Re: [dpdk-dev] [PATCH v3 1/5] mbuf: fix clone support when application uses private mbuf data

["Ananyev, Konstantin" <konstantin.ananyev@intel.com>]

Hi Olivier,

> -----Original Message-----
> From: Olivier Matz [mailto:olivier.matz@6wind.com]
> Sent: Tuesday, March 31, 2015 8:23 PM
> To: dev@dpdk.org
> Cc: Ananyev, Konstantin; zoltan.kiss@linaro.org; Richardson, Bruce; Olivier Matz
> Subject: [PATCH v3 1/5] mbuf: fix clone support when application uses private mbuf data
> 
> From: Olivier Matz <olivier.matz@6wind.com>
> 
> Add a new private_size field in mbuf structure that should
> be initialized at mbuf pool creation. This field contains the
> size of the application private data in mbufs.
> 
> Introduce new static inline functions rte_mbuf_from_indirect()
> and rte_mbuf_to_baddr() to replace the existing macros, which
> take the private size in account when attaching and detaching
> mbufs.
> 
> Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
> ---
>  app/test-pmd/testpmd.c     |  1 +
>  examples/vhost/main.c      |  4 +--
>  lib/librte_mbuf/rte_mbuf.c |  1 +
>  lib/librte_mbuf/rte_mbuf.h | 77 +++++++++++++++++++++++++++++++++++-----------
>  4 files changed, 63 insertions(+), 20 deletions(-)
> 
> diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
> index 3057791..c5a195a 100644
> --- a/app/test-pmd/testpmd.c
> +++ b/app/test-pmd/testpmd.c
> @@ -425,6 +425,7 @@ testpmd_mbuf_ctor(struct rte_mempool *mp,
>  	mb->tx_offload   = 0;
>  	mb->vlan_tci     = 0;
>  	mb->hash.rss     = 0;
> +	mb->priv_size    = 0;
>  }
> 
>  static void
> diff --git a/examples/vhost/main.c b/examples/vhost/main.c
> index c3fcb80..e44e82f 100644
> --- a/examples/vhost/main.c
> +++ b/examples/vhost/main.c
> @@ -139,7 +139,7 @@
>  /* Number of descriptors per cacheline. */
>  #define DESC_PER_CACHELINE (RTE_CACHE_LINE_SIZE / sizeof(struct vring_desc))
> 
> -#define MBUF_EXT_MEM(mb)   (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb))
> +#define MBUF_EXT_MEM(mb)   (rte_mbuf_from_indirect(mb) != (mb))
> 
>  /* mask of enabled ports */
>  static uint32_t enabled_port_mask = 0;
> @@ -1550,7 +1550,7 @@ attach_rxmbuf_zcp(struct virtio_net *dev)
>  static inline void pktmbuf_detach_zcp(struct rte_mbuf *m)
>  {
>  	const struct rte_mempool *mp = m->pool;
> -	void *buf = RTE_MBUF_TO_BADDR(m);
> +	void *buf = rte_mbuf_to_baddr(m);
>  	uint32_t buf_ofs;
>  	uint32_t buf_len = mp->elt_size - sizeof(*m);
>  	m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof(*m);
> diff --git a/lib/librte_mbuf/rte_mbuf.c b/lib/librte_mbuf/rte_mbuf.c
> index 526b18d..e095999 100644
> --- a/lib/librte_mbuf/rte_mbuf.c
> +++ b/lib/librte_mbuf/rte_mbuf.c
> @@ -125,6 +125,7 @@ rte_pktmbuf_init(struct rte_mempool *mp,
>  	m->pool = mp;
>  	m->nb_segs = 1;
>  	m->port = 0xff;
> +	m->priv_size = 0;

Why it is 0?
Shouldn't it be the same calulations as in detach() below:
m->priv_size = /*get private size from mempool private*/;
m->buf_addr = (char *)m + sizeof(struct rte_mbuf) + m->priv_size;
m->buf_len = mp->elt_size - sizeof(struct rte_mbuf) - m->priv_size;
?

BTW, don't see changes in rte_pktmbuf_pool_init() to setup
mbp_priv->mbuf_data_room_size properly.
Without that changes, how can people start using that feature?
It seems that the only way now - setup priv_size and buf_len for each mbuf manually.

>  }
> 
>  /* do some sanity checks on a mbuf: panic if it fails */
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index 17ba791..932fe58 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -317,18 +317,51 @@ struct rte_mbuf {
>  			/* uint64_t unused:8; */
>  		};
>  	};
> +
> +	/** Size of the application private data. In case of an indirect
> +	 * mbuf, it stores the direct mbuf private data size. */
> +	uint16_t priv_size;
>  } __rte_cache_aligned;
> 
>  /**
> - * Given the buf_addr returns the pointer to corresponding mbuf.
> + * Return the mbuf owning the data buffer address of an indirect mbuf.
> + *
> + * @param mi
> + *   The pointer to the indirect mbuf.
> + * @return
> + *   The address of the direct mbuf corresponding to buffer_addr.
>   */
> -#define RTE_MBUF_FROM_BADDR(ba)     (((struct rte_mbuf *)(ba)) - 1)
> +static inline struct rte_mbuf *
> +rte_mbuf_from_indirect(struct rte_mbuf *mi)
> +{
> +       struct rte_mbuf *md;
> +
> +       /* mi->buf_addr and mi->priv_size correspond to buffer and
> +	* private size of the direct mbuf */
> +       md = (struct rte_mbuf *)((char *)mi->buf_addr - sizeof(*mi) -
> +	       mi->priv_size);

(uintptr_t)mi->buf_addr?

