From 6f461f6c7c961f0b1b73c0f27becf472a0ac606b Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Tue, 27 Apr 2010 03:33:04 +0000 Subject: e1000e: enable/disable ASPM L0s and L1 and ERT according to hardware errata Prompted by a previous patch submitted by Matthew Garret , further digging into errata documentation reveals the current enabling or disabling of ASPM L0s and L1 states for certain parts supported by this driver are incorrect. 82571 and 82572 should always disable L1. For standard frames, 82573/82574/82583 can enable L1 but L0s must be disabled, and for jumbo frames 82573/82574 must disable L1. This allows for some parts to enable L1 in certain configurations leading to better power savings. Also according to the same errata, Early Receive (ERT) should be disabled on 82573 when using jumbo frames. Cc: Matthew Garret Signed-off-by: Bruce Allan Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 70 +++++++++++++++++++++++++++------------------ 1 file changed, 42 insertions(+), 28 deletions(-) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 73d43c53015a..fb8fc7d1b50d 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -4283,6 +4283,14 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu) return -EINVAL; } + /* 82573 Errata 17 */ + if (((adapter->hw.mac.type == e1000_82573) || + (adapter->hw.mac.type == e1000_82574)) && + (max_frame > ETH_FRAME_LEN + ETH_FCS_LEN)) { + adapter->flags2 |= FLAG2_DISABLE_ASPM_L1; + e1000e_disable_aspm(adapter->pdev, PCIE_LINK_STATE_L1); + } + while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) msleep(1); /* e1000e_down -> e1000e_reset dependent on max_frame_size & mtu */ @@ -4605,29 +4613,39 @@ static void e1000_complete_shutdown(struct pci_dev *pdev, bool sleep, } } -static void e1000e_disable_l1aspm(struct pci_dev *pdev) +#ifdef CONFIG_PCIEASPM +static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) +{ + pci_disable_link_state(pdev, state); +} +#else +static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) { int pos; - u16 val; + u16 reg16; /* - * 82573 workaround - disable L1 ASPM on mobile chipsets - * - * L1 ASPM on various mobile (ich7) chipsets do not behave properly - * resulting in lost data or garbage information on the pci-e link - * level. This could result in (false) bad EEPROM checksum errors, - * long ping times (up to 2s) or even a system freeze/hang. - * - * Unfortunately this feature saves about 1W power consumption when - * active. + * Both device and parent should have the same ASPM setting. + * Disable ASPM in downstream component first and then upstream. */ - pos = pci_find_capability(pdev, PCI_CAP_ID_EXP); - pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, &val); - if (val & 0x2) { - dev_warn(&pdev->dev, "Disabling L1 ASPM\n"); - val &= ~0x2; - pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, val); - } + pos = pci_pcie_cap(pdev); + pci_read_config_word(pdev, pos + PCI_EXP_LNKCTL, ®16); + reg16 &= ~state; + pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16); + + pos = pci_pcie_cap(pdev->bus->self); + pci_read_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, ®16); + reg16 &= ~state; + pci_write_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, reg16); +} +#endif +void e1000e_disable_aspm(struct pci_dev *pdev, u16 state) +{ + dev_info(&pdev->dev, "Disabling ASPM %s %s\n", + (state & PCIE_LINK_STATE_L0S) ? "L0s" : "", + (state & PCIE_LINK_STATE_L1) ? "L1" : ""); + + __e1000e_disable_aspm(pdev, state); } #ifdef CONFIG_PM @@ -4653,7 +4671,8 @@ static int e1000_resume(struct pci_dev *pdev) pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); pci_save_state(pdev); - e1000e_disable_l1aspm(pdev); + if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1) + e1000e_disable_aspm(pdev, PCIE_LINK_STATE_L1); err = pci_enable_device_mem(pdev); if (err) { @@ -4795,7 +4814,8 @@ static pci_ers_result_t e1000_io_slot_reset(struct pci_dev *pdev) int err; pci_ers_result_t result; - e1000e_disable_l1aspm(pdev); + if (adapter->flags2 & FLAG2_DISABLE_ASPM_L1) + e1000e_disable_aspm(pdev, PCIE_LINK_STATE_L1); err = pci_enable_device_mem(pdev); if (err) { dev_err(&pdev->dev, @@ -4889,13 +4909,6 @@ static void e1000_eeprom_checks(struct e1000_adapter *adapter) dev_warn(&adapter->pdev->dev, "Warning: detected DSPD enabled in EEPROM\n"); } - - ret_val = e1000_read_nvm(hw, NVM_INIT_3GIO_3, 1, &buf); - if (!ret_val && (le16_to_cpu(buf) & (3 << 2))) { - /* ASPM enable */ - dev_warn(&adapter->pdev->dev, - "Warning: detected ASPM enabled in EEPROM\n"); - } } static const struct net_device_ops e1000e_netdev_ops = { @@ -4944,7 +4957,8 @@ static int __devinit e1000_probe(struct pci_dev *pdev, u16 eeprom_data = 0; u16 eeprom_apme_mask = E1000_EEPROM_APME; - e1000e_disable_l1aspm(pdev); + if (ei->flags2 & FLAG2_DISABLE_ASPM_L1) + e1000e_disable_aspm(pdev, PCIE_LINK_STATE_L1); err = pci_enable_device_mem(pdev); if (err) -- cgit v1.2.2 From 0be3f55f8aa5f9d1882255128bd79d4885b0cbe4 Mon Sep 17 00:00:00 2001 From: Nick Nunley Date: Tue, 27 Apr 2010 13:09:05 +0000 Subject: e1000e: use DMA API instead of PCI DMA functions Signed-off-by: Nicholas Nunley Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 99 +++++++++++++++++++++++---------------------- 1 file changed, 50 insertions(+), 49 deletions(-) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 2476f8c24c54..3a712157b6a1 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -181,10 +181,10 @@ static void e1000_alloc_rx_buffers(struct e1000_adapter *adapter, buffer_info->skb = skb; map_skb: - buffer_info->dma = pci_map_single(pdev, skb->data, + buffer_info->dma = dma_map_single(&pdev->dev, skb->data, adapter->rx_buffer_len, - PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(pdev, buffer_info->dma)) { + DMA_FROM_DEVICE); + if (dma_mapping_error(&pdev->dev, buffer_info->dma)) { dev_err(&pdev->dev, "RX DMA map failed\n"); adapter->rx_dma_failed++; break; @@ -250,11 +250,12 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, adapter->alloc_rx_buff_failed++; goto no_buffers; } - ps_page->dma = pci_map_page(pdev, - ps_page->page, - 0, PAGE_SIZE, - PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(pdev, ps_page->dma)) { + ps_page->dma = dma_map_page(&pdev->dev, + ps_page->page, + 0, PAGE_SIZE, + DMA_FROM_DEVICE); + if (dma_mapping_error(&pdev->dev, + ps_page->dma)) { dev_err(&adapter->pdev->dev, "RX DMA page map failed\n"); adapter->rx_dma_failed++; @@ -279,10 +280,10 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, } buffer_info->skb = skb; - buffer_info->dma = pci_map_single(pdev, skb->data, + buffer_info->dma = dma_map_single(&pdev->dev, skb->data, adapter->rx_ps_bsize0, - PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(pdev, buffer_info->dma)) { + DMA_FROM_DEVICE); + if (dma_mapping_error(&pdev->dev, buffer_info->dma)) { dev_err(&pdev->dev, "RX DMA map failed\n"); adapter->rx_dma_failed++; /* cleanup skb */ @@ -369,10 +370,10 @@ check_page: } if (!buffer_info->dma) - buffer_info->dma = pci_map_page(pdev, + buffer_info->dma = dma_map_page(&pdev->dev, buffer_info->page, 0, PAGE_SIZE, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); rx_desc = E1000_RX_DESC(*rx_ring, i); rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); @@ -446,10 +447,10 @@ static bool e1000_clean_rx_irq(struct e1000_adapter *adapter, cleaned = 1; cleaned_count++; - pci_unmap_single(pdev, + dma_unmap_single(&pdev->dev, buffer_info->dma, adapter->rx_buffer_len, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); buffer_info->dma = 0; length = le16_to_cpu(rx_desc->length); @@ -550,12 +551,11 @@ static void e1000_put_txbuf(struct e1000_adapter *adapter, { if (buffer_info->dma) { if (buffer_info->mapped_as_page) - pci_unmap_page(adapter->pdev, buffer_info->dma, - buffer_info->length, PCI_DMA_TODEVICE); + dma_unmap_page(&adapter->pdev->dev, buffer_info->dma, + buffer_info->length, DMA_TO_DEVICE); else - pci_unmap_single(adapter->pdev, buffer_info->dma, - buffer_info->length, - PCI_DMA_TODEVICE); + dma_unmap_single(&adapter->pdev->dev, buffer_info->dma, + buffer_info->length, DMA_TO_DEVICE); buffer_info->dma = 0; } if (buffer_info->skb) { @@ -756,9 +756,9 @@ static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter, cleaned = 1; cleaned_count++; - pci_unmap_single(pdev, buffer_info->dma, + dma_unmap_single(&pdev->dev, buffer_info->dma, adapter->rx_ps_bsize0, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); buffer_info->dma = 0; /* see !EOP comment in other rx routine */ @@ -814,13 +814,13 @@ static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter, * kmap_atomic, so we can't hold the mapping * very long */ - pci_dma_sync_single_for_cpu(pdev, ps_page->dma, - PAGE_SIZE, PCI_DMA_FROMDEVICE); + dma_sync_single_for_cpu(&pdev->dev, ps_page->dma, + PAGE_SIZE, DMA_FROM_DEVICE); vaddr = kmap_atomic(ps_page->page, KM_SKB_DATA_SOFTIRQ); memcpy(skb_tail_pointer(skb), vaddr, l1); kunmap_atomic(vaddr, KM_SKB_DATA_SOFTIRQ); - pci_dma_sync_single_for_device(pdev, ps_page->dma, - PAGE_SIZE, PCI_DMA_FROMDEVICE); + dma_sync_single_for_device(&pdev->dev, ps_page->dma, + PAGE_SIZE, DMA_FROM_DEVICE); /* remove the CRC */ if (!(adapter->flags2 & FLAG2_CRC_STRIPPING)) @@ -837,8 +837,8 @@ static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter, break; ps_page = &buffer_info->ps_pages[j]; - pci_unmap_page(pdev, ps_page->dma, PAGE_SIZE, - PCI_DMA_FROMDEVICE); + dma_unmap_page(&pdev->dev, ps_page->dma, PAGE_SIZE, + DMA_FROM_DEVICE); ps_page->dma = 0; skb_fill_page_desc(skb, j, ps_page->page, 0, length); ps_page->page = NULL; @@ -956,8 +956,8 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter, cleaned = true; cleaned_count++; - pci_unmap_page(pdev, buffer_info->dma, PAGE_SIZE, - PCI_DMA_FROMDEVICE); + dma_unmap_page(&pdev->dev, buffer_info->dma, PAGE_SIZE, + DMA_FROM_DEVICE); buffer_info->dma = 0; length = le16_to_cpu(rx_desc->length); @@ -1093,17 +1093,17 @@ static void e1000_clean_rx_ring(struct e1000_adapter *adapter) buffer_info = &rx_ring->buffer_info[i]; if (buffer_info->dma) { if (adapter->clean_rx == e1000_clean_rx_irq) - pci_unmap_single(pdev, buffer_info->dma, + dma_unmap_single(&pdev->dev, buffer_info->dma, adapter->rx_buffer_len, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); else if (adapter->clean_rx == e1000_clean_jumbo_rx_irq) - pci_unmap_page(pdev, buffer_info->dma, + dma_unmap_page(&pdev->dev, buffer_info->dma, PAGE_SIZE, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); else if (adapter->clean_rx == e1000_clean_rx_irq_ps) - pci_unmap_single(pdev, buffer_info->dma, + dma_unmap_single(&pdev->dev, buffer_info->dma, adapter->rx_ps_bsize0, - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); buffer_info->dma = 0; } @@ -1121,8 +1121,8 @@ static void e1000_clean_rx_ring(struct e1000_adapter *adapter) ps_page = &buffer_info->ps_pages[j]; if (!ps_page->page) break; - pci_unmap_page(pdev, ps_page->dma, PAGE_SIZE, - PCI_DMA_FROMDEVICE); + dma_unmap_page(&pdev->dev, ps_page->dma, PAGE_SIZE, + DMA_FROM_DEVICE); ps_page->dma = 0; put_page(ps_page->page); ps_page->page = NULL; @@ -3917,10 +3917,11 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = pci_map_single(pdev, skb->data + offset, - size, PCI_DMA_TODEVICE); + buffer_info->dma = dma_map_single(&pdev->dev, + skb->data + offset, + size, DMA_TO_DEVICE); buffer_info->mapped_as_page = false; - if (pci_dma_mapping_error(pdev, buffer_info->dma)) + if (dma_mapping_error(&pdev->dev, buffer_info->dma)) goto dma_error; len -= size; @@ -3952,11 +3953,11 @@ static int e1000_tx_map(struct e1000_adapter *adapter, buffer_info->length = size; buffer_info->time_stamp = jiffies; buffer_info->next_to_watch = i; - buffer_info->dma = pci_map_page(pdev, frag->page, + buffer_info->dma = dma_map_page(&pdev->dev, frag->page, offset, size, - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); buffer_info->mapped_as_page = true; - if (pci_dma_mapping_error(pdev, buffer_info->dma)) + if (dma_mapping_error(&pdev->dev, buffer_info->dma)) goto