Blob Blame History Raw
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Fri, 27 Oct 2017 19:35:19 -0400
Subject: drm/amdkfd: Don't dereference kfd_process.mm
Git-commit: 9b56bb115460cee92a80bf85232b4b7da2f080e6
Patch-mainline: v4.15-rc1
References: FATE#326289 FATE#326079 FATE#326049 FATE#322398 FATE#326166

The kfd_process doesn't own a reference to the mm_struct, so it can
disappear without warning even while the kfd_process still exists.

Therefore, avoid dereferencing the kfd_process.mm pointer and make
it opaque. Use get_task_mm to get a temporary reference to the mm
when it's needed.

v2: removed unnecessary WARN_ON

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Acked-by: Petr Tesarik <ptesarik@suse.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_events.c  |   19 +++++++++++++++----
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |    7 ++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_process.c |    1 -
 3 files changed, 21 insertions(+), 6 deletions(-)

--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -24,8 +24,8 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/uaccess.h>
-#include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/memory.h>
 #include "kfd_priv.h"
@@ -904,14 +904,24 @@ void kfd_signal_iommu_event(struct kfd_d
 	 * running so the lookup function returns a locked process.
 	 */
 	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	struct mm_struct *mm;
 
 	if (!p)
 		return; /* Presumably process exited. */
 
+	/* Take a safe reference to the mm_struct, which may otherwise
+	 * disappear even while the kfd_process is still referenced.
+	 */
+	mm = get_task_mm(p->lead_thread);
+	if (!mm) {
+		mutex_unlock(&p->mutex);
+		return; /* Process is exiting */
+	}
+
 	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
 
-	down_read(&p->mm->mmap_sem);
-	vma = find_vma(p->mm, address);
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, address);
 
 	memory_exception_data.gpu_id = dev->id;
 	memory_exception_data.va = address;
@@ -937,7 +947,8 @@ void kfd_signal_iommu_event(struct kfd_d
 		}
 	}
 
-	up_read(&p->mm->mmap_sem);
+	up_read(&mm->mmap_sem);
+	mmput(mm);
 
 	mutex_lock(&p->event_mutex);
 
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -494,7 +494,12 @@ struct kfd_process {
 	 */
 	struct hlist_node kfd_processes;
 
-	struct mm_struct *mm;
+	/*
+	 * Opaque pointer to mm_struct. We don't hold a reference to
+	 * it so it should never be dereferenced from here. This is
+	 * only used for looking up processes by their mm.
+	 */
+	void *mm;
 
 	struct mutex mutex;
 
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -200,7 +200,6 @@ static void kfd_process_destroy_delayed(
 	struct kfd_process *p;
 
 	p = container_of(rcu, struct kfd_process, rcu);
-	WARN_ON(atomic_read(&p->mm->mm_count) <= 0);
 
 	mmdrop(p->mm);