1 files changed, 63 insertions, 26 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index e44376c2ecdc..b059a77b6081 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -33,6 +33,7 @@
 #include "kfd_priv.h"
 #include "kfd_svm.h"
 #include "kfd_migrate.h"
+#include "kfd_smi_events.h"
 
 #ifdef dev_fmt
 #undef dev_fmt
@@ -402,8 +403,9 @@ out:
 static long
 svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			struct vm_area_struct *vma, uint64_t start,
-			uint64_t end)
+			uint64_t end, uint32_t trigger)
 {
+	struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms);
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
 	struct kfd_process_device *pdd;
 	struct dma_fence *mfence = NULL;
@@ -430,6 +432,11 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	migrate.dst = migrate.src + npages;
 	scratch = (dma_addr_t *)(migrate.dst + npages);
 
+	kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid,
+				      start >> PAGE_SHIFT, end >> PAGE_SHIFT,
+				      0, adev->kfd.dev->id, prange->prefetch_loc,
+				      prange->preferred_loc, trigger);
+
 	r = migrate_vma_setup(&migrate);
 	if (r) {
 		dev_err(adev->dev, "%s: vma setup fail %d range [0x%lx 0x%lx]\n",
@@ -458,6 +465,10 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 	svm_migrate_copy_done(adev, mfence);
 	migrate_vma_finalize(&migrate);
 
+	kfd_smi_event_migration_end(adev->kfd.dev, p->lead_thread->pid,
+				    start >> PAGE_SHIFT, end >> PAGE_SHIFT,
+				    0, adev->kfd.dev->id, trigger);
+
 	svm_range_dma_unmap(adev->dev, scratch, 0, npages);
 	svm_range_free_dma_mappings(prange);
 
@@ -479,6 +490,7 @@ out:
  * @prange: range structure
  * @best_loc: the device to migrate to
  * @mm: the process mm structure
+ * @trigger: reason of migration
  *
  * Context: Process context, caller hold mmap read lock, svms lock, prange lock
  *
@@ -487,7 +499,7 @@ out:
  */
 static int
 svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
-			struct mm_struct *mm)
+			struct mm_struct *mm, uint32_t trigger)
 {
 	unsigned long addr, start, end;
 	struct vm_area_struct *vma;
@@ -524,7 +536,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 			break;
 
 		next = min(vma->vm_end, end);
-		r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next);
+		r = svm_migrate_vma_to_vram(adev, prange, vma, addr, next, trigger);
 		if (r < 0) {
 			pr_debug("failed %ld to migrate\n", r);
 			break;
@@ -655,8 +667,10 @@ out_oom:
  */
 static long
 svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
-		       struct vm_area_struct *vma, uint64_t start, uint64_t end)
+		       struct vm_area_struct *vma, uint64_t start, uint64_t end,
+		       uint32_t trigger)
 {
+	struct kfd_process *p = container_of(prange->svms, struct kfd_process, svms);
 	uint64_t npages = (end - start) >> PAGE_SHIFT;
 	unsigned long upages = npages;
 	unsigned long cpages = 0;
@@ -671,13 +685,15 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	migrate.vma = vma;
 	migrate.start = start;
 	migrate.end = end;
-	migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 	migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev);
+	if (adev->gmc.xgmi.connected_to_cpu)
+		migrate.flags = MIGRATE_VMA_SELECT_DEVICE_COHERENT;
+	else
+		migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
 
 	buf = kvcalloc(npages,
 		       2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t),
 		       GFP_KERNEL);
-
 	if (!buf)
 		goto out;
 
@@ -685,6 +701,11 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 	migrate.dst = migrate.src + npages;
 	scratch = (dma_addr_t *)(migrate.dst + npages);
 
+	kfd_smi_event_migration_start(adev->kfd.dev, p->lead_thread->pid,
+				      start >> PAGE_SHIFT, end >> PAGE_SHIFT,
+				      adev->kfd.dev->id, 0, prange->prefetch_loc,
+				      prange->preferred_loc, trigger);
+
 	r = migrate_vma_setup(&migrate);
 	if (r) {
 		dev_err(adev->dev, "%s: vma setup fail %d range [0x%lx 0x%lx]\n",
@@ -715,6 +736,11 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange,
 
 	svm_migrate_copy_done(adev, mfence);
 	migrate_vma_finalize(&migrate);
+
+	kfd_smi_event_migration_end(adev->kfd.dev, p->lead_thread->pid,
+				    start >> PAGE_SHIFT, end >> PAGE_SHIFT,
+				    adev->kfd.dev->id, 0, trigger);
+
 	svm_range_dma_unmap(adev->dev, scratch, 0, npages);
 
 out_free:
@@ -732,13 +758,15 @@ out:
  * svm_migrate_vram_to_ram - migrate svm range from device to system
  * @prange: range structure
  * @mm: process mm, use current->mm if NULL
+ * @trigger: reason of migration
  *
  * Context: Process context, caller hold mmap read lock, prange->migrate_mutex
  *
  * Return:
  * 0 - OK, otherwise error code
  */
-int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
+int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm,
+			    uint32_t trigger)
 {
 	struct amdgpu_device *adev;
 	struct vm_area_struct *vma;
@@ -779,7 +807,7 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
 		}
 