dma_error; len -= size; @@ -5050,16 +5051,16 @@ static int __devinit e1000_probe(struct pci_dev *pdev, return err; pci_using_dac = 0; - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); if (!err) pci_using_dac = 1; } else { - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = pci_set_consistent_dma_mask(pdev, - DMA_BIT_MASK(32)); + err = dma_set_coherent_mask(&pdev->dev, + DMA_BIT_MASK(32)); if (err) { dev_err(&pdev->dev, "No usable DMA " "configuration, aborting\n"); -- cgit v1.2.2 From 84f4ee902ad3ee964b7b3a13d5b7cf9c086e9916 Mon Sep 17 00:00:00 2001 From: Taku Izumi Date: Tue, 27 Apr 2010 14:39:08 +0000 Subject: e1000e: add registers etc. printout code just before resetting adapters This patch adds registers (,tx/rx rings' status and so on) printout code just before resetting adapters. This will be helpful for detecting the root cause of adapters reset. Signed-off-by: Taku Izumi Signed-off-by: Koki Sanagi Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 357 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 357 insertions(+) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 3a712157b6a1..904bd6bf3199 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -69,6 +69,361 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pchlan] = &e1000_pch_info, }; +struct e1000_reg_info { + u32 ofs; + char *name; +}; + +#define E1000_RDFH 0x02410 /* Rx Data FIFO Head - RW */ +#define E1000_RDFT 0x02418 /* Rx Data FIFO Tail - RW */ +#define E1000_RDFHS 0x02420 /* Rx Data FIFO Head Saved - RW */ +#define E1000_RDFTS 0x02428 /* Rx Data FIFO Tail Saved - RW */ +#define E1000_RDFPC 0x02430 /* Rx Data FIFO Packet Count - RW */ + +#define E1000_TDFH 0x03410 /* Tx Data FIFO Head - RW */ +#define E1000_TDFT 0x03418 /* Tx Data FIFO Tail - RW */ +#define E1000_TDFHS 0x03420 /* Tx Data FIFO Head Saved - RW */ +#define E1000_TDFTS 0x03428 /* Tx Data FIFO Tail Saved - RW */ +#define E1000_TDFPC 0x03430 /* Tx Data FIFO Packet Count - RW */ + +static const struct e1000_reg_info e1000_reg_info_tbl[] = { + + /* General Registers */ + {E1000_CTRL, "CTRL"}, + {E1000_STATUS, "STATUS"}, + {E1000_CTRL_EXT, "CTRL_EXT"}, + + /* Interrupt Registers */ + {E1000_ICR, "ICR"}, + + /* RX Registers */ + {E1000_RCTL, "RCTL"}, + {E1000_RDLEN, "RDLEN"}, + {E1000_RDH, "RDH"}, + {E1000_RDT, "RDT"}, + {E1000_RDTR, "RDTR"}, + {E1000_RXDCTL(0), "RXDCTL"}, + {E1000_ERT, "ERT"}, + {E1000_RDBAL, "RDBAL"}, + {E1000_RDBAH, "RDBAH"}, + {E1000_RDFH, "RDFH"}, + {E1000_RDFT, "RDFT"}, + {E1000_RDFHS, "RDFHS"}, + {E1000_RDFTS, "RDFTS"}, + {E1000_RDFPC, "RDFPC"}, + + /* TX Registers */ + {E1000_TCTL, "TCTL"}, + {E1000_TDBAL, "TDBAL"}, + {E1000_TDBAH, "TDBAH"}, + {E1000_TDLEN, "TDLEN"}, + {E1000_TDH, "TDH"}, + {E1000_TDT, "TDT"}, + {E1000_TIDV, "TIDV"}, + {E1000_TXDCTL(0), "TXDCTL"}, + {E1000_TADV, "TADV"}, + {E1000_TARC(0), "TARC"}, + {E1000_TDFH, "TDFH"}, + {E1000_TDFT, "TDFT"}, + {E1000_TDFHS, "TDFHS"}, + {E1000_TDFTS, "TDFTS"}, + {E1000_TDFPC, "TDFPC"}, + + /* List Terminator */ + {} +}; + +/* + * e1000_regdump - register printout routine + */ +static void e1000_regdump(struct e1000_hw *hw, struct e1000_reg_info *reginfo) +{ + int n = 0; + char rname[16]; + u32 regs[8]; + + switch (reginfo->ofs) { + case E1000_RXDCTL(0): + for (n = 0; n < 2; n++) + regs[n] = __er32(hw, E1000_RXDCTL(n)); + break; + case E1000_TXDCTL(0): + for (n = 0; n < 2; n++) + regs[n] = __er32(hw, E1000_TXDCTL(n)); + break; + case E1000_TARC(0): + for (n = 0; n < 2; n++) + regs[n] = __er32(hw, E1000_TARC(n)); + break; + default: + printk(KERN_INFO "%-15s %08x\n", + reginfo->name, __er32(hw, reginfo->ofs)); + return; + } + + snprintf(rname, 16, "%s%s", reginfo->name, "[0-1]"); + printk(KERN_INFO "%-15s ", rname); + for (n = 0; n < 2; n++) + printk(KERN_CONT "%08x ", regs[n]); + printk(KERN_CONT "\n"); +} + + +/* + * e1000e_dump - Print registers, tx-ring and rx-ring + */ +static void e1000e_dump(struct e1000_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct e1000_hw *hw = &adapter->hw; + struct e1000_reg_info *reginfo; + struct e1000_ring *tx_ring = adapter->tx_ring; + struct e1000_tx_desc *tx_desc; + struct my_u0 { u64 a; u64 b; } *u0; + struct e1000_buffer *buffer_info; + struct e1000_ring *rx_ring = adapter->rx_ring; + union e1000_rx_desc_packet_split *rx_desc_ps; + struct e1000_rx_desc *rx_desc; + struct my_u1 { u64 a; u64 b; u64 c; u64 d; } *u1; + u32 staterr; + int i = 0; + + if (!netif_msg_hw(adapter)) + return; + + /* Print netdevice Info */ + if (netdev) { + dev_info(&adapter->pdev->dev, "Net device Info\n"); + printk(KERN_INFO "Device Name state " + "trans_start last_rx\n"); + printk(KERN_INFO "%-15s %016lX %016lX %016lX\n", + netdev->name, + netdev->state, + netdev->trans_start, + netdev->last_rx); + } + + /* Print Registers */ + dev_info(&adapter->pdev->dev, "Register Dump\n"); + printk(KERN_INFO " Register Name Value\n"); + for (reginfo = (struct e1000_reg_info *)e1000_reg_info_tbl; + reginfo->name; reginfo++) { + e1000_regdump(hw, reginfo); + } + + /* Print TX Ring Summary */ + if (!netdev || !netif_running(netdev)) + goto exit; + + dev_info(&adapter->pdev->dev, "TX Rings Summary\n"); + printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma ]" + " leng ntw timestamp\n"); + buffer_info = &tx_ring->buffer_info[tx_ring->next_to_clean]; + printk(KERN_INFO " %5d %5X %5X %016llX %04X %3X %016llX\n", + 0, tx_ring->next_to_use, tx_ring->next_to_clean, + (u64)buffer_info->dma, + buffer_info->length, + buffer_info->next_to_watch, + (u64)buffer_info->time_stamp); + + /* Print TX Rings */ + if (!netif_msg_tx_done(adapter)) + goto rx_ring_summary; + + dev_info(&adapter->pdev->dev, "TX Rings Dump\n"); + + /* Transmit Descriptor Formats - DEXT[29] is 0 (Legacy) or 1 (Extended) + * + * Legacy Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] (Reserved on Write Back) | + * +--------------------------------------------------------------+ + * 8 | Special | CSS | Status | CMD | CSO | Length | + * +--------------------------------------------------------------+ + * 63 48 47 36 35 32 31 24 23 16 15 0 + * + * Extended Context Descriptor (DTYP=0x0) for TSO or checksum offload + * 63 48 47 40 39 32 31 16 15 8 7 0 + * +----------------------------------------------------------------+ + * 0 | TUCSE | TUCS0 | TUCSS | IPCSE | IPCS0 | IPCSS | + * +----------------------------------------------------------------+ + * 8 | MSS | HDRLEN | RSV | STA | TUCMD | DTYP | PAYLEN | + * +----------------------------------------------------------------+ + * 63 48 47 40 39 36 35 32 31 24 23 20 19 0 + * + * Extended Data Descriptor (DTYP=0x1) + * +----------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +----------------------------------------------------------------+ + * 8 | VLAN tag | POPTS | Rsvd | Status | Command | DTYP | DTALEN | + * +----------------------------------------------------------------+ + * 63 48 47 40 39 36 35 32 31 24 23 20 19 0 + */ + printk(KERN_INFO "Tl[desc] [address 63:0 ] [SpeCssSCmCsLen]" + " [bi->dma ] leng ntw timestamp bi->skb " + "<-- Legacy format\n"); + printk(KERN_INFO "Tc[desc] [Ce CoCsIpceCoS] [MssHlRSCm0Plen]" + " [bi->dma ] leng ntw timestamp bi->skb " + "<-- Ext Context format\n"); + printk(KERN_INFO "Td[desc] [address 63:0 ] [VlaPoRSCm1Dlen]" + " [bi->dma ] leng ntw timestamp bi->skb " + "<-- Ext Data format\n"); + for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { + tx_desc = E1000_TX_DESC(*tx_ring, i); + buffer_info = &tx_ring->buffer_info[i]; + u0 = (struct my_u0 *)tx_desc; + printk(KERN_INFO "T%c[0x%03X] %016llX %016llX %016llX " + "%04X %3X %016llX %p", + (!(le64_to_cpu(u0->b) & (1<<29)) ? 'l' : + ((le64_to_cpu(u0->b) & (1<<20)) ? 