diff options
Diffstat (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c')
| -rw-r--r-- | drivers/net/ethernet/freescale/enetc/enetc.c | 2228 |
1 files changed, 1655 insertions, 573 deletions
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3ca93adb9662..d5e5800b84ef 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3,20 +3,90 @@ #include "enetc.h" #include <linux/bpf_trace.h> +#include <linux/clk.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/vmalloc.h> #include <linux/ptp_classify.h> +#include <net/ip6_checksum.h> #include <net/pkt_sched.h> +#include <net/tso.h> + +u32 enetc_port_mac_rd(struct enetc_si *si, u32 reg) +{ + /* ENETC with pseudo MAC does not have Ethernet MAC + * port registers. + */ + if (enetc_is_pseudo_mac(si)) + return 0; + + return enetc_port_rd(&si->hw, reg); +} +EXPORT_SYMBOL_GPL(enetc_port_mac_rd); + +void enetc_port_mac_wr(struct enetc_si *si, u32 reg, u32 val) +{ + if (enetc_is_pseudo_mac(si)) + return; + + enetc_port_wr(&si->hw, reg, val); + if (si->hw_features & ENETC_SI_F_QBU) + enetc_port_wr(&si->hw, reg + si->drvdata->pmac_offset, val); +} +EXPORT_SYMBOL_GPL(enetc_port_mac_wr); + +static void enetc_change_preemptible_tcs(struct enetc_ndev_priv *priv, + u8 preemptible_tcs) +{ + if (!(priv->si->hw_features & ENETC_SI_F_QBU)) + return; + + priv->preemptible_tcs = preemptible_tcs; + enetc_mm_commit_preemptible_tcs(priv); +} + +static int enetc_mac_addr_hash_idx(const u8 *addr) +{ + u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16; + u64 mask = 0; + int res = 0; + int i; + + for (i = 0; i < 8; i++) + mask |= BIT_ULL(i * 6); + + for (i = 0; i < 6; i++) + res |= (hweight64(fold & (mask << i)) & 0x1) << i; + + return res; +} + +void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter, + const unsigned char *addr) +{ + int idx = enetc_mac_addr_hash_idx(addr); + + /* add hash table entry */ + __set_bit(idx, filter->mac_hash_table); + filter->mac_addr_cnt++; +} +EXPORT_SYMBOL_GPL(enetc_add_mac_addr_ht_filter); + +void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter) +{ + filter->mac_addr_cnt = 0; + + bitmap_zero(filter->mac_hash_table, + ENETC_MADDR_HASH_TBL_SZ); +} +EXPORT_SYMBOL_GPL(enetc_reset_mac_addr_filter); static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv) { int num_tx_rings = priv->num_tx_rings; - int i; - for (i = 0; i < priv->num_rx_rings; i++) - if (priv->rx_ring[i]->xdp.prog) - return num_tx_rings - num_possible_cpus(); + if (priv->xdp_prog) + return num_tx_rings - num_possible_cpus(); return num_tx_rings; } @@ -121,22 +191,181 @@ static int enetc_ptp_parse(struct sk_buff *skb, u8 *udp, return 0; } +static bool enetc_tx_csum_offload_check(struct sk_buff *skb) +{ + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + case offsetof(struct udphdr, check): + return true; + default: + return false; + } +} + +static bool enetc_skb_is_ipv6(struct sk_buff *skb) +{ + return vlan_get_protocol(skb) == htons(ETH_P_IPV6); +} + +static bool enetc_skb_is_tcp(struct sk_buff *skb) +{ + return skb->csum_offset == offsetof(struct tcphdr, check); +} + +/** + * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame + * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located + * @count: Number of Tx buffer descriptors which need to be unmapped + * @i: Index of the last successfully mapped Tx buffer descriptor + */ +static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i) +{ + while (count--) { + struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i]; + + enetc_free_tx_frame(tx_ring, tx_swbd); + if (i == 0) + i = tx_ring->bd_count; + i--; + } +} + +static void enetc_set_one_step_ts(struct enetc_si *si, bool udp, int offset) +{ + u32 val = ENETC_PM0_SINGLE_STEP_EN; + + val |= ENETC_SET_SINGLE_STEP_OFFSET(offset); + if (udp) + val |= ENETC_PM0_SINGLE_STEP_CH; + + /* The "Correction" field of a packet is updated based on the + * current time and the timestamp provided + */ + enetc_port_mac_wr(si, ENETC_PM0_SINGLE_STEP, val); +} + +static void enetc4_set_one_step_ts(struct enetc_si *si, bool udp, int offset) +{ + u32 val = PM_SINGLE_STEP_EN; + + val |= PM_SINGLE_STEP_OFFSET_SET(offset); + if (udp) + val |= PM_SINGLE_STEP_CH; + + enetc_port_mac_wr(si, ENETC4_PM_SINGLE_STEP(0), val); +} + +static u32 enetc_update_ptp_sync_msg(struct enetc_ndev_priv *priv, + struct sk_buff *skb, bool csum_offload) +{ + struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb); + u16 tstamp_off = enetc_cb->origin_tstamp_off; + u16 corr_off = enetc_cb->correction_off; + struct enetc_si *si = priv->si; + struct enetc_hw *hw = &si->hw; + __be32 new_sec_l, new_nsec; + __be16 new_sec_h; + u32 lo, hi, nsec; + u8 *data; + u64 sec; + + lo = enetc_rd_hot(hw, ENETC_SICTR0); + hi = enetc_rd_hot(hw, ENETC_SICTR1); + sec = (u64)hi << 32 | lo; + nsec = do_div(sec, 1000000000); + + /* Update originTimestamp field of Sync packet + * - 48 bits seconds field + * - 32 bits nanseconds field + * + * In addition, if csum_offload is false, the UDP checksum needs + * to be updated by software after updating originTimestamp field, + * otherwise the hardware will calculate the wrong checksum when + * updating the correction field and update it to the packet. + */ + + data = skb_mac_header(skb); + new_sec_h = htons((sec >> 32) & 0xffff); + new_sec_l = htonl(sec & 0xffffffff); + new_nsec = htonl(nsec); + if (enetc_cb->udp && !csum_offload) { + struct udphdr *uh = udp_hdr(skb); + __be32 old_sec_l, old_nsec; + __be16 old_sec_h; + + old_sec_h = *(__be16 *)(data + tstamp_off); + inet_proto_csum_replace2(&uh->check, skb, old_sec_h, + new_sec_h, false); + + old_sec_l = *(__be32 *)(data + tstamp_off + 2); + inet_proto_csum_replace4(&uh->check, skb, old_sec_l, + new_sec_l, false); + + old_nsec = *(__be32 *)(data + tstamp_off + 6); + inet_proto_csum_replace4(&uh->check, skb, old_nsec, + new_nsec, false); + } + + *(__be16 *)(data + tstamp_off) = new_sec_h; + *(__be32 *)(data + tstamp_off + 2) = new_sec_l; + *(__be32 *)(data + tstamp_off + 6) = new_nsec; + + /* Configure single-step register */ + if (is_enetc_rev1(si)) + enetc_set_one_step_ts(si, enetc_cb->udp, corr_off); + else + enetc4_set_one_step_ts(si, enetc_cb->udp, corr_off); + + return lo & ENETC_TXBD_TSTAMP; +} + static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) { bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false; struct enetc_ndev_priv *priv = netdev_priv(tx_ring->ndev); - struct enetc_hw *hw = &priv->si->hw; + struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb); struct enetc_tx_swbd *tx_swbd; int len = skb_headlen(skb); union enetc_tx_bd temp_bd; - u8 msgtype, twostep, udp; + bool csum_offload = false; union enetc_tx_bd *txbd; - u16 offset1, offset2; int i, count = 0; skb_frag_t *frag; unsigned int f; dma_addr_t dma; u8 flags = 0; + u32 tstamp; + + enetc_clear_tx_bd(&temp_bd); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + /* Can not support TSD and checksum offload at the same time */ + if (priv->active_offloads & ENETC_F_TXCSUM && + enetc_tx_csum_offload_check(skb) && !tx_ring->tsd_enable) { + temp_bd.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START, + skb_network_offset(skb)); + temp_bd.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN, + skb_network_header_len(skb) / 4); + temp_bd.l3_aux1 |= FIELD_PREP(ENETC_TX_BD_L3T, + enetc_skb_is_ipv6(skb)); + if (enetc_skb_is_tcp(skb)) + temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, + ENETC_TXBD_L4T_TCP); + else + temp_bd.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, + ENETC_TXBD_L4T_UDP); + flags |= ENETC_TXBD_FLAGS_CSUM_LSO | ENETC_TXBD_FLAGS_L4CS; + csum_offload = true; + } else if (skb_checksum_help(skb)) { + return 0; + } + } + + if (enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { + do_onestep_tstamp = true; + tstamp = enetc_update_ptp_sync_msg(priv, skb, csum_offload); + } else if (enetc_cb->flag & ENETC_F_TX_TSTAMP) { + do_twostep_tstamp = true; + } i = tx_ring->next_to_use; txbd = ENETC_TXBD(*tx_ring, i); @@ -148,7 +377,6 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) temp_bd.addr = cpu_to_le64(dma); temp_bd.buf_len = cpu_to_le16(len); - temp_bd.lstatus = 0; tx_swbd = &tx_ring->tx_swbd[i]; tx_swbd->dma = dma; @@ -158,19 +386,9 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) count++; do_vlan = skb_vlan_tag_present(skb); - if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { - if (enetc_ptp_parse(skb, &udp, &msgtype, &twostep, &offset1, - &offset2) || - msgtype != PTP_MSGTYPE_SYNC || twostep) - WARN_ONCE(1, "Bad packet for one-step timestamping\n"); - else - do_onestep_tstamp = true; - } else if (skb->cb[0] & ENETC_F_TX_TSTAMP) { - do_twostep_tstamp = true; - } - tx_swbd->do_twostep_tstamp = do_twostep_tstamp; - tx_swbd->check_wb = tx_swbd->do_twostep_tstamp; + tx_swbd->qbv_en = !!(priv->active_offloads & ENETC_F_QBV); + tx_swbd->check_wb = tx_swbd->do_twostep_tstamp || tx_swbd->qbv_en; if (do_vlan || do_onestep_tstamp || do_twostep_tstamp) flags |= ENETC_TXBD_FLAGS_EX; @@ -210,38 +428,9 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) } if (do_onestep_tstamp) { - u32 lo, hi, val; - u64 sec, nsec; - u8 *data; - - lo = enetc_rd_hot(hw, ENETC_SICTR0); - hi = enetc_rd_hot(hw, ENETC_SICTR1); - sec = (u64)hi << 32 | lo; - nsec = do_div(sec, 1000000000); - /* Configure extension BD */ - temp_bd.ext.tstamp = cpu_to_le32(lo & 0x3fffffff); + temp_bd.ext.tstamp = cpu_to_le32(tstamp); e_flags |= ENETC_TXBD_E_FLAGS_ONE_STEP_PTP; - - /* Update originTimestamp field of Sync packet - * - 48 bits seconds field - * - 32 bits nanseconds field - */ - data = skb_mac_header(skb); - *(__be16 *)(data + offset2) = - htons((sec >> 32) & 0xffff); - *(__be32 *)(data + offset2 + 2) = - htonl(sec & 0xffffffff); - *(__be32 *)(data + offset2 + 6) = htonl(nsec); - - /* Configure single-step register */ - val = ENETC_PM0_SINGLE_STEP_EN; - val |= ENETC_SET_SINGLE_STEP_OFFSET(offset1); - if (udp) - val |= ENETC_PM0_SINGLE_STEP_CH; - - enetc_port_wr(hw, ENETC_PM0_SINGLE_STEP, val); - enetc_port_wr(hw, ENETC_PM1_SINGLE_STEP, val); } else if (do_twostep_tstamp) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; e_flags |= ENETC_TXBD_E_FLAGS_TWO_STEP_PTP; @@ -303,13 +492,484 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) dma_err: dev_err(tx_ring->dev, "DMA map error"); + enetc_unwind_tx_frame(tx_ring, count, i); + + return 0; +} + +static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, int *i, int hdr_len, + int data_len) +{ + union enetc_tx_bd txbd_tmp; + u8 flags = 0, e_flags = 0; + dma_addr_t addr; + int