diff mbox

[dpdk-dev,04/17] ixgbe: support of unified packet type

Message ID 1422501365-12643-5-git-send-email-helin.zhang@intel.com (mailing list archive)
State Superseded, archived
Headers

Commit Message

Zhang, Helin Jan. 29, 2015, 3:15 a.m. UTC 
To unify packet types among all PMDs, bit masks of packet type for
ol_flags are replaced by unified packet type for Vector PMD.

Signed-off-by: Cunming Liang <cunming.liang@intel.com>
Signed-off-by: Helin Zhang <helin.zhang@intel.com>
---
 lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 39 +++++++++++++++++++----------------
 1 file changed, 21 insertions(+), 18 deletions(-)

Comments

Bruce Richardson Jan. 29, 2015, 11:30 p.m. UTC | #1 
On Thu, Jan 29, 2015 at 11:15:52AM +0800, Helin Zhang wrote:
> To unify packet types among all PMDs, bit masks of packet type for
> ol_flags are replaced by unified packet type for Vector PMD.
> 

Two suggestions on the commit log:
1. Can you add scalar and vector into the titles to make it clear how this
patch and the previous ones differ
2. Can you add a note calling out performance impacts for this patch. If no
performance impacts, then please note that for reviewers.

/Bruce

> Signed-off-by: Cunming Liang <cunming.liang@intel.com>
> Signed-off-by: Helin Zhang <helin.zhang@intel.com>
> ---
>  lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 39 +++++++++++++++++++----------------
>  1 file changed, 21 insertions(+), 18 deletions(-)
> 
> diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> index b54cb19..b3cf7dd 100644
> --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> @@ -134,44 +134,35 @@ ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
>   */
>  #ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE
>  
> -#define OLFLAGS_MASK     ((uint16_t)(PKT_RX_VLAN_PKT | PKT_RX_IPV4_HDR |\
> -				     PKT_RX_IPV4_HDR_EXT | PKT_RX_IPV6_HDR |\
> -				     PKT_RX_IPV6_HDR_EXT))
> -#define OLFLAGS_MASK_V   (((uint64_t)OLFLAGS_MASK << 48) | \
> -			  ((uint64_t)OLFLAGS_MASK << 32) | \
> -			  ((uint64_t)OLFLAGS_MASK << 16) | \
> -			  ((uint64_t)OLFLAGS_MASK))
> -#define PTYPE_SHIFT    (1)
> +#define OLFLAGS_MASK_V   (((uint64_t)PKT_RX_VLAN_PKT << 48) | \
> +			  ((uint64_t)PKT_RX_VLAN_PKT << 32) | \
> +			  ((uint64_t)PKT_RX_VLAN_PKT << 16) | \
> +			  ((uint64_t)PKT_RX_VLAN_PKT))
>  #define VTAG_SHIFT     (3)
>  
>  static inline void
>  desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
>  {
> -	__m128i ptype0, ptype1, vtag0, vtag1;
> +	__m128i vtag0, vtag1;
>  	union {
>  		uint16_t e[4];
>  		uint64_t dword;
>  	} vol;
>  
> -	ptype0 = _mm_unpacklo_epi16(descs[0], descs[1]);
> -	ptype1 = _mm_unpacklo_epi16(descs[2], descs[3]);
>  	vtag0 = _mm_unpackhi_epi16(descs[0], descs[1]);
>  	vtag1 = _mm_unpackhi_epi16(descs[2], descs[3]);
>  
> -	ptype1 = _mm_unpacklo_epi32(ptype0, ptype1);
>  	vtag1 = _mm_unpacklo_epi32(vtag0, vtag1);
> -
> -	ptype1 = _mm_slli_epi16(ptype1, PTYPE_SHIFT);
>  	vtag1 = _mm_srli_epi16(vtag1, VTAG_SHIFT);
>  
> -	ptype1 = _mm_or_si128(ptype1, vtag1);
> -	vol.dword = _mm_cvtsi128_si64(ptype1) & OLFLAGS_MASK_V;
> +	vol.dword = _mm_cvtsi128_si64(vtag1) & OLFLAGS_MASK_V;
>  
>  	rx_pkts[0]->ol_flags = vol.e[0];
>  	rx_pkts[1]->ol_flags = vol.e[1];
