Re: [PATCH v3 7/8] dma-buf: transfer memcg charges via DMA_BUF_IOCTL_XFER_CHARGE

["Christian König" <christian.koenig@amd.com>]

On 10/27/26 16:02, Albert Esteve wrote:
> dma-heap already supports charging a specific cgroup at allocation
> time via charge_fd in DMA_HEAP_IOCTL_ALLOC. However, dma-bufs can
> originate from any exporter (DRM, V4L2, etc.), and the allocator may
> not know the final owner at allocation time.
> 
> Add DMA_BUF_IOCTL_XFER_CHARGE to transfer a dma-buf's memcg charge
> to a different cgroup after allocation. The target is identified by
> charge_fd, which may be a cgroupfd or a pidfd.
> 
> The transfer charges the new cgroup before uncharging the old one,
> preserving the original charge on failure. An atomic cmpxchg on
> dmabuf->memcg prevents races with concurrent transfers.
> 
> Not all dma-buf exporters back their buffers with reclaimable system
> memory. Some represent device registers, VRAM, or carved-out pools
> where size is not a meaningful memory cost. Add a memcg_account flag
> to dma_buf_export_info that exporters set when their buffers should
> participate in memcg accounting. The xfer ioctl returns -EOPNOTSUPP
> for buffers that do not set the flag. Currently only the system heap
> sets it, other exporters can opt in as needed.
> 
> Usage example:
>   int cg_fd = open("/sys/fs/cgroup/clients/app1", O_RDONLY | O_DIRECTORY);
> 
>   struct dma_buf_transfer_charge xfer = {
>       .charge_fd = cg_fd,
>   };
>   ioctl(dmabuf_fd, DMA_BUF_IOCTL_XFER_CHARGE, &xfer);
>   /* charge now on app1's cgroup */
>   close(cg_fd);
> 
> Signed-off-by: Albert Esteve <aesteve@redhat.com>
> ---
>  drivers/dma-buf/dma-buf.c           | 43 +++++++++++++++++++++++++++++++++++++
>  drivers/dma-buf/heaps/system_heap.c |  1 +
>  include/linux/dma-buf.h             |  5 +++++
>  include/linux/memcontrol.h          |  9 ++++++++
>  include/uapi/linux/dma-buf.h        | 26 ++++++++++++++++++++++
>  mm/memcontrol.c                     | 41 +++++++++++++++++++++++++++++++++++
>  6 files changed, 125 insertions(+)
> 
> diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
> index f31f49ebd0af..07513ecedc10 100644
> --- a/drivers/dma-buf/dma-buf.c
> +++ b/drivers/dma-buf/dma-buf.c
> @@ -540,6 +540,45 @@ static long dma_buf_import_sync_file(struct dma_buf *dmabuf,
>  }
>  #endif
>  
> +/* Transfer a dma-buf's memcg charge; see struct dma_buf_transfer_charge */
> +static long dma_buf_xfer_charge(struct dma_buf *dmabuf,
> +				const void __user *user_data)
> +{
> +	struct dma_buf_transfer_charge arg;
> +	struct mem_cgroup *memcg;
> +	int ret = 0;
> +
> +	if (copy_from_user(&arg, user_data, sizeof(arg)))
> +		return -EFAULT;
> +
> +	if (!IS_ENABLED(CONFIG_MEMCG))
> +		return 0;
> +
> +	if (arg.flags != 0)
> +		return -EINVAL;
> +
> +	if (!dmabuf->memcg_account)
> +		return -EOPNOTSUPP;
> +
> +	memcg = mem_cgroup_get_from_fd(arg.charge_fd);
> +	if (IS_ERR(memcg))
> +		return PTR_ERR(memcg);
> +
> +	if (dmabuf->memcg == memcg)
> +		goto skip_transfer;
> +
> +	if (!mem_cgroup_transfer_dmabuf_charge(dmabuf, memcg)) {
> +		ret = -ENOMEM;
> +		goto skip_transfer;
> +	}
> +
> +	return 0;
> +
> +skip_transfer:
> +	mem_cgroup_put(memcg);
> +	return ret;
> +}
> +
>  static long dma_buf_ioctl(struct file *file,
>  			  unsigned int cmd, unsigned long arg)
>  {
> @@ -590,6 +629,9 @@ static long dma_buf_ioctl(struct file *file,
>  		return dma_buf_import_sync_file(dmabuf, (const void __user *)arg);
>  #endif
>  
> +	case DMA_BUF_IOCTL_XFER_CHARGE:
> +		return dma_buf_xfer_charge(dmabuf, (const void __user *)arg);
> +
>  	default:
>  		return -ENOTTY;
>  	}
> @@ -750,6 +792,7 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
>  	dmabuf->size = exp_info->size;
>  	dmabuf->exp_name = exp_info->exp_name;
>  	dmabuf->owner = exp_info->owner;
> +	dmabuf->memcg_account = exp_info->memcg_account;

The initial charging should probably be done here as well.

