From c646d10dda2dcde82c6ce5a474522621ab2b8b19 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 1 Mar 2021 13:18:11 +0200 Subject: net: enetc: don't overwrite the RSS indirection table when initializing After the blamed patch, all RX traffic gets hashed to CPU 0 because the hashing indirection table set up in: enetc_pf_probe -> enetc_alloc_si_resources -> enetc_configure_si -> enetc_setup_default_rss_table is overwritten later in: enetc_pf_probe -> enetc_init_port_rss_memory which zero-initializes the entire port RSS table in order to avoid ECC errors. The trouble really is that enetc_init_port_rss_memory really neads enetc_alloc_si_resources to be called, because it depends upon enetc_alloc_cbdr and enetc_setup_cbdr. But that whole enetc_configure_si thing could have been better thought out, it has nothing to do in a function called "alloc_si_resources", especially since its counterpart, "free_si_resources", does nothing to unwind the configuration of the SI. The point is, we need to pull out enetc_configure_si out of enetc_alloc_resources, and move it after enetc_init_port_rss_memory. This allows us to set up the default RSS indirection table after initializing the memory. Fixes: 07bf34a50e32 ("net: enetc: initialize the RFS and RSS memories") Cc: Jesse Brandeburg Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index c78d12229730..fdb6b9e8da78 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1058,13 +1058,12 @@ static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups) return 0; } -static int enetc_configure_si(struct enetc_ndev_priv *priv) +int enetc_configure_si(struct enetc_ndev_priv *priv) { struct enetc_si *si = priv->si; struct enetc_hw *hw = &si->hw; int err; - enetc_setup_cbdr(hw, &si->cbd_ring); /* set SI cache attributes */ enetc_wr(hw, ENETC_SICAR0, ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT); @@ -1112,6 +1111,8 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv) if (err) return err; + enetc_setup_cbdr(&si->hw, &si->cbd_ring); + priv->cls_rules = kcalloc(si->num_fs_entries, sizeof(*priv->cls_rules), GFP_KERNEL); if (!priv->cls_rules) { @@ -1119,14 +1120,8 @@ int enetc_alloc_si_resources(struct enetc_ndev_priv *priv) goto err_alloc_cls; } - err = enetc_configure_si(priv); - if (err) - goto err_config_si; - return 0; -err_config_si: - kfree(priv->cls_rules); err_alloc_cls: enetc_clear_cbdr(&si->hw); enetc_free_cbdr(priv->dev, &si->cbd_ring); -- cgit v1.2.3 From 3222b5b613db558e9a494bbf53f3c984d90f71ea Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 1 Mar 2021 13:18:12 +0200 Subject: net: enetc: initialize RFS/RSS memories for unused ports too Michael reports that since linux-next-20210211, the AER messages for ECC errors have started reappearing, and this time they can be reliably reproduced with the first ping on one of his LS1028A boards. $ ping 1[ 33.258069] pcieport 0000:00:1f.0: AER: Multiple Corrected error received: 0000:00:00.0 72.16.0.1 PING [ 33.267050] pcieport 0000:00:1f.0: AER: can't find device of ID0000 172.16.0.1 (172.16.0.1): 56 data bytes 64 bytes from 172.16.0.1: seq=0 ttl=64 time=17.124 ms 64 bytes from 172.16.0.1: seq=1 ttl=64 time=0.273 ms $ devmem 0x1f8010e10 32 0xC0000006 It isn't clear why this is necessary, but it seems that for the errors to go away, we must clear the entire RFS and RSS memory, not just for the ports in use. Sadly the code is structured in such a way that we can't have unified logic for the used and unused ports. For the minimal initialization of an unused port, we need just to enable and ioremap the PF memory space, and a control buffer descriptor ring. Unused ports must then free the CBDR because the driver will exit, but used ports can not pick up from where that code path left, since the CBDR API does not reinitialize a ring when setting it up, so its producer and consumer indices are out of sync between the software and hardware state. So a separate enetc_init_unused_port function was created, and it gets called right after the PF memory space is enabled. Fixes: 07bf34a50e32 ("net: enetc: initialize the RFS and RSS memories") Reported-by: Michael Walle Cc: Jesse