The IPv6 can have large extension header, like the "Segment Routing" may have (32 + 1) * 8 = 264 bytes, the 8 bits size of L3 length can't handle this case correctly. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> --- lib/librte_net/rte_net.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h index 94b06d9ee..992fb088a 100644 --- a/lib/librte_net/rte_net.h +++ b/lib/librte_net/rte_net.h @@ -20,11 +20,11 @@ extern "C" { */ struct rte_net_hdr_lens { uint8_t l2_len; - uint8_t l3_len; + uint16_t l3_len; uint8_t l4_len; uint8_t tunnel_len; uint8_t inner_l2_len; - uint8_t inner_l3_len; + uint16_t inner_l3_len; uint8_t inner_l4_len; }; -- 2.28.0
On Fri, 4 Sep 2020 13:40:20 +0800
Haiyue Wang <haiyue.wang@intel.com> wrote:
> diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h
> index 94b06d9ee..992fb088a 100644
> --- a/lib/librte_net/rte_net.h
> +++ b/lib/librte_net/rte_net.h
> @@ -20,11 +20,11 @@ extern "C" {
> */
> struct rte_net_hdr_lens {
> uint8_t l2_len;
> - uint8_t l3_len;
> + uint16_t l3_len;
> uint8_t l4_len;
Please reorder these to avoid creating a structure hole.
Align to the rte_mbuf's design about Tx header length data size for the header length parse result. struct { uint64_t l2_len:7; /* 88: 0 8 */ uint64_t l3_len:9; /* 88: 7 8 */ uint64_t l4_len:8; /* 88:16 8 */ uint64_t tso_segsz:16; /* 88:24 8 */ uint64_t outer_l3_len:9; /* 88:40 8 */ uint64_t outer_l2_len:7; /* 88:49 8 */ }; Now the IPv6 can support bigger extension header. The below is the structure hole analysis result: Before: struct rte_net_hdr_lens { uint8_t l2_len; /* 0 1 */ uint8_t l3_len; /* 1 1 */ uint8_t l4_len; /* 2 1 */ uint8_t tunnel_len; /* 3 1 */ uint8_t inner_l2_len; /* 4 1 */ uint8_t inner_l3_len; /* 5 1 */ uint8_t inner_l4_len; /* 6 1 */ /* size: 7, cachelines: 1, members: 7 */ /* last cacheline: 7 bytes */ }; Now: struct rte_net_hdr_lens { uint64_t l2_len:7; /* 0: 0 8 */ uint64_t l3_len:9; /* 0: 7 8 */ uint64_t l4_len:8; /* 0:16 8 */ uint64_t tunnel_len:8; /* 0:24 8 */ uint64_t inner_l2_len:7; /* 0:32 8 */ uint64_t inner_l3_len:9; /* 0:39 8 */ uint64_t inner_l4_len:8; /* 0:48 8 */ /* size: 8, cachelines: 1, members: 7 */ /* bit_padding: 8 bits */ /* last cacheline: 8 bytes */ }; Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> --- v2: use bit field to avoid creating a structure hole. --- lib/librte_net/rte_net.h | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h index 94b06d9ee..a14e3d814 100644 --- a/lib/librte_net/rte_net.h +++ b/lib/librte_net/rte_net.h @@ -18,14 +18,15 @@ extern "C" { * Structure containing header lengths associated to a packet, filled * by rte_net_get_ptype(). */ +__extension__ struct rte_net_hdr_lens { - uint8_t l2_len; - uint8_t l3_len; - uint8_t l4_len; - uint8_t tunnel_len; - uint8_t inner_l2_len; - uint8_t inner_l3_len; - uint8_t inner_l4_len; + uint64_t l2_len:7; + uint64_t l3_len:9; + uint64_t l4_len:8; + uint64_t tunnel_len:8; + uint64_t inner_l2_len:7; + uint64_t inner_l3_len:9; + uint64_t inner_l4_len:8; }; /** -- 2.28.0
> -----Original Message-----
> From: Stephen Hemminger <stephen@networkplumber.org>
> Sent: Saturday, September 5, 2020 02:56
> To: Wang, Haiyue <haiyue.wang@intel.com>
> Cc: dev@dpdk.org; Olivier Matz <olivier.matz@6wind.com>
> Subject: Re: [dpdk-dev] [PATCH v1] net: expand the data size of L3 length to 16 bits
>
> On Fri, 4 Sep 2020 13:40:20 +0800
> Haiyue Wang <haiyue.wang@intel.com> wrote:
>
> > diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h
> > index 94b06d9ee..992fb088a 100644
> > --- a/lib/librte_net/rte_net.h
> > +++ b/lib/librte_net/rte_net.h
> > @@ -20,11 +20,11 @@ extern "C" {
> > */
> > struct rte_net_hdr_lens {
> > uint8_t l2_len;
> > - uint8_t l3_len;
> > + uint16_t l3_len;
> > uint8_t l4_len;
>
> Please reorder these to avoid creating a structure hole.