>  	rx_pkts[2]->ol_flags = vol.e[2];
>  	rx_pkts[3]->ol_flags = vol.e[3];
>  }
> +
>  #else
>  #define desc_to_olflags_v(desc, rx_pkts) do {} while (0)
>  #endif
> @@ -204,6 +195,8 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
>  				0            /* ignore pkt_type field */
>  			);
>  	__m128i dd_check, eop_check;
> +	__m128i desc_mask = _mm_set_epi32(0xFFFFFFFF, 0xFFFFFFFF,
> +					  0xFFFFFFFF, 0xFFFF07F0);
>  
>  	if (unlikely(nb_pkts < RTE_IXGBE_VPMD_RX_BURST))
>  		return 0;
> @@ -239,7 +232,8 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
>  		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
>  		13, 12,      /* octet 12~13, low 16 bits pkt_len */
>  		13, 12,      /* octet 12~13, 16 bits data_len */
> -		0xFF, 0xFF   /* skip pkt_type field */
> +		1,           /* octet 1, 8 bits pkt_type field */
> +		0            /* octet 0, 4 bits offset 4 pkt_type field */
>  		);
>  
>  	/* Cache is empty -> need to scan the buffer rings, but first move
> @@ -248,6 +242,7 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
>  
>  	/*
>  	 * A. load 4 packet in one loop
> +	 * [A*. mask out 4 unused dirty field in desc]
>  	 * B. copy 4 mbuf point from swring to rx_pkts
>  	 * C. calc the number of DD bits among the 4 packets
>  	 * [C*. extract the end-of-packet bit, if requested]
> @@ -289,6 +284,14 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
>  		/* B.2 copy 2 mbuf point into rx_pkts  */
>  		_mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
>  
> +		/* A* mask out 0~3 bits RSS type */
> +		descs[3] = _mm_and_si128(descs[3], desc_mask);
> +		descs[2] = _mm_and_si128(descs[2], desc_mask);
> +
> +		/* A* mask out 0~3 bits RSS type */
> +		descs[1] = _mm_and_si128(descs[1], desc_mask);
> +		descs[0] = _mm_and_si128(descs[0], desc_mask);
> +
>  		/* avoid compiler reorder optimization */
>  		rte_compiler_barrier();
>  
> @@ -301,7 +304,7 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
>  		/* C.1 4=>2 filter staterr info only */
>  		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
>  
> -		/* set ol_flags with packet type and vlan tag */
> +		/* set ol_flags with vlan packet type */
>  		desc_to_olflags_v(descs, &rx_pkts[pos]);
>  
>  		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
> -- 
> 1.8.1.4
>
Cunming Liang Jan. 29, 2015, 11:52 p.m. UTC | #2 
> -----Original Message-----
> From: Richardson, Bruce
> Sent: Thursday, January 29, 2015 4:30 PM
> To: Zhang, Helin
> Cc: dev@dpdk.org; Cao, Waterman; Liang, Cunming; Liu, Jijiang; Ananyev,
> Konstantin
> Subject: Re: [PATCH 04/17] ixgbe: support of unified packet type
> 
> On Thu, Jan 29, 2015 at 11:15:52AM +0800, Helin Zhang wrote:
> > To unify packet types among all PMDs, bit masks of packet type for
> > ol_flags are replaced by unified packet type for Vector PMD.
> >
> 
> Two suggestions on the commit log:
> 1. Can you add scalar and vector into the titles to make it clear how this
> patch and the previous ones differ
> 2. Can you add a note calling out performance impacts for this patch. If no
> performance impacts, then please note that for reviewers.
[Liang, Cunming] Accept, will update it in v2.
For performance, lose 1 cycle per packet during 4x10GE io fwd loopback unit test.