Brandeburg Signed-off-by: Vladimir Oltean Tested-by: Michael Walle Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 8 +++--- drivers/net/ethernet/freescale/enetc/enetc.h | 4 +++ drivers/net/ethernet/freescale/enetc/enetc_pf.c | 33 +++++++++++++++++++++---- 3 files changed, 36 insertions(+), 9 deletions(-) (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index fdb6b9e8da78..eb45830a1667 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -984,7 +984,7 @@ static void enetc_free_rxtx_rings(struct enetc_ndev_priv *priv) enetc_free_tx_ring(priv->tx_ring[i]); } -static int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr) +int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr) { int size = cbdr->bd_count * sizeof(struct enetc_cbd); @@ -1005,7 +1005,7 @@ static int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr) return 0; } -static void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr) +void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr) { int size = cbdr->bd_count * sizeof(struct enetc_cbd); @@ -1013,7 +1013,7 @@ static void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr) cbdr->bd_base = NULL; } -static void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr) +void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr) { /* set CBDR cache attributes */ enetc_wr(hw, ENETC_SICAR2, @@ -1033,7 +1033,7 @@ static void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr) cbdr->cir = hw->reg + ENETC_SICBDRCIR; } -static void enetc_clear_cbdr(struct enetc_hw *hw) +void enetc_clear_cbdr(struct enetc_hw *hw) { enetc_wr(hw, ENETC_SICBDRMR, 0); } diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index f8275cef3b5c..8b380fc13314 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -310,6 +310,10 @@ int enetc_setup_tc(struct net_device *ndev, enum tc_setup_type type, void enetc_set_ethtool_ops(struct net_device *ndev); /* control buffer descriptor ring (CBDR) */ +int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr); +void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr); +void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr); +void enetc_clear_cbdr(struct enetc_hw *hw); int enetc_set_mac_flt_entry(struct enetc_si *si, int index, char *mac_addr, int si_map); int enetc_clear_mac_flt_entry(struct enetc_si *si, int index); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index d02ecb2e46ae..62ba4bf56f0d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1041,6 +1041,26 @@ static int enetc_init_port_rss_memory(struct enetc_si *si) return err; } +static void enetc_init_unused_port(struct enetc_si *si) +{ + struct device *dev = &si->pdev->dev; + struct enetc_hw *hw = &si->hw; + int err; + + si->cbd_ring.bd_count = ENETC_CBDR_DEFAULT_SIZE; + err = enetc_alloc_cbdr(dev, &si->cbd_ring); + if (err) + return; + + enetc_setup_cbdr(hw, &si->cbd_ring); + + enetc_init_port_rfs_memory(si); + enetc_init_port_rss_memory(si); + + enetc_clear_cbdr(hw); + enetc_free_cbdr(dev, &si->cbd_ring); +} + static int enetc_pf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -1051,11 +1071,6 @@ static int enetc_pf_probe(struct pci_dev *pdev, struct enetc_pf *pf; int err; - if (node && !of_device_is_available(node)) { - dev_info(&pdev->dev, "device is disabled, skipping\n"); - return -ENODEV; - } - err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf)); if (err) { dev_err(&pdev->dev, "PCI probing failed\n"); @@ -1069,6 +1084,13 @@ static int enetc_pf_probe(struct pci_dev *pdev, goto err_map_pf_space; } + if (node && !of_device_is_available(node)) { + enetc_init_unused_port(si); + dev_info(&pdev->dev, "device is disabled, skipping\n"); + err = -ENODEV; + goto err_device_disabled; + } + pf = enetc_si_priv(si); pf->si = si; pf->total_vfs = pci_sriov_get_totalvfs(pdev); @@ -1151,6 +1173,7 @@ err_alloc_si_res: si->ndev = NULL; free_netdev(ndev); err_alloc_netdev: +err_device_disabled: err_map_pf_space: enetc_pci_remove(pdev); -- cgit v1.2.3 From 6d36ecdbc4410e61a0e02adc5d3abeee22a8ffd3 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 1 Mar 2021 13:18:13 +0200 Subject: net: enetc: take the MDIO lock only once per NAPI poll cycle