[v2,3/5] net/ice: support flow mark in AVX path
diff mbox series

Message ID 20200907091711.5980-4-junyux.jiang@intel.com
State Superseded, archived
Delegated to: Qi Zhang
Headers show
Series
  • supports RxDID #22 and FDID
Related show

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Junyu Jiang Sept. 7, 2020, 9:17 a.m. UTC
From: Guinan Sun <guinanx.sun@intel.com>

Support Flow Director mark ID parsing from Flex
Rx descriptor in AVX path.

Signed-off-by: Guinan Sun <guinanx.sun@intel.com>
---
 drivers/net/ice/ice_rxtx_vec_avx2.c | 64 ++++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 1 deletion(-)

Comments

Yang, Qiming Sept. 8, 2020, 7:54 a.m. UTC | #1
> -----Original Message-----
> From: Jiang, JunyuX <junyux.jiang@intel.com>
> Sent: Monday, September 7, 2020 17:17
> To: dev@dpdk.org
> Cc: Zhang, Qi Z <qi.z.zhang@intel.com>; Yang, Qiming
> <qiming.yang@intel.com>; Sun, GuinanX <guinanx.sun@intel.com>
> Subject: [PATCH v2 3/5] net/ice: support flow mark in AVX path
> 
> From: Guinan Sun <guinanx.sun@intel.com>
> 
> Support Flow Director mark ID parsing from Flex Rx descriptor in AVX path.
Same comments.

> 
> Signed-off-by: Guinan Sun <guinanx.sun@intel.com>
> ---
>  drivers/net/ice/ice_rxtx_vec_avx2.c | 64
> ++++++++++++++++++++++++++++-
>  1 file changed, 63 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/net/ice/ice_rxtx_vec_avx2.c
> b/drivers/net/ice/ice_rxtx_vec_avx2.c
> index 07d129e3f..70e4b76db 100644
> --- a/drivers/net/ice/ice_rxtx_vec_avx2.c
> +++ b/drivers/net/ice/ice_rxtx_vec_avx2.c
> @@ -132,6 +132,25 @@ ice_rxq_rearm(struct ice_rx_queue *rxq)
>  	ICE_PCI_REG_WRITE(rxq->qrx_tail, rx_id);  }
> 
> +static inline __m256i
> +ice_flex_rxd_to_fdir_flags_vec_avx2(const __m256i fdir_id0_7) { #define
> +FDID_MIS_MAGIC 0xFFFFFFFF
> +	RTE_BUILD_BUG_ON(PKT_RX_FDIR != (1 << 2));
> +	RTE_BUILD_BUG_ON(PKT_RX_FDIR_ID != (1 << 13));
> +	const __m256i pkt_fdir_bit = _mm256_set1_epi32(PKT_RX_FDIR |
> +			PKT_RX_FDIR_ID);
> +	/* desc->flow_id field == 0xFFFFFFFF means fdir mismatch */
> +	const __m256i fdir_mis_mask =
> _mm256_set1_epi32(FDID_MIS_MAGIC);
> +	__m256i fdir_mask = _mm256_cmpeq_epi32(fdir_id0_7,
> +			fdir_mis_mask);
> +	/* this XOR op results to bit-reverse the fdir_mask */
> +	fdir_mask = _mm256_xor_si256(fdir_mask, fdir_mis_mask);
> +	const __m256i fdir_flags = _mm256_and_si256(fdir_mask,
> pkt_fdir_bit);
> +
> +	return fdir_flags;
> +}
> +
>  static inline uint16_t
>  _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf
> **rx_pkts,
>  			    uint16_t nb_pkts, uint8_t *split_packet) @@ -459,9
> +478,51 @@ _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct
> rte_mbuf **rx_pkts,
>  					    rss_vlan_flag_bits);
> 
>  		/* merge flags */
> -		const __m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
> +		__m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
>  				rss_vlan_flags);
> 
> +		if (rxq->fdir_enabled) {
> +			const __m256i fdir_id4_7 =
> +				_mm256_unpackhi_epi32(raw_desc6_7,
> raw_desc4_5);
> +
> +			const __m256i fdir_id0_3 =
> +				_mm256_unpackhi_epi32(raw_desc2_3,
> raw_desc0_1);
> +
> +			const __m256i fdir_id0_7 =
> +				_mm256_unpackhi_epi64(fdir_id4_7,
> fdir_id0_3);
> +
> +			const __m256i fdir_flags =
> +
> 	ice_flex_rxd_to_fdir_flags_vec_avx2(fdir_id0_7);
> +
> +			/* merge with fdir_flags */
> +			mbuf_flags = _mm256_or_si256(mbuf_flags,
> fdir_flags);
> +
> +			/* write to mbuf: have to use scalar store here */
> +			rx_pkts[i + 0]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 3);
> +
> +			rx_pkts[i + 1]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 7);
> +
> +			rx_pkts[i + 2]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 2);
> +
> +			rx_pkts[i + 3]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 6);
> +
> +			rx_pkts[i + 4]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 1);
> +
> +			rx_pkts[i + 5]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 5);
> +
> +			rx_pkts[i + 6]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 0);
> +
> +			rx_pkts[i + 7]->hash.fdir.hi =
> +				_mm256_extract_epi32(fdir_id0_7, 4);
> +		} /* if() on fdir_enabled */
> +
>  #ifndef RTE_LIBRTE_ICE_16BYTE_RX_DESC
>  		/**
>  		 * needs to load 2nd 16B of each desc for RSS hash parsing,
> @@ -551,6 +612,7 @@ _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue
> *rxq, struct rte_mbuf **rx_pkts,
>  			mb0_1 = _mm256_or_si256(mb0_1, rss_hash0_1);
>  		} /* if() on RSS hash parsing */
>  #endif
> +
>  		/**
>  		 * At this point, we have the 8 sets of flags in the low 16-bits
>  		 * of each 32-bit value in vlan0.
> --
> 2.17.1