> 
> /Bruce
> 
> > Signed-off-by: Cunming Liang <cunming.liang@intel.com>
> > Signed-off-by: Helin Zhang <helin.zhang@intel.com>
> > ---
> >  lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 39
> +++++++++++++++++++----------------
> >  1 file changed, 21 insertions(+), 18 deletions(-)
> >
> > diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > index b54cb19..b3cf7dd 100644
> > --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > @@ -134,44 +134,35 @@ ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
> >   */
> >  #ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE
> >
> > -#define OLFLAGS_MASK     ((uint16_t)(PKT_RX_VLAN_PKT |
> PKT_RX_IPV4_HDR |\
> > -				     PKT_RX_IPV4_HDR_EXT | PKT_RX_IPV6_HDR |\
> > -				     PKT_RX_IPV6_HDR_EXT))
> > -#define OLFLAGS_MASK_V   (((uint64_t)OLFLAGS_MASK << 48) | \
> > -			  ((uint64_t)OLFLAGS_MASK << 32) | \
> > -			  ((uint64_t)OLFLAGS_MASK << 16) | \
> > -			  ((uint64_t)OLFLAGS_MASK))
> > -#define PTYPE_SHIFT    (1)
> > +#define OLFLAGS_MASK_V   (((uint64_t)PKT_RX_VLAN_PKT << 48) | \
> > +			  ((uint64_t)PKT_RX_VLAN_PKT << 32) | \
> > +			  ((uint64_t)PKT_RX_VLAN_PKT << 16) | \
> > +			  ((uint64_t)PKT_RX_VLAN_PKT))
> >  #define VTAG_SHIFT     (3)
> >
> >  static inline void
> >  desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
> >  {
> > -	__m128i ptype0, ptype1, vtag0, vtag1;
> > +	__m128i vtag0, vtag1;
> >  	union {
> >  		uint16_t e[4];
> >  		uint64_t dword;
> >  	} vol;
> >
> > -	ptype0 = _mm_unpacklo_epi16(descs[0], descs[1]);
> > -	ptype1 = _mm_unpacklo_epi16(descs[2], descs[3]);
> >  	vtag0 = _mm_unpackhi_epi16(descs[0], descs[1]);
> >  	vtag1 = _mm_unpackhi_epi16(descs[2], descs[3]);
> >
> > -	ptype1 = _mm_unpacklo_epi32(ptype0, ptype1);
> >  	vtag1 = _mm_unpacklo_epi32(vtag0, vtag1);
> > -
> > -	ptype1 = _mm_slli_epi16(ptype1, PTYPE_SHIFT);
> >  	vtag1 = _mm_srli_epi16(vtag1, VTAG_SHIFT);
> >
> > -	ptype1 = _mm_or_si128(ptype1, vtag1);
> > -	vol.dword = _mm_cvtsi128_si64(ptype1) & OLFLAGS_MASK_V;
> > +	vol.dword = _mm_cvtsi128_si64(vtag1) & OLFLAGS_MASK_V;
> >
> >  	rx_pkts[0]->ol_flags = vol.e[0];
> >  	rx_pkts[1]->ol_flags = vol.e[1];
> >  	rx_pkts[2]->ol_flags = vol.e[2];
> >  	rx_pkts[3]->ol_flags = vol.e[3];
> >  }
> > +
> >  #else
> >  #define desc_to_olflags_v(desc, rx_pkts) do {} while (0)
> >  #endif
> > @@ -204,6 +195,8 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,
> >  				0            /* ignore pkt_type field */
> >  			);
> >  	__m128i dd_check, eop_check;
> > +	__m128i desc_mask = _mm_set_epi32(0xFFFFFFFF, 0xFFFFFFFF,
> > +					  0xFFFFFFFF, 0xFFFF07F0);
> >
> >  	if (unlikely(nb_pkts < RTE_IXGBE_VPMD_RX_BURST))
> >  		return 0;
> > @@ -239,7 +232,8 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,
> >  		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
> >  		13, 12,      /* octet 12~13, low 16 bits pkt_len */
> >  		13, 12,      /* octet 12~13, 16 bits data_len */
> > -		0xFF, 0xFF   /* skip pkt_type field */
> > +		1,           /* octet 1, 8 bits pkt_type field */
> > +		0            /* octet 0, 4 bits offset 4 pkt_type field */
> >  		);
> >
> >  	/* Cache is empty -> need to scan the buffer rings, but first move
> > @@ -248,6 +242,7 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,
> >
> >  	/*
> >  	 * A. load 4 packet in one loop
> > +	 * [A*. mask out 4 unused dirty field in desc]
> >  	 * B. copy 4 mbuf point from swring to rx_pkts
> >  	 * C. calc the number of DD bits among the 4 packets
> >  	 * [C*. extract the end-of-packet bit, if requested]
> > @@ -289,6 +284,14 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,
> >  		/* B.2 copy 2 mbuf point into rx_pkts  */
> >  		_mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
> >
> > +		/* A* mask out 0~3 bits RSS type */
> > +		descs[3] = _mm_and_si128(descs[3], desc_mask);
> > +		descs[2] = _mm_and_si128(descs[2], desc_mask);
> > +
> > +		/* A* mask out 0~3 bits RSS type */
> > +		descs[1] = _mm_and_si128(descs[1], desc_mask);
> > +		descs[0] = _mm_and_si128(descs[0], desc_mask);
> > +
> >  		/* avoid compiler reorder optimization */
> >  		rte_compiler_barrier();
> >
> > @@ -301,7 +304,7 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,
> >  		/* C.1 4=>2 filter staterr info only */
> >  		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
> >
> > -		/* set ol_flags with packet type and vlan tag */
> > +		/* set ol_flags with vlan packet type */
> >  		desc_to_olflags_v(descs, &rx_pkts[pos]);
> >
> >  		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
> > --
> > 1.8.1.4
> >
Bruce Richardson Jan. 30, 2015, 3:39 a.m. UTC | #3 
On Thu, Jan 29, 2015 at 11:52:03PM +0000, Liang, Cunming wrote:
> 
> 
> > -----Original Message-----
> > From: Richardson, Bruce
> > Sent: Thursday, January 29, 2015 4:30 PM
> > To: Zhang, Helin
> > Cc: dev@dpdk.org; Cao, Waterman; Liang, Cunming; Liu, Jijiang; Ananyev,
> > Konstantin
> > Subject: Re: [PATCH 04/17] ixgbe: support of unified packet type
> > 
> > On Thu, Jan 29, 2015 at 11:15:52AM +0800, Helin Zhang wrote:
> > > To unify packet types among all PMDs, bit masks of packet type for
> > > ol_flags are replaced by unified packet type for Vector PMD.
> > >
> > 
> > Two suggestions on the commit log:
> > 1. Can you add scalar and vector into the titles to make it clear how this
> > patch and the previous ones differ
> > 2. Can you add a note calling out performance impacts for this patch. If no
> > performance impacts, then please note that for reviewers.
> [Liang, Cunming] Accept, will update it in v2.
> For performance, lose 1 cycle per packet during 4x10GE io fwd loopback unit test.
> 
Good to know, thanks.