The workaround for the ENETC MDIO erratum caused a performance degradation of 82 Kpps (seen with IP forwarding of two 1Gbps streams of 64B packets). This is due to excessive locking and unlocking in the fast path, which can be avoided. By taking the MDIO read-side lock only once per NAPI poll cycle, we are able to regain 54 Kpps (65%) of the performance hit. The rest of the performance degradation comes from the TX data path, but unfortunately it doesn't look like we can optimize that away easily, even with netdev_xmit_more(), there just isn't any skb batching done, to help with taking the MDIO lock less often than once per packet. We need to change the register accessor type for enetc_get_tx_tstamp, because it now runs under the enetc_lock_mdio as per the new call path detailed below: enetc_msix -> napi_schedule -> enetc_poll -> enetc_lock_mdio -> enetc_clean_tx_ring -> enetc_get_tx_tstamp -> enetc_clean_rx_ring -> enetc_unlock_mdio Fixes: fd5736bf9f23 ("enetc: Workaround for MDIO register access issue") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 31 +++++++------------------ drivers/net/ethernet/freescale/enetc/enetc_hw.h | 2 ++ 2 files changed, 11 insertions(+), 22 deletions(-) (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index eb45830a1667..9bcceb74fb9c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -281,6 +281,8 @@ static int enetc_poll(struct napi_struct *napi, int budget) int work_done; int i; + enetc_lock_mdio(); + for (i = 0; i < v->count_tx_rings; i++) if (!enetc_clean_tx_ring(&v->tx_ring[i], budget)) complete = false; @@ -291,8 +293,10 @@ static int enetc_poll(struct napi_struct *napi, int budget) if (work_done) v->rx_napi_work = true; - if (!complete) + if (!complete) { + enetc_unlock_mdio(); return budget; + } napi_complete_done(napi, work_done); @@ -301,8 +305,6 @@ 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); @@ -327,8 +329,8 @@ static void enetc_get_tx_tstamp(struct enetc_hw *hw, union enetc_tx_bd *txbd, { u32 lo, hi, tstamp_lo; - lo = enetc_rd(hw, ENETC_SICTR0); - hi = enetc_rd(hw, ENETC_SICTR1); + lo = enetc_rd_hot(hw, ENETC_SICTR0); + hi = enetc_rd_hot(hw, ENETC_SICTR1); tstamp_lo = le32_to_cpu(txbd->wb.tstamp); if (lo <= tstamp_lo) hi -= 1; @@ -358,9 +360,7 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) i = tx_ring->next_to_clean; tx_swbd = &tx_ring->tx_swbd[i]; - enetc_lock_mdio(); bds_to_clean = enetc_bd_ready_count(tx_ring, i); - enetc_unlock_mdio(); do_tstamp = false; @@ -403,8 +403,6 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) tx_swbd = tx_ring->tx_swbd; } - enetc_lock_mdio(); - /* BD iteration loop end */ if (is_eof) { tx_frm_cnt++; @@ -415,8 +413,6 @@ static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget) if (unlikely(!bds_to_clean)) bds_to_clean = enetc_bd_ready_count(tx_ring, i); - - enetc_unlock_mdio(); } tx_ring->next_to_clean = i; @@ -660,8 +656,6 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, u32 bd_status; u16 size; - enetc_lock_mdio(); - if (cleaned_cnt >= ENETC_RXBD_BUNDLE) { int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt); @@ -672,19 +666,15 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, rxbd = enetc_rxbd(rx_ring, i); bd_status = le32_to_cpu(rxbd->r.lstatus); - if (!bd_status) { - enetc_unlock_mdio(); + if (!bd_status) break; - } enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index)); dma_rmb(); /* for reading other rxbd fields */ size = le16_to_cpu(rxbd->r.buf_len); skb = enetc_map_rx_buff_to_skb(rx_ring, i, size); - if (!skb) { - enetc_unlock_mdio(); + if (!skb) break; - } enetc_get_offloads(rx_ring, rxbd, skb); @@ -696,7 +686,6 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, if (unlikely(bd_status & ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) { - enetc_unlock_mdio(); dev_kfree_skb(skb); while (!