'd' : 'c')), i, + le64_to_cpu(u0->a), le64_to_cpu(u0->b), + (u64)buffer_info->dma, buffer_info->length, + buffer_info->next_to_watch, (u64)buffer_info->time_stamp, + buffer_info->skb); + if (i == tx_ring->next_to_use && i == tx_ring->next_to_clean) + printk(KERN_CONT " NTC/U\n"); + else if (i == tx_ring->next_to_use) + printk(KERN_CONT " NTU\n"); + else if (i == tx_ring->next_to_clean) + printk(KERN_CONT " NTC\n"); + else + printk(KERN_CONT "\n"); + + if (netif_msg_pktdata(adapter) && buffer_info->dma != 0) + print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, + 16, 1, phys_to_virt(buffer_info->dma), + buffer_info->length, true); + } + + /* Print RX Rings Summary */ +rx_ring_summary: + dev_info(&adapter->pdev->dev, "RX Rings Summary\n"); + printk(KERN_INFO "Queue [NTU] [NTC]\n"); + printk(KERN_INFO " %5d %5X %5X\n", 0, + rx_ring->next_to_use, rx_ring->next_to_clean); + + /* Print RX Rings */ + if (!netif_msg_rx_status(adapter)) + goto exit; + + dev_info(&adapter->pdev->dev, "RX Rings Dump\n"); + switch (adapter->rx_ps_pages) { + case 1: + case 2: + case 3: + /* [Extended] Packet Split Receive Descriptor Format + * + * +-----------------------------------------------------+ + * 0 | Buffer Address 0 [63:0] | + * +-----------------------------------------------------+ + * 8 | Buffer Address 1 [63:0] | + * +-----------------------------------------------------+ + * 16 | Buffer Address 2 [63:0] | + * +-----------------------------------------------------+ + * 24 | Buffer Address 3 [63:0] | + * +-----------------------------------------------------+ + */ + printk(KERN_INFO "R [desc] [buffer 0 63:0 ] " + "[buffer 1 63:0 ] " + "[buffer 2 63:0 ] [buffer 3 63:0 ] [bi->dma ] " + "[bi->skb] <-- Ext Pkt Split format\n"); + /* [Extended] Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 13 12 8 7 4 3 0 + * +------------------------------------------------------+ + * 0 | Packet | IP | Rsvd | MRQ | Rsvd | MRQ RSS | + * | Checksum | Ident | | Queue | | Type | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length | Extended Error | Extended Status | + * +------------------------------------------------------+ + * 63 48 47 32 31 20 19 0 + */ + printk(KERN_INFO "RWB[desc] [ck ipid mrqhsh] " + "[vl l0 ee es] " + "[ l3 l2 l1 hs] [reserved ] ---------------- " + "[bi->skb] <-- Ext Rx Write-Back format\n"); + for (i = 0; i < rx_ring->count; i++) { + buffer_info = &rx_ring->buffer_info[i]; + rx_desc_ps = E1000_RX_DESC_PS(*rx_ring, i); + u1 = (struct my_u1 *)rx_desc_ps; + staterr = + le32_to_cpu(rx_desc_ps->wb.middle.status_error); + if (staterr & E1000_RXD_STAT_DD) { + /* Descriptor Done */ + printk(KERN_INFO "RWB[0x%03X] %016llX " + "%016llX %016llX %016llX " + "---------------- %p", i, + le64_to_cpu(u1->a), + le64_to_cpu(u1->b), + le64_to_cpu(u1->c), + le64_to_cpu(u1->d), + buffer_info->skb); + } else { + printk(KERN_INFO "R [0x%03X] %016llX " + "%016llX %016llX %016llX %016llX %p", i, + le64_to_cpu(u1->a), + le64_to_cpu(u1->b), + le64_to_cpu(u1->c), + le64_to_cpu(u1->d), + (u64)buffer_info->dma, + buffer_info->skb); + + if (netif_msg_pktdata(adapter)) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, 16, 1, + phys_to_virt(buffer_info->dma), + adapter->rx_ps_bsize0, true); + } + + if (i == rx_ring->next_to_use) + printk(KERN_CONT " NTU\n"); + else if (i == rx_ring->next_to_clean) + printk(KERN_CONT " NTC\n"); + else + printk(KERN_CONT "\n"); + } + break; + default: + case 0: + /* Legacy Receive Descriptor Format + * + * +-----------------------------------------------------+ + * | Buffer Address [63:0] | + * +-----------------------------------------------------+ + * | VLAN Tag | Errors | Status 0 | Packet csum | Length | + * +-----------------------------------------------------+ + * 63 48 47 40 39 32 31 16 15 0 + */ + printk(KERN_INFO "Rl[desc] [address 63:0 ] " + "[vl er S cks ln] [bi->dma ] [bi->skb] " + "<-- Legacy format\n"); + for (i = 0; rx_ring->desc && (i < rx_ring->count); i++) { + rx_desc = E1000_RX_DESC(*rx_ring, i); + buffer_info = &rx_ring->buffer_info[i]; + u0 = (struct my_u0 *)rx_desc; + printk(KERN_INFO "Rl[0x%03X] %016llX %016llX " + "%016llX %p", + i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), + (u64)buffer_info->dma, buffer_info->skb); + if (i == rx_ring->next_to_use) + printk(KERN_CONT " NTU\n"); + else if (i == rx_ring->next_to_clean) + printk(KERN_CONT " NTC\n"); + else + printk(KERN_CONT "\n"); + + if (netif_msg_pktdata(adapter)) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, + 16, 1, phys_to_virt(buffer_info->dma), + adapter->rx_buffer_len, true); + } + } + +exit: + return; +} + /** * e1000_desc_unused - calculate if we have unused descriptors **/ @@ -4269,6 +4624,8 @@ static void e1000_reset_task(struct work_struct *work) struct e1000_adapter *adapter; adapter = container_of(work, struct e1000_adapter, reset_task); + e1000e_dump(adapter); + e_err("Reset adapter\n"); e1000e_reinit_locked(adapter); } -- cgit v1.2.2 From 0c75ba22541ccea88e89782373991109a7ec2a54 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Wed, 28 Apr 2010 21:46:06 +0000 Subject: e1000e: Fix oops caused by ASPM patch. Commit 6f461f6c7c961f0b1b73c0f27becf472a0ac606b ("e1000e: enable/disable ASPM L0s and L1 and ERT according to hardware errata") oopses on one of my ppc64 boxes with a NULL pointer (0x4a): Unable to handle kernel paging request for data at address 0x0000004a Faulting instruction address: 0xc0000000004d2f1c cpu 0xe: Vector: 300 (Data Access) at [c000000bec1833a0] pc: c0000000004d2f1c: .e1000e_disable_aspm+0xe0/0x150 lr: c0000000004d2f0c: .e1000e_disable_aspm+0xd0/0x150 dar: 4a [c000000bec1836d0] c00000000069b9d8 .e1000_probe+0x84/0xe8c [c000000bec1837b0] c000000000386d90 .local_pci_probe+0x4c/0x68 [c000000bec183840] c0000000003872ac .pci_device_probe+0xfc/0x148 [c000000bec183900] c000000000409e8c .driver_probe_device+0xe4/0x1d0 [c000000bec1839a0] c00000000040a024 .__driver_attach+0xac/0xf4 [c000000bec183a40] c000000000409124 .bus_for_each_dev+0x9c/0x10c [c000000bec183b00] c000000000409c1c .driver_attach+0x40/0x60 [c000000bec183b90] c0000000004085dc .bus_add_driver+0x150/0x328 [c000000bec183c40] c00000000040a58c .driver_register+0x100/0x1c4 [c000000bec183cf0] c00000000038764c .__pci_register_driver+0x78/0x128 Seems like pdev->bus->self == NULL. I haven't touched pci in a long time so I'm trying to remember what this means (no pcie bridge perhaps?) The patch below fixes the oops for me. Signed-off-by: Anton Blanchard Reviewed-by: Bruce Allan Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index fb8fc7d1b50d..dbf81788bb40 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -4633,6 +4633,9 @@ static void __e1000e_disable_aspm(struct pci_dev *pdev, u16 state) reg16 &= ~state; pci_write_config_word(pdev, pos + PCI_EXP_LNKCTL, reg16); + if (!pdev->bus->self) + return; + pos = pci_pcie_cap(pdev->bus->self); pci_read_config_word(pdev->bus->self, pos + PCI_EXP_LNKCTL, ®16); reg16 &= ~state; -- cgit v1.2.2 From 9ed318d546a29d7a591dbe648fd1a2efe3be1180 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 5 May 2010 14:02:27 +0000 Subject: e1000e: save skb counts in TX to avoid cache misses In e1000_tx_map, precompute number of segements and bytecounts which are derived from fields in skb; these are stored in buffer_info. When cleaning tx in e1000_clean_tx_irq use the values in the associated buffer_info for statistics counting, this eliminates cache misses on skb fields. Signed-off-by: Tom Herbert Acked-by: Bruce Allan Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index d13760dc27f8..8de64ed8762c 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -1001,14 +1001,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter) cleaned = (i == eop); if (cleaned) { - struct sk_buff *skb = buffer_info->skb; - unsigned int segs, bytecount; - segs = skb_shinfo(skb)->gso_segs ?: 1; - /* multiply data chunks by size of headers */ - bytecount = ((segs - 1) * skb_headlen(skb)) + - skb->len; - total_tx_packets += segs; - total_tx_bytes += bytecount; + total_tx_packets += buffer_info->segs; + total_tx_bytes += buffer_info->bytecount; } e1000_put_txbuf(adapter, buffer_info); @@ -4261,7 +4255,7 @@ static int e1000_tx_map(struct e1000_adapter *adapter, struct e1000_buffer *buffer_info; unsigned int len = skb_headlen(skb); unsigned