diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index d3a974d10552940030ae84c6350b1154c844f40a..7eae06d8c54ec083812565a05766d4b3e9425c3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -310,15 +310,15 @@ int amdgpu_amdkfd_alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	return r;
 }
 
-void amdgpu_amdkfd_free_gtt_mem(struct kgd_dev *kgd, void *mem_obj)
+void amdgpu_amdkfd_free_gtt_mem(struct kgd_dev *kgd, void **mem_obj)
 {
-	struct amdgpu_bo *bo = (struct amdgpu_bo *) mem_obj;
+	struct amdgpu_bo **bo = (struct amdgpu_bo **) mem_obj;
 
-	amdgpu_bo_reserve(bo, true);
-	amdgpu_bo_kunmap(bo);
-	amdgpu_bo_unpin(bo);
-	amdgpu_bo_unreserve(bo);
-	amdgpu_bo_unref(&(bo));
+	amdgpu_bo_reserve(*bo, true);
+	amdgpu_bo_kunmap(*bo);
+	amdgpu_bo_unpin(*bo);
+	amdgpu_bo_unreserve(*bo);
+	amdgpu_bo_unref(bo);
 }
 
 int amdgpu_amdkfd_alloc_gws(struct kgd_dev *kgd, size_t size,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 32e385f287cb63e5dc1c0c8d3f012d391bac7619..24848048fb823b309480b7a6850b7836b26185a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -183,7 +183,7 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm)
 int amdgpu_amdkfd_alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 				void **mem_obj, uint64_t *gpu_addr,
 				void **cpu_ptr, bool mqd_gfx9);
-void amdgpu_amdkfd_free_gtt_mem(struct kgd_dev *kgd, void *mem_obj);
+void amdgpu_amdkfd_free_gtt_mem(struct kgd_dev *kgd, void **mem_obj);
 int amdgpu_amdkfd_alloc_gws(struct kgd_dev *kgd, size_t size, void **mem_obj);
 void amdgpu_amdkfd_free_gws(struct kgd_dev *kgd, void *mem_obj);
 int amdgpu_amdkfd_add_gws_to_process(void *info, void *gws, struct kgd_mem **mem);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 04126ffbc9733ae1c4b5be5ec11328d0097c75ad..806c38492768ff211bed7f83e3f6119777982826 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -782,7 +782,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 kfd_doorbell_error:
 	kfd_gtt_sa_fini(kfd);
 kfd_gtt_sa_init_error:
-	amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem);
+	amdgpu_amdkfd_free_gtt_mem(kfd->kgd, &kfd->gtt_mem);
 alloc_gtt_mem_failure:
 	if (kfd->gws)
 		amdgpu_amdkfd_free_gws(kfd->kgd, kfd->gws);
@@ -803,7 +803,7 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 		kfd_doorbell_fini(kfd);
 		ida_destroy(&kfd->doorbell_ida);
 		kfd_gtt_sa_fini(kfd);
-		amdgpu_amdkfd_free_gtt_mem(kfd->kgd, kfd->gtt_mem);
+		amdgpu_amdkfd_free_gtt_mem(kfd->kgd, &kfd->gtt_mem);
 		if (kfd->gws)
 			amdgpu_amdkfd_free_gws(kfd->kgd, kfd->gws);
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 195b7e02dc4b0ef671f14a7574dff8f82674f03b..62f7aa61873d8997f8f9edda63cb264f1472094a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1971,7 +1971,7 @@ static void deallocate_hiq_sdma_mqd(struct kfd_dev *dev,
 {
 	WARN(!mqd, "No hiq sdma mqd trunk to free");
 
-	amdgpu_amdkfd_free_gtt_mem(dev->kgd, mqd->gtt_mem);
+	amdgpu_amdkfd_free_gtt_mem(dev->kgd, &mqd->gtt_mem);
 }
 
 void device_queue_manager_uninit(struct device_queue_manager *dqm)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 3b6f5963180d5250ac6b50daeeb360ea3ed90f3b..156abf2526d2b168e904b30b9fea23c154bdeea4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -292,7 +292,7 @@ static void free_mqd(struct mqd_manager *mm, void *mqd,
 	struct kfd_dev *kfd = mm->dev;
 