(bd_status & ENETC_RXBD_LSTATUS_F)) { dma_rmb(); @@ -736,8 +725,6 @@ static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring, enetc_process_skb(rx_ring, skb); - enetc_unlock_mdio(); - napi_gro_receive(napi, skb); rx_frm_cnt++; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index c71fe8d751d5..8b54562f5da6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -453,6 +453,8 @@ static inline u64 _enetc_rd_reg64_wa(void __iomem *reg) #define enetc_wr_reg(reg, val) _enetc_wr_reg_wa((reg), (val)) #define enetc_rd(hw, off) enetc_rd_reg((hw)->reg + (off)) #define enetc_wr(hw, off, val) enetc_wr_reg((hw)->reg + (off), val) +#define enetc_rd_hot(hw, off) enetc_rd_reg_hot((hw)->reg + (off)) +#define enetc_wr_hot(hw, off, val) enetc_wr_reg_hot((hw)->reg + (off), val) #define enetc_rd64(hw, off) _enetc_rd_reg64_wa((hw)->reg + (off)) /* port register accessors - PF only */ #define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off)) -- cgit v1.2.3 From 827b6fd046516af605e190c872949f22208b5d41 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 1 Mar 2021 13:18:14 +0200 Subject: net: enetc: fix incorrect TPID when receiving 802.1ad tagged packets When the enetc ports have rx-vlan-offload enabled, they report a TPID of ETH_P_8021Q regardless of what was actually in the packet. When rx-vlan-offload is disabled, packets have the proper TPID. Fix this inconsistency by finishing the TODO left in the code. Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 34 +++++++++++++++++++------ drivers/net/ethernet/freescale/enetc/enetc_hw.h | 3 +++ 2 files changed, 29 insertions(+), 8 deletions(-) (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 9bcceb74fb9c..8ddf0cdc37a5 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -523,9 +523,8 @@ static void enetc_get_rx_tstamp(struct net_device *ndev, static void enetc_get_offloads(struct enetc_bdr *rx_ring, union enetc_rx_bd *rxbd, struct sk_buff *skb) { -#ifdef CONFIG_FSL_ENETC_PTP_CLOCK struct enetc_ndev_priv *priv = netdev_priv(rx_ring->ndev); -#endif + /* TODO: hashing */ if (rx_ring->ndev->features & NETIF_F_RXCSUM) { u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum); @@ -534,12 +533,31 @@ static void enetc_get_offloads(struct enetc_bdr *rx_ring, skb->ip_summed = CHECKSUM_COMPLETE; } - /* copy VLAN to skb, if one is extracted, for now we assume it's a - * standard TPID, but HW also supports custom values - */ - if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), - le16_to_cpu(rxbd->r.vlan_opt)); + if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) { + __be16 tpid = 0; + + switch (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TPID) { + case 0: + tpid = htons(ETH_P_8021Q); + break; + case 1: + tpid = htons(ETH_P_8021AD); + break; + case 2: + tpid = htons(enetc_port_rd(&priv->si->hw, + ENETC_PCVLANR1)); + break; + case 3: + tpid = htons(enetc_port_rd(&priv->si->hw, + ENETC_PCVLANR2)); + break; + default: + break; + } + + __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); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 8b54562f5da6..a62604a1e54e 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -172,6 +172,8 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PSIPMAR0(n) (0x0100 + (n) * 0x8) /* n = SI index */ #define ENETC_PSIPMAR1(n) (0x0104 + (n) * 0x8) #define ENETC_PVCLCTR 0x0208 +#define ENETC_PCVLANR1 0x0210 +#define ENETC_PCVLANR2 0x0214 #define ENETC_VLAN_TYPE_C BIT(0) #define ENETC_VLAN_TYPE_S BIT(1) #define ENETC_PVCLCTR_OVTPIDL(bmp) ((bmp) & 0xff) /* VLAN_TYPE */ @@ -570,6 +572,7 @@ union enetc_rx_bd { #define ENETC_RXBD_LSTATUS(flags) ((flags) << 16) #define ENETC_RXBD_FLAG_VLAN BIT(9) #define ENETC_RXBD_FLAG_TSTMP BIT(10) +#define ENETC_RXBD_FLAG_TPID GENMASK(1, 0) #define ENETC_MAC_ADDR_FILT_CNT 8 /* # of supported entries per port */ #define EMETC_MAC_ADDR_FILT_RES 3 /* # of reserved entries at the beginning */ -- cgit v1.2.3 From 96a5223b918c8b79270fc0fec235a7ebad459098 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 1 Mar 2021 13:18:17 +0200 Subject: net: enetc: remove bogus write to SIRXIDR from enetc_setup_rxbdr The Station Interface Receive Interrupt Detect Register (SIRXIDR) contains a 16-bit wide mask of 'interrupt detected' events for each ring associated with a port. Bit i is write-1-to-clean for RX ring i. I have no explanation whatsoever how this line of code came to be inserted in the blamed commit. I checked the downstream versions of that patch