[v4,1/2] mbuf: add function returning default buffer address

Message ID 20190110224030.2671-1-yskoh@mellanox.com
State Superseded, archived
Delegated to: Thomas Monjalon
Headers show
Series
  • [v4,1/2] mbuf: add function returning default buffer address
Related show

Checks

Context Check Description
ci/mellanox-Performance-Testing success Performance Testing PASS
ci/intel-Performance-Testing success Performance Testing PASS
ci/Intel-compilation success Compilation OK
ci/checkpatch warning coding style issues

Commit Message

Yongseok Koh Jan. 10, 2019, 10:40 p.m.
This patch introduces two new functions - rte_mbuf_buf_addr() and
rte_mbuf_data_addr_default().

rte_mbuf_buf_addr() reutrns the default buffer address of given mbuf which
comes after mbuf structure and private data.

rte_mbuf_data_addr_default() returns the default address of mbuf data
taking the headroom into account.

Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
---

Please ignore v3, there were errors with some compilers.

v4:
* fix compilation error due to the experimental tag
* add warning of experimental tag to the comments

v3:
* rename functions

v2:
* initial implementation

 lib/librte_mbuf/rte_mbuf.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

Comments

Olivier Matz Jan. 11, 2019, 8:05 a.m. | #1
On Thu, Jan 10, 2019 at 02:40:29PM -0800, Yongseok Koh wrote:
> This patch introduces two new functions - rte_mbuf_buf_addr() and
> rte_mbuf_data_addr_default().
> 
> rte_mbuf_buf_addr() reutrns the default buffer address of given mbuf which
> comes after mbuf structure and private data.
> 
> rte_mbuf_data_addr_default() returns the default address of mbuf data
> taking the headroom into account.
> 
> Signed-off-by: Yongseok Koh <yskoh@mellanox.com>

Acked-by: Olivier Matz <olivier.matz@6wind.com>
David Marchand Jan. 11, 2019, 8:11 a.m. | #2
On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh <yskoh@mellanox.com> wrote:

> This patch introduces two new functions - rte_mbuf_buf_addr() and
> rte_mbuf_data_addr_default().
>
> rte_mbuf_buf_addr() reutrns the default buffer address of given mbuf which
>

returns


> comes after mbuf structure and private data.
>
> rte_mbuf_data_addr_default() returns the default address of mbuf data
> taking the headroom into account.
>
> Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
> ---
>
> Please ignore v3, there were errors with some compilers.
>
> v4:
> * fix compilation error due to the experimental tag
> * add warning of experimental tag to the comments
>
> v3:
> * rename functions
>
> v2:
> * initial implementation
>
>  lib/librte_mbuf/rte_mbuf.h | 46
> ++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 46 insertions(+)
>
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index bc562dc8a9..5787616999 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -788,8 +788,54 @@ rte_mbuf_from_indirect(struct rte_mbuf *mi)
>  }
>
>  /**
> + * Return the default buffer address of the mbuf.
>

Nit: missed it... s/default //

+ *
> + * @warning
> + * @b EXPERIMENTAL: This API may change without prior notice.
> + * This will be used by rte_mbuf_to_baddr() which has redundant code once
> + * experimental tag is removed.
>

Good point.
I wonder if we have a "todolist" for release n+2 so that we don't forget
about such things to do.
Thomas ?

+ *
> + * @param mb
> + *   The pointer to the mbuf.
> + * @param mp
> + *   The pointer to the mempool of the mbuf.
> + * @return
> + *   The pointer of the mbuf buffer.
> + */
> +static inline char * __rte_experimental
> +rte_mbuf_buf_addr(struct rte_mbuf *mb, struct rte_mempool *mp)
> +{
> +       char *buffer_addr;
> +
> +       buffer_addr = (char *)mb + sizeof(*mb) + rte_pktmbuf_priv_size(mp);
> +       return buffer_addr;
> +}
>

Nit:
+       return (char *)mb + sizeof(*mb) + rte_pktmbuf_priv_size(mp);

+
> +/**
> + * Return the default address of the beginning of the mbuf data.
> + *
> + * @warning
> + * @b EXPERIMENTAL: This API may change without prior notice.
> + *
> + * @param mb
> + *   The pointer to the mbuf.
> + * @return
> + *   The pointer of the beginning of the mbuf data.
> + */
> +static inline char * __rte_experimental
> +rte_mbuf_data_addr_default(struct rte_mbuf *mb)
> +{
> +       return rte_mbuf_buf_addr(mb, mb->pool) + RTE_PKTMBUF_HEADROOM;
> +}
> +
> +/**
>   * Return the buffer address embedded in the given mbuf.
>   *
> + * @note: Accessing mempool pointer of a mbuf is expensive because the
> + * pointer is stored in the 2nd cache line of mbuf. If mempool is known,
> it
> + * is better not to reference the mempool pointer in mbuf but calling
> + * rte_mbuf_buf_addr() would be more efficient.
> + *
>   * @param md
>   *   The pointer to the mbuf.
>   * @return
> --
> 2.11.0
>
>
Thanks Yongseok.
Reviewed-by: David Marchand <david.marchand@redhat.com>
David Marchand Jan. 11, 2019, 8:32 a.m. | #3
On Fri, Jan 11, 2019 at 9:11 AM David Marchand <david.marchand@redhat.com>
wrote:

> On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh <yskoh@mellanox.com> wrote:
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
>
>> index bc562dc8a9..5787616999 100644
>> --- a/lib/librte_mbuf/rte_mbuf.h
>> +++ b/lib/librte_mbuf/rte_mbuf.h
>> @@ -788,8 +788,54 @@ rte_mbuf_from_indirect(struct rte_mbuf *mi)
>>  }
>>
>>  /**
>> + * Return the default buffer address of the mbuf.
>>
>
> Nit: missed it... s/default //
>
> + *
>> + * @warning
>> + * @b EXPERIMENTAL: This API may change without prior notice.
>> + * This will be used by rte_mbuf_to_baddr() which has redundant code once
>> + * experimental tag is removed.
>>
>
> Good point.
> I wonder if we have a "todolist" for release n+2 so that we don't forget
> about such things to do.
> Thomas ?
>

Maybe we could have something explicit in rte_mbuf_to_baddr that would
avoid it "inherits" the experimental tag.

