mbuf: introduce indirect attached flag

Currently for mbufs with refcnt, we cannot free mbufs with external memory
buffers (ie. vhost zero copy), as they are recognized as indirect
attached mbufs and therefore we free the direct mbuf it points to,
resulting in an error in the case of external memory buffers.

We solve the issue by introducing the IND_ATTACHED_MBUF flag, which indicates
that the mbuf is an indirect attached mbuf pointing to another mbuf.
When we free an mbuf, we only free the direct mbuf if the flag is set.
Freeing an mbuf with external buffer is the same as freeing a non attached mbuf.
The flag is set during attach and clear on detach.

So in the case of vhost zero copy where we have mbufs with external
buffers, by default we just free the mbuf and it is up to the user to deal with
the external buffer.

This patch would allow the removal of the RTE_MBUF_REFCNT config option,
setting refcnt for all mbufs permanently.

The patch also modifies the vhost example as it was using the
RTE_MBUF_INDIRECT macro to detect if it was an mbuf with external buffer.

Signed-off-by: Sergio Gonzalez Monroy <sergio.gonzalez.monroy@intel.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

diff --git a/examples/vhost/main.c b/examples/vhost/main.c
index a397eae..3220bf6 100644 (file)
--- a/examples/vhost/main.c
+++ b/examples/vhost/main.c
@@ -139,6 +139,8 @@
 /* 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))
+
 /* mask of enabled ports */
 static uint32_t enabled_port_mask = 0;
 
@@ -1601,7 +1603,7 @@ txmbuf_clean_zcp(struct virtio_net *dev, struct vpool *vpool)
 
        for (index = 0; index < mbuf_count; index++) {
                mbuf = __rte_mbuf_raw_alloc(vpool->pool);
-               if (likely(RTE_MBUF_INDIRECT(mbuf)))
+               if (likely(MBUF_EXT_MEM(mbuf)))
                        pktmbuf_detach_zcp(mbuf);
                rte_ring_sp_enqueue(vpool->ring, mbuf);
 
@@ -1664,7 +1666,7 @@ static void mbuf_destroy_zcp(struct vpool *vpool)
        for (index = 0; index < mbuf_count; index++) {
                mbuf = __rte_mbuf_raw_alloc(vpool->pool);
                if (likely(mbuf != NULL)) {
-                       if (likely(RTE_MBUF_INDIRECT(mbuf)))
+                       if (likely(MBUF_EXT_MEM(mbuf)))
                                pktmbuf_detach_zcp(mbuf);
                        rte_ring_sp_enqueue(vpool->ring, (void *)mbuf);
                }

diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index ace6736..f5bafa8 100644 (file)
--- a/lib/librte_mbuf/rte_mbuf.h
+++ b/lib/librte_mbuf/rte_mbuf.h
@@ -189,6 +189,8 @@ extern "C" {
  */
 #define PKT_TX_OUTER_IPV6    (1ULL << 60)
 
+#define IND_ATTACHED_MBUF    (1ULL << 62) /**< Indirect attached mbuf */
+
 /* Use final bit of flags to indicate a control mbuf */
 #define CTRL_MBUF_FLAG       (1ULL << 63) /**< Mbuf contains control data */
 
@@ -335,13 +337,12 @@ struct rte_mbuf {
 /**
  * Returns TRUE if given mbuf is indirect, or FALSE otherwise.
  */
-#define RTE_MBUF_INDIRECT(mb)   (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb))
+#define RTE_MBUF_INDIRECT(mb)   ((mb)->ol_flags & IND_ATTACHED_MBUF)
 
 /**
  * Returns TRUE if given mbuf is direct, or FALSE otherwise.
  */
-#define RTE_MBUF_DIRECT(mb)     (RTE_MBUF_FROM_BADDR((mb)->buf_addr) == (mb))
-
+#define RTE_MBUF_DIRECT(mb)     (!RTE_MBUF_INDIRECT(mb))
 
 /**
  * Private data in case of pktmbuf pool.
@@ -743,7 +744,7 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
        mi->next = NULL;
        mi->pkt_len = mi->data_len;
        mi->nb_segs = 1;
-       mi->ol_flags = md->ol_flags;
+       mi->ol_flags = md->ol_flags | IND_ATTACHED_MBUF;
        mi->packet_type = md->packet_type;
 
        __rte_mbuf_sanity_check(mi, 1);
@@ -774,6 +775,8 @@ static inline void rte_pktmbuf_detach(struct rte_mbuf *m)
                        RTE_PKTMBUF_HEADROOM : m->buf_len;
 
        m->data_len = 0;
+
+       m->ol_flags = 0;
 }
 
 #endif /* RTE_MBUF_REFCNT */
@@ -787,7 +790,6 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
 #ifdef RTE_MBUF_REFCNT
        if (likely (rte_mbuf_refcnt_read(m) == 1) ||
                        likely (rte_mbuf_refcnt_update(m, -1) == 0)) {
-               struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr);
 
                rte_mbuf_refcnt_set(m, 0);
 
@@ -795,7 +797,8 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m)
                 *  - detach mbuf
                 *  - free attached mbuf segment
                 */
-               if (unlikely (md != m)) {
+               if (RTE_MBUF_INDIRECT(m)) {
+                       struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr);
                        rte_pktmbuf_detach(m);
                        if (rte_mbuf_refcnt_update(md, -1) == 0)
                                __rte_mbuf_raw_free(md);