and none of them have it. The somewhat comical aspect of it is that we're writing a binary number to the SIRXIDR register, which is derived from enetc_bd_unused(rx_ring). Since the RX rings have 512 buffer descriptors, we end up writing 511 to this register, which is 0x1ff, so we are effectively clearing the 'interrupt detected' event for rings 0-8. This register is not what is used for interrupt handling though - it only provides a summary for the entire SI. The hardware provides one separate Interrupt Detect Register per RX ring, which auto-clears upon read. So there doesn't seem to be any adverse effect caused by this bogus write. There is, however, one reason why this should be handled as a bugfix: next_to_clean _should_ be committed to hardware, just not to that register, and this was obscuring the fact that it wasn't. This is fixed in the next patch, and removing the bogus line now allows the fix patch to be backported beyond that point. Fixes: fd5736bf9f23 ("enetc: Workaround for MDIO register access issue") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 1 - 1 file changed, 1 deletion(-) (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 8ddf0cdc37a5..abb29ee81463 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1212,7 +1212,6 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) rx_ring->idr = hw->reg + ENETC_SIRXIDR; enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring)); - enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use); /* enable ring */ enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); -- cgit v1.2.3 From 3a5d12c9be6f30080600c8bacaf310194e37d029 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 1 Mar 2021 13:18:18 +0200 Subject: net: enetc: keep RX ring consumer index in sync with hardware The RX rings have a producer index owned by hardware, where newly received frame buffers are placed, and a consumer index owned by software, where newly allocated buffers are placed, in expectation of hardware being able to place frame data in them. Hardware increments the producer index when a frame is received, however it is not allowed to increment the producer index to match the consumer index (RBCIR) since the ring can hold at most RBLENR[LENGTH]-1 received BDs. Whenever the producer index matches the value of the consumer index, the ring has no unprocessed received frames and all BDs in the ring have been initialized/prepared by software, i.e. hardware owns all BDs in the ring. The code uses the next_to_clean variable to keep track of the producer index, and the next_to_use variable to keep track of the consumer index. The RX rings are seeded from enetc_refill_rx_ring, which is called from two places: 1. initially the ring is seeded until full with enetc_bd_unused(rx_ring), i.e. with 511 buffers. This will make next_to_clean=0 and next_to_use=511: .ndo_open -> enetc_open -> enetc_setup_bdrs -> enetc_setup_rxbdr -> enetc_refill_rx_ring 2. then during the data path processing, it is refilled with 16 buffers at a time: enetc_msix -> napi_schedule -> enetc_poll -> enetc_clean_rx_ring -> enetc_refill_rx_ring There is just one problem: the initial seeding done during .ndo_open updates just the producer index (ENETC_RBPIR) with 0, and the software next_to_clean and next_to_use variables. Notably, it will not update the consumer index to make the hardware aware of the newly added buffers. Wait, what? So how does it work? Well, the reset values of the producer index and of the consumer index of a ring are both zero. As per the description in the second paragraph, it means that the ring is full of buffers waiting for hardware to put frames in them, which by coincidence is almost true, because we have in fact seeded 511 buffers into the ring. But will the hardware attempt to access the 512th entry of the ring, which has an invalid BD in it? Well, no, because in order to do that, it would have to first populate the first 511 entries, and the NAPI enetc_poll will kick in by then. Eventually, after 16 processed slots have become available in the RX ring, enetc_clean_rx_ring will call enetc_refill_rx_ring and then will [ finally ] update the consumer index with the new software next_to_use variable. From now on, the next_to_clean and next_to_use variables are in sync with the producer and consumer ring indices. So the day is saved, right? Well, not quite. Freeing the memory allocated for the rings is done in: enetc_close -> enetc_clear_bdrs -> enetc_clear_rxbdr -> this just disables the ring -> enetc_free_rxtx_rings -> enetc_free_rx_ring -> sets next_to_clean and next_to_use to 0 but again, nothing is committed to the hardware producer and consumer indices (yay!). The assumption is that the ring is disabled, so the indices don't matter anyway, and it's the responsibility of the "open" code path to set those up. .. Except that the "open" code path does not set those up properly. While initially, things almost work, during subsequent enetc_close -> enetc_open sequences, we have problems. To be precise, the enetc_open that is subsequent to enetc_close will again refill the ring with 511 entries, but it will leave the consumer index untouched. Untouched means, of course, equal to the value it had before disabling the ring and draining the old buffers in enetc_close. But as mentioned, enetc_setup_rxbdr will at least update the producer index though, through this line of code: enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0); so at this stage we'll have: next_to_clean=0 (in hardware 0) next_to_use=511 (in hardware we'll have the refill index prior to enetc_close) Again, the next_to_clean and producer index are in sync and set to correct values, so the driver manages to limp on. Eventually, 16 ring entries will be consumed by enetc_poll, and the savior enetc_clean_rx_ring will come and call enetc_refill_rx_ring, and then update the hardware consumer ring based upon the new next_to_use. So.. it works? Well, by coincidence, it almost does, but there's a circumstance where enetc_clean_rx_ring won't be there to save us. If the previous value of the consumer index was 15, there's a problem, because the NAPI poll sequence will only issue a refill when 16 or more buffers have been consumed. It's easiest to illustrate this with an example: ip link set eno0 up ip addr add 192.168.100.1/24 dev eno0 ping 192.168.100.1 -c 20 # ping this port from another board ip link set eno0 down ip link set eno0 up ping 192.168.100.1 -c 20 # ping it again from the same other board One by one: 1. ip link set eno0 up -> calls enetc_setup_rxbdr: -> calls enetc_refill_rx_ring(511 buffers) -> next_to_clean=0 (in hw 0) -> next_to_use=511 (in hw 0) 2. ping 192.168.100.1 -c 20 # ping this port from another board enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=1 next_to_clean 0 (in hw 1) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=2 next_to_clean 1 (in hw 2) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=3 next_to_clean 2 (in hw 3) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=4 next_to_clean 3 (in hw 4) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=5 next_to_clean 4 (in hw 5) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=6 next_to_clean 5 (in hw 6) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=7 next_to_clean 6 (in hw 7) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=8 next_to_clean 7 (in hw 8) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=9 next_to_clean 8 (in hw 9) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=10 next_to_clean 9 (in hw 10) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=11 next_to_clean 10 (in hw 11) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=12 next_to_clean 11 (in hw 12) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=13 next_to_clean 12 (in hw 13) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=14 next_to_clean 13 (in hw 14) next_to_use 511 (in hw 0) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=15 next_to_clean 14 (in hw 15) next_to_use 511 (in hw 0) enetc_clean_rx_ring: enetc_refill_rx_ring(16) increments next_to_use by 16 (mod 512) and writes it to hw enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=0 next_to_clean 15 (in hw 16) next_to_use 15 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=1 