count = 1; + + enetc_clear_tx_bd(&txbd_tmp); + addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE; + + if (skb_vlan_tag_present(skb)) + flags |= ENETC_TXBD_FLAGS_EX; + + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.buf_len = cpu_to_le16(hdr_len); + + /* first BD needs frm_len and offload flags set */ + txbd_tmp.frm_len = cpu_to_le16(hdr_len + data_len); + txbd_tmp.flags = flags; + + /* For the TSO header we do not set the dma address since we do not + * want it unmapped when we do cleanup. We still set len so that we + * count the bytes sent. + */ + tx_swbd->len = hdr_len; + tx_swbd->do_twostep_tstamp = false; + tx_swbd->check_wb = false; + + /* Actually write the header in the BD */ + *txbd = txbd_tmp; + + /* Add extension BD for VLAN */ + if (flags & ENETC_TXBD_FLAGS_EX) { + /* Get the next BD */ + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + + /* Setup the VLAN fields */ + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb)); + txbd_tmp.ext.tpid = 0; /* < C-TAG */ + e_flags |= ENETC_TXBD_E_FLAGS_VLAN_INS; + + /* Write the BD */ + txbd_tmp.ext.e_flags = e_flags; + *txbd = txbd_tmp; + count++; + } + + return count; +} + +static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb, + struct enetc_tx_swbd *tx_swbd, + union enetc_tx_bd *txbd, char *data, + int size, bool last_bd) +{ + union enetc_tx_bd txbd_tmp; + dma_addr_t addr; + u8 flags = 0; + + enetc_clear_tx_bd(&txbd_tmp); + + addr = dma_map_single(tx_ring->dev, data, size, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx_ring->dev, addr))) { + netdev_err(tx_ring->ndev, "DMA map error\n"); + return -ENOMEM; + } + + if (last_bd) { + flags |= ENETC_TXBD_FLAGS_F; + tx_swbd->is_eof = 1; + } + + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.buf_len = cpu_to_le16(size); + txbd_tmp.flags = flags; + + tx_swbd->dma = addr; + tx_swbd->len = size; + tx_swbd->dir = DMA_TO_DEVICE; + + *txbd = txbd_tmp; + + return 0; +} + +static __wsum enetc_tso_hdr_csum(struct tso_t *tso, struct sk_buff *skb, + char *hdr, int hdr_len, int *l4_hdr_len) +{ + char *l4_hdr = hdr + skb_transport_offset(skb); + int mac_hdr_len = skb_network_offset(skb); + + if (tso->tlen != sizeof(struct udphdr)) { + struct tcphdr *tcph = (struct tcphdr *)(l4_hdr); + + tcph->check = 0; + } else { + struct udphdr *udph = (struct udphdr *)(l4_hdr); + + udph->check = 0; + } + + /* Compute the IP checksum. This is necessary since tso_build_hdr() + * already incremented the IP ID field. + */ + if (!tso->ipv6) { + struct iphdr *iph = (void *)(hdr + mac_hdr_len); + + iph->check = 0; + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + } + + /* Compute the checksum over the L4 header. */ + *l4_hdr_len = hdr_len - skb_transport_offset(skb); + return csum_partial(l4_hdr, *l4_hdr_len, 0); +} + +static void enetc_tso_complete_csum(struct enetc_bdr *tx_ring, struct tso_t *tso, + struct sk_buff *skb, char *hdr, int len, + __wsum sum) +{ + char *l4_hdr = hdr + skb_transport_offset(skb); + __sum16 csum_final; + + /* Complete the L4 checksum by appending the pseudo-header to the + * already computed checksum. + */ + if (!tso->ipv6) + csum_final = csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + len, ip_hdr(skb)->protocol, sum); + else + csum_final = csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + len, ipv6_hdr(skb)->nexthdr, sum); + + if (tso->tlen != sizeof(struct udphdr)) { + struct tcphdr *tcph = (struct tcphdr *)(l4_hdr); + + tcph->check = csum_final; + } else { + struct udphdr *udph = (struct udphdr *)(l4_hdr); + + udph->check = csum_final; + } +} + +static int enetc_lso_count_descs(const struct sk_buff *skb) +{ + /* 4 BDs: 1 BD for LSO header + 1 BD for extended BD + 1 BD + * for linear area data but not include LSO header, namely + * skb_headlen(skb) - lso_hdr_len (it may be 0, but that's + * okay, we only need to consider the worst case). And 1 BD + * for gap. + */ + return skb_shinfo(skb)->nr_frags + 4; +} + +static int enetc_lso_get_hdr_len(const struct sk_buff *skb) +{ + int hdr_len, tlen; + + tlen = skb_is_gso_tcp(skb) ? tcp_hdrlen(skb) : sizeof(struct udphdr); + hdr_len = skb_transport_offset(skb) + tlen; + + return hdr_len; +} + +static void enetc_lso_start(struct sk_buff *skb, struct enetc_lso_t *lso) +{ + lso->lso_seg_size = skb_shinfo(skb)->gso_size; + lso->ipv6 = enetc_skb_is_ipv6(skb); + lso->tcp = skb_is_gso_tcp(skb); + lso->l3_hdr_len = skb_network_header_len(skb); + lso->l3_start = skb_network_offset(skb); + lso->hdr_len = enetc_lso_get_hdr_len(skb); + lso->total_len = skb->len - lso->hdr_len; +} + +static void enetc_lso_map_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb, + int *i, struct enetc_lso_t *lso) +{ + union enetc_tx_bd txbd_tmp, *txbd; + struct enetc_tx_swbd *tx_swbd; + u16 frm_len, frm_len_ext; + u8 flags, e_flags = 0; + dma_addr_t addr; + char *hdr; + + /* Get the first BD of the LSO BDs chain */ + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + + /* Prepare LSO header: MAC + IP + TCP/UDP */ + hdr = tx_ring->tso_headers + *i * TSO_HEADER_SIZE; + memcpy(hdr, skb->data, lso->hdr_len); + addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE; + + /* {frm_len_ext, frm_len} indicates the total length of + * large transmit data unit. frm_len contains the 16 least + * significant bits and frm_len_ext contains the 4 most + * significant bits. + */ + frm_len = lso->total_len & 0xffff; + frm_len_ext = (lso->total_len >> 16) & 0xf; + + /* Set the flags of the first BD */ + flags = ENETC_TXBD_FLAGS_EX | ENETC_TXBD_FLAGS_CSUM_LSO | + ENETC_TXBD_FLAGS_LSO | ENETC_TXBD_FLAGS_L4CS; + + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.addr = cpu_to_le64(addr); + txbd_tmp.hdr_len = cpu_to_le16(lso->hdr_len); + + /* first BD needs frm_len and offload flags set */ + txbd_tmp.frm_len = cpu_to_le16(frm_len); + txbd_tmp.flags = flags; + + txbd_tmp.l3_aux0 = FIELD_PREP(ENETC_TX_BD_L3_START, lso->l3_start); + /* l3_hdr_size in 32-bits (4 bytes) */ + txbd_tmp.l3_aux1 = FIELD_PREP(ENETC_TX_BD_L3_HDR_LEN, + lso->l3_hdr_len / 4); + if (lso->ipv6) + txbd_tmp.l3_aux1 |= ENETC_TX_BD_L3T; + else + txbd_tmp.l3_aux0 |= ENETC_TX_BD_IPCS; + + txbd_tmp.l4_aux = FIELD_PREP(ENETC_TX_BD_L4T, lso->tcp ? + ENETC_TXBD_L4T_TCP : ENETC_TXBD_L4T_UDP); + + /* For the LSO header we do not set the dma address since + * we do not want it unmapped when we do cleanup. We still + * set len so that we count the bytes sent. + */ + tx_swbd->len = lso->hdr_len; + tx_swbd->do_twostep_tstamp = false; + tx_swbd->check_wb = false; + + /* Actually write the header in the BD */ + *txbd = txbd_tmp; + + /* Get the next BD, and the next BD is extended BD */ + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + + enetc_clear_tx_bd(&txbd_tmp); + if (skb_vlan_tag_present(skb)) { + /* Setup the VLAN fields */ + txbd_tmp.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb)); + txbd_tmp.ext.tpid = ENETC_TPID_8021Q; + e_flags = ENETC_TXBD_E_FLAGS_VLAN_INS; + } + + /* Write the BD */ + txbd_tmp.ext.e_flags = e_flags; + txbd_tmp.ext.lso_sg_size = cpu_to_le16(lso->lso_seg_size); + txbd_tmp.ext.frm_len_ext = cpu_to_le16(frm_len_ext); + *txbd = txbd_tmp; +} + +static int enetc_lso_map_data(struct enetc_bdr *tx_ring, struct sk_buff *skb, + int *i, struct enetc_lso_t *lso, int *count) +{ + union enetc_tx_bd txbd_tmp, *txbd = NULL; + struct enetc_tx_swbd *tx_swbd; + skb_frag_t *frag; + dma_addr_t dma; + u8 flags = 0; + int len, f; + + len = skb_headlen(skb) - lso->hdr_len; + if (len > 0) { + dma = dma_map_single(tx_ring->dev, skb->data + lso->hdr_len, + len, DMA_TO_DEVICE); + if (dma_mapping_error(tx_ring->dev, dma)) + return -ENOMEM; + + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + *count += 1; + + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.addr = cpu_to_le64(dma); + txbd_tmp.buf_len = cpu_to_le16(len); + + tx_swbd->dma = dma; + tx_swbd->len = len; + tx_swbd->is_dma_page = 0; + tx_swbd->dir = DMA_TO_DEVICE; + } + + frag = &skb_shinfo(skb)->frags[0]; + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++, frag++) { + if (txbd) + *txbd = txbd_tmp; + + len = skb_frag_size(frag); + dma = skb_frag_dma_map(tx_ring->dev, frag); + if (dma_mapping_error(tx_ring->dev, dma)) + return -ENOMEM; + + /* Get the next BD */ + enetc_bdr_idx_inc(tx_ring, i); + txbd = ENETC_TXBD(*tx_ring, *i); + tx_swbd = &tx_ring->tx_swbd[*i]; + prefetchw(txbd); + *count += 1; + + enetc_clear_tx_bd(&txbd_tmp); + txbd_tmp.addr = cpu_to_le64(dma); + txbd_tmp.buf_len = cpu_to_le16(len); + + tx_swbd->dma = dma; + tx_swbd->len = len; + tx_swbd->is_dma_page = 1; + tx_swbd->dir = DMA_TO_DEVICE; + } + + /* Last BD needs 'F' bit set */ + flags |= ENETC_TXBD_FLAGS_F; + txbd_tmp.flags = flags; + *txbd = txbd_tmp; + + tx_swbd->is_eof = 1; + tx_swbd->skb = skb; + + return 0; +} + +static int enetc_lso_hw_offload(struct enetc_bdr *tx_ring, struct sk_buff *skb) +{ + struct enetc_tx_swbd *tx_swbd; + struct enetc_lso_t lso = {0}; + int err, i, count = 0; + + /* Initialize the LSO handler */ + enetc_lso_start(skb, &lso); + i = tx_ring->next_to_use; + + enetc_lso_map_hdr(tx_ring, skb, &i, &lso); + /* First BD and an extend BD */ + count += 2; + + err = enetc_lso_map_data(tx_ring, skb, &i, &lso, &count); + if (err) + goto dma_err; + + /* Go to the next BD */ + enetc_bdr_idx_inc(tx_ring, &i); + tx_ring->next_to_use = i; + enetc_update_tx_ring_tail(tx_ring); + + return count; + +dma_err: do { tx_swbd = &tx_ring->tx_swbd[i]; enetc_free_tx_frame(tx_ring, tx_swbd); if (i == 0) i = tx_ring->bd_count; i--; - } while (count--); + } while (--count); + + return 0; +} + +static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb) +{ + struct enetc_ndev_priv *priv = netdev_priv(tx_ring->ndev); + int hdr_len, total_len, data_len; + struct enetc_tx_swbd *tx_swbd; + union enetc_tx_bd *txbd; + struct tso_t tso; + __wsum csum, csum2; + int count = 0, pos; + int err, i, bd_data_num; + + /* Initialize the TSO handler, and prepare the first payload */ + hdr_len = tso_start(skb, &tso); + total_len = skb->len - hdr_len; + i = tx_ring->next_to_use; + + while (total_len > 0) { + char *hdr; + + /* Get the BD */ + txbd = ENETC_TXBD(*tx_ring, i); + tx_swbd = &tx_ring->tx_swbd[i]; + prefetchw(txbd); + + /* Determine the length of this packet */ + data_len = min_t(int, skb_shinfo(skb)->gso_size, total_len); + total_len -= data_len; + + /* prepare packet headers: MAC + IP + TCP */ + hdr = tx_ring->tso_headers + i * TSO_HEADER_SIZE; + tso_build_hdr(skb, hdr, &tso, data_len, total_len == 0); + + /* compute the csum over the L4 header */ + csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos); + count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, + &i, hdr_len, data_len); + bd_data_num = 0; + + while (data_len > 0) { + int size; + + size = min_t(int, tso.size, data_len); + + /* Advance the index in the BDR */ + enetc_bdr_idx_inc(tx_ring, &i); + txbd = ENETC_TXBD(*tx_ring, i); + tx_swbd = &tx_ring->tx_swbd[i]; + prefetchw(txbd); + + /* Compute the checksum over this segment of data and + * add it to the csum already computed (over the L4 + * header and possible other data segments). + */ + csum2 = csum_partial(tso.data, size, 0); + csum = csum_block_add(csum, csum2, pos); + pos += size; + + err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd, + tso.data, size, + size == data_len); + if (err) { + if (i == 0) + i = tx_ring->bd_count; + i--; + + goto err_map_data; + } + + data_len -= size; + count++; + bd_data_num++; + tso_build_data(skb, &tso, size); + + if (unlikely(bd_data_num >= priv->max_frags && data_len)) + goto err_chained_bd; + } + + enetc_tso_complete_csum(tx_ring, &tso, skb, hdr, pos, csum); + + if (total_len == 0) + tx_swbd->skb = skb; + + /* Go to the next BD */ + enetc_bdr_idx_inc(tx_ring, &i); + } + + tx_ring->next_to_use = i; + enetc_update_tx_ring_tail(tx_ring); + + return count; + +err_map_data: + dev_err(tx_ring->dev, "DMA map error"); + +err_chained_bd: + enetc_unwind_tx_frame(tx_ring, count, i); return 0; } @@ -317,12 +977,13 @@ dma_err: static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, struct net_device *ndev) { + struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb); struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_bdr *tx_ring; int count; /* Queue one-step Sync packet if already locked */ - if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { + if (enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { if (test_and_set_bit_lock(ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS, &priv->flags)) { skb_queue_tail(&priv->tx_skbs, skb); @@ -332,24 +993,47 @@ static netdev_tx_t enetc_start_xmit(struct sk_buff *skb, tx_ring = priv->tx_ring[skb->queue_mapping]; - if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS)) - if (unlikely(skb_linearize(skb))) - goto drop_packet_err; + if (skb_is_gso(skb)) { + /* LSO data unit lengths of up to 256KB are supported */ + if (priv->active_offloads & ENETC_F_LSO && + (skb->len - enetc_lso_get_hdr_len(skb)) <= + ENETC_LSO_MAX_DATA_LEN) { + if (enetc_bd_unused(tx_ring) < enetc_lso_count_descs(skb)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } - count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */ - if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) { - netif_stop_subqueue(ndev, tx_ring->index); - return NETDEV_TX_BUSY; - } + count = enetc_lso_hw_offload(tx_ring, skb); + } else { + if (enetc_bd_unused(tx_ring) < tso_count_descs(skb)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } - enetc_lock_mdio(); - count = enetc_map_tx_buffs(tx_ring, skb); - enetc_unlock_mdio(); + enetc_lock_mdio(); + count = enetc_map_tx_tso_buffs(tx_ring, skb); + enetc_unlock_mdio(); + } + } else { + if (unlikely(skb_shinfo(skb)->nr_frags > priv->max_frags)) + if (unlikely(skb_linearize(skb))) + goto drop_packet_err; + + count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */ + if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) { + netif_stop_subqueue(ndev, tx_ring->index); + return NETDEV_TX_BUSY; + } + + enetc_lock_mdio(); + count = enetc_map_tx_buffs(tx_ring, skb); + enetc_unlock_mdio(); + } if (unlikely(!count)) goto drop_packet_err; - if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED) + if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED(priv->max_frags)) netif_stop_subqueue(ndev, tx_ring->index); return NETDEV_TX_OK; @@ -361,28 +1045,34 @@ drop_packet_err: netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev) { + struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb); struct enetc_ndev_priv *priv = netdev_priv(ndev); u8 udp, msgtype, twostep; u16 offset1, offset2; - /* Mark tx timestamp type on skb->cb[0] if requires */ + /* Mark tx timestamp type on enetc_cb->flag if requires */ if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - (priv->active_offloads & ENETC_F_TX_TSTAMP_MASK)) { - skb->cb[0] = priv->active_offloads & ENETC_F_TX_TSTAMP_MASK; - } else { - skb->cb[0] = 0; - } + (priv->active_offloads & ENETC_F_TX_TSTAMP_MASK)) + enetc_cb->flag = priv->active_offloads & ENETC_F_TX_TSTAMP_MASK; + else + enetc_cb->flag = 0; /* Fall back to two-step timestamp if not one-step Sync packet */ - if (skb->cb[0] & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { + if (enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) { if (enetc_ptp_parse(skb, &udp, &msgtype, &twostep, &offset1, &offset2) || - msgtype != PTP_MSGTYPE_SYNC || twostep != 0) - skb->cb[0] = ENETC_F_TX_TSTAMP; + msgtype != PTP_MSGTYPE_SYNC || twostep != 0) { + enetc_cb->flag = ENETC_F_TX_TSTAMP; + } else { + enetc_cb->udp = !!udp; + enetc_cb->correction_off = offset1; + enetc_cb->origin_tstamp_off = offset2; + } } return enetc_start_xmit(skb, ndev); } +EXPORT_SYMBOL_GPL(enetc_xmit); static irqreturn_t enetc_msix(int irq, void *data) { @@ -412,14 +1102,15 @@ static void enetc_rx_dim_work(struct work_struct *w) net_dim_get_rx_moderation(dim->mode, dim->profile_ix); struct enetc_int_vector *v = container_of(dim, struct enetc_int_vector, rx_dim); + struct enetc_ndev_priv *priv = netdev_priv(v->rx_ring.ndev); - v->rx_ictt = enetc_usecs_to_cycles(moder.usec); + v->rx_ictt = enetc_usecs_to_cycles(moder.usec, priv->sysclk_freq); dim->state = DIM_START_MEASURE; } static void enetc_rx_net_dim(struct enetc_int_vector *v) { - struct dim_sample dim_sample; + struct dim_sample dim_sample = {}; v->comp_cnt++; @@ -430,7 +1121,7 @@ static void enetc_rx_net_dim(struct enetc_int_vector *v) v->rx_ring.stats.packets, v->rx_ring.stats.bytes, &dim_sample); - net_dim(&v->rx_dim, dim_sample); + net_dim(&v->rx_dim, &dim_sample); } static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci) @@ -525,9 +1216,9 @@ static void enetc_recycle_xdp_tx_buff(struct enetc_bdr *tx_ring, static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) { + int tx_frm_cnt = 0, tx_byte_cnt = 0, tx_win_drop = 0; struct net_device *ndev = tx_ring->ndev; struct enetc_ndev_priv *priv = netdev_priv(ndev); - int tx_frm_cnt = 0, tx_byte_cnt = 0; struct enetc_tx_swbd *tx_swbd; int i, bds_to_clean; bool do_twostep_tstamp; @@ -546,10 +1237,7 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) bool is_eof = tx_swbd->is_eof; if (unlikely(tx_swbd->check_wb)) { - struct enetc_ndev_priv *priv = netdev_priv(ndev); - union enetc_tx_bd *txbd; - - txbd = ENETC_TXBD(*tx_ring, i); + union enetc_tx_bd *txbd = ENETC_TXBD(*tx_ring, i); if (txbd->flags & ENETC_TXBD_FLAGS_W && tx_swbd->do_twostep_tstamp) { @@ -557,6 +1245,10 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) &tstamp); do_twostep_tstamp = true; } + + if (tx_swbd->qbv_en && + txbd->wb.status & ENETC_TXBD_STATS_WIN) + tx_win_drop++; } if (tx_swbd->is_xdp_tx) @@ -567,8 +1259,9 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) if (xdp_frame) { xdp_return_frame(xdp_frame); } else if (skb) { - if (unlikely(tx_swbd->skb->cb[0] & - ENETC_F_TX_ONESTEP_SYNC_TSTAMP)) { + struct enetc_skb_cb *enetc_cb = ENETC_SKB_CB(skb); + + if (unlikely(enetc_cb->flag & ENETC_F_TX_ONESTEP_SYNC_TSTAMP)) { /* Start work to release lock for next one-step * timestamping packet. And send one skb in * tx_skbs queue if has. @@ -610,10 +1303,13 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) tx_ring->next_to_clean = i; tx_ring->stats.packets += tx_frm_cnt; tx_ring->stats.bytes += tx_byte_cnt; + tx_ring->stats.win_drop += tx_win_drop; if (unlikely(tx_frm_cnt && netif_carrier_ok(ndev) && __netif_subqueue_stopped(ndev, tx_ring->index) && - (enetc_bd_unused(tx_ring) >= ENETC_TXBDS_MAX_NEEDED))) { + !test_bit(ENETC_TX_DOWN, &priv->flags) && + (enetc_bd_unused(tx_ring) >= + ENETC_TXBDS_MAX_NEEDED(priv->max_frags)))) { netif_wake_subqueue(ndev, tx_ring->index); } @@ -688,7 +1384,6 @@ static int enetc_refill_rx_ring(struct enetc_bdr *rx_ring, const int buff_cnt) return j; } -#ifdef CONFIG_FSL_ENETC_PTP_CLOCK static void enetc_get_rx_tstamp(struct net_device *ndev, union enetc_rx_bd *rxbd, struct sk_buff *skb) @@ -712,7 +1407,6 @@ static void enetc_get_rx_tstamp(struct net_device *ndev, shhwtstamps->hwtstamp = ns_to_ktime(tstamp); } } -#endif static void enetc_get_offloads(struct enetc_bdr *rx_ring, union enetc_rx_bd *rxbd, struct sk_buff *skb) @@ -728,6 +1422,7 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring, } if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) { + struct enetc_hw *hw = &priv->si->hw; __be16 tpid = 0; switch (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TPID) { @@ -738,24 +1433,19 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring, tpid = htons(ETH_P_8021AD); break; case 2: - tpid = htons(enetc_port_rd(&priv->si->hw, - ENETC_PCVLANR1)); + tpid = htons(enetc_rd_hot(hw, ENETC_SICVLANR1) & + SICVLANR_ETYPE); break; case 3: - tpid = htons(enetc_port_rd(&priv->si->hw, - ENETC_PCVLANR2)); - break; - default: - break; + tpid = htons(enetc_rd_hot(hw, ENETC_SICVLANR2) & + SICVLANR_ETYPE); } __vlan_hwaccel_put_tag(skb, tpid, le16_to_cpu(rxbd->r.vlan_opt)); } -#ifdef CONFIG_FSL_ENETC_PTP_CLOCK if (priv->active_offloads & ENETC_F_RX_TSTAMP) enetc_get_rx_tstamp(rx_ring->ndev, rxbd, skb); -#endif } /* This gets called during the non-XDP NAPI poll cycle as well as on XDP_PASS, @@ -914,6 +1604,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, /* next descriptor to process */ i = rx_ring->next_to_clean; + enetc_lock_mdio(); + while (likely(rx_frm_cnt < work_limit)) { union enetc_rx_bd *rxbd; struct sk_buff *skb; @@ -940,10 +1632,18 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, if (!skb) break; - rx_byte_cnt += skb->len; + /* When set, the outer VLAN header is extracted and reported + * in the receive buffer descriptor. So rx_byte_cnt should + * add the length of the extracted VLAN header. + */ + if (bd_status & ENETC_RXBD_FLAG_VLAN) + rx_byte_cnt += VLAN_HLEN; + rx_byte_cnt += skb->len + ETH_HLEN; rx_frm_cnt++; + enetc_unlock_mdio(); napi_gro_receive(napi, skb); + enetc_lock_mdio(); } rx_ring->next_to_clean = i; @@ -951,6 +1651,8 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, rx_ring->stats.packets += rx_frm_cnt; rx_ring->stats.bytes += rx_byte_cnt; + enetc_unlock_mdio(); + return rx_frm_cnt; } @@ -1036,6 +1738,10 @@ static int enetc_xdp_frame_to_xdp_tx_swbd(struct enetc_bdr *tx_ring, xdp_tx_swbd->xdp_frame = NULL; n++; + + if (!xdp_frame_has_frags(xdp_frame)) + goto out; + xdp_tx_swbd = &xdp_tx_arr[n]; shinfo = xdp_get_shared_info_from_frame(xdp_frame); @@ -1065,7 +1771,7 @@ static int enetc_xdp_frame_to_xdp_tx_swbd(struct enetc_bdr *tx_ring, n++; xdp_tx_swbd = &xdp_tx_arr[n]; } - +out: xdp_tx_arr[n - 1].is_eof = true; xdp_tx_arr[n - 1].xdp_frame = xdp_frame; @@ -1081,6 +1787,9 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames, int xdp_tx_bd_cnt, i, k; int xdp_tx_frm_cnt = 0; + if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags))) + return -ENETDOWN; + enetc_lock_mdio(); tx_ring = priv->xdp_tx_ring[smp_processor_id()]; @@ -1115,22 +1824,19 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames, return xdp_tx_frm_cnt; } +EXPORT_SYMBOL_GPL(enetc_xdp_xmit); static void enetc_map_rx_buff_to_xdp(struct enetc_bdr *rx_ring, int i, struct xdp_buff *xdp_buff, u16 size) { struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size); void *hard_start = page_address(rx_swbd->page) + rx_swbd->page_offset; - struct skb_shared_info *shinfo; /* To be used for XDP_TX */ rx_swbd->len = size; xdp_prepare_buff(xdp_buff, hard_start - rx_ring->buffer_offset, rx_ring->buffer_offset, size, false); - - shinfo = xdp_get_shared_info_from_buff(xdp_buff); - shinfo->nr_frags = 0; } static void enetc_add_rx_buff_to_xdp(struct enetc_bdr *rx_ring, int i, @@ -1138,14 +1844,25 @@ static void enetc_add_rx_buff_to_xdp(struct enetc_bdr *rx_ring, int i, { struct skb_shared_info *shinfo = xdp_get_shared_info_from_buff(xdp_buff); struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size); - skb_frag_t *frag = &shinfo->frags[shinfo->nr_frags]; + skb_frag_t *frag; /* To be used for XDP_TX */ rx_swbd->len = size; - skb_frag_off_set(frag, rx_swbd->page_offset); - skb_frag_size_set(frag, size); - __skb_frag_set_page(frag, rx_swbd->page); + if (!xdp_buff_has_frags(xdp_buff)) { + xdp_buff_set_frags_flag(xdp_buff); + shinfo->xdp_frags_size = size; + shinfo->nr_frags = 0; + } else { + shinfo->xdp_frags_size += size; + } + + if (page_is_pfmemalloc(rx_swbd->page)) + xdp_buff_set_frag_pfmemalloc(xdp_buff); + + frag = &shinfo->frags[shinfo->nr_frags]; + skb_frag_fill_page_desc(frag, rx_swbd->page, rx_swbd->page_offset, + size); shinfo->nr_frags++; } @@ -1217,24 +1934,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first, &rx_ring->rx_swbd[rx_ring_first]); enetc_bdr_idx_inc(rx_ring, &rx_ring_first); } - rx_ring->stats.xdp_drops++; } -static void enetc_xdp_free(struct enetc_bdr *rx_ring, int rx_ring_first, - int rx_ring_last) +static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first, + int rx_ring_last) { while (rx_ring_first != rx_ring_last) { - struct enetc_rx_swbd *rx_swbd = &rx_ring->rx_swbd[rx_ring_first]; - - if (rx_swbd->page) { - dma_unmap_page(rx_ring->dev, rx_swbd->dma, PAGE_SIZE, - rx_swbd->dir); - __free_page(rx_swbd->page); - rx_swbd->page = NULL; - } + enetc_flip_rx_buff(rx_ring, + &rx_ring->rx_swbd[rx_ring_first]); enetc_bdr_idx_inc(rx_ring, &rx_ring_first); } - rx_ring->stats.xdp_redirect_failures++; } static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, @@ -1253,12 +1962,13 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, /* next descriptor to process */ i = rx_ring->next_to_clean; + enetc_lock_mdio(); + while (likely(rx_frm_cnt < work_limit)) { union enetc_rx_bd *rxbd, *orig_rxbd; - int orig_i, orig_cleaned_cnt; struct xdp_buff xdp_buff; struct sk_buff *skb; - int tmp_orig_i, err; + int orig_i, err; u32 bd_status; rxbd = enetc_rxbd(rx_ring, i); @@ -1274,39 +1984,61 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, break; orig_rxbd = rxbd; - orig_cleaned_cnt = cleaned_cnt; orig_i = i; enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i, &cleaned_cnt, &xdp_buff); + /* When set, the outer VLAN header is extracted and reported + * in the receive buffer descriptor. So rx_byte_cnt should + * add the length of the extracted VLAN header. + */ + if (bd_status & ENETC_RXBD_FLAG_VLAN) + rx_byte_cnt += VLAN_HLEN; + rx_byte_cnt += xdp_get_buff_len(&xdp_buff); + xdp_act = bpf_prog_run_xdp(prog, &xdp_buff); switch (xdp_act) { default: - bpf_warn_invalid_xdp_action(xdp_act); + bpf_warn_invalid_xdp_action(rx_ring->ndev, prog, xdp_act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rx_ring->ndev, prog, xdp_act); fallthrough; case XDP_DROP: enetc_xdp_drop(rx_ring, orig_i, i); + rx_ring->stats.xdp_drops++; break; case XDP_PASS: - rxbd = orig_rxbd; - cleaned_cnt = orig_cleaned_cnt; - i = orig_i; - - skb = enetc_build_skb(rx_ring, bd_status, &rxbd, - &i, &cleaned_cnt, - ENETC_RXB_DMA_SIZE_XDP); - if (unlikely(!skb)) + skb = xdp_build_skb_from_buff(&xdp_buff); + /* Probably under memory pressure, stop NAPI */ + if (unlikely(!skb)) { + enetc_xdp_drop(rx_ring, orig_i, i); + rx_ring->stats.xdp_drops++; goto out; + } + enetc_get_offloads(rx_ring, orig_rxbd, skb); + + /* These buffers are about to be owned by the stack. + * Update our buffer cache (the rx_swbd array elements) + * with their other page halves. + */ + enetc_bulk_flip_buff(rx_ring, orig_i, i); + + enetc_unlock_mdio(); napi_gro_receive(napi, skb); + enetc_lock_mdio(); break; case XDP_TX: tx_ring = priv->xdp_tx_ring[rx_ring->index]; + if (unlikely(test_bit(ENETC_TX_DOWN, &priv->flags))) { + enetc_xdp_drop(rx_ring, orig_i, i); + tx_ring->stats.xdp_tx_drops++; + break; + } + xdp_tx_bd_cnt = enetc_rx_swbd_to_xdp_tx_swbd(xdp_tx_arr, rx_ring, orig_i, i); @@ -1315,7 +2047,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, enetc_xdp_drop(rx_ring, orig_i, i); tx_ring->stats.xdp_tx_drops++; } else { - tx_ring->stats.xdp_tx += xdp_tx_bd_cnt; + tx_ring->stats.xdp_tx++; rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt; xdp_tx_frm_cnt++; /* The XDP_TX enqueue was successful, so we @@ -1332,32 +2064,14 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, } break; case XDP_REDIRECT: - /* xdp_return_frame does not support S/G in the sense - * that it leaks the fragments (__xdp_return should not - * call page_frag_free only for the initial buffer). - * Until XDP_REDIRECT gains support for S/G let's keep - * the code structure in place, but dead. We drop the - * S/G frames ourselves to avoid memory leaks which - * would otherwise leave the kernel OOM. - */ - if (unlikely(cleaned_cnt - orig_cleaned_cnt != 1)) { - enetc_xdp_drop(rx_ring, orig_i, i); - rx_ring->stats.xdp_redirect_sg++; - break; - } - - tmp_orig_i = orig_i; - - while (orig_i != i) { - enetc_flip_rx_buff(rx_ring, - &rx_ring->rx_swbd[orig_i]); - enetc_bdr_idx_inc(rx_ring, &orig_i); - } - + enetc_unlock_mdio(); err = xdp_do_redirect(rx_ring->ndev, &xdp_buff, prog); + enetc_lock_mdio(); if (unlikely(err)) { - enetc_xdp_free(rx_ring, tmp_orig_i, i); + enetc_xdp_drop(rx_ring, orig_i, i); + rx_ring->stats.xdp_redirect_failures++; } else { + enetc_bulk_flip_buff(rx_ring, orig_i, i); xdp_redirect_frm_cnt++; rx_ring->stats.xdp_redirect++; } @@ -1372,8 +2086,11 @@ out: rx_ring->stats.packets += rx_frm_cnt; rx_ring->stats.bytes += rx_byte_cnt; - if (xdp_redirect_frm_cnt) - xdp_do_flush_map(); + if (xdp_redirect_frm_cnt) { + enetc_unlock_mdio(); + xdp_do_flush(); + enetc_lock_mdio(); + } if (xdp_tx_frm_cnt) enetc_update_tx_ring_tail(tx_ring); @@ -1382,6 +2099,8 @@ out: enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring) - rx_ring->xdp.xdp_tx_in_flight); + enetc_unlock_mdio(); + return rx_frm_cnt; } @@ -1400,6 +2119,7 @@ static int enetc_poll(struct napi_struct *napi, int budget) for (i = 0; i < v->count_tx_rings; i++) if (!enetc_clean_tx_ring(&v->tx_ring[i], budget)) complete = false; + enetc_unlock_mdio(); prog = rx_ring->xdp.prog; if (prog) @@ -1411,10 +2131,8 @@ static int enetc_poll(struct napi_struct *napi, int budget) if (work_done) v->rx_napi_work = true; - if (!complete) { - enetc_unlock_mdio(); + if (!complete) return budget; - } napi_complete_done(napi, work_done); @@ -1423,6 +2141,7 @@ static int enetc_poll(struct napi_struct *napi, int budget) v->rx_napi_work = false; + enetc_lock_mdio(); /* enable interrupts */ enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE); @@ -1447,9 +2166,15 @@ void enetc_get_si_caps(struct enetc_si *si) si->num_rx_rings = (val >> 16) & 0xff; si->num_tx_rings = val & 0xff; - val = enetc_rd(hw, ENETC_SIRFSCAPR); - si->num_fs_entries = ENETC_SIRFSCAPR_GET_NUM_RFS(val); - si->num_fs_entries = min(si->num_fs_entries, ENETC_MAX_RFS_SIZE); + val = enetc_rd(hw, ENETC_SIPCAPR0); + if (val & ENETC_SIPCAPR0_RFS) { + val = enetc_rd(hw, ENETC_SIRFSCAPR); + si->num_fs_entries = ENETC_SIRFSCAPR_GET_NUM_RFS(val); + si->num_fs_entries = min(si->num_fs_entries, ENETC_MAX_RFS_SIZE); + } else { + /* ENETC which not supports RFS */ + si->num_fs_entries = 0; + } si->num_rss = 0; val = enetc_rd(hw, ENETC_SIPCAPR0); @@ -1460,186 +2185,260 @@ void enetc_get_si_caps(struct enetc_si *si) si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(rss); } - if (val & ENETC_SIPCAPR0_QBV) - si->hw_features |= ENETC_SI_F_QBV; - - if (val & ENETC_SIPCAPR0_PSFP) - si->hw_features |= ENETC_SI_F_PSFP; + if (val & ENETC_SIPCAPR0_LSO) + si->hw_features |= ENETC_SI_F_LSO; } +EXPORT_SYMBOL_GPL(enetc_get_si_caps); -static int enetc_dma_alloc_bdr(struct enetc_bdr *r, size_t bd_size) +static int enetc_dma_alloc_bdr(struct enetc_bdr_resource *res) { - r->bd_base = dma_alloc_coherent(r->dev, r->bd_count * bd_size, - &r->bd_dma_base, GFP_KERNEL); - if (!r->bd_base) + size_t bd_base_size = res->bd_count * res->bd_size; + + res->bd_base = dma_alloc_coherent(res->dev, bd_base_size, + &res->bd_dma_base, GFP_KERNEL); + if (!res->bd_base) return -ENOMEM; /* h/w requires 128B alignment */ - if (!IS_ALIGNED(r->bd_dma_base, 128)) { - dma_free_coherent(r->dev, r->bd_count * bd_size, r->bd_base, - r->bd_dma_base); + if (!IS_ALIGNED(res->bd_dma_base, 128)) { + dma_free_coherent(res->dev, bd_base_size, res->bd_base, + res->bd_dma_base); return -EINVAL; } return 0; } -static int enetc_alloc_txbdr(struct enetc_bdr *txr) +static void enetc_dma_free_bdr(const struct enetc_bdr_resource *res) +{ + size_t bd_base_size = res->bd_count * res->bd_size; + + dma_free_coherent(res->dev, bd_base_size, res->bd_base, + res->bd_dma_base); +} + +static int enetc_alloc_tx_resource(struct enetc_bdr_resource *res, + struct device *dev, size_t bd_count) { int err; - txr->tx_swbd = vzalloc(txr->bd_count * sizeof(struct enetc_tx_swbd)); - if (!txr->tx_swbd) + res->dev = dev; + res->bd_count = bd_count; + res->bd_size = sizeof(union