 	if (mqd_mem_obj->gtt_mem) {
-		amdgpu_amdkfd_free_gtt_mem(kfd->kgd, mqd_mem_obj->gtt_mem);
+		amdgpu_amdkfd_free_gtt_mem(kfd->kgd, &mqd_mem_obj->gtt_mem);
 		kfree(mqd_mem_obj);
 	} else {
 		kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 921463625d82e86f152769c79ce8828c48eec19e..a094ca5b19b171f33dbf4b0c955b82af3d47feb8 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -673,6 +673,8 @@ struct vc4_exec_info {
  * released when the DRM file is closed should be placed here.
  */
 struct vc4_file {
+	struct vc4_dev *dev;
+
 	struct {
 		struct idr idr;
 		struct mutex lock;
diff --git a/drivers/gpu/drm/vc4/vc4_perfmon.c b/drivers/gpu/drm/vc4/vc4_perfmon.c
index f4aa75efd16b0d41df379a3d73efca20593e5296..8aa0825aa85b8998ff06621f6bbf2be14f2fc7b6 100644
--- a/drivers/gpu/drm/vc4/vc4_perfmon.c
+++ b/drivers/gpu/drm/vc4/vc4_perfmon.c
@@ -83,6 +83,11 @@ void vc4_perfmon_open_file(struct vc4_file *vc4file)
 static int vc4_perfmon_idr_del(int id, void *elem, void *data)
 {
 	struct vc4_perfmon *perfmon = elem;
+	struct vc4_dev *vc4 = (struct vc4_dev *)data;
+
+	/* If the active perfmon is being destroyed, stop it first */
+	if (perfmon == vc4->active_perfmon)
+		vc4_perfmon_stop(vc4, perfmon, false);
 
 	vc4_perfmon_put(perfmon);
 
@@ -92,7 +97,7 @@ static int vc4_perfmon_idr_del(int id, void *elem, void *data)
 void vc4_perfmon_close_file(struct vc4_file *vc4file)
 {
 	mutex_lock(&vc4file->perfmon.lock);
-	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, NULL);
+	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, vc4file->dev);
 	idr_destroy(&vc4file->perfmon.idr);
 	mutex_unlock(&vc4file->perfmon.lock);
 }
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 4cd1dcea99946b5d4eb31ba119d5624ad0d0d684..052151a77fb4dabb697870f23eadf91d9d57d307 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -78,7 +78,8 @@ void nilfs_forget_buffer(struct buffer_head *bh)
 	const unsigned long clear_bits =
 		(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
 		 BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
-		 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected));
+		 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) |
+		 BIT(BH_Delay));
 
 	lock_buffer(bh);
 	set_mask_bits(&bh->b_state, clear_bits, 0);
@@ -403,7 +404,8 @@ void nilfs_clear_dirty_page(struct page *page, bool silent)
 		const unsigned long clear_bits =
 			(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
 			 BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
-			 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected));
+			 BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) |
+			 BIT(BH_Delay));
 
 		bh = head = page_buffers(page);
 		do {
diff --git a/mm/filemap.c b/mm/filemap.c
index 328bc2b1fb58f1a0780dcbfbdc729bf9db8cb3c1..68c368c0782b92cb4fa340f04ad1cd49958eec2b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2554,7 +2554,7 @@ ssize_t generic_file_buffered_read(struct kiocb *iocb,
 	if (unlikely(!iov_iter_count(iter)))
 		return 0;
 
-	iov_iter_truncate(iter, inode->i_sb->s_maxbytes);
+	iov_iter_truncate(iter, inode->i_sb->s_maxbytes - iocb->ki_pos);
 
 	if (nr_pages > ARRAY_SIZE(pages_onstack))
 		pages = kmalloc_array(nr_pages, sizeof(void *), GFP_KERNEL);
diff --git a/mm/shmem.c b/mm/shmem.c
index f7caf1dec81c3b41546a2a817a2cf1ce69d88cda..7b872389bb994e6c56eb0177ca9d0209236ffa4b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1083,7 +1083,9 @@ static int shmem_getattr(const struct path *path, struct kstat *stat,
 		shmem_recalc_inode(inode);
 		spin_unlock_irq(&info->lock);
 	}
+	inode_lock_shared(inode);
 	generic_fillattr(inode, stat);
+	inode_unlock_shared(inode);
 
 	if (is_huge_enabled(sb_info))
 		stat->blksize = HPAGE_PMD_SIZE;