Patch
diff mbox series

diff --git a/drivers/net/ice/ice_rxtx_vec_avx2.c b/drivers/net/ice/ice_rxtx_vec_avx2.c
index 07d129e3f..70e4b76db 100644
--- a/drivers/net/ice/ice_rxtx_vec_avx2.c
+++ b/drivers/net/ice/ice_rxtx_vec_avx2.c
@@ -132,6 +132,25 @@  ice_rxq_rearm(struct ice_rx_queue *rxq)
 	ICE_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
 }
 
+static inline __m256i
+ice_flex_rxd_to_fdir_flags_vec_avx2(const __m256i fdir_id0_7)
+{
+#define FDID_MIS_MAGIC 0xFFFFFFFF
+	RTE_BUILD_BUG_ON(PKT_RX_FDIR != (1 << 2));
+	RTE_BUILD_BUG_ON(PKT_RX_FDIR_ID != (1 << 13));
+	const __m256i pkt_fdir_bit = _mm256_set1_epi32(PKT_RX_FDIR |
+			PKT_RX_FDIR_ID);
+	/* desc->flow_id field == 0xFFFFFFFF means fdir mismatch */
+	const __m256i fdir_mis_mask = _mm256_set1_epi32(FDID_MIS_MAGIC);
+	__m256i fdir_mask = _mm256_cmpeq_epi32(fdir_id0_7,
+			fdir_mis_mask);
+	/* this XOR op results to bit-reverse the fdir_mask */
+	fdir_mask = _mm256_xor_si256(fdir_mask, fdir_mis_mask);
+	const __m256i fdir_flags = _mm256_and_si256(fdir_mask, pkt_fdir_bit);
+
+	return fdir_flags;
+}
+
 static inline uint16_t
 _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 			    uint16_t nb_pkts, uint8_t *split_packet)
@@ -459,9 +478,51 @@  _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 					    rss_vlan_flag_bits);
 
 		/* merge flags */
-		const __m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
+		__m256i mbuf_flags = _mm256_or_si256(l3_l4_flags,
 				rss_vlan_flags);
 
+		if (rxq->fdir_enabled) {
+			const __m256i fdir_id4_7 =
+				_mm256_unpackhi_epi32(raw_desc6_7, raw_desc4_5);
+
+			const __m256i fdir_id0_3 =
+				_mm256_unpackhi_epi32(raw_desc2_3, raw_desc0_1);
+
+			const __m256i fdir_id0_7 =
+				_mm256_unpackhi_epi64(fdir_id4_7, fdir_id0_3);
+
+			const __m256i fdir_flags =
+				ice_flex_rxd_to_fdir_flags_vec_avx2(fdir_id0_7);
+
+			/* merge with fdir_flags */
+			mbuf_flags = _mm256_or_si256(mbuf_flags, fdir_flags);
+
+			/* write to mbuf: have to use scalar store here */
+			rx_pkts[i + 0]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 3);
+
+			rx_pkts[i + 1]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 7);
+
+			rx_pkts[i + 2]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 2);
+
+			rx_pkts[i + 3]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 6);
+
+			rx_pkts[i + 4]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 1);
+
+			rx_pkts[i + 5]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 5);
+
+			rx_pkts[i + 6]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 0);
+
+			rx_pkts[i + 7]->hash.fdir.hi =
+				_mm256_extract_epi32(fdir_id0_7, 4);
+		} /* if() on fdir_enabled */
+
 #ifndef RTE_LIBRTE_ICE_16BYTE_RX_DESC
 		/**
 		 * needs to load 2nd 16B of each desc for RSS hash parsing,
@@ -551,6 +612,7 @@  _ice_recv_raw_pkts_vec_avx2(struct ice_rx_queue *rxq, struct rte_mbuf **rx_pkts,
 			mb0_1 = _mm256_or_si256(mb0_1, rss_hash0_1);
 		} /* if() on RSS hash parsing */
 #endif
+
 		/**
 		 * At this point, we have the 8 sets of flags in the low 16-bits
 		 * of each 32-bit value in vlan0.