diff mbox series

[10/10] drm/amdkfd: protect svm_bo ref in case prange has forked

Message ID 20210527205606.2660-10-Felix.Kuehling@amd.com (mailing list archive)
State New, archived
Headers show
Series [01/10] drm/amdkfd: device pgmap owner at the svm migrate init | expand

Commit Message

Felix Kuehling May 27, 2021, 8:56 p.m. UTC 
From: Alex Sierra <alex.sierra@amd.com>

Keep track of all the pages inside of pranges referenced to
the same svm_bo. This is done, by using the ref count inside this object.
This makes sure the object has freed after the last prange is not longer
at any GPU. Including references shared between a parent and child during
a fork.

Signed-off-by: Alex Sierra <alex.sierra@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 10 ++++++++--
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c     | 10 +---------
 drivers/gpu/drm/amd/amdkfd/kfd_svm.h     | 10 +++++++++-
 3 files changed, 18 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index acb9f64577a0..c8ca3252cbc2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -245,7 +245,7 @@  svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn)
 	struct page *page;
 
 	page = pfn_to_page(pfn);
-	page->zone_device_data = prange;
+	page->zone_device_data = prange->svm_bo;
 	get_page(page);
 	lock_page(page);
 }
@@ -336,6 +336,7 @@  svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange,
 			svm_migrate_get_vram_page(prange, migrate->dst[i]);
 			migrate->dst[i] = migrate_pfn(migrate->dst[i]);
 			migrate->dst[i] |= MIGRATE_PFN_LOCKED;
+			svm_range_bo_ref(prange->svm_bo);
 		}
 		if (migrate->dst[i] & MIGRATE_PFN_VALID) {
 			spage = migrate_pfn_to_page(migrate->src[i]);
@@ -540,7 +541,12 @@  svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 
 static void svm_migrate_page_free(struct page *page)
 {
-	/* Keep this function to avoid warning */
+	struct svm_range_bo *svm_bo = page->zone_device_data;
+
+	if (svm_bo) {
+		pr_debug("svm_bo ref left: %d\n", kref_read(&svm_bo->kref));
+		svm_range_bo_unref(svm_bo);
+	}
 }
 
 static int
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 1e15a6170635..2bc20752ee30 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -309,14 +309,6 @@  static bool svm_bo_ref_unless_zero(struct svm_range_bo *svm_bo)
 	return true;
 }
 
-static struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo)
-{
-	if (svm_bo)
-		kref_get(&svm_bo->kref);
-
-	return svm_bo;
-}
-
 static void svm_range_bo_release(struct kref *kref)
 {
 	struct svm_range_bo *svm_bo;
@@ -355,7 +347,7 @@  static void svm_range_bo_release(struct kref *kref)
 	kfree(svm_bo);
 }
 
-static void svm_range_bo_unref(struct svm_range_bo *svm_bo)
+void svm_range_bo_unref(struct svm_range_bo *svm_bo)
 {
 	if (!svm_bo)
 		return;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
index 27fbe1936493..21f693767a0d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h
@@ -150,6 +150,14 @@  static inline void svm_range_unlock(struct svm_range *prange)
 	mutex_unlock(&prange->lock);
 }
 
+static inline struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo)
+{
+	if (svm_bo)
+		kref_get(&svm_bo->kref);
+
+	return svm_bo;
+}
+
 int svm_range_list_init(struct kfd_process *p);
 void svm_range_list_fini(struct kfd_process *p);
 int svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
@@ -178,7 +186,7 @@  void svm_range_dma_unmap(struct device *dev, dma_addr_t *dma_addr,
 void svm_range_free_dma_mappings(struct svm_range *prange);
 void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm,
 			void *owner);
-
+void svm_range_bo_unref(struct svm_range_bo *svm_bo);
 #else
 
 struct kfd_process;