Done in v2, I use the bit field like rte_mbuf, and keep the member's original order.
On Sat, 5 Sep 2020 11:06:46 +0800
Haiyue Wang <haiyue.wang@intel.com> wrote:
> Align to the rte_mbuf's design about Tx header length data size for the
> header length parse result.
> struct {
> uint64_t l2_len:7; /* 88: 0 8 */
> uint64_t l3_len:9; /* 88: 7 8 */
> uint64_t l4_len:8; /* 88:16 8 */
> uint64_t tso_segsz:16; /* 88:24 8 */
> uint64_t outer_l3_len:9; /* 88:40 8 */
> uint64_t outer_l2_len:7; /* 88:49 8 */
> };
>
> Now the IPv6 can support bigger extension header.
>
> The below is the structure hole analysis result:
>
> Before:
> struct rte_net_hdr_lens {
> uint8_t l2_len; /* 0 1 */
> uint8_t l3_len; /* 1 1 */
> uint8_t l4_len; /* 2 1 */
> uint8_t tunnel_len; /* 3 1 */
> uint8_t inner_l2_len; /* 4 1 */
> uint8_t inner_l3_len; /* 5 1 */
> uint8_t inner_l4_len; /* 6 1 */
>
> /* size: 7, cachelines: 1, members: 7 */
> /* last cacheline: 7 bytes */
> };
>
> Now:
> struct rte_net_hdr_lens {
> uint64_t l2_len:7; /* 0: 0 8 */
> uint64_t l3_len:9; /* 0: 7 8 */
> uint64_t l4_len:8; /* 0:16 8 */
> uint64_t tunnel_len:8; /* 0:24 8 */
> uint64_t inner_l2_len:7; /* 0:32 8 */
> uint64_t inner_l3_len:9; /* 0:39 8 */
> uint64_t inner_l4_len:8; /* 0:48 8 */
>
> /* size: 8, cachelines: 1, members: 7 */
> /* bit_padding: 8 bits */
> /* last cacheline: 8 bytes */
> };
>
> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
Bitfields are slow to access, compiler has to do mask/shift operations.
And there is no requirement that structure be the same size.
There is no requirement that fields be ordered the same as
the protocol header. Also tunnel length might get big.
Why not:
struct rte_net_hdr_lens {
uint8_t l2_len;
uint8_t inner_l2_len;
uint16_t l3_len;
uint16_t inner_l3_len;
uint16_t tunnel_len;
uint8_t l4_len;
uint8_t inner_l4_len;
};
Enlarge the L3 and tunnel header length from 8-bit to 16-bit to handle the bigger headers. And reorder the fields to avoid creating a structure hole. Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> --- v2: use bit field to avoid creating a structure hole. v3: use basic type and reorder to avoid structure hole. --- lib/librte_net/rte_net.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h index 94b06d9ee..434435ffa 100644 --- a/lib/librte_net/rte_net.h +++ b/lib/librte_net/rte_net.h @@ -20,11 +20,11 @@ extern "C" { */ struct rte_net_hdr_lens { uint8_t l2_len; - uint8_t l3_len; - uint8_t l4_len; - uint8_t tunnel_len; uint8_t inner_l2_len; - uint8_t inner_l3_len; + uint16_t l3_len; + uint16_t inner_l3_len; + uint16_t tunnel_len; + uint8_t l4_len; uint8_t inner_l4_len; }; -- 2.28.0
Hi Stephen, > -----Original Message----- > From: Stephen Hemminger <stephen@networkplumber.org> > Sent: Sunday, September 6, 2020 00:56 > To: Wang, Haiyue <haiyue.wang@intel.com> > Cc: dev@dpdk.org; Yigit, Ferruh <ferruh.yigit@intel.com>; Olivier Matz <olivier.matz@6wind.com> > Subject: Re: [PATCH v2] net: adjust the header length parse size > > On Sat, 5 Sep 2020 11:06:46 +0800 > Haiyue Wang <haiyue.wang@intel.com> wrote: > > > Align to the rte_mbuf's design about Tx header length data size for the > > header length parse result. > > struct { > > uint64_t l2_len:7; /* 88: 0 8 */ > > uint64_t l3_len:9; /* 88: 7 8 */ > > uint64_t l4_len:8; /* 88:16 8 */ > > uint64_t tso_segsz:16; /* 88:24 8 */ > > uint64_t outer_l3_len:9; /* 88:40 8 */ > > uint64_t outer_l2_len:7; /* 88:49 8 */ > > }; > > > > Now the IPv6 can support bigger extension header. > > > > The below is the structure hole analysis result: > > > > Before: > > struct rte_net_hdr_lens { > > uint8_t l2_len; /* 0 1 */ > > uint8_t l3_len; /* 