From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) by dpdk.org (Postfix) with ESMTP id 5EB26B62 for ; Fri, 27 Mar 2015 02:04:29 +0100 (CET) Received: from orsmga003.jf.intel.com ([10.7.209.27]) by orsmga101.jf.intel.com with ESMTP; 26 Mar 2015 18:04:27 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.11,476,1422950400"; d="scan'208";a="547012072" Received: from irsmsx101.ger.corp.intel.com ([163.33.3.153]) by orsmga003.jf.intel.com with ESMTP; 26 Mar 2015 18:04:27 -0700 Received: from irsmsx105.ger.corp.intel.com ([169.254.7.47]) by IRSMSX101.ger.corp.intel.com ([163.33.3.153]) with mapi id 14.03.0224.002; Fri, 27 Mar 2015 01:04:26 +0000 From: "Ananyev, Konstantin" To: "xuelin.shi@freescale.com" , "thomas.monjalon@6wind.com" Thread-Topic: [dpdk-dev] [PATCH v2] ixgbe: fix ixgbe access endian issue on bigendian arch Thread-Index: AQHQZgOFx4q9kK6qzEWCTsSZjMbX4Z0vgRcg Date: Fri, 27 Mar 2015 01:04:25 +0000 Message-ID: <2601191342CEEE43887BDE71AB97725821407D74@irsmsx105.ger.corp.intel.com> References: <1427178825-4172-1-git-send-email-xuelin.shi@freescale.com> In-Reply-To: <1427178825-4172-1-git-send-email-xuelin.shi@freescale.com> Accept-Language: en-IE, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [163.33.239.180] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Cc: "dev@dpdk.org" Subject: Re: [dpdk-dev] [PATCH v2] ixgbe: fix ixgbe access endian issue on bigendian arch X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 Mar 2015 01:04:31 -0000 Hi, > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of xuelin.shi@freescale= .com > Sent: Tuesday, March 24, 2015 6:34 AM > To: thomas.monjalon@6wind.com > Cc: dev@dpdk.org; Xuelin Shi > Subject: [dpdk-dev] [PATCH v2] ixgbe: fix ixgbe access endian issue on bi= gendian arch >=20 > From: Xuelin Shi >=20 > enforce rules of the cpu and ixgbe exchange data. > 1. cpu use data owned by ixgbe must use rte_le_to_cpu_xx(...) > 2. cpu fill data to ixgbe must use rte_cpu_to_le_xx(...) >=20 > Signed-off-by: Xuelin Shi > --- > changes for v2: > rebased on latest head. > fix some style issue detected by checkpatch.pl >=20 > lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 104 ++++++++++++++++++++++++--------= ------ > 1 file changed, 66 insertions(+), 38 deletions(-) >=20 > diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c b/lib/librte_pmd_ixgbe/ixg= be_rxtx.c > index 9da2c7e..961ac08 100644 > --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c > +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c > @@ -128,7 +128,7 @@ ixgbe_tx_free_bufs(struct ixgbe_tx_queue *txq) > int i; >=20 > /* check DD bit on threshold descriptor */ > - status =3D txq->tx_ring[txq->tx_next_dd].wb.status; > + status =3D rte_le_to_cpu_32(txq->tx_ring[txq->tx_next_dd].wb.status); > if (! (status & IXGBE_ADVTXD_STAT_DD)) > return 0; >=20 > @@ -174,11 +174,14 @@ tx4(volatile union ixgbe_adv_tx_desc *txdp, struct = rte_mbuf **pkts) > pkt_len =3D (*pkts)->data_len; >=20 > /* write data to descriptor */ > - txdp->read.buffer_addr =3D buf_dma_addr; > + txdp->read.buffer_addr =3D rte_cpu_to_le_64(buf_dma_addr); > + > txdp->read.cmd_type_len =3D > - ((uint32_t)DCMD_DTYP_FLAGS | pkt_len); > + rte_cpu_to_le_32((uint32_t)DCMD_DTYP_FLAGS | pkt_len); > + > txdp->read.olinfo_status =3D > - (pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); > + rte_cpu_to_le_32(pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); > + > rte_prefetch0(&(*pkts)->pool); > } > } > @@ -194,11 +197,14 @@ tx1(volatile union ixgbe_adv_tx_desc *txdp, struct = rte_mbuf **pkts) > pkt_len =3D (*pkts)->data_len; >=20 > /* write data to descriptor */ > - txdp->read.buffer_addr =3D buf_dma_addr; > + txdp->read.buffer_addr =3D rte_cpu_to_le_64(buf_dma_addr); > + > txdp->read.cmd_type_len =3D > - ((uint32_t)DCMD_DTYP_FLAGS | pkt_len); > + rte_cpu_to_le_32((uint32_t)DCMD_DTYP_FLAGS | pkt_len); > + > txdp->read.olinfo_status =3D > - (pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); > + rte_cpu_to_le_32(pkt_len << IXGBE_ADVTXD_PAYLEN_SHIFT); > + > rte_prefetch0(&(*pkts)->pool); > } >=20 > @@ -285,7 +291,7 @@ tx_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkt= s, > * a divisor of the ring size > */ > tx_r[txq->tx_next_rs].read.cmd_type_len |=3D > - rte_cpu_to_le_32(IXGBE_ADVTXD_DCMD_RS); > + rte_cpu_to_le_32(IXGBE_ADVTXD_DCMD_RS); > txq->tx_next_rs =3D (uint16_t)(txq->tx_rs_thresh - 1); >=20 > txq->tx_tail =3D 0; > @@ -304,7 +310,7 @@ tx_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkt= s, > */ > if (txq->tx_tail > txq->tx_next_rs) { > tx_r[txq->tx_next_rs].read.cmd_type_len |=3D > - rte_cpu_to_le_32(IXGBE_ADVTXD_DCMD_RS); > + rte_cpu_to_le_32(IXGBE_ADVTXD_DCMD_RS); > txq->tx_next_rs =3D (uint16_t)(txq->tx_next_rs + > txq->tx_rs_thresh); > if (txq->tx_next_rs >=3D txq->nb_tx_desc) > @@ -505,6 +511,7 @@ ixgbe_xmit_cleanup(struct ixgbe_tx_queue *txq) > uint16_t nb_tx_desc =3D txq->nb_tx_desc; > uint16_t desc_to_clean_to; > uint16_t nb_tx_to_clean; > + uint32_t stat; >=20 > /* Determine the last descriptor needing to be cleaned */ > desc_to_clean_to =3D (uint16_t)(last_desc_cleaned + txq->tx_rs_thresh); > @@ -513,7 +520,9 @@ ixgbe_xmit_cleanup(struct ixgbe_tx_queue *txq) >=20 > /* Check to make sure the last descriptor to clean is done */ > desc_to_clean_to =3D sw_ring[desc_to_clean_to].last_id; > - if (! (txr[desc_to_clean_to].wb.status & IXGBE_TXD_STAT_DD)) > + > + stat =3D rte_le_to_cpu_32(txr[desc_to_clean_to].wb.status); > + if (!(stat & IXGBE_TXD_STAT_DD)) > { > PMD_TX_FREE_LOG(DEBUG, > "TX descriptor %4u is not done" > @@ -544,7 +553,7 @@ ixgbe_xmit_cleanup(struct ixgbe_tx_queue *txq) > * up to the last descriptor with the RS bit set > * are done. Only reset the threshold descriptor. > */ > - txr[desc_to_clean_to].wb.status =3D 0; > + txr[desc_to_clean_to].wb.status =3D rte_cpu_to_le_32(0); Don't think you need swap bytes here. >=20 > /* Update the txq to reflect the last descriptor that was cleaned */ > txq->last_desc_cleaned =3D desc_to_clean_to; > @@ -801,12 +810,14 @@ ixgbe_xmit_pkts(void *tx_queue, struct rte_mbuf **t= x_pkts, > */ > slen =3D m_seg->data_len; > buf_dma_addr =3D RTE_MBUF_DATA_DMA_ADDR(m_seg); > + > txd->read.buffer_addr =3D > - rte_cpu_to_le_64(buf_dma_addr); > + rte_cpu_to_le_64(buf_dma_addr); > txd->read.cmd_type_len =3D > - rte_cpu_to_le_32(cmd_type_len | slen); > + rte_cpu_to_le_32(cmd_type_len | slen); > txd->read.olinfo_status =3D > - rte_cpu_to_le_32(olinfo_status); > + rte_cpu_to_le_32(olinfo_status); > + > txe->last_id =3D tx_last; > tx_id =3D txe->next_id; > txe =3D txn; > @@ -946,14 +957,16 @@ ixgbe_rx_scan_hw_ring(struct ixgbe_rx_queue *rxq) > uint64_t pkt_flags; > int s[LOOK_AHEAD], nb_dd; > int i, j, nb_rx =3D 0; > + uint32_t stat; >=20 >=20 > /* get references to current descriptor and S/W ring entry */ > rxdp =3D &rxq->rx_ring[rxq->rx_tail]; > rxep =3D &rxq->sw_ring[rxq->rx_tail]; >=20 > + stat =3D rte_le_to_cpu_32(rxdp->wb.upper.status_error); > /* check to make sure there is at least 1 packet to receive */ > - if (! (rxdp->wb.upper.status_error & IXGBE_RXDADV_STAT_DD)) > + if (!(stat & IXGBE_RXDADV_STAT_DD)) > return 0; >=20 > /* > @@ -965,7 +978,7 @@ ixgbe_rx_scan_hw_ring(struct ixgbe_rx_queue *rxq) > { > /* Read desc statuses backwards to avoid race condition */ > for (j =3D LOOK_AHEAD-1; j >=3D 0; --j) > - s[j] =3D rxdp[j].wb.upper.status_error; > + s[j] =3D rte_le_to_cpu_32(rxdp[j].wb.upper.status_error); >=20 > /* Compute how many status bits were set */ > nb_dd =3D 0; > @@ -976,28 +989,36 @@ ixgbe_rx_scan_hw_ring(struct ixgbe_rx_queue *rxq) >=20 > /* Translate descriptor info to mbuf format */ > for (j =3D 0; j < nb_dd; ++j) { > + uint16_t tmp16; > + uint32_t tmp32; > + > mb =3D rxep[j].mbuf; > - pkt_len =3D (uint16_t)(rxdp[j].wb.upper.length - rxq->crc_len); > + tmp16 =3D rte_le_to_cpu_16(rxdp[j].wb.upper.length); > + pkt_len =3D tmp16 - rxq->crc_len; Here and in other places, wonder why do you introduce temporary variables? Why not just: pkt_len =3D rte_le_to_cpu_16( (rxdp[j].wb.upper.length) - rxq->crc_len; ? > mb->data_len =3D pkt_len; > mb->pkt_len =3D pkt_len; > - mb->vlan_tci =3D rxdp[j].wb.upper.vlan; > mb->vlan_tci =3D rte_le_to_cpu_16(rxdp[j].wb.upper.vlan); >=20 > /* convert descriptor fields to rte mbuf flags */ > - pkt_flags =3D rx_desc_hlen_type_rss_to_pkt_flags( > + tmp32 =3D rte_le_to_cpu_32( > rxdp[j].wb.lower.lo_dword.data); Same here, why just not: pkt_flags =3D rx_desc_hlen_type_rss_to_pkt_flags(rte_le_to_cpu_32(rxdp[j].= wb.lower.lo_dword.data)); ? > + pkt_flags =3D rx_desc_hlen_type_rss_to_pkt_flags(tmp32); > + > /* reuse status field from scan list */ > pkt_flags |=3D rx_desc_status_to_pkt_flags(s[j]); > pkt_flags |=3D rx_desc_error_to_pkt_flags(s[j]); > mb->ol_flags =3D pkt_flags; >=20 > if (likely(pkt_flags & PKT_RX_RSS_HASH)) > - mb->hash.rss =3D rxdp[j].wb.lower.hi_dword.rss; > + mb->hash.rss =3D rte_le_to_cpu_32( > + rxdp[j].wb.lower.hi_dword.rss); > else if (pkt_flags & PKT_RX_FDIR) { > - mb->hash.fdir.hash =3D > - (uint16_t)((rxdp[j].wb.lower.hi_dword.csum_ip.csum) > - & IXGBE_ATR_HASH_MASK); > - mb->hash.fdir.id =3D rxdp[j].wb.lower.hi_dword.csum_ip.ip_id; > + tmp16 =3D rxdp[j].wb.lower.hi_dword.csum_ip.csum; > + mb->hash.fdir.hash =3D rte_le_to_cpu_16( > + tmp16 & IXGBE_ATR_HASH_MASK); Shouldn't it be: rte_le_to_cpu_16(tmp16) & IXGBE_ATR_HASH_MASK; ? > + > + tmp16 =3D rxdp[j].wb.lower.hi_dword.csum_ip.ip_id; > + mb->hash.fdir.id =3D rte_le_to_cpu_16(tmp16); > } > } >=20 > @@ -1051,8 +1072,8 @@ ixgbe_rx_alloc_bufs(struct ixgbe_rx_queue *rxq) >=20 > /* populate the descriptors */ > dma_addr =3D rte_cpu_to_le_64(RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mb)); > - rxdp[i].read.hdr_addr =3D dma_addr; > - rxdp[i].read.pkt_addr =3D