From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id 1181F9A99 for ; Thu, 2 Apr 2015 19:21:33 +0200 (CEST) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga103.fm.intel.com with ESMTP; 02 Apr 2015 10:21:28 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,512,1422950400"; d="scan'208";a="702359890" Received: from irsmsx110.ger.corp.intel.com ([163.33.3.25]) by fmsmga002.fm.intel.com with ESMTP; 02 Apr 2015 10:21:28 -0700 Received: from irsmsx105.ger.corp.intel.com ([169.254.7.2]) by irsmsx110.ger.corp.intel.com ([169.254.15.247]) with mapi id 14.03.0224.002; Thu, 2 Apr 2015 18:21:25 +0100 From: "Ananyev, Konstantin" To: Olivier Matz , "dev@dpdk.org" Thread-Topic: [PATCH v3 1/5] mbuf: fix clone support when application uses private mbuf data Thread-Index: AQHQa+gyjaiCAXJ/uUmIkTCvT5y80Z058RBA Date: Thu, 2 Apr 2015 17:21:25 +0000 Message-ID: <2601191342CEEE43887BDE71AB97725821413A2D@irsmsx105.ger.corp.intel.com> References: <1427385595-15011-1-git-send-email-olivier.matz@6wind.com> <1427829784-12323-1-git-send-email-zer0@droids-corp.org> <1427829784-12323-2-git-send-email-zer0@droids-corp.org> In-Reply-To: <1427829784-12323-2-git-send-email-zer0@droids-corp.org> Accept-Language: en-IE, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [163.33.239.181] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v3 1/5] mbuf: fix clone support when application uses private mbuf data X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 02 Apr 2015 17:21:35 -0000 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; Olivi= er Matz > Subject: [PATCH v3 1/5] mbuf: fix clone support when application uses pri= vate mbuf data >=20 > From: Olivier Matz >=20 > 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. >=20 > 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. >=20 > Signed-off-by: Olivier Matz > --- > 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(-) >=20 > 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 =3D 0; > mb->vlan_tci =3D 0; > mb->hash.rss =3D 0; > + mb->priv_size =3D 0; > } >=20 > 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_de= sc)) >=20 > -#define MBUF_EXT_MEM(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) !=3D (mb= )) > +#define MBUF_EXT_MEM(mb) (rte_mbuf_from_indirect(mb) !=3D (mb)) >=20 > /* mask of enabled ports */ > static uint32_t enabled_port_mask =3D 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 =3D m->pool; > - void *buf =3D RTE_MBUF_TO_BADDR(m); > + void *buf =3D rte_mbuf_to_baddr(m); > uint32_t buf_ofs; > uint32_t buf_len =3D mp->elt_size - sizeof(*m); > m->buf_physaddr =3D 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 =3D mp; > m->nb_segs =3D 1; > m->port =3D 0xff; > + m->priv_size =3D 0; Why it is 0? Shouldn't it be the same calulations as in detach() below: m->priv_size =3D /*get private size from mempool private*/; m->buf_addr =3D (char *)m + sizeof(struct rte_mbuf) + m->priv_size; m->buf_len =3D 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. > } >=20 > /* 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; >=20 > /** > - * 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 =3D (struct rte_mbuf *)((char *)mi->buf_addr - sizeof(*mi) - > + mi->priv_size); (uintptr_t)mi->buf_addr? > + return md; > +} >=20 > /** > - * 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?=20 > + buffer_addr =3D (char *)md + sizeof(*md) + md->priv_size; > + return buffer_addr; > +} >=20 > /** > * Returns TRUE if given mbuf is indirect, or FALSE otherwise. > @@ -688,6 +721,7 @@ static inline struct rte_mbuf *rte_pktmbuf_alloc(stru= ct rte_mempool *mp) >=20 > /** > * 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(stru= ct rte_mempool *mp) > * @param md > * The direct packet mbuf. > */ > - > static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mb= uf *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 =3D md->buf_physaddr; > mi->buf_addr =3D md->buf_addr; > mi->buf_len =3D md->buf_len; > + mi->priv_size =3D md->priv_size; >=20 > mi->next =3D md->next; > mi->data_off =3D md->data_off; > @@ -732,7 +766,8 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf= *mi, struct rte_mbuf *md) > } >=20 > /** > - * 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_mb= uf *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 =3D m->pool; > - void *buf =3D RTE_MBUF_TO_BADDR(m); > - uint32_t buf_len =3D mp->elt_size - sizeof(*m); > - m->buf_physaddr =3D rte_mempool_virt2phy(mp, m) + sizeof (*m); > - > + struct rte_pktmbuf_pool_private *mbp_priv; > + struct rte_mempool *mp =3D m->pool; > + void *buf; > + unsigned mhdr_size; > + > + /* first, restore the priv_size, this is needed before calling > + * rte_mbuf_to_baddr() */ > + mbp_priv =3D rte_mempool_get_priv(mp); > + m->priv_size =3D 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 separ= ate function - rte_mbuf_get_priv_size(m) or something. We need it in few places, and users would probably need it anyway.=20 > + > + buf =3D rte_mbuf_to_baddr(m); > + mhdr_size =3D (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 ab= ove. > + m->buf_physaddr =3D rte_mempool_virt2phy(mp, m) + mhdr_size; Actually I think could just be: m->buf_physaddr =3D rte_mempool_virt2phy(mp, buf); > m->buf_addr =3D buf; > - m->buf_len =3D (uint16_t)buf_len; > - > + m->buf_len =3D (uint16_t)(mp->elt_size - mhdr_size); > m->data_off =3D (RTE_PKTMBUF_HEADROOM <=3D m->buf_len) ? > RTE_PKTMBUF_HEADROOM : m->buf_len; > - > m->data_len =3D 0; > - > m->ol_flags =3D 0; > } >=20 > @@ -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 =3D RTE_MBUF_FROM_BADDR(m->buf_addr); > + struct rte_mbuf *md =3D rte_mbuf_from_indirect(m); > rte_pktmbuf_detach(m); > if (rte_mbuf_refcnt_update(md, -1) =3D=3D 0) > __rte_mbuf_raw_free(md); > -- > 2.1.4