enetc_tx_bd); + + res->tx_swbd = vcalloc(bd_count, sizeof(*res->tx_swbd)); + if (!res->tx_swbd) return -ENOMEM; - err = enetc_dma_alloc_bdr(txr, sizeof(union enetc_tx_bd)); - if (err) { - vfree(txr->tx_swbd); - return err; - } + err = enetc_dma_alloc_bdr(res); + if (err) + goto err_alloc_bdr; - txr->next_to_clean = 0; - txr->next_to_use = 0; + res->tso_headers = dma_alloc_coherent(dev, bd_count * TSO_HEADER_SIZE, + &res->tso_headers_dma, + GFP_KERNEL); + if (!res->tso_headers) { + err = -ENOMEM; + goto err_alloc_tso; + } return 0; -} - -static void enetc_free_txbdr(struct enetc_bdr *txr) -{ - int size, i; - for (i = 0; i < txr->bd_count; i++) - enetc_free_tx_frame(txr, &txr->tx_swbd[i]); +err_alloc_tso: + enetc_dma_free_bdr(res); +err_alloc_bdr: + vfree(res->tx_swbd); + res->tx_swbd = NULL; - size = txr->bd_count * sizeof(union enetc_tx_bd); - - dma_free_coherent(txr->dev, size, txr->bd_base, txr->bd_dma_base); - txr->bd_base = NULL; + return err; +} - vfree(txr->tx_swbd); - txr->tx_swbd = NULL; +static void enetc_free_tx_resource(const struct enetc_bdr_resource *res) +{ + dma_free_coherent(res->dev, res->bd_count * TSO_HEADER_SIZE, + res->tso_headers, res->tso_headers_dma); + enetc_dma_free_bdr(res); + vfree(res->tx_swbd); } -static int enetc_alloc_tx_resources(struct enetc_ndev_priv *priv) +static struct enetc_bdr_resource * +enetc_alloc_tx_resources(struct enetc_ndev_priv *priv) { + struct enetc_bdr_resource *tx_res; int i, err; + tx_res = kcalloc(priv->num_tx_rings, sizeof(*tx_res), GFP_KERNEL); + if (!tx_res) + return ERR_PTR(-ENOMEM); + for (i = 0; i < priv->num_tx_rings; i++) { - err = enetc_alloc_txbdr(priv->tx_ring[i]); + struct enetc_bdr *tx_ring = priv->tx_ring[i]; + err = enetc_alloc_tx_resource(&tx_res[i], tx_ring->dev, + tx_ring->bd_count); if (err) goto fail; } - return 0; + return tx_res; fail: while (i-- > 0) - enetc_free_txbdr(priv->tx_ring[i]); + enetc_free_tx_resource(&tx_res[i]); - return err; + kfree(tx_res); + + return ERR_PTR(err); } -static void enetc_free_tx_resources(struct enetc_ndev_priv *priv) +static void enetc_free_tx_resources(const struct enetc_bdr_resource *tx_res, + size_t num_resources) { - int i; + size_t i; - for (i = 0; i < priv->num_tx_rings; i++) - enetc_free_txbdr(priv->tx_ring[i]); + for (i = 0; i < num_resources; i++) + enetc_free_tx_resource(&tx_res[i]); + + kfree(tx_res); } -static int enetc_alloc_rxbdr(struct enetc_bdr *rxr, bool extended) +static int enetc_alloc_rx_resource(struct enetc_bdr_resource *res, + struct device *dev, size_t bd_count, + bool extended) { - size_t size = sizeof(union enetc_rx_bd); int err; - rxr->rx_swbd = vzalloc(rxr->bd_count * sizeof(struct enetc_rx_swbd)); - if (!rxr->rx_swbd) - return -ENOMEM; - + res->dev = dev; + res->bd_count = bd_count; + res->bd_size = sizeof(union enetc_rx_bd); if (extended) - size *= 2; + res->bd_size *= 2; - err = enetc_dma_alloc_bdr(rxr, size); + res->rx_swbd = vcalloc(bd_count, sizeof(struct enetc_rx_swbd)); + if (!res->rx_swbd) + return -ENOMEM; + + err = enetc_dma_alloc_bdr(res); if (err) { - vfree(rxr->rx_swbd); + vfree(res->rx_swbd); return err; } - rxr->next_to_clean = 0; - rxr->next_to_use = 0; - rxr->next_to_alloc = 0; - rxr->ext_en = extended; - return 0; } -static void enetc_free_rxbdr(struct enetc_bdr *rxr) +static void enetc_free_rx_resource(const struct enetc_bdr_resource *res) { - int size; - - size = rxr->bd_count * sizeof(union enetc_rx_bd); - - dma_free_coherent(rxr->dev, size, rxr->bd_base, rxr->bd_dma_base); - rxr->bd_base = NULL; - - vfree(rxr->rx_swbd); - rxr->rx_swbd = NULL; + enetc_dma_free_bdr(res); + vfree(res->rx_swbd); } -static int enetc_alloc_rx_resources(struct enetc_ndev_priv *priv) +static struct enetc_bdr_resource * +enetc_alloc_rx_resources(struct enetc_ndev_priv *priv, bool extended) { - bool extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); + struct enetc_bdr_resource *rx_res; int i, err; + rx_res = kcalloc(priv->num_rx_rings, sizeof(*rx_res), GFP_KERNEL); + if (!rx_res) + return ERR_PTR(-ENOMEM); + for (i = 0; i < priv->num_rx_rings; i++) { - err = enetc_alloc_rxbdr(priv->rx_ring[i], extended); + struct enetc_bdr *rx_ring = priv->rx_ring[i]; + err = enetc_alloc_rx_resource(&rx_res[i], rx_ring->dev, + rx_ring->bd_count, extended); if (err) goto fail; } - return 0; + return rx_res; fail: while (i-- > 0) - enetc_free_rxbdr(priv->rx_ring[i]); + enetc_free_rx_resource(&rx_res[i]); - return err; + kfree(rx_res); + + return ERR_PTR(err); +} + +static void enetc_free_rx_resources(const struct enetc_bdr_resource *rx_res, + size_t num_resources) +{ + size_t i; + + for (i = 0; i < num_resources; i++) + enetc_free_rx_resource(&rx_res[i]); + + kfree(rx_res); +} + +static void enetc_assign_tx_resource(struct enetc_bdr *tx_ring, + const struct enetc_bdr_resource *res) +{ + tx_ring->bd_base = res ? res->bd_base : NULL; + tx_ring->bd_dma_base = res ? res->bd_dma_base : 0; + tx_ring->tx_swbd = res ? res->tx_swbd : NULL; + tx_ring->tso_headers = res ? res->tso_headers : NULL; + tx_ring->tso_headers_dma = res ? res->tso_headers_dma : 0; +} + +static void enetc_assign_rx_resource(struct enetc_bdr *rx_ring, + const struct enetc_bdr_resource *res) +{ + rx_ring->bd_base = res ? res->bd_base : NULL; + rx_ring->bd_dma_base = res ? res->bd_dma_base : 0; + rx_ring->rx_swbd = res ? res->rx_swbd : NULL; } -static void enetc_free_rx_resources(struct enetc_ndev_priv *priv) +static void enetc_assign_tx_resources(struct enetc_ndev_priv *priv, + const struct enetc_bdr_resource *res) { int i; - for (i = 0; i < priv->num_rx_rings; i++) - enetc_free_rxbdr(priv->rx_ring[i]); + if (priv->tx_res) + enetc_free_tx_resources(priv->tx_res, priv->num_tx_rings); + + for (i = 0; i < priv->num_tx_rings; i++) { + enetc_assign_tx_resource(priv->tx_ring[i], + res ? &res[i] : NULL); + } + + priv->tx_res = res; } -static void enetc_free_tx_ring(struct enetc_bdr *tx_ring) +static void enetc_assign_rx_resources(struct enetc_ndev_priv *priv, + const struct enetc_bdr_resource *res) { int i; - if (!tx_ring->tx_swbd) - return; + if (priv->rx_res) + enetc_free_rx_resources(priv->rx_res, priv->num_rx_rings); + + for (i = 0; i < priv->num_rx_rings; i++) { + enetc_assign_rx_resource(priv->rx_ring[i], + res ? &res[i] : NULL); + } + + priv->rx_res = res; +} + +static void enetc_free_tx_ring(struct enetc_bdr *tx_ring) +{ + int i; for (i = 0; i < tx_ring->bd_count; i++) { struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i]; enetc_free_tx_frame(tx_ring, tx_swbd); } - - tx_ring->next_to_clean = 0; - tx_ring->next_to_use = 0; } static void enetc_free_rx_ring(struct enetc_bdr *rx_ring) { int i; - if (!rx_ring->rx_swbd) - return; - for (i = 0; i < rx_ring->bd_count; i++) { struct enetc_rx_swbd *rx_swbd = &rx_ring->rx_swbd[i]; @@ -1651,10 +2450,6 @@ static void enetc_free_rx_ring(struct enetc_bdr *rx_ring) __free_page(rx_swbd->page); rx_swbd->page = NULL; } - - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; - rx_ring->next_to_alloc = 0; } static void enetc_free_rxtx_rings(struct enetc_ndev_priv *priv) @@ -1681,13 +2476,35 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups) for (i = 0; i < si->num_rss; i++) rss_table[i] = i % num_groups; - enetc_set_rss_table(si, rss_table, si->num_rss); + si->ops->set_rss_table(si, rss_table, si->num_rss); kfree(rss_table); return 0; } +static void enetc_set_lso_flags_mask(struct enetc_hw *hw) +{ + enetc_wr(hw, ENETC4_SILSOSFMR0, + SILSOSFMR0_VAL_SET(ENETC4_TCP_NL_SEG_FLAGS_DMASK, + ENETC4_TCP_NL_SEG_FLAGS_DMASK)); + enetc_wr(hw, ENETC4_SILSOSFMR1, 0); +} + +static void enetc_set_rss(struct net_device *ndev, int en) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; + u32 reg; + + enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings); + + reg = enetc_rd(hw, ENETC_SIMR); + reg &= ~ENETC_SIMR_RSSE; + reg |= (en) ? ENETC_SIMR_RSSE : 0; + enetc_wr(hw, ENETC_SIMR, reg); +} + int enetc_configure_si(struct enetc_ndev_priv *priv) { struct enetc_si *si = priv->si; @@ -1701,14 +2518,21 @@ int enetc_configure_si(struct enetc_ndev_priv *priv) /* enable SI */ enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN); + if (si->hw_features & ENETC_SI_F_LSO) + enetc_set_lso_flags_mask(hw); + if (si->num_rss) { err = enetc_setup_default_rss_table(si, priv->num_rx_rings); if (err) return err; + + if (priv->ndev->features & NETIF_F_RXHASH) + enetc_set_rss(priv->ndev, true); } return 0; } +EXPORT_SYMBOL_GPL(enetc_configure_si); void enetc_init_si_rings_params(struct enetc_ndev_priv *priv) { @@ -1724,10 +2548,11 @@ void enetc_init_si_rings_params(struct enetc_ndev_priv *priv) */ priv->num_rx_rings = min_t(int, cpus, si->num_rx_rings); priv->num_tx_rings = si->num_tx_rings; - priv->bdr_int_num = cpus; + priv->bdr_int_num = priv->num_rx_rings; priv->ic_mode = ENETC_IC_RX_ADAPTIVE | ENETC_IC_TX_MANUAL; - priv->tx_ictt = ENETC_TXIC_TIMETHR; + priv->tx_ictt = enetc_usecs_to_cycles(600, priv->sysclk_freq); } +EXPORT_SYMBOL_GPL(enetc_init_si_rings_params); int enetc_alloc_si_resources(struct enetc_ndev_priv *priv) { @@ -1740,11 +2565,13 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv) return 0; } +EXPORT_SYMBOL_GPL(enetc_alloc_si_resources); void enetc_free_si_resources(struct enetc_ndev_priv *priv) { kfree(priv->cls_rules); } +EXPORT_SYMBOL_GPL(enetc_free_si_resources); static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) { @@ -1768,7 +2595,7 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) /* enable Tx ints by setting pkt thr to 1 */ enetc_txbdr_wr(hw, idx, ENETC_TBICR0, ENETC_TBICR0_ICEN | 0x1); - tbmr = ENETC_TBMR_EN; + tbmr = ENETC_TBMR_SET_PRIO(tx_ring->prio); if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX) tbmr |= ENETC_TBMR_VIH; @@ -1780,10 +2607,11 @@ static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) tx_ring->idr = hw->reg + ENETC_SITXIDR; } -static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) +static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring, + bool extended) { int idx = rx_ring->index; - u32 rbmr; + u32 rbmr = 0; enetc_rxbdr_wr(hw, idx, ENETC_RBBAR0, lower_32_bits(rx_ring->bd_dma_base)); @@ -1800,13 +2628,17 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) else enetc_rxbdr_wr(hw, idx, ENETC_RBBSR, ENETC_RXB_DMA_SIZE); + /* Also prepare the consumer index in case page allocation never + * succeeds. In that case, hardware will never advance producer index + * to match consumer index, and will drop all frames. + */ enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0); + enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, 