next_to_clean 16 (in hw 17) next_to_use 15 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=2 next_to_clean 17 (in hw 18) next_to_use 15 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=3 next_to_clean 18 (in hw 19) next_to_use 15 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=4 next_to_clean 19 (in hw 20) next_to_use 15 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=5 next_to_clean 20 (in hw 21) next_to_use 15 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=6 next_to_clean 21 (in hw 22) next_to_use 15 (in hw 15) 20 packets transmitted, 20 packets received, 0% packet loss 3. ip link set eno0 down enetc_free_rx_ring: next_to_clean 0 (in hw 22), next_to_use 0 (in hw 15) 4. ip link set eno0 up -> calls enetc_setup_rxbdr: -> calls enetc_refill_rx_ring(511 buffers) -> next_to_clean=0 (in hw 0) -> next_to_use=511 (in hw 15) 5. ping 192.168.100.1 -c 20 # ping it again from the same other board enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=1 next_to_clean 0 (in hw 1) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=2 next_to_clean 1 (in hw 2) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=3 next_to_clean 2 (in hw 3) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=4 next_to_clean 3 (in hw 4) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=5 next_to_clean 4 (in hw 5) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=6 next_to_clean 5 (in hw 6) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=7 next_to_clean 6 (in hw 7) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=8 next_to_clean 7 (in hw 8) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=9 next_to_clean 8 (in hw 9) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=10 next_to_clean 9 (in hw 10) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=11 next_to_clean 10 (in hw 11) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=12 next_to_clean 11 (in hw 12) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=13 next_to_clean 12 (in hw 13) next_to_use 511 (in hw 15) enetc_clean_rx_ring: rx_frm_cnt=1 cleaned_cnt=14 next_to_clean 13 (in hw 14) next_to_use 511 (in hw 15) 20 packets transmitted, 12 packets received, 40% packet loss And there it dies. No enetc_refill_rx_ring (because cleaned_cnt must be equal to 15 for that to happen), no nothing. The hardware enters the condition where the producer (14) + 1 is equal to the consumer (15) index, which makes it believe it has no more free buffers to put packets in, so it starts discarding them: ip netns exec ns0 ethtool -S eno0 | grep -v ': 0' NIC statistics: Rx ring 0 discarded frames: 8 Summarized, if the interface receives between 16 and 32 (mod 512) frames and then there is a link flap, then the port will eventually die with no way to recover. If it receives less than 16 (mod 512) frames, then the initial NAPI poll [ before the link flap ] will not update the consumer index in hardware (it will remain zero) which will be ok when the buffers are later reinitialized. If more than 32 (mod 512) frames are received, the initial NAPI poll has the chance to refill the ring twice, updating the consumer index to at least 32. So after the link flap, the consumer index is still wrong, but the post-flap NAPI poll gets a chance to refill the ring once (because it passes through cleaned_cnt=15) and makes the consumer index be again back in sync with next_to_use. The solution to this problem is actually simple, we just need to write next_to_use into the hardware consumer index at enetc_open time, which always brings it back in sync after an initial buffer seeding process. The simpler thing would be to put the write to the consumer index into enetc_refill_rx_ring directly, but there are issues with the MDIO locking: in the NAPI poll code we have the enetc_lock_mdio() taken from top-level and we use the unlocked enetc_wr_reg_hot, whereas in enetc_open, the enetc_lock_mdio() is not taken at the top level, but instead by each individual enetc_wr_reg, so we are forced to put an additional enetc_wr_reg in enetc_setup_rxbdr. Better organization of the code is left as a refactoring exercise. Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index abb29ee81463..30d7d4e83900 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1212,6 +1212,8 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring) rx_ring->idr = hw->reg + ENETC_SIRXIDR; enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring)); + /* update ENETC's consumer index */ + enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, rx_ring->next_to_use); /* enable ring */ enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr); -- cgit v1.2.3 From 29d98f54a4fe1b6a9089bec8715a1b89ff9ad59c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Sun, 7 Mar 2021 15:23:39 +0200 Subject: net: enetc: allow hardware timestamping on TX queues with tc-etf enabled The txtime is passed to the driver in skb->skb_mstamp_ns, which is actually in a union with skb->tstamp (the place where software timestamps are kept). Since commit b50a5c70ffa4 ("net: allow simultaneous SW and HW transmit timestamping"), __sock_recv_timestamp has some logic for making sure that the two calls to skb_tstamp_tx: skb_tx_timestamp(skb) # Software timestamp in the driver -> skb_tstamp_tx(skb, NULL) and skb_tstamp_tx(skb, &shhwtstamps) # Hardware timestamp in the driver will both do the right thing and in a race-free manner, meaning that skb_tx_timestamp will deliver a cmsg with the software timestamp only, and skb_tstamp_tx with a non-NULL hwtstamps argument will deliver a cmsg with the hardware timestamp only. Why are races even possible? Well, because although the software timestamp skb->tstamp is private per skb, the hardware timestamp skb_hwtstamps(skb) lives in skb_shinfo(skb), an area which is shared between skbs and their clones. And skb_tstamp_tx works by cloning the packets when timestamping them, therefore attempting to perform hardware timestamping on an skb's clone will also change the hardware timestamp of the original skb. And the original skb might have been yet again cloned for software timestamping, at an earlier stage. So the logic in __sock_recv_timestamp can't be as simple as saying "does this skb have a hardware timestamp? if yes I'll send the hardware timestamp to the socket, otherwise I'll send the software timestamp", precisely because the hardware timestamp is shared. Instead, it's quite the other way around: __sock_recv_timestamp says "does this skb have a software timestamp? if yes, I'll send the software timestamp, otherwise the hardware one". This works because the software timestamp is not shared with clones. But that means we have a problem when we attempt hardware timestamping with skbs that don't have the skb->tstamp == 0. __sock_recv_timestamp will say "oh, yeah, this must be some sort of odd clone" and will not deliver the hardware timestamp to the socket. And this is exactly what is happening when we have txtime enabled on the socket: as mentioned, that is put in a union with skb->tstamp, so it is quite easy to mistake it. Do what other drivers do (intel igb/igc) and write zero to skb->tstamp before taking the hardware timestamp. It's of no use to us now (we're already on the TX confirmation path). Fixes: 0d08c9ec7d6e ("enetc: add support time specific departure base on the qos etf") Cc: Vinicius Costa Gomes Signed-off-by: Vladimir Oltean Acked-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- drivers/net/ethernet/freescale/enetc/enetc.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/net/ethernet/freescale/enetc/enetc.c') diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 30d7d4e83900..09471329f3a3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -344,6 +344,12 @@ static void enetc_tstamp_tx(struct sk_buff *skb, u64 tstamp) if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) { memset(&shhwtstamps, 0, sizeof(shhwtstamps)); shhwtstamps.hwtstamp = ns_to_ktime(tstamp); + /* Ensure skb_mstamp_ns, which might have been populated with + * the txtime, is not mistaken for a software timestamp, + * because this will prevent the dispatch of our hardware + * timestamp to the socket. + */ + skb->tstamp = ktime_set(0, 0); skb_tstamp_tx(skb, &shhwtstamps); } } -- cgit v1.2.3