> +       return md;
> +}
> 
>  /**
> - * Given the pointer to mbuf returns an address where it's  buf_addr
> - * should point to.
> + * Return the buffer address embedded in the given mbuf.
> + *
> + * The user must ensure that m->priv_size corresponds to the
> + * private size of this mbuf, which is not the case for indirect
> + * mbufs.
> + *
> + * @param md
> + *   The pointer to the mbuf.
> + * @return
> + *   The address of the data buffer owned by the mbuf.
>   */
> -#define RTE_MBUF_TO_BADDR(mb)       (((struct rte_mbuf *)(mb)) + 1)
> +static inline char *

Might be better to return 'void *' here.

> +rte_mbuf_to_baddr(struct rte_mbuf *md)
> +{
> +       char *buffer_addr;

uintptr_t buffer_addr? 

> +       buffer_addr = (char *)md + sizeof(*md) + md->priv_size;
> +       return buffer_addr;
> +}
> 
>  /**
>   * Returns TRUE if given mbuf is indirect, or FALSE otherwise.
> @@ -688,6 +721,7 @@ static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp)
> 
>  /**
>   * Attach packet mbuf to another packet mbuf.
> + *
>   * After attachment we refer the mbuf we attached as 'indirect',
>   * while mbuf we attached to as 'direct'.
>   * Right now, not supported:
> @@ -701,7 +735,6 @@ static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp)
>   * @param md
>   *   The direct packet mbuf.
>   */
> -
>  static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
>  {
>  	RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(md) &&
> @@ -712,6 +745,7 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
>  	mi->buf_physaddr = md->buf_physaddr;
>  	mi->buf_addr = md->buf_addr;
>  	mi->buf_len = md->buf_len;
> +	mi->priv_size = md->priv_size;
> 
>  	mi->next = md->next;
>  	mi->data_off = md->data_off;
> @@ -732,7 +766,8 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
>  }
> 
>  /**
> - * Detach an indirect packet mbuf -
> + * Detach an indirect packet mbuf.
> + *
>   *  - restore original mbuf address and length values.
>   *  - reset pktmbuf data and data_len to their default values.
>   *  All other fields of the given packet mbuf will be left intact.
> @@ -740,22 +775,28 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
>   * @param m
>   *   The indirect attached packet mbuf.
>   */
> -
>  static inline void rte_pktmbuf_detach(struct rte_mbuf *m)
>  {
> -	const struct rte_mempool *mp = m->pool;
> -	void *buf = RTE_MBUF_TO_BADDR(m);
> -	uint32_t buf_len = mp->elt_size - sizeof(*m);
> -	m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof (*m);
> -
> +	struct rte_pktmbuf_pool_private *mbp_priv;
> +	struct rte_mempool *mp = m->pool;
> +	void *buf;
> +	unsigned mhdr_size;
> +
> +	/* first, restore the priv_size, this is needed before calling
> +	 * rte_mbuf_to_baddr() */
> +	mbp_priv = rte_mempool_get_priv(mp);
> +	m->priv_size = mp->elt_size - RTE_PKTMBUF_HEADROOM -
> +		mbp_priv->mbuf_data_room_size -
> +		sizeof(struct rte_mbuf);

I think it is better to put this priv_size calculation above into the separate function -
rte_mbuf_get_priv_size(m) or something.
We need it in few places, and users would probably need it anyway. 

> +
> +	buf = rte_mbuf_to_baddr(m);
> +	mhdr_size = (char *)buf - (char *)m;

Why do you need to recalculate mhdr_size here?
As I understand it is a m->priv_size, and you just retrieved it, 2 lines above.

> +	m->buf_physaddr = rte_mempool_virt2phy(mp, m) + mhdr_size;

Actually I think could just be:
m->buf_physaddr = rte_mempool_virt2phy(mp, buf);

>  	m->buf_addr = buf;
> -	m->buf_len = (uint16_t)buf_len;
> -
> +	m->buf_len = (uint16_t)(mp->elt_size - mhdr_size);
>  	m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ?
>  			RTE_PKTMBUF_HEADROOM : m->buf_len;
> -
>  	m->data_len = 0;
> -
>  	m->ol_flags = 0;
>  }
> 
> @@ -774,7 +815,7 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
>  		 *  - free attached mbuf segment
>  		 */
>  		if (RTE_MBUF_INDIRECT(m)) {
> -			struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr);
> +			struct rte_mbuf *md = rte_mbuf_from_indirect(m);
>  			rte_pktmbuf_detach(m);
>  			if (rte_mbuf_refcnt_update(md, -1) == 0)
>  				__rte_mbuf_raw_free(md);
> --
> 2.1.4