This is a commonly used operation that surprisingly the
DPDK has not supported. The new rte_pktmbuf_copy does a
deep copy of packet. This is a complete copy including
meta-data.
It handles the case where the source mbuf comes from a pool
with larger data area than the destination pool. The routine
also has options for skipping data, or truncating at a fixed
length.
This patch also introduces internal inline to copy the
metadata fields of mbuf.
Signed-off-by: Stephen Hemminger <step...@networkplumber.org>
---
lib/librte_mbuf/rte_mbuf.c | 77 ++++++++++++++++++++++++++++
lib/librte_mbuf/rte_mbuf.h | 55 ++++++++++++++++----
lib/librte_mbuf/rte_mbuf_version.map | 1 +
3 files changed, 122 insertions(+), 11 deletions(-)
diff --git a/lib/librte_mbuf/rte_mbuf.c b/lib/librte_mbuf/rte_mbuf.c
index 9a1a1b5f9468..0236fba76bbc 100644
--- a/lib/librte_mbuf/rte_mbuf.c
+++ b/lib/librte_mbuf/rte_mbuf.c
@@ -321,6 +321,83 @@ __rte_pktmbuf_linearize(struct rte_mbuf *mbuf)
return 0;
}
+/* Create a deep copy of mbuf */
+struct rte_mbuf *
+rte_pktmbuf_copy(const struct rte_mbuf *m, struct rte_mempool *mp,
+ uint32_t off, uint32_t len)
+{
+ const struct rte_mbuf *seg = m;
+ struct rte_mbuf *mc, *m_last, **prev;
+
+ /* garbage in check */
+ __rte_mbuf_sanity_check(m, 1);
+
+ /* check for request to copy at offset past end of mbuf */
+ if (unlikely(off >= m->pkt_len))
+ return NULL;
+
+ mc = rte_pktmbuf_alloc(mp);
+ if (unlikely(mc == NULL))
+ return NULL;
+
+ /* truncate requested length to available data */
+ if (len > m->pkt_len - off)
+ len = m->pkt_len - off;
+
+ __rte_pktmbuf_copy_hdr(mc, m);
+
+ /* copied mbuf is not indirect or external */
+ mc->ol_flags = m->ol_flags & ~(IND_ATTACHED_MBUF|EXT_ATTACHED_MBUF);
+
+ prev = &mc->next;
+ m_last = mc;
+ while (len > 0) {
+ uint32_t copy_len;
+
+ /* skip leading mbuf segments */
+ while (off >= seg->data_len) {
+ off -= seg->data_len;
+ seg = seg->next;
+ }
+
+ /* current buffer is full, chain a new one */
+ if (rte_pktmbuf_tailroom(m_last) == 0) {
+ m_last = rte_pktmbuf_alloc(mp);
+ if (unlikely(m_last == NULL)) {
+ rte_pktmbuf_free(mc);
+ return NULL;
+ }
+ ++mc->nb_segs;
+ *prev = m_last;
+ prev = &m_last->next;
+ }
+
+ /*
+ * copy the min of data in input segment (seg)
+ * vs space available in output (m_last)
+ */
+ copy_len = RTE_MIN(seg->data_len - off, len);
+ if (copy_len > rte_pktmbuf_tailroom(m_last))
+ copy_len = rte_pktmbuf_tailroom(m_last);
+
+ /* append from seg to m_last */
+ rte_memcpy(rte_pktmbuf_mtod_offset(m_last, char *,
+ m_last->data_len),
+ rte_pktmbuf_mtod_offset(seg, char *, off),
+ copy_len);
+
+ /* update offsets and lengths */
+ m_last->data_len += copy_len;
+ mc->pkt_len += copy_len;
+ off += copy_len;
+ len -= copy_len;
+ }
+
+ /* garbage out check */
+ __rte_mbuf_sanity_check(mc, 1);
+ return mc;
+}
+
/* dump a mbuf on console */
void
rte_pktmbuf_dump(FILE *f, const struct rte_mbuf *m, unsigned dump_len)
diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index 6133f12172ae..fb0849ac1473 100644
--- a/lib/librte_mbuf/rte_mbuf.h
+++ b/lib/librte_mbuf/rte_mbuf.h
@@ -1684,6 +1684,19 @@ rte_pktmbuf_attach_extbuf(struct rte_mbuf *m, void
*buf_addr,
*/
#define rte_pktmbuf_detach_extbuf(m) rte_pktmbuf_detach(m)
+/* internal */
+static inline void
+__rte_pktmbuf_copy_hdr(struct rte_mbuf *mdst, const struct rte_mbuf *msrc)
+{
+ mdst->port = msrc->port;
+ mdst->vlan_tci = msrc->vlan_tci;
+ mdst->vlan_tci_outer = msrc->vlan_tci_outer;
+ mdst->tx_offload = msrc->tx_offload;
+ mdst->hash = msrc->hash;
+ mdst->packet_type = msrc->packet_type;
+ mdst->timestamp = msrc->timestamp;
+}
+
/**
* Attach packet mbuf to another packet mbuf.