 		next = min(vma->vm_end, end);
-		r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next);
+		r = svm_migrate_vma_to_ram(adev, prange, vma, addr, next, trigger);
 		if (r < 0) {
 			pr_debug("failed %ld to migrate prange %p\n", r, prange);
 			break;
@@ -802,6 +830,7 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
  * @prange: range structure
  * @best_loc: the device to migrate to
  * @mm: process mm, use current->mm if NULL
+ * @trigger: reason of migration
  *
  * Context: Process context, caller hold mmap read lock, svms lock, prange lock
  *
@@ -810,7 +839,7 @@ int svm_migrate_vram_to_ram(struct svm_range *prange, struct mm_struct *mm)
  */
 static int
 svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
-			 struct mm_struct *mm)
+			 struct mm_struct *mm, uint32_t trigger)
 {
 	int r, retries = 3;
 
@@ -822,7 +851,7 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	pr_debug("from gpu 0x%x to gpu 0x%x\n", prange->actual_loc, best_loc);
 
 	do {
-		r = svm_migrate_vram_to_ram(prange, mm);
+		r = svm_migrate_vram_to_ram(prange, mm, trigger);
 		if (r)
 			return r;
 	} while (prange->actual_loc && --retries);
@@ -830,17 +859,17 @@ svm_migrate_vram_to_vram(struct svm_range *prange, uint32_t best_loc,
 	if (prange->actual_loc)
 		return -EDEADLK;
 
-	return svm_migrate_ram_to_vram(prange, best_loc, mm);
+	return svm_migrate_ram_to_vram(prange, best_loc, mm, trigger);
 }
 
 int
 svm_migrate_to_vram(struct svm_range *prange, uint32_t best_loc,
-		    struct mm_struct *mm)
+		    struct mm_struct *mm, uint32_t trigger)
 {
 	if  (!prange->actual_loc)
-		return svm_migrate_ram_to_vram(prange, best_loc, mm);
+		return svm_migrate_ram_to_vram(prange, best_loc, mm, trigger);
 	else
-		return svm_migrate_vram_to_vram(prange, best_loc, mm);
+		return svm_migrate_vram_to_vram(prange, best_loc, mm, trigger);
 
 }
 
@@ -909,7 +938,7 @@ static vm_fault_t svm_migrate_to_ram(struct vm_fault *vmf)
 		goto out_unlock_prange;
 	}
 
-	r = svm_migrate_vram_to_ram(prange, mm);
+	r = svm_migrate_vram_to_ram(prange, mm, KFD_MIGRATE_TRIGGER_PAGEFAULT_CPU);
 	if (r)
 		pr_debug("failed %d migrate 0x%p [0x%lx 0x%lx] to ram\n", r,
 			 prange, prange->start, prange->last);
@@ -947,7 +976,7 @@ int svm_migrate_init(struct amdgpu_device *adev)
 {
 	struct kfd_dev *kfddev = adev->kfd.dev;
 	struct dev_pagemap *pgmap;
-	struct resource *res;
+	struct resource *res = NULL;
 	unsigned long size;
 	void *r;
 
@@ -962,28 +991,34 @@ int svm_migrate_init(struct amdgpu_device *adev)
 	 * should remove reserved size
 	 */
 	size = ALIGN(adev->gmc.real_vram_size, 2ULL << 20);
-	res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
-	if (IS_ERR(res))
-		return -ENOMEM;
+	if (adev->gmc.xgmi.connected_to_cpu) {
+		pgmap->range.start = adev->gmc.aper_base;
+		pgmap->range.end = adev->gmc.aper_base + adev->gmc.aper_size - 1;
+		pgmap->type = MEMORY_DEVICE_COHERENT;
+	} else {
+		res = devm_request_free_mem_region(adev->dev, &iomem_resource, size);
+		if (IS_ERR(res))
+			return -ENOMEM;
+		pgmap->range.start = res->start;
+		pgmap->range.end = res->end;
+		pgmap->type = MEMORY_DEVICE_PRIVATE;
+	}
 
-	pgmap->type = MEMORY_DEVICE_PRIVATE;
 	pgmap->nr_range = 1;
-	pgmap->range.start = res->start;
-	pgmap->range.end = res->end;
 	pgmap->ops = &svm_migrate_pgmap_ops;
 	pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev);
-	pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
-
+	pgmap->flags = 0;
 	/* Device manager releases device-specific resources, memory region and
 	 * pgmap when driver disconnects from device.
 	 */
 	r = devm_memremap_pages(adev->dev, pgmap);
 	if (IS_ERR(r)) {
 		pr_err("failed to register HMM device memory\n");
-
 		/* Disable SVM support capability */
 		pgmap->type = 0;
-		devm_release_mem_region(adev->dev, res->start, resource_size(res));
+		if (pgmap->type == MEMORY_DEVICE_PRIVATE)
+			devm_release_mem_region(adev->dev, res->start,
+						res->end - res->start + 1);
 		return PTR_ERR(r);
 	}
 
@@ -992,6 +1027,8 @@ int svm_migrate_init(struct amdgpu_device *adev)
 
 	amdgpu_amdkfd_reserve_system_mem(SVM_HMM_PAGE_STRUCT_SIZE(size));
 
+	svm_range_set_max_pages(adev);
+
 	pr_info("HMM registered %ldMB device memory\n", size >> 20);
 
 	return 0;