This way DMA-buf heaps only needs to pass in the charge_fd and we can re-use the functionality for other DMA-buf exporters as well.

>  	spin_lock_init(&dmabuf->name_lock);
>  	init_waitqueue_head(&dmabuf->poll);
>  	dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll;
> diff --git a/drivers/dma-buf/heaps/system_heap.c b/drivers/dma-buf/heaps/system_heap.c
> index adeea8cd328b..a764167167ba 100644
> --- a/drivers/dma-buf/heaps/system_heap.c
> +++ b/drivers/dma-buf/heaps/system_heap.c
> @@ -479,6 +479,7 @@ static struct dma_buf *system_heap_allocate(struct dma_heap *heap,
>  	exp_info.size = buffer->len;
>  	exp_info.flags = fd_flags;
>  	exp_info.priv = buffer;
> +	exp_info.memcg_account = true;
>  	dmabuf = dma_buf_export(&exp_info);
>  	if (IS_ERR(dmabuf)) {
>  		ret = PTR_ERR(dmabuf);
> diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
> index 23ec0ff23fba..ac0ec88cab93 100644
> --- a/include/linux/dma-buf.h
> +++ b/include/linux/dma-buf.h
> @@ -433,6 +433,9 @@ struct dma_buf {
>  
>  	/** @memcg: the cgroup to which this buffer is currently attributed */
>  	struct mem_cgroup *memcg;
> +
> +	/** @memcg_account: account buffer memory to cgroup */
> +	bool memcg_account;
>  };
>  
>  /**
> @@ -505,6 +508,7 @@ struct dma_buf_attachment {
>   * @flags:	mode flags for the file
>   * @resv:	reservation-object, NULL to allocate default one
>   * @priv:	Attach private data of allocator to this buffer
> + * @memcg_account:	account buffer memory to cgroup
>   *
>   * This structure holds the information required to export the buffer. Used
>   * with dma_buf_export() only.
> @@ -517,6 +521,7 @@ struct dma_buf_export_info {
>  	int flags;
>  	struct dma_resv *resv;
>  	void *priv;
> +	bool memcg_account;
>  };
>  
>  /**
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 6b30baa79fa9..36fddafbef4e 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -679,6 +679,9 @@ bool mem_cgroup_reserve_dmabuf(struct mem_cgroup *memcg, gfp_t gfp,
>  void mem_cgroup_commit_dmabuf(struct dma_buf *dmabuf, struct mem_cgroup *memcg,
>  			      unsigned int nr_pages);
>  
> +bool mem_cgroup_transfer_dmabuf_charge(struct dma_buf *dmabuf,
> +				       struct mem_cgroup *new_memcg);
> +
>  void __mem_cgroup_uncharge(struct folio *folio);
>  
>  /**
> @@ -1206,6 +1209,12 @@ static inline void mem_cgroup_cancel_dmabuf(struct mem_cgroup *memcg,
>  {
>  }
>  
> +static inline bool mem_cgroup_transfer_dmabuf_charge(struct dma_buf *dmabuf,
> +						     struct mem_cgroup *new_memcg)
> +{
> +	return true;
> +}
> +
>  static inline void mem_cgroup_uncharge(struct folio *folio)
>  {
>  }
> diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h
> index e827c9d20c5d..ea957f4b1d38 100644
> --- a/include/uapi/linux/dma-buf.h
> +++ b/include/uapi/linux/dma-buf.h
> @@ -168,6 +168,31 @@ struct dma_buf_import_sync_file {
>  	__s32 fd;
>  };
>  
> +/**
> + * struct dma_buf_transfer_charge - Transfer a dma-buf's memcg charge
> + *
> + * Any holder of a dma-buf file descriptor can perform a
> + * DMA_BUF_IOCTL_XFER_CHARGE to attribute the buffer's memory
> + * cost to a specific cgroup, or move it from one cgroup to
> + * another.  The ioctl charges the new cgroup before uncharging
> + * the old one atomically.  On failure the original charge is
> + * preserved.  If the buffer has no existing charge, a new
> + * charge is established.
> + */
> +struct dma_buf_transfer_charge {
> +	/** @flags: Reserved, must be zero */
> +	__u32 flags; /* unused for now */
> +	/**
> +	 * @charge_fd: File descriptor identifying the target cgroup.
> +	 *
> +	 * May be either a pidfd, in which case the charge moves to the
> +	 * memory cgroup of the referenced process, or a cgroupfd obtained
> +	 * by opening a cgroup v2 directory, in which case the charge moves
> +	 * directly to that cgroup's memory controller.
> +	 */
> +	__u32 charge_fd;
> +};
> +
>  #define DMA_BUF_BASE		'b'
>  #define DMA_BUF_IOCTL_SYNC	_IOW(DMA_BUF_BASE, 0, struct dma_buf_sync)
>  
> @@ -179,5 +204,6 @@ struct dma_buf_import_sync_file {
>  #define DMA_BUF_SET_NAME_B	_IOW(DMA_BUF_BASE, 1, __u64)
>  #define DMA_BUF_IOCTL_EXPORT_SYNC_FILE	_IOWR(DMA_BUF_BASE, 2, struct dma_buf_export_sync_file)
>  #define DMA_BUF_IOCTL_IMPORT_SYNC_FILE	_IOW(DMA_BUF_BASE, 3, struct dma_buf_import_sync_file)
> +#define DMA_BUF_IOCTL_XFER_CHARGE	_IOW(DMA_BUF_BASE, 4, struct dma_buf_transfer_charge)
>  
>  #endif
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 7b841b905759..3adc84fe6668 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -5786,6 +5786,47 @@ void mem_cgroup_cancel_dmabuf(struct mem_cgroup *memcg, unsigned int nr_pages)
>  		refill_stock(memcg, nr_pages);
>  }
>  
> +/**
> + * mem_cgroup_transfer_dmabuf_charge - move a dma-buf charge
> + * @dmabuf: buffer to transfer charge
> + * @new_memcg: target memcg; caller must hold a reference
> + *
> + * Transfers the charge for @dmabuf to @new_memcg and, on
> + * success, stores @new_memcg in @dmabuf->memcg.
> + * Returns %true on success, %false if the charge against @new_memcg
> + * failed or a concurrent transfer raced on @dmabuf->memcg.
> + * On failure the caller retains its reference to @new_memcg.
> + */
> +bool mem_cgroup_transfer_dmabuf_charge(struct dma_buf *dmabuf,
> +				       struct mem_cgroup *new_memcg)