1); /* enable Rx ints by setting pkt thr to 1 */ enetc_rxbdr_wr(hw, idx, ENETC_RBICR0, ENETC_RBICR0_ICEN | 0x1); - rbmr = ENETC_RBMR_EN; - + rx_ring->ext_en = extended; if (rx_ring->ext_en) rbmr |= ENETC_RBMR_BDS; @@ -1816,26 +2648,68 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) rx_ring->rcir = hw->reg + ENETC_BDR(RX, idx, ENETC_RBCIR); rx_ring->idr = hw->reg + ENETC_SIRXIDR; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + rx_ring->next_to_alloc = 0; + enetc_lock_mdio(); enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring)); enetc_unlock_mdio(); - /* enable ring */ enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); } -static void enetc_setup_bdrs(struct enetc_ndev_priv *priv) +static void enetc_setup_bdrs(struct enetc_ndev_priv *priv, bool extended) { + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_setup_txbdr(&priv->si->hw, priv->tx_ring[i]); + enetc_setup_txbdr(hw, priv->tx_ring[i]); + + for (i = 0; i < priv->num_rx_rings; i++) + enetc_setup_rxbdr(hw, priv->rx_ring[i], extended); +} + +static void enetc_enable_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) +{ + int idx = tx_ring->index; + u32 tbmr; + + tbmr = enetc_txbdr_rd(hw, idx, ENETC_TBMR); + tbmr |= ENETC_TBMR_EN; + enetc_txbdr_wr(hw, idx, ENETC_TBMR, tbmr); +} + +static void enetc_enable_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) +{ + int idx = rx_ring->index; + u32 rbmr; + + rbmr = enetc_rxbdr_rd(hw, idx, ENETC_RBMR); + rbmr |= ENETC_RBMR_EN; + enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); +} + +static void enetc_enable_rx_bdrs(struct enetc_ndev_priv *priv) +{ + struct enetc_hw *hw = &priv->si->hw; + int i; for (i = 0; i < priv->num_rx_rings; i++) - enetc_setup_rxbdr(&priv->si->hw, priv->rx_ring[i]); + enetc_enable_rxbdr(hw, priv->rx_ring[i]); } -static void enetc_clear_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) +static void enetc_enable_tx_bdrs(struct enetc_ndev_priv *priv) +{ + struct enetc_hw *hw = &priv->si->hw; + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + enetc_enable_txbdr(hw, priv->tx_ring[i]); +} + +static void enetc_disable_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) { int idx = rx_ring->index; @@ -1843,13 +2717,36 @@ static void enetc_clear_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) enetc_rxbdr_wr(hw, idx, ENETC_RBMR, 0); } -static void enetc_clear_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) +static void enetc_disable_txbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) { - int delay = 8, timeout = 100; - int idx = tx_ring->index; + int idx = rx_ring->index; /* disable EN bit on ring */ enetc_txbdr_wr(hw, idx, ENETC_TBMR, 0); +} + +static void enetc_disable_rx_bdrs(struct enetc_ndev_priv *priv) +{ + struct enetc_hw *hw = &priv->si->hw; + int i; + + for (i = 0; i < priv->num_rx_rings; i++) + enetc_disable_rxbdr(hw, priv->rx_ring[i]); +} + +static void enetc_disable_tx_bdrs(struct enetc_ndev_priv *priv) +{ + struct enetc_hw *hw = &priv->si->hw; + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + enetc_disable_txbdr(hw, priv->tx_ring[i]); +} + +static void enetc_wait_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) +{ + int delay = 8, timeout = 100; + int idx = tx_ring->index; /* wait for busy to clear */ while (delay < timeout && @@ -1863,39 +2760,33 @@ static void enetc_clear_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring) idx); } -static void enetc_clear_bdrs(struct enetc_ndev_priv *priv) +static void enetc_wait_bdrs(struct enetc_ndev_priv *priv) { + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_clear_txbdr(&priv->si->hw, priv->tx_ring[i]); - - for (i = 0; i < priv->num_rx_rings; i++) - enetc_clear_rxbdr(&priv->si->hw, priv->rx_ring[i]); - - udelay(1); + enetc_wait_txbdr(hw, priv->tx_ring[i]); } static int enetc_setup_irqs(struct enetc_ndev_priv *priv) { struct pci_dev *pdev = priv->si->pdev; - cpumask_t cpu_mask; + struct enetc_hw *hw = &priv->si->hw; int i, j, err; for (i = 0; i < priv->bdr_int_num; i++) { int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i); struct enetc_int_vector *v = priv->int_vector[i]; int entry = ENETC_BDR_INT_BASE_IDX + i; - struct enetc_hw *hw = &priv->si->hw; snprintf(v->name, sizeof(v->name), "%s-rxtx%d", priv->ndev->name, i); - err = request_irq(irq, enetc_msix, 0, v->name, v); + err = request_irq(irq, enetc_msix, IRQF_NO_AUTOEN, v->name, v); if (err) { dev_err(priv->dev, "request_irq() failed!\n"); goto irq_err; } - disable_irq(irq); v->tbier_base = hw->reg + ENETC_BDR(TX, 0, ENETC_TBIER); v->rbier = hw->reg + ENETC_BDR(RX, i, ENETC_RBIER); @@ -1908,9 +2799,7 @@ static int enetc_setup_irqs(struct enetc_ndev_priv *priv) enetc_wr(hw, ENETC_SIMSITRV(idx), entry); } - cpumask_clear(&cpu_mask); - cpumask_set_cpu(i % num_online_cpus(), &cpu_mask); - irq_set_affinity_hint(irq, &cpu_mask); + irq_set_affinity_hint(irq, get_cpu_mask(i % num_online_cpus())); } return 0; @@ -1976,23 +2865,27 @@ static void enetc_setup_interrupts(struct enetc_ndev_priv *priv) static void enetc_clear_interrupts(struct enetc_ndev_priv *priv) { + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_txbdr_wr(&priv->si->hw, i, ENETC_TBIER, 0); + enetc_txbdr_wr(hw, i, ENETC_TBIER, 0); for (i = 0; i < priv->num_rx_rings; i++) - enetc_rxbdr_wr(&priv->si->hw, i, ENETC_RBIER, 0); + enetc_rxbdr_wr(hw, i, ENETC_RBIER, 0); } static int enetc_phylink_connect(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct ethtool_eee edata; + struct ethtool_keee edata; int err; - if (!priv->phylink) - return 0; /* phy-less mode */ + if (!priv->phylink) { + /* phy-less mode */ + netif_carrier_on(ndev); + return 0; + } err = phylink_of_phy_connect(priv->phylink, priv->dev->of_node, 0); if (err) { @@ -2001,9 +2894,11 @@ static int enetc_phylink_connect(struct net_device *ndev) } /* disable EEE autoneg, until ENETC driver supports it */ - memset(&edata, 0, sizeof(struct ethtool_eee)); + memset(&edata, 0, sizeof(struct ethtool_keee)); phylink_ethtool_set_eee(priv->phylink, &edata); + phylink_start(priv->phylink); + return 0; } @@ -2014,14 +2909,14 @@ static void enetc_tx_onestep_tstamp(struct work_struct *work) priv = container_of(work, struct enetc_ndev_priv, tx_onestep_tstamp); - netif_tx_lock(priv->ndev); + netif_tx_lock_bh(priv->ndev); clear_bit_unlock(ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS, &priv->flags); skb = skb_dequeue(&priv->tx_skbs); if (skb) enetc_start_xmit(skb, priv->ndev); - netif_tx_unlock(priv->ndev); + netif_tx_unlock_bh(priv->ndev); } static void enetc_tx_onestep_tstamp_init(struct enetc_ndev_priv *priv) @@ -2045,72 +2940,86 @@ void enetc_start(struct net_device *ndev) enable_irq(irq); } - if (priv->phylink) - phylink_start(priv->phylink); - else - netif_carrier_on(ndev); + enetc_enable_tx_bdrs(priv); + + enetc_enable_rx_bdrs(priv); netif_tx_start_all_queues(ndev); + + clear_bit(ENETC_TX_DOWN, &priv->flags); } +EXPORT_SYMBOL_GPL(enetc_start); int enetc_open(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - int num_stack_tx_queues; + struct enetc_bdr_resource *tx_res, *rx_res; + bool extended; int err; - err = enetc_setup_irqs(priv); + extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); + + err = clk_prepare_enable(priv->ref_clk); if (err) return err; + err = enetc_setup_irqs(priv); + if (err) + goto err_setup_irqs; + err = enetc_phylink_connect(ndev); if (err) goto err_phy_connect; - err = enetc_alloc_tx_resources(priv); - if (err) + tx_res = enetc_alloc_tx_resources(priv); + if (IS_ERR(tx_res)) { + err = PTR_ERR(tx_res); goto err_alloc_tx; + } - err = enetc_alloc_rx_resources(priv); - if (err) + rx_res = enetc_alloc_rx_resources(priv, extended); + if (IS_ERR(rx_res)) { + err = PTR_ERR(rx_res); goto err_alloc_rx; - - num_stack_tx_queues = enetc_num_stack_tx_queues(priv); - - err = netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(ndev, priv->num_rx_rings); - if (err) - goto err_set_queues; + } enetc_tx_onestep_tstamp_init(priv); - enetc_setup_bdrs(priv); + enetc_assign_tx_resources(priv, tx_res); + enetc_assign_rx_resources(priv, rx_res); + enetc_setup_bdrs(priv, extended); enetc_start(ndev); return 0; -err_set_queues: - enetc_free_rx_resources(priv); err_alloc_rx: - enetc_free_tx_resources(priv); + enetc_free_tx_resources(tx_res, priv->num_tx_rings); err_alloc_tx: if (priv->phylink) phylink_disconnect_phy(priv->phylink); err_phy_connect: enetc_free_irqs(priv); +err_setup_irqs: + clk_disable_unprepare(priv->ref_clk); return err; } +EXPORT_SYMBOL_GPL(enetc_open); void enetc_stop(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); int i; + set_bit(ENETC_TX_DOWN, &priv->flags); + netif_tx_stop_all_queues(ndev); + enetc_disable_rx_bdrs(priv); + + enetc_wait_bdrs(priv); + + enetc_disable_tx_bdrs(priv); + for (i = 0; i < priv->bdr_int_num; i++) { int irq = pci_irq_vector(priv->si->pdev, ENETC_BDR_INT_BASE_IDX + i); @@ -2120,120 +3029,210 @@ void enetc_stop(struct net_device *ndev) napi_disable(&priv->int_vector[i]->napi); } - if (priv->phylink) - phylink_stop(priv->phylink); - else - netif_carrier_off(ndev); - enetc_clear_interrupts(priv); } +EXPORT_SYMBOL_GPL(enetc_stop); int enetc_close(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); enetc_stop(ndev); - enetc_clear_bdrs(priv); - if (priv->phylink) + if (priv->phylink) { + phylink_stop(priv->phylink); phylink_disconnect_phy(priv->phylink); + } else { + netif_carrier_off(ndev); + } + enetc_free_rxtx_rings(priv); - enetc_free_rx_resources(priv); - enetc_free_tx_resources(priv); + + /* Avoids dangling pointers and also frees old resources */ + enetc_assign_rx_resources(priv, NULL); + enetc_assign_tx_resources(priv, NULL); + enetc_free_irqs(priv); + clk_disable_unprepare(priv->ref_clk); + + return 0; +} +EXPORT_SYMBOL_GPL(enetc_close); + +static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, + int (*cb)(struct enetc_ndev_priv *priv, void *ctx), + void *ctx) +{ + struct enetc_bdr_resource *tx_res, *rx_res; + int err; + + ASSERT_RTNL(); + + /* If the interface is down, run the callback right away, + * without reconfiguration. + */ + if (!netif_running(priv->ndev)) { + if (cb) { + err = cb(priv, ctx); + if (err) + return err; + } + + return 0; + } + + tx_res = enetc_alloc_tx_resources(priv); + if (IS_ERR(tx_res)) { + err = PTR_ERR(tx_res); + goto out; + } + + rx_res = enetc_alloc_rx_resources(priv, extended); + if (IS_ERR(rx_res)) { + err = PTR_ERR(rx_res); + goto out_free_tx_res; + } + + enetc_stop(priv->ndev); + enetc_free_rxtx_rings(priv); + + /* Interface is down, run