/Bruce
Zhang, Helin Jan. 30, 2015, 6:09 a.m. UTC | #4 
Hi Bruce

> -----Original Message-----
> From: Richardson, Bruce
> Sent: Friday, January 30, 2015 7:30 AM
> To: Zhang, Helin
> Cc: dev@dpdk.org; Cao, Waterman; Liang, Cunming; Liu, Jijiang; Ananyev,
> Konstantin
> Subject: Re: [PATCH 04/17] ixgbe: support of unified packet type
> 
> On Thu, Jan 29, 2015 at 11:15:52AM +0800, Helin Zhang wrote:
> > To unify packet types among all PMDs, bit masks of packet type for
> > ol_flags are replaced by unified packet type for Vector PMD.
> >
> 
> Two suggestions on the commit log:
> 1. Can you add scalar and vector into the titles to make it clear how this patch
> and the previous ones differ 2. Can you add a note calling out performance
> impacts for this patch. If no performance impacts, then please note that for
> reviewers.
OK. That will be in the v2 patches. Thanks for the good comments!

Regards,
Helin

> 
> /Bruce
> 
> > Signed-off-by: Cunming Liang <cunming.liang@intel.com>
> > Signed-off-by: Helin Zhang <helin.zhang@intel.com>
> > ---
> >  lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c | 39
> > +++++++++++++++++++----------------
> >  1 file changed, 21 insertions(+), 18 deletions(-)
> >
> > diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > index b54cb19..b3cf7dd 100644
> > --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
> > @@ -134,44 +134,35 @@ ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
> >   */
> >  #ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE
> >
> > -#define OLFLAGS_MASK     ((uint16_t)(PKT_RX_VLAN_PKT |
> PKT_RX_IPV4_HDR |\
> > -				     PKT_RX_IPV4_HDR_EXT | PKT_RX_IPV6_HDR |\
> > -				     PKT_RX_IPV6_HDR_EXT))
> > -#define OLFLAGS_MASK_V   (((uint64_t)OLFLAGS_MASK << 48) | \
> > -			  ((uint64_t)OLFLAGS_MASK << 32) | \
> > -			  ((uint64_t)OLFLAGS_MASK << 16) | \
> > -			  ((uint64_t)OLFLAGS_MASK))
> > -#define PTYPE_SHIFT    (1)
> > +#define OLFLAGS_MASK_V   (((uint64_t)PKT_RX_VLAN_PKT << 48) | \
> > +			  ((uint64_t)PKT_RX_VLAN_PKT << 32) | \
> > +			  ((uint64_t)PKT_RX_VLAN_PKT << 16) | \
> > +			  ((uint64_t)PKT_RX_VLAN_PKT))
> >  #define VTAG_SHIFT     (3)
> >
> >  static inline void
> >  desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)  {
> > -	__m128i ptype0, ptype1, vtag0, vtag1;
> > +	__m128i vtag0, vtag1;
> >  	union {
> >  		uint16_t e[4];
> >  		uint64_t dword;
> >  	} vol;
> >
> > -	ptype0 = _mm_unpacklo_epi16(descs[0], descs[1]);
> > -	ptype1 = _mm_unpacklo_epi16(descs[2], descs[3]);
> >  	vtag0 = _mm_unpackhi_epi16(descs[0], descs[1]);
> >  	vtag1 = _mm_unpackhi_epi16(descs[2], descs[3]);
> >
> > -	ptype1 = _mm_unpacklo_epi32(ptype0, ptype1);
> >  	vtag1 = _mm_unpacklo_epi32(vtag0, vtag1);
> > -
> > -	ptype1 = _mm_slli_epi16(ptype1, PTYPE_SHIFT);
