > +
> >  	struct xe_device *xe;
> >  
> >  	/* exec queue used for (un)binding vma's */
> 
> Thanks,
> Thomas
>