[dpdk-dev] [PATCH 1/2] mbuf: Add rte_pktmbuf_copy

Stephen Hemminger stephen at networkplumber.org
Fri Jan 22 18:33:45 CET 2016


On Fri, 22 Jan 2016 13:40:44 +0000
"Mrzyglod, DanielX T" <danielx.t.mrzyglod at intel.com> wrote:

> 
> 
> >-----Original Message-----
> >From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen Hemminger
> >Sent: Friday, July 10, 2015 1:38 AM
> >To: dev at dpdk.org
> >Cc: Mike Davison <mdavison at brocade.com>; Stephen Hemminger
> ><shemming at brocade.com>
> >Subject: [dpdk-dev] [PATCH 1/2] mbuf: Add rte_pktmbuf_copy
> >
> >From: Stephen Hemminger <shemming at brocade.com>
> >
> >Added rte_pktmbuf_copy() function since copying multi-part
> >segments is common issue and can be problematic.
> >
> >Signed-off-by: Mike Davison <mdavison at brocade.com>
> >Reviewed-by: Stephen Hemminger <shemming at brocade.com>
> >---
> > lib/librte_mbuf/rte_mbuf.h | 59
> >++++++++++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 59 insertions(+)
> >
> >diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> >index 80419df..f0a543b 100644
> >--- a/lib/librte_mbuf/rte_mbuf.h
> >+++ b/lib/librte_mbuf/rte_mbuf.h
> >@@ -60,6 +60,7 @@
> > #include <rte_atomic.h>
> > #include <rte_prefetch.h>
> > #include <rte_branch_prediction.h>
> >+#include <rte_memcpy.h>
> >
> > #ifdef __cplusplus
> > extern "C" {
> >@@ -1272,6 +1273,64 @@ static inline int rte_pktmbuf_is_contiguous(const
> >struct rte_mbuf *m)
> > 	return !!(m->nb_segs == 1);
> > }
> >
> >+/*
> >+ * Creates a copy of the given packet mbuf.
> >+ *
> >+ * Walks through all segments of the given packet mbuf, and for each of them:
> >+ *  - Creates a new packet mbuf from the given pool.
> >+ *  - Copy segment to newly created mbuf.
> >+ * Then updates pkt_len and nb_segs of the new packet mbuf to match values
> >+ * from the original packet mbuf.
> >+ *
> >+ * @param md
> >+ *   The packet mbuf to be copied.
> >+ * @param mp
> >+ *   The mempool from which the mbufs are allocated.
> >+ * @return
> >+ *   - The pointer to the new mbuf on success.
> >+ *   - NULL if allocation fails.
> >+ */
> >+static inline struct rte_mbuf *rte_pktmbuf_copy(struct rte_mbuf *md,
> >+		struct rte_mempool *mp)
> >+{
> >+	struct rte_mbuf *mc = NULL;
> >+	struct rte_mbuf **prev = &mc;
> >+
> >+	do {
> >+		struct rte_mbuf *mi;
> >+
> >+		mi = rte_pktmbuf_alloc(mp);
> >+		if (unlikely(mi == NULL)) {
> >+			rte_pktmbuf_free(mc);
> >+			return NULL;
> >+		}
> >+
> >+		mi->data_off = md->data_off;
> >+		mi->data_len = md->data_len;
> >+		mi->port = md->port;
> >+		mi->vlan_tci = md->vlan_tci;
> >+		mi->tx_offload = md->tx_offload;
> >+		mi->hash = md->hash;
> >+
> >+		mi->next = NULL;
> >+		mi->pkt_len = md->pkt_len;
> >+		mi->nb_segs = md->nb_segs;
> >+		mi->ol_flags = md->ol_flags;
> >+		mi->packet_type = md->packet_type;
> >+
> >+		rte_memcpy(rte_pktmbuf_mtod(mi, char *),
> >+			   rte_pktmbuf_mtod(md, char *),
> >+			   md->data_len);
> >+
> >+		*prev = mi;
> >+		prev = &mi->next;
> >+	} while ((md = md->next) != NULL);
> >+
> >+	*prev = NULL;
> >+	__rte_mbuf_sanity_check(mc, 1);
> >+	return mc;
> >+}
> >+
> > /**
> >  * Dump an mbuf structure to the console.
> >  *
> >--
> >2.1.4
> 
> Hi Stephen :>
> This patch look useful in case of backup buffs. 
> There will be second approach ?

I did bother resubmitting it since unless there are users in current
code base it would likely rot.


More information about the dev mailing list