optional callback now */ + if (cb) { + err = cb(priv, ctx); + if (err) + goto out_restart; + } + + enetc_assign_tx_resources(priv, tx_res); + enetc_assign_rx_resources(priv, rx_res); + enetc_setup_bdrs(priv, extended); + enetc_start(priv->ndev); return 0; + +out_restart: + enetc_setup_bdrs(priv, extended); + enetc_start(priv->ndev); + enetc_free_rx_resources(rx_res, priv->num_rx_rings); +out_free_tx_res: + enetc_free_tx_resources(tx_res, priv->num_tx_rings); +out: + return err; +} + +static void enetc_debug_tx_ring_prios(struct enetc_ndev_priv *priv) +{ + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + netdev_dbg(priv->ndev, "TX ring %d prio %d\n", i, + priv->tx_ring[i]->prio); } -static int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +void enetc_reset_tc_mqprio(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct tc_mqprio_qopt *mqprio = type_data; + struct enetc_hw *hw = &priv->si->hw; struct enetc_bdr *tx_ring; int num_stack_tx_queues; - u8 num_tc; int i; num_stack_tx_queues = enetc_num_stack_tx_queues(priv); - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - num_tc = mqprio->num_tc; - if (!num_tc) { - netdev_reset_tc(ndev); - netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + netdev_reset_tc(ndev); + netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + priv->min_num_stack_tx_queues = num_possible_cpus(); - /* Reset all ring priorities to 0 */ - for (i = 0; i < priv->num_tx_rings; i++) { - tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(&priv->si->hw, tx_ring->index, 0); - } + /* Reset all ring priorities to 0 */ + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } + + enetc_debug_tx_ring_prios(priv); + + enetc_change_preemptible_tcs(priv, 0); +} +EXPORT_SYMBOL_GPL(enetc_reset_tc_mqprio); + +int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +{ + struct tc_mqprio_qopt_offload *mqprio = type_data; + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct tc_mqprio_qopt *qopt = &mqprio->qopt; + struct enetc_hw *hw = &priv->si->hw; + int num_stack_tx_queues = 0; + struct enetc_bdr *tx_ring; + u8 num_tc = qopt->num_tc; + int offset, count; + int err, tc, q; + if (!num_tc) { + enetc_reset_tc_mqprio(ndev); return 0; } - /* Check if we have enough BD rings available to accommodate all TCs */ - if (num_tc > num_stack_tx_queues) { - netdev_err(ndev, "Max %d traffic classes supported\n", - priv->num_tx_rings); - return -EINVAL; - } + err = netdev_set_num_tc(ndev, num_tc); + if (err) + return err; - /* For the moment, we use only one BD ring per TC. - * - * Configure num_tc BD rings with increasing priorities. - */ - for (i = 0; i < num_tc; i++) { - tx_ring = priv->tx_ring[i]; - enetc_set_bdr_prio(&priv->si->hw, tx_ring->index, i); + for (tc = 0; tc < num_tc; tc++) { + offset = qopt->offset[tc]; + count = qopt->count[tc]; + num_stack_tx_queues += count; + + err = netdev_set_tc_queue(ndev, tc, count, offset); + if (err) + goto err_reset_tc; + + for (q = offset; q < offset + count; q++) { + tx_ring = priv->tx_ring[q]; + /* The prio_tc_map is skb_tx_hash()'s way of selecting + * between TX queues based on skb->priority. As such, + * there's nothing to offload based on it. + * Make the mqprio "traffic class" be the priority of + * this ring group, and leave the Tx IPV to traffic + * class mapping as its default mapping value of 1:1. + */ + tx_ring->prio = tc; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } } - /* Reset the number of netdev queues based on the TC count */ - netif_set_real_num_tx_queues(ndev, num_tc); + err = netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + if (err) + goto err_reset_tc; + + priv->min_num_stack_tx_queues = num_stack_tx_queues; - netdev_set_num_tc(ndev, num_tc); + enetc_debug_tx_ring_prios(priv); - /* Each TC is associated with one netdev queue */ - for (i = 0; i < num_tc; i++) - netdev_set_tc_queue(ndev, i, 1, i); + enetc_change_preemptible_tcs(priv, mqprio->preemptible_tcs); return 0; -} -int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type, - void *type_data) -{ - switch (type) { - case TC_SETUP_QDISC_MQPRIO: - return enetc_setup_tc_mqprio(ndev, type_data); - case TC_SETUP_QDISC_TAPRIO: - return enetc_setup_tc_taprio(ndev, type_data); - case TC_SETUP_QDISC_CBS: - return enetc_setup_tc_cbs(ndev, type_data); - case TC_SETUP_QDISC_ETF: - return enetc_setup_tc_txtime(ndev, type_data); - case TC_SETUP_BLOCK: - return enetc_setup_tc_psfp(ndev, type_data); - default: - return -EOPNOTSUPP; - } +err_reset_tc: + enetc_reset_tc_mqprio(ndev); + return err; } +EXPORT_SYMBOL_GPL(enetc_setup_tc_mqprio); -static int enetc_setup_xdp_prog(struct net_device *dev, struct bpf_prog *prog, - struct netlink_ext_ack *extack) +static int enetc_reconfigure_xdp_cb(struct enetc_ndev_priv *priv, void *ctx) { - struct enetc_ndev_priv *priv = netdev_priv(dev); - struct bpf_prog *old_prog; - bool is_up; - int i; - - /* The buffer layout is changing, so we need to drain the old - * RX buffers and seed new ones. - */ - is_up = netif_running(dev); - if (is_up) - dev_close(dev); + struct bpf_prog *old_prog, *prog = ctx; + int num_stack_tx_queues; + int err, i; old_prog = xchg(&priv->xdp_prog, prog); + + num_stack_tx_queues = enetc_num_stack_tx_queues(priv); + err = netif_set_real_num_tx_queues(priv->ndev, num_stack_tx_queues); + if (err) { + xchg(&priv->xdp_prog, old_prog); + return err; + } + if (old_prog) bpf_prog_put(old_prog); @@ -2248,29 +3247,53 @@ static int enetc_setup_xdp_prog(struct net_device *dev, struct bpf_prog *prog, rx_ring->buffer_offset = ENETC_RXB_PAD; } - if (is_up) - return dev_open(dev, extack); - return 0; } -int enetc_setup_bpf(struct net_device *dev, struct netdev_bpf *xdp) +static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog, + struct netlink_ext_ack *extack) { - switch (xdp->command) { + int num_xdp_tx_queues = prog ? num_possible_cpus() : 0; + struct enetc_ndev_priv *priv = netdev_priv(ndev); + bool extended; + + if (priv->min_num_stack_tx_queues + num_xdp_tx_queues > + priv->num_tx_rings) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Reserving %d XDP TXQs leaves under %d for stack (total %d)", + num_xdp_tx_queues, + priv->min_num_stack_tx_queues, + priv->num_tx_rings); + return -EBUSY; + } + + extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); + + /* The buffer layout is changing, so we need to drain the old + * RX buffers and seed new ones. + */ + return enetc_reconfigure(priv, extended, enetc_reconfigure_xdp_cb, prog); +} + +int enetc_setup_bpf(struct net_device *ndev, struct netdev_bpf *bpf) +{ + switch (bpf->command) { case XDP_SETUP_PROG: - return enetc_setup_xdp_prog(dev, xdp->prog, xdp->extack); + return enetc_setup_xdp_prog(ndev, bpf->prog, bpf->extack); default: return -EINVAL; } return 0; } +EXPORT_SYMBOL_GPL(enetc_setup_bpf); struct net_device_stats *enetc_get_stats(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; unsigned long packets = 0, bytes = 0; + unsigned long tx_dropped = 0; int i; for (i = 0; i < priv->num_rx_rings; i++) { @@ -2286,76 +3309,40 @@ struct net_device_stats *enetc_get_stats(struct net_device *ndev) for (i = 0; i < priv->num_tx_rings; i++) { packets += priv->tx_ring[i]->stats.packets; bytes += priv->tx_ring[i]->stats.bytes; + tx_dropped += priv->tx_ring[i]->stats.win_drop; } stats->tx_packets = packets; stats->tx_bytes = bytes; + stats->tx_dropped = tx_dropped; return stats; } - -static int enetc_set_rss(struct net_device *ndev, int en) -{ - struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct enetc_hw *hw = &priv->si->hw; - u32 reg; - - enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings); - - reg = enetc_rd(hw, ENETC_SIMR); - reg &= ~ENETC_SIMR_RSSE; - reg |= (en) ? ENETC_SIMR_RSSE : 0; - enetc_wr(hw, ENETC_SIMR, reg); - - return 0; -} - -static int enetc_set_psfp(struct net_device *ndev, int en) -{ - struct enetc_ndev_priv *priv = netdev_priv(ndev); - int err; - - if (en) { - err = enetc_psfp_enable(priv); - if (err) - return err; - - priv->active_offloads |= ENETC_F_QCI; - return 0; - } - - err = enetc_psfp_disable(priv); - if (err) - return err; - - priv->active_offloads &= ~ENETC_F_QCI; - - return 0; -} +EXPORT_SYMBOL_GPL(enetc_get_stats); static void enetc_enable_rxvlan(struct net_device *ndev, bool en) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_rx_rings; i++) - enetc_bdr_enable_rxvlan(&priv->si->hw, i, en); + enetc_bdr_enable_rxvlan(hw, i, en); } static void enetc_enable_txvlan(struct net_device *ndev, bool en) { struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; int i; for (i = 0; i < priv->num_tx_rings; i++) - enetc_bdr_enable_txvlan(&priv->si->hw, i, en); + enetc_bdr_enable_txvlan(hw, i, en); } -int enetc_set_features(struct net_device *ndev, - netdev_features_t features) +void enetc_set_features(struct net_device *ndev, netdev_features_t features) { netdev_features_t changed = ndev->features ^ features; - int err = 0; if (changed & NETIF_F_RXHASH) enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH)); @@ -2367,102 +3354,189 @@ int enetc_set_features(struct net_device *ndev, if (changed & NETIF_F_HW_VLAN_CTAG_TX) enetc_enable_txvlan(ndev, !!(features & NETIF_F_HW_VLAN_CTAG_TX)); - - if (changed & NETIF_F_HW_TC) - err = enetc_set_psfp(ndev, !!(features & NETIF_F_HW_TC)); - - return err; } +EXPORT_SYMBOL_GPL(enetc_set_features); -#ifdef CONFIG_FSL_ENETC_PTP_CLOCK -static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr) +int enetc_hwtstamp_set(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct hwtstamp_config config; - int ao; + int err, new_offloads = priv->active_offloads; - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; + if (!enetc_ptp_clock_is_enabled(priv->si)) + return -EOPNOTSUPP; - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: - priv->active_offloads &= ~ENETC_F_TX_TSTAMP_MASK; + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; break; case HWTSTAMP_TX_ON: - priv->active_offloads &= ~ENETC_F_TX_TSTAMP_MASK; - priv->active_offloads |= ENETC_F_TX_TSTAMP; + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; + new_offloads |= ENETC_F_TX_TSTAMP; break; case HWTSTAMP_TX_ONESTEP_SYNC: - priv->active_offloads &= ~ENETC_F_TX_TSTAMP_MASK; - priv->active_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP; + if (!enetc_si_is_pf(priv->si) || + enetc_is_pseudo_mac(priv->si)) + return -EOPNOTSUPP; + + new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; + new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP; break; default: return -ERANGE; } - ao = priv->active_offloads; - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - priv->active_offloads &= ~ENETC_F_RX_TSTAMP; + new_offloads &= ~ENETC_F_RX_TSTAMP; break; default: - priv->active_offloads |= ENETC_F_RX_TSTAMP; - config.rx_filter = HWTSTAMP_FILTER_ALL; + new_offloads |= ENETC_F_RX_TSTAMP; + config->rx_filter = HWTSTAMP_FILTER_ALL; } - if (netif_running(ndev) && ao != priv->active_offloads) { - enetc_close(ndev); - enetc_open(ndev); + if ((new_offloads ^ priv->active_offloads) & ENETC_F_RX_TSTAMP) { + bool extended = !!