> >  	vtag1 = _mm_srli_epi16(vtag1, VTAG_SHIFT);
> >
> > -	ptype1 = _mm_or_si128(ptype1, vtag1);
> > -	vol.dword = _mm_cvtsi128_si64(ptype1) & OLFLAGS_MASK_V;
> > +	vol.dword = _mm_cvtsi128_si64(vtag1) & OLFLAGS_MASK_V;
> >
> >  	rx_pkts[0]->ol_flags = vol.e[0];
> >  	rx_pkts[1]->ol_flags = vol.e[1];
> >  	rx_pkts[2]->ol_flags = vol.e[2];
> >  	rx_pkts[3]->ol_flags = vol.e[3];
> >  }
> > +
> >  #else
> >  #define desc_to_olflags_v(desc, rx_pkts) do {} while (0)  #endif @@
> > -204,6 +195,8 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,
> >  				0            /* ignore pkt_type field */
> >  			);
> >  	__m128i dd_check, eop_check;
> > +	__m128i desc_mask = _mm_set_epi32(0xFFFFFFFF, 0xFFFFFFFF,
> > +					  0xFFFFFFFF, 0xFFFF07F0);
> >
> >  	if (unlikely(nb_pkts < RTE_IXGBE_VPMD_RX_BURST))
> >  		return 0;
> > @@ -239,7 +232,8 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq,
> struct rte_mbuf **rx_pkts,
> >  		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
> >  		13, 12,      /* octet 12~13, low 16 bits pkt_len */
> >  		13, 12,      /* octet 12~13, 16 bits data_len */
> > -		0xFF, 0xFF   /* skip pkt_type field */
> > +		1,           /* octet 1, 8 bits pkt_type field */
> > +		0            /* octet 0, 4 bits offset 4 pkt_type field */
> >  		);
> >
> >  	/* Cache is empty -> need to scan the buffer rings, but first move
> > @@ -248,6 +242,7 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq,
> > struct rte_mbuf **rx_pkts,
> >
> >  	/*
> >  	 * A. load 4 packet in one loop
> > +	 * [A*. mask out 4 unused dirty field in desc]
> >  	 * B. copy 4 mbuf point from swring to rx_pkts
> >  	 * C. calc the number of DD bits among the 4 packets
> >  	 * [C*. extract the end-of-packet bit, if requested] @@ -289,6
> > +284,14 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf
> **rx_pkts,
> >  		/* B.2 copy 2 mbuf point into rx_pkts  */
> >  		_mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
> >
> > +		/* A* mask out 0~3 bits RSS type */
> > +		descs[3] = _mm_and_si128(descs[3], desc_mask);
> > +		descs[2] = _mm_and_si128(descs[2], desc_mask);
> > +
> > +		/* A* mask out 0~3 bits RSS type */
> > +		descs[1] = _mm_and_si128(descs[1], desc_mask);
> > +		descs[0] = _mm_and_si128(descs[0], desc_mask);
> > +
> >  		/* avoid compiler reorder optimization */
> >  		rte_compiler_barrier();
> >
> > @@ -301,7 +304,7 @@ _recv_raw_pkts_vec(struct igb_rx_queue *rxq,
> struct rte_mbuf **rx_pkts,
> >  		/* C.1 4=>2 filter staterr info only */
> >  		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
> >
> > -		/* set ol_flags with packet type and vlan tag */
> > +		/* set ol_flags with vlan packet type */
> >  		desc_to_olflags_v(descs, &rx_pkts[pos]);
> >
> >  		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */
> > --
> > 1.8.1.4
> >
diff mbox