I would make that more generic instead of dmabuf specific. E.g. something like this:

bool mem_cgroup_transfer_charge(struct struct mem_cgroup **ptr_memcg, struct mem_cgroup *new_memcg, enum memcg_stat_item item, unsigned int nr_pages)

> +{
> +	struct mem_cgroup *old_memcg = READ_ONCE(dmabuf->memcg);

> +	unsigned int nr_pages = PAGE_ALIGN(dmabuf->size) >> PAGE_SHIFT;

This way we can also document in the DMA-buf caller that this conversation must be ok when memcg_account is true.

Regards,
Christian.

> +
> +	if (mem_cgroup_disabled())
> +		return true;
> +
> +	if (!mem_cgroup_reserve_dmabuf(new_memcg, GFP_KERNEL, nr_pages))
> +		return false;
> +
> +	mod_memcg_state(new_memcg, MEMCG_DMABUF, nr_pages);
> +
> +	if (cmpxchg(&dmabuf->memcg, old_memcg, new_memcg) != old_memcg) {
> +		mod_memcg_state(new_memcg, MEMCG_DMABUF, -nr_pages);
> +		mem_cgroup_cancel_dmabuf(new_memcg, nr_pages);
> +		return false;
> +	}
> +
> +	if (old_memcg) {
> +		/* Uncharge old cgroup */
> +		mod_memcg_state(old_memcg, MEMCG_DMABUF, -nr_pages);
> +		mem_cgroup_cancel_dmabuf(old_memcg, nr_pages);
> +		mem_cgroup_put(old_memcg);
> +	}
> +
> +	return true;
> +}
> +
>  /**
>   * mem_cgroup_uncharge_dmabuf - uncharge a dma-buf from its memcg
>   * @dmabuf: buffer to uncharge
>