(new_offloads & ENETC_F_RX_TSTAMP); + + err = enetc_reconfigure(priv, extended, NULL, NULL); + if (err) + return err; } - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; + priv->active_offloads = new_offloads; + + return 0; } +EXPORT_SYMBOL_GPL(enetc_hwtstamp_set); -static int enetc_hwtstamp_get(struct net_device *ndev, struct ifreq *ifr) +int enetc_hwtstamp_get(struct net_device *ndev, + struct kernel_hwtstamp_config *config) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct hwtstamp_config config; - config.flags = 0; + if (!enetc_ptp_clock_is_enabled(priv->si)) + return -EOPNOTSUPP; if (priv->active_offloads & ENETC_F_TX_ONESTEP_SYNC_TSTAMP) - config.tx_type = HWTSTAMP_TX_ONESTEP_SYNC; + config->tx_type = HWTSTAMP_TX_ONESTEP_SYNC; else if (priv->active_offloads & ENETC_F_TX_TSTAMP) - config.tx_type = HWTSTAMP_TX_ON; + config->tx_type = HWTSTAMP_TX_ON; else - config.tx_type = HWTSTAMP_TX_OFF; + config->tx_type = HWTSTAMP_TX_OFF; - config.rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ? - HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; + config->rx_filter = (priv->active_offloads & ENETC_F_RX_TSTAMP) ? + HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; + return 0; } -#endif +EXPORT_SYMBOL_GPL(enetc_hwtstamp_get); int enetc_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd) { struct enetc_ndev_priv *priv = netdev_priv(ndev); -#ifdef CONFIG_FSL_ENETC_PTP_CLOCK - if (cmd == SIOCSHWTSTAMP) - return enetc_hwtstamp_set(ndev, rq); - if (cmd == SIOCGHWTSTAMP) - return enetc_hwtstamp_get(ndev, rq); -#endif if (!priv->phylink) return -EOPNOTSUPP; return phylink_mii_ioctl(priv->phylink, rq, cmd); } +EXPORT_SYMBOL_GPL(enetc_ioctl); + +static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i, + int v_tx_rings) +{ + struct enetc_int_vector *v; + struct enetc_bdr *bdr; + int j, err; + + v = kzalloc(struct_size(v, tx_ring, v_tx_rings), GFP_KERNEL); + if (!v) + return -ENOMEM; + + priv->int_vector[i] = v; + bdr = &v->rx_ring; + bdr->index = i; + bdr->ndev = priv->ndev; + bdr->dev = priv->dev; + bdr->bd_count = priv->rx_bd_count; + bdr->buffer_offset = ENETC_RXB_PAD; + priv->rx_ring[i] = bdr; + + err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0, + ENETC_RXB_DMA_SIZE_XDP); + if (err) + goto free_vector; + + err = xdp_rxq_info_reg_mem_model(&bdr->xdp.rxq, MEM_TYPE_PAGE_SHARED, + NULL); + if (err) { + xdp_rxq_info_unreg(&bdr->xdp.rxq); + goto free_vector; + } + + /* init defaults for adaptive IC */ + if (priv->ic_mode & ENETC_IC_RX_ADAPTIVE) { + v->rx_ictt = 0x1; + v->rx_dim_en = true; + } + + INIT_WORK(&v->rx_dim.work, enetc_rx_dim_work); + netif_napi_add(priv->ndev, &v->napi, enetc_poll); + v->count_tx_rings = v_tx_rings; + + for (j = 0; j < v_tx_rings; j++) { + int idx; + + /* default tx ring mapping policy */ + idx = priv->bdr_int_num * j + i; + __set_bit(idx, &v->tx_rings_map); + bdr = &v->tx_ring[j]; + bdr->index = idx; + bdr->ndev = priv->ndev; + bdr->dev = priv->dev; + bdr->bd_count = priv->tx_bd_count; + priv->tx_ring[idx] = bdr; + } + + return 0; + +free_vector: + priv->rx_ring[i] = NULL; + priv->int_vector[i] = NULL; + kfree(v); + + return err; +} + +static void enetc_int_vector_destroy(struct enetc_ndev_priv *priv, int i) +{ + struct enetc_int_vector *v = priv->int_vector[i]; + struct enetc_bdr *rx_ring = &v->rx_ring; + int j, tx_ring_index; + + xdp_rxq_info_unreg_mem_model(&rx_ring->xdp.rxq); + xdp_rxq_info_unreg(&rx_ring->xdp.rxq); + netif_napi_del(&v->napi); + cancel_work_sync(&v->rx_dim.work); + + for (j = 0; j < v->count_tx_rings; j++) { + tx_ring_index = priv->bdr_int_num * j + i; + priv->tx_ring[tx_ring_index] = NULL; + } + + priv->rx_ring[i] = NULL; + priv->int_vector[i] = NULL; + kfree(v); +} int enetc_alloc_msix(struct enetc_ndev_priv *priv) { struct pci_dev *pdev = priv->si->pdev; + int v_tx_rings, v_remainder; + int num_stack_tx_queues; int first_xdp_tx_ring; int i, n, err, nvec; - int v_tx_rings; nvec = ENETC_BDR_INT_BASE_IDX + priv->bdr_int_num; /* allocate MSIX for both messaging and Rx/Tx interrupts */ @@ -2476,117 +3550,56 @@ int enetc_alloc_msix(struct enetc_ndev_priv *priv) /* # of tx rings per int vector */ v_tx_rings = priv->num_tx_rings / priv->bdr_int_num; + v_remainder = priv->num_tx_rings % priv->bdr_int_num; for (i = 0; i < priv->bdr_int_num; i++) { - struct enetc_int_vector *v; - struct enetc_bdr *bdr; - int j; + /* Distribute the remaining TX rings to the first v_remainder + * interrupt vectors + */ + int num_tx_rings = i < v_remainder ? v_tx_rings + 1 : v_tx_rings; - v = kzalloc(struct_size(v, tx_ring, v_tx_rings), GFP_KERNEL); - if (!v) { - err = -ENOMEM; + err = enetc_int_vector_init(priv, i, num_tx_rings); + if (err) goto fail; - } - - priv->int_vector[i] = v; - - bdr = &v->rx_ring; - bdr->index = i; - bdr->ndev = priv->ndev; - bdr->dev = priv->dev; - bdr->bd_count = priv->rx_bd_count; - bdr->buffer_offset = ENETC_RXB_PAD; - priv->rx_ring[i] = bdr; + } - err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0); - if (err) { - kfree(v); - goto fail; - } + num_stack_tx_queues = enetc_num_stack_tx_queues(priv); - err = xdp_rxq_info_reg_mem_model(&bdr->xdp.rxq, - MEM_TYPE_PAGE_SHARED, NULL); - if (err) { - xdp_rxq_info_unreg(&bdr->xdp.rxq); - kfree(v); - goto fail; - } + err = netif_set_real_num_tx_queues(priv->ndev, num_stack_tx_queues); + if (err) + goto fail; - /* init defaults for adaptive IC */ - if (priv->ic_mode & ENETC_IC_RX_ADAPTIVE) { - v->rx_ictt = 0x1; - v->rx_dim_en = true; - } - INIT_WORK(&v->rx_dim.work, enetc_rx_dim_work); - netif_napi_add(priv->ndev, &v->napi, enetc_poll, - NAPI_POLL_WEIGHT); - v->count_tx_rings = v_tx_rings; - - for (j = 0; j < v_tx_rings; j++) { - int idx; - - /* default tx ring mapping policy */ - idx = priv->bdr_int_num * j + i; - __set_bit(idx, &v->tx_rings_map); - bdr = &v->tx_ring[j]; - bdr->index = idx; - bdr->ndev = priv->ndev; - bdr->dev = priv->dev; - bdr->bd_count = priv->tx_bd_count; - priv->tx_ring[idx] = bdr; - } - } + err = netif_set_real_num_rx_queues(priv->ndev, priv->num_rx_rings); + if (err) + goto fail; + priv->min_num_stack_tx_queues = num_possible_cpus(); first_xdp_tx_ring = priv->num_tx_rings - num_possible_cpus(); priv->xdp_tx_ring = &priv->tx_ring[first_xdp_tx_ring]; return 0; fail: - while (i--) { - struct enetc_int_vector *v = priv->int_vector[i]; - struct enetc_bdr *rx_ring = &v->rx_ring; - - xdp_rxq_info_unreg_mem_model(&rx_ring->xdp.rxq); - xdp_rxq_info_unreg(&rx_ring->xdp.rxq); - netif_napi_del(&v->napi); - cancel_work_sync(&v->rx_dim.work); - kfree(v); - } + while (i--) + enetc_int_vector_destroy(priv, i); pci_free_irq_vectors(pdev); return err; } +EXPORT_SYMBOL_GPL(enetc_alloc_msix); void enetc_free_msix(struct enetc_ndev_priv *priv) { int i; - for (i = 0; i < priv->bdr_int_num; i++) { - struct enetc_int_vector *v = priv->int_vector[i]; - struct enetc_bdr *rx_ring = &v->rx_ring; - - xdp_rxq_info_unreg_mem_model(&rx_ring->xdp.rxq); - xdp_rxq_info_unreg(&rx_ring->xdp.rxq); - netif_napi_del(&v->napi); - cancel_work_sync(&v->rx_dim.work); - } - - for (i = 0; i < priv->num_rx_rings; i++) - priv->rx_ring[i] = NULL; - - for (i = 0; i < priv->num_tx_rings; i++) - priv->tx_ring[i] = NULL; - - for (i = 0; i < priv->bdr_int_num; i++) { - kfree(priv->int_vector[i]); - priv->int_vector[i] = NULL; - } + for (i = 0; i < priv->bdr_int_num; i++) + enetc_int_vector_destroy(priv, i); /* disable all MSIX for this device */ pci_free_irq_vectors(priv->si->pdev); } +EXPORT_SYMBOL_GPL(enetc_free_msix); static void enetc_kfree_si(struct enetc_si *si) { @@ -2610,20 +3623,14 @@ int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv) pcie_flr(pdev); err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "device enable failed\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "device enable failed\n"); /* set up for high or low dma */ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, "DMA configuration failed: 0x%x\n", err); + goto err_dma; } err = pci_request_mem_regions(pdev, name); @@ -2682,6 +3689,7 @@ err_dma: return err; } +EXPORT_SYMBOL_GPL(enetc_pci_probe); void enetc_pci_remove(struct pci_dev *pdev) { @@ -2693,3 +3701,77 @@ void enetc_pci_remove(struct pci_dev *pdev) pci_release_mem_regions(pdev); pci_disable_device(pdev); } +EXPORT_SYMBOL_GPL(enetc_pci_remove); + +static const struct enetc_drvdata enetc_pf_data = { + .sysclk_freq = ENETC_CLK_400M, + .pmac_offset = ENETC_PMAC_OFFSET, + .max_frags = ENETC_MAX_SKB_FRAGS, + .eth_ops = &enetc_pf_ethtool_ops, +}; + +static const struct enetc_drvdata enetc4_pf_data = { + .sysclk_freq = ENETC_CLK_333M, + .tx_csum = true, + .max_frags = ENETC4_MAX_SKB_FRAGS, + .pmac_offset = ENETC4_PMAC_OFFSET, + .eth_ops = &enetc4_pf_ethtool_ops, +}; + +static const struct enetc_drvdata enetc4_ppm_data = { + .sysclk_freq = ENETC_CLK_333M, + .tx_csum = true, + .max_frags = ENETC4_MAX_SKB_FRAGS, + .eth_ops = &enetc4_ppm_ethtool_ops, +}; + +static const struct enetc_drvdata enetc_vf_data = { + .sysclk_freq = ENETC_CLK_400M, + .max_frags = ENETC_MAX_SKB_FRAGS, + .eth_ops = &enetc_vf_ethtool_ops, +}; + +static const struct enetc_platform_info enetc_info[] = { + { .revision = ENETC_REV_1_0, + .dev_id = ENETC_DEV_ID_PF, + .data = &enetc_pf_data, + }, + { .revision = ENETC_REV_4_1, + .dev_id = NXP_ENETC_PF_DEV_ID, + .data = &enetc4_pf_data, + }, + { .revision = ENETC_REV_1_0, + .dev_id = ENETC_DEV_ID_VF, + .data = &enetc_vf_data, + }, + { + .revision = ENETC_REV_4_3, + .dev_id = NXP_ENETC_PPM_DEV_ID, + .data = &enetc4_ppm_data, + }, + { .revision = ENETC_REV_4_3, + .dev_id = NXP_ENETC_PF_DEV_ID, + .data = &enetc4_pf_data, + }, +}; + +int enetc_get_driver_data(struct enetc_si *si) +{ + u16 dev_id = si->pdev->device; + int i; + + for (i = 0; i < ARRAY_SIZE(enetc_info); i++) { + if (si->revision == enetc_info[i].revision && + dev_id == enetc_info[i].dev_id) { + si->drvdata = enetc_info[i].data; + + return 0; + } + } + + return -ERANGE; +} +EXPORT_SYMBOL_GPL(enetc_get_driver_data); + +MODULE_DESCRIPTION("NXP ENETC Ethernet driver"); +MODULE_LICENSE("Dual BSD/GPL"); |