Patch

diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
index b54cb19..b3cf7dd 100644
--- a/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
+++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx_vec.c
@@ -134,44 +134,35 @@  ixgbe_rxq_rearm(struct igb_rx_queue *rxq)
  */
 #ifdef RTE_IXGBE_RX_OLFLAGS_ENABLE
 
-#define OLFLAGS_MASK     ((uint16_t)(PKT_RX_VLAN_PKT | PKT_RX_IPV4_HDR |\
-				     PKT_RX_IPV4_HDR_EXT | PKT_RX_IPV6_HDR |\
-				     PKT_RX_IPV6_HDR_EXT))
-#define OLFLAGS_MASK_V   (((uint64_t)OLFLAGS_MASK << 48) | \
-			  ((uint64_t)OLFLAGS_MASK << 32) | \
-			  ((uint64_t)OLFLAGS_MASK << 16) | \
-			  ((uint64_t)OLFLAGS_MASK))
-#define PTYPE_SHIFT    (1)
+#define OLFLAGS_MASK_V   (((uint64_t)PKT_RX_VLAN_PKT << 48) | \
+			  ((uint64_t)PKT_RX_VLAN_PKT << 32) | \
+			  ((uint64_t)PKT_RX_VLAN_PKT << 16) | \
+			  ((uint64_t)PKT_RX_VLAN_PKT))
 #define VTAG_SHIFT     (3)
 
 static inline void
 desc_to_olflags_v(__m128i descs[4], struct rte_mbuf **rx_pkts)
 {
-	__m128i ptype0, ptype1, vtag0, vtag1;
+	__m128i vtag0, vtag1;
 	union {
 		uint16_t e[4];
 		uint64_t dword;
 	} vol;
 