@@ -844,9 +844,13 @@ struct rte_mbuf_ext_shared_info {
 static inline char *
 rte_mbuf_to_baddr(struct rte_mbuf *md)
 {
+#ifdef ALLOW_EXPERIMENTAL_API
+       return rte_mbuf_buf_addr(md, md->pool);
+#else
        char *buffer_addr;
        buffer_addr = (char *)md + sizeof(*md) +
rte_pktmbuf_priv_size(md->pool);
        return buffer_addr;
+#endif
 }

 /**
Thomas Monjalon Jan. 11, 2019, 10:25 a.m. | #4
11/01/2019 09:11, David Marchand:
> On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh <yskoh@mellanox.com> wrote:
> > + * @warning
> > + * @b EXPERIMENTAL: This API may change without prior notice.
> > + * This will be used by rte_mbuf_to_baddr() which has redundant code once
> > + * experimental tag is removed.
> 
> Good point.
> I wonder if we have a "todolist" for release n+2 so that we don't forget
> about such things to do.
> Thomas ?

If code comment is not enough, we can use Bugzilla.
Yongseok Koh Jan. 11, 2019, 11:09 a.m. | #5
On Fri, Jan 11, 2019 at 09:32:52AM +0100, David Marchand wrote:
> On Fri, Jan 11, 2019 at 9:11 AM David Marchand <david.marchand@redhat.com>
> wrote:
> 
> > On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh <yskoh@mellanox.com> wrote:
> > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> >
> >> index bc562dc8a9..5787616999 100644
> >> --- a/lib/librte_mbuf/rte_mbuf.h
> >> +++ b/lib/librte_mbuf/rte_mbuf.h
> >> @@ -788,8 +788,54 @@ rte_mbuf_from_indirect(struct rte_mbuf *mi)
> >>  }
> >>
> >>  /**
> >> + * Return the default buffer address of the mbuf.
> >>
> >
> > Nit: missed it... s/default //

Okay

> >
> > + *
> >> + * @warning
> >> + * @b EXPERIMENTAL: This API may change without prior notice.
> >> + * This will be used by rte_mbuf_to_baddr() which has redundant code once
> >> + * experimental tag is removed.
> >>
> >
> > Good point.
> > I wonder if we have a "todolist" for release n+2 so that we don't forget
> > about such things to do.
> > Thomas ?
> >
> 
> Maybe we could have something explicit in rte_mbuf_to_baddr that would
> avoid it "inherits" the experimental tag.
> 
> @@ -844,9 +844,13 @@ struct rte_mbuf_ext_shared_info {
>  static inline char *
>  rte_mbuf_to_baddr(struct rte_mbuf *md)
>  {
> +#ifdef ALLOW_EXPERIMENTAL_API
> +       return rte_mbuf_buf_addr(md, md->pool);
> +#else
>         char *buffer_addr;
>         buffer_addr = (char *)md + sizeof(*md) +
> rte_pktmbuf_priv_size(md->pool);
>         return buffer_addr;
> +#endif

I like it, so that we can't forget to change it.

Yongseok

Patch

diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
index bc562dc8a9..5787616999 100644
--- a/lib/librte_mbuf/rte_mbuf.h
+++ b/lib/librte_mbuf/rte_mbuf.h
@@ -788,8 +788,54 @@  rte_mbuf_from_indirect(struct rte_mbuf *mi)
 }
 
 /**
+ * Return the default buffer address of the mbuf.
+ *
+ * @warning
+ * @b EXPERIMENTAL: This API may change without prior notice.
+ * This will be used by rte_mbuf_to_baddr() which has redundant code once
+ * experimental tag is removed.
+ *
+ * @param mb
+ *   The pointer to the mbuf.
+ * @param mp
+ *   The pointer to the mempool of the mbuf.
+ * @return
+ *   The pointer of the mbuf buffer.
+ */
+static inline char * __rte_experimental
+rte_mbuf_buf_addr(struct rte_mbuf *mb, struct rte_mempool *mp)
+{
+	char *buffer_addr;
+
+	buffer_addr = (char *)mb + sizeof(*mb) + rte_pktmbuf_priv_size(mp);
+	return buffer_addr;
+}
+
+/**
+ * Return the default address of the beginning of the mbuf data.
+ *
+ * @warning
+ * @b EXPERIMENTAL: This API may change without prior notice.
+ *
+ * @param mb
+ *   The pointer to the mbuf.
+ * @return
+ *   The pointer of the beginning of the mbuf data.
+ */
+static inline char * __rte_experimental
+rte_mbuf_data_addr_default(struct rte_mbuf *mb)
+{
+	return rte_mbuf_buf_addr(mb, mb->pool) + RTE_PKTMBUF_HEADROOM;
+}
+
+/**
  * Return the buffer address embedded in the given mbuf.
  *
+ * @note: Accessing mempool pointer of a mbuf is expensive because the
+ * pointer is stored in the 2nd cache line of mbuf. If mempool is known, it
+ * is better not to reference the mempool pointer in mbuf but calling
+ * rte_mbuf_buf_addr() would be more efficient.
+ *
  * @param md
  *   The pointer to the mbuf.
  * @return