dma_addr; > + rxdp[i].read.hdr_addr =3D rte_cpu_to_le_64(dma_addr); > + rxdp[i].read.pkt_addr =3D rte_cpu_to_le_64(dma_addr); No need these 2 swaps here. dma_addr already converted to LE, just a line above. > } >=20 > /* update tail pointer */ > @@ -1220,8 +1241,8 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf **r= x_pkts, > * using invalid descriptor fields when read from rxd. > */ > rxdp =3D &rx_ring[rx_id]; > - staterr =3D rxdp->wb.upper.status_error; > - if (! (staterr & rte_cpu_to_le_32(IXGBE_RXDADV_STAT_DD))) > + staterr =3D rte_le_to_cpu_32(rxdp->wb.upper.status_error); > + if (!(staterr & IXGBE_RXDADV_STAT_DD)) Why do you need that change here? Original code seems also ok to me. > break; > rxd =3D *rxdp; >=20 > @@ -1325,12 +1346,17 @@ ixgbe_recv_pkts(void *rx_queue, struct rte_mbuf *= *rx_pkts, > rxm->ol_flags =3D pkt_flags; >=20 > if (likely(pkt_flags & PKT_RX_RSS_HASH)) > - rxm->hash.rss =3D rxd.wb.lower.hi_dword.rss; > + rxm->hash.rss =3D rte_le_to_cpu_32( > + rxd.wb.lower.hi_dword.rss); > else if (pkt_flags & PKT_RX_FDIR) { > - rxm->hash.fdir.hash =3D > - (uint16_t)((rxd.wb.lower.hi_dword.csum_ip.csum) > - & IXGBE_ATR_HASH_MASK); > - rxm->hash.fdir.id =3D rxd.wb.lower.hi_dword.csum_ip.ip_id; > + uint16_t tmp16; > + > + tmp16 =3D rxd.wb.lower.hi_dword.csum_ip.csum; > + rxm->hash.fdir.hash =3D rte_le_to_cpu_16( > + tmp16 & IXGBE_ATR_HASH_MASK); Same thing here, seems should be: rte_le_to_cpu_16(tmp16) & IXGBE_ATR_HASH_= MASK; > + > + rxm->hash.fdir.id =3D rte_le_to_cpu_16( > + rxd.wb.lower.hi_dword.csum_ip.ip_id); > } > /* > * Store the mbuf address into the next entry of the array > @@ -1412,8 +1438,8 @@ ixgbe_recv_scattered_pkts(void *rx_queue, struct rt= e_mbuf **rx_pkts, > * using invalid descriptor fields when read from rxd. > */ > rxdp =3D &rx_ring[rx_id]; > - staterr =3D rxdp->wb.upper.status_error; > - if (! (staterr & rte_cpu_to_le_32(IXGBE_RXDADV_STAT_DD))) > + staterr =3D rte_cpu_to_le_32(rxdp->wb.upper.status_error); > + if (!(staterr & IXGBE_RXDADV_STAT_DD)) Again, seems unnecessary. > break; > rxd =3D *rxdp; >=20 > @@ -1742,7 +1768,7 @@ ixgbe_reset_tx_queue(struct ixgbe_tx_queue *txq) > prev =3D (uint16_t) (txq->nb_tx_desc - 1); > for (i =3D 0; i < txq->nb_tx_desc; i++) { > volatile union ixgbe_adv_tx_desc *txd =3D &txq->tx_ring[i]; > - txd->wb.status =3D IXGBE_TXD_STAT_DD; > + txd->wb.status =3D rte_cpu_to_le_32(IXGBE_TXD_STAT_DD); > txe[i].mbuf =3D NULL; > txe[i].last_id =3D i; > txe[prev].next_id =3D i; > @@ -2293,7 +2319,8 @@ ixgbe_dev_rx_queue_count(struct rte_eth_dev *dev, u= int16_t rx_queue_id) > rxdp =3D &(rxq->rx_ring[rxq->rx_tail]); >=20 > while ((desc < rxq->nb_rx_desc) && > - (rxdp->wb.upper.status_error & IXGBE_RXDADV_STAT_DD)) { > + (rte_le_to_cpu_32(rxdp->wb.upper.status_error) & > + IXGBE_RXDADV_STAT_DD)) { > desc +=3D IXGBE_RXQ_SCAN_INTERVAL; > rxdp +=3D IXGBE_RXQ_SCAN_INTERVAL; > if (rxq->rx_tail + desc >=3D rxq->nb_rx_desc) > @@ -2318,7 +2345,8 @@ ixgbe_dev_rx_descriptor_done(void *rx_queue, uint16= _t offset) > desc -=3D rxq->nb_rx_desc; >=20 > rxdp =3D &rxq->rx_ring[desc]; > - return !!(rxdp->wb.upper.status_error & IXGBE_RXDADV_STAT_DD); > + return !!(rte_le_to_cpu_32(rxdp->wb.upper.status_error) & > + IXGBE_RXDADV_STAT_DD); > } >=20 > void > -- > 1.9.1