*
@@ -1721,23 +1734,17 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf
*mi, struct rte_mbuf *m)
mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF;
}
- mi->buf_iova = m->buf_iova;
- mi->buf_addr = m->buf_addr;
- mi->buf_len = m->buf_len;
+ __rte_pktmbuf_copy_hdr(mi, m);
mi->data_off = m->data_off;
mi->data_len = m->data_len;
- mi->port = m->port;
- mi->vlan_tci = m->vlan_tci;
- mi->vlan_tci_outer = m->vlan_tci_outer;
- mi->tx_offload = m->tx_offload;
- mi->hash = m->hash;
+ mi->buf_iova = m->buf_iova;
+ mi->buf_addr = m->buf_addr;
+ mi->buf_len = m->buf_len;
mi->next = NULL;
mi->pkt_len = mi->data_len;
mi->nb_segs = 1;
- mi->packet_type = m->packet_type;
- mi->timestamp = m->timestamp;
__rte_mbuf_sanity_check(mi, 1);
__rte_mbuf_sanity_check(m, 0);
@@ -1908,7 +1915,7 @@ static inline void rte_pktmbuf_free(struct rte_mbuf *m)
}
/**
- * Creates a "clone" of the given packet mbuf.
+ * Create a "clone" 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.
@@ -1927,6 +1934,32 @@ static inline void rte_pktmbuf_free(struct rte_mbuf *m)
struct rte_mbuf *
rte_pktmbuf_clone(struct rte_mbuf *md, struct rte_mempool *mp);
+/**
+ * Create a full copy of a given packet mbuf.
+ *
+ * Copies all the data from a given packet mbuf to a newly allocated
+ * set of mbufs. The private data are is not copied.
+ *
+ * @param m
+ * The packet mbuf to be copiedd.
+ * @param mp
+ * The mempool from which the "clone" mbufs are allocated.
+ * @param offset
+ * The number of bytes to skip before copying.
+ * If the mbuf does not have that many bytes, it is an error
+ * and NULL is returned.
+ * @param length
+ * The upper limit on bytes to copy. Passing UINT32_MAX
+ * means all data (after offset).
+ * @return
+ * - The pointer to the new "clone" mbuf on success.
+ * - NULL if allocation fails.
+ */
+__rte_experimental
+struct rte_mbuf *
+rte_pktmbuf_copy(const struct rte_mbuf *m, struct rte_mempool *mp,
+ uint32_t offset, uint32_t length);
+
/**
* Adds given value to the refcnt of all packet mbuf segments.
*
diff --git a/lib/librte_mbuf/rte_mbuf_version.map
b/lib/librte_mbuf/rte_mbuf_version.map
index ff5c18a5559b..a50dcb6db9ec 100644
--- a/lib/librte_mbuf/rte_mbuf_version.map
+++ b/lib/librte_mbuf/rte_mbuf_version.map
@@ -57,4 +57,5 @@ EXPERIMENTAL {
global:
rte_mbuf_check;
+ rte_pktmbuf_copy;
} DPDK_18.08;
--
2.20.1