-	ptype0 = _mm_unpacklo_epi16(descs[0], descs[1]);
-	ptype1 = _mm_unpacklo_epi16(descs[2], descs[3]);
 	vtag0 = _mm_unpackhi_epi16(descs[0], descs[1]);
 	vtag1 = _mm_unpackhi_epi16(descs[2], descs[3]);
 
-	ptype1 = _mm_unpacklo_epi32(ptype0, ptype1);
 	vtag1 = _mm_unpacklo_epi32(vtag0, vtag1);
-
-	ptype1 = _mm_slli_epi16(ptype1, PTYPE_SHIFT);
 	vtag1 = _mm_srli_epi16(vtag1, VTAG_SHIFT);
 
-	ptype1 = _mm_or_si128(ptype1, vtag1);
-	vol.dword = _mm_cvtsi128_si64(ptype1) & OLFLAGS_MASK_V;
+	vol.dword = _mm_cvtsi128_si64(vtag1) & OLFLAGS_MASK_V;
 
 	rx_pkts[0]->ol_flags = vol.e[0];
 	rx_pkts[1]->ol_flags = vol.e[1];
 	rx_pkts[2]->ol_flags = vol.e[2];
 	rx_pkts[3]->ol_flags = vol.e[3];
 }
+
 #else
 #define desc_to_olflags_v(desc, rx_pkts) do {} while (0)
 #endif
@@ -204,6 +195,8 @@  _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 				0            /* ignore pkt_type field */
 			);
 	__m128i dd_check, eop_check;
+	__m128i desc_mask = _mm_set_epi32(0xFFFFFFFF, 0xFFFFFFFF,
+					  0xFFFFFFFF, 0xFFFF07F0);
 
 	if (unlikely(nb_pkts < RTE_IXGBE_VPMD_RX_BURST))
 		return 0;
@@ -239,7 +232,8 @@  _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		0xFF, 0xFF,  /* skip high 16 bits pkt_len, zero out */
 		13, 12,      /* octet 12~13, low 16 bits pkt_len */
 		13, 12,      /* octet 12~13, 16 bits data_len */
-		0xFF, 0xFF   /* skip pkt_type field */
+		1,           /* octet 1, 8 bits pkt_type field */
+		0            /* octet 0, 4 bits offset 4 pkt_type field */
 		);
 
 	/* Cache is empty -> need to scan the buffer rings, but first move
@@ -248,6 +242,7 @@  _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 
 	/*
 	 * A. load 4 packet in one loop
+	 * [A*. mask out 4 unused dirty field in desc]
 	 * B. copy 4 mbuf point from swring to rx_pkts
 	 * C. calc the number of DD bits among the 4 packets
 	 * [C*. extract the end-of-packet bit, if requested]
@@ -289,6 +284,14 @@  _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		/* B.2 copy 2 mbuf point into rx_pkts  */
 		_mm_storeu_si128((__m128i *)&rx_pkts[pos+2], mbp2);
 
+		/* A* mask out 0~3 bits RSS type */
+		descs[3] = _mm_and_si128(descs[3], desc_mask);
+		descs[2] = _mm_and_si128(descs[2], desc_mask);
+
+		/* A* mask out 0~3 bits RSS type */
+		descs[1] = _mm_and_si128(descs[1], desc_mask);
+		descs[0] = _mm_and_si128(descs[0], desc_mask);
+
 		/* avoid compiler reorder optimization */
 		rte_compiler_barrier();
 
@@ -301,7 +304,7 @@  _recv_raw_pkts_vec(struct igb_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 		/* C.1 4=>2 filter staterr info only */
 		sterr_tmp1 = _mm_unpackhi_epi32(descs[1], descs[0]);
 
-		/* set ol_flags with packet type and vlan tag */
+		/* set ol_flags with vlan packet type */
 		desc_to_olflags_v(descs, &rx_pkts[pos]);
 
 		/* D.2 pkt 3,4 set in_port/nb_seg and remove crc */