int offset = 0, size, count = 0, i; - unsigned int f; + unsigned int f, bytecount, segs; i = tx_ring->next_to_use; @@ -4321,7 +4315,13 @@ static int e1000_tx_map(struct e1000_adapter *adapter, } } + segs = skb_shinfo(skb)->gso_segs ?: 1; + /* multiply data chunks by size of headers */ + bytecount = ((segs - 1) * skb_headlen(skb)) + skb->len; + tx_ring->buffer_info[i].skb = skb; + tx_ring->buffer_info[i].segs = segs; + tx_ring->buffer_info[i].bytecount = bytecount; tx_ring->buffer_info[first].next_to_watch = i; return count; -- cgit v1.2.2 From 50849d792b97c546c45a6652a16ba9be7d635c69 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 5 May 2010 14:02:49 +0000 Subject: e1000e: reduce writes of RX producer ptr Reduce number of writes to RX producer pointer. When alloc'ing RX buffers, only write the RX producer pointer once every E1000_RX_BUFFER_WRITE (16) buffers created. Signed-off-by: Tom Herbert Acked-by: Bruce Allan Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 57 ++++++++++++++++++--------------------------- 1 file changed, 23 insertions(+), 34 deletions(-) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 8de64ed8762c..b049d1a3c861 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -548,26 +548,23 @@ map_skb: rx_desc = E1000_RX_DESC(*rx_ring, i); rx_desc->buffer_addr = cpu_to_le64(buffer_info->dma); + if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) { + /* + * Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, adapter->hw.hw_addr + rx_ring->tail); + } i++; if (i == rx_ring->count) i = 0; buffer_info = &rx_ring->buffer_info[i]; } - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - if (i-- == 0) - i = (rx_ring->count - 1); - - /* - * Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); - writel(i, adapter->hw.hw_addr + rx_ring->tail); - } + rx_ring->next_to_use = i; } /** @@ -649,6 +646,17 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, rx_desc->read.buffer_addr[0] = cpu_to_le64(buffer_info->dma); + if (unlikely(!(i & (E1000_RX_BUFFER_WRITE - 1)))) { + /* + * Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i<<1, adapter->hw.hw_addr + rx_ring->tail); + } + i++; if (i == rx_ring->count) i = 0; @@ -656,26 +664,7 @@ static void e1000_alloc_rx_buffers_ps(struct e1000_adapter *adapter, } no_buffers: - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - - if (!(i--)) - i = (rx_ring->count - 1); - - /* - * Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); - /* - * Hardware increments by 16 bytes, but packet split - * descriptors are 32 bytes...so we increment tail - * twice as much. - */ - writel(i<<1, adapter->hw.hw_addr + rx_ring->tail); - } + rx_ring->next_to_use = i; } /** -- cgit v1.2.2 From f85e4dfac666e41b91e2b77fa563398e9379d5eb Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Wed, 5 May 2010 14:03:32 +0000 Subject: e1000e: Save irq into netdev structure Set net->devirq to pdev->irq. This should be consistent with other drivers. Signed-off-by: Tom Herbert Acked-by: Bruce Allan Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index b049d1a3c861..478c34a47d18 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -5440,6 +5440,8 @@ static int __devinit e1000_probe(struct pci_dev *pdev, SET_NETDEV_DEV(netdev, &pdev->dev); + netdev->irq = pdev->irq; + pci_set_drvdata(pdev, netdev); adapter = netdev_priv(netdev); hw = &adapter->hw; -- cgit v1.2.2 From eab2abf5826b78b126826cc70e564c44816396da Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Tue, 4 May 2010 22:26:03 +0000 Subject: e1000/e1000e: implement a simple interrupt moderation Back before e1000-7.3.20, the e1000 driver had a simple algorithm that managed interrupt moderation. The driver was updated in 7.3.20 to have the new "adaptive" interrupt moderation but we have customer requests to redeploy the old way as an option. This patch adds the old functionality back. The new functionality can be enabled via module parameter or at runtime via ethtool. Module parameter: (InterruptThrottleRate