1 1 */ > > uint8_t l4_len; /* 2 1 */ > > uint8_t tunnel_len; /* 3 1 */ > > uint8_t inner_l2_len; /* 4 1 */ > > uint8_t inner_l3_len; /* 5 1 */ > > uint8_t inner_l4_len; /* 6 1 */ > > > > /* size: 7, cachelines: 1, members: 7 */ > > /* last cacheline: 7 bytes */ > > }; > > > > Now: > > struct rte_net_hdr_lens { > > uint64_t l2_len:7; /* 0: 0 8 */ > > uint64_t l3_len:9; /* 0: 7 8 */ > > uint64_t l4_len:8; /* 0:16 8 */ > > uint64_t tunnel_len:8; /* 0:24 8 */ > > uint64_t inner_l2_len:7; /* 0:32 8 */ > > uint64_t inner_l3_len:9; /* 0:39 8 */ > > uint64_t inner_l4_len:8; /* 0:48 8 */ > > > > /* size: 8, cachelines: 1, members: 7 */ > > /* bit_padding: 8 bits */ > > /* last cacheline: 8 bytes */ > > }; > > > > Signed-off-by: Haiyue Wang <haiyue.wang@intel.com> > > Bitfields are slow to access, compiler has to do mask/shift operations. Yes, you are right, I use rdtsc to trace the rte_net_get_ptype run clock about 100000 times, bitfields is near 40, but original is about 30. > And there is no requirement that structure be the same size. > > There is no requirement that fields be ordered the same as > the protocol header. Also tunnel length might get big. > Why not: > > struct rte_net_hdr_lens { > uint8_t l2_len; > uint8_t inner_l2_len; > uint16_t l3_len; > uint16_t inner_l3_len; > uint16_t tunnel_len; > uint8_t l4_len; > uint8_t inner_l4_len; > }; > Thanks for your comment, this is better, and in v3. ;-) The run clock is nearly the same as original type.
On Mon, 7 Sep 2020 09:56:50 +0800
Haiyue Wang <haiyue.wang@intel.com> wrote:
> Enlarge the L3 and tunnel header length from 8-bit to 16-bit to handle
> the bigger headers. And reorder the fields to avoid creating a structure
> hole.
>
> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
> ---
> v2: use bit field to avoid creating a structure hole.
> v3: use basic type and reorder to avoid structure hole.
> ---
> lib/librte_net/rte_net.h | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h
> index 94b06d9ee..434435ffa 100644
> --- a/lib/librte_net/rte_net.h
> +++ b/lib/librte_net/rte_net.h
> @@ -20,11 +20,11 @@ extern "C" {
> */
> struct rte_net_hdr_lens {
> uint8_t l2_len;
> - uint8_t l3_len;
> - uint8_t l4_len;
> - uint8_t tunnel_len;
> uint8_t inner_l2_len;
> - uint8_t inner_l3_len;
> + uint16_t l3_len;
> + uint16_t inner_l3_len;
> + uint16_t tunnel_len;
> + uint8_t l4_len;
> uint8_t inner_l4_len;
> };
>
Acked-by: Stephhen Hemminger <stephen@networkplumber.org>
On 9/8/2020 3:53 PM, Stephen Hemminger wrote:
> On Mon, 7 Sep 2020 09:56:50 +0800
> Haiyue Wang <haiyue.wang@intel.com> wrote:
>
>> Enlarge the L3 and tunnel header length from 8-bit to 16-bit to handle
>> the bigger headers. And reorder the fields to avoid creating a structure
>> hole.
>>
>> Signed-off-by: Haiyue Wang <haiyue.wang@intel.com>
>> ---
>> v2: use bit field to avoid creating a structure hole.
>> v3: use basic type and reorder to avoid structure hole.
>> ---
>> lib/librte_net/rte_net.h | 8 ++++----
>> 1 file changed, 4 insertions(+), 4 deletions(-)
>>
>> diff --git a/lib/librte_net/rte_net.h b/lib/librte_net/rte_net.h
>> index 94b06d9ee..434435ffa 100644
>> --- a/lib/librte_net/rte_net.h
>> +++ b/lib/librte_net/rte_net.h
>> @@ -20,11 +20,11 @@ extern "C" {
>> */
>> struct rte_net_hdr_lens {
>> uint8_t l2_len;
>> - uint8_t l3_len;
>> - uint8_t l4_len;
>> - uint8_t tunnel_len;
>> uint8_t inner_l2_len;
>> - uint8_t inner_l3_len;
>> + uint16_t l3_len;
>> + uint16_t inner_l3_len;
>> + uint16_t tunnel_len;
>> + uint8_t l4_len;
>> uint8_t inner_l4_len;
>> };
>>
>
> Acked-by: Stephhen Hemminger <stephen@networkplumber.org>
>
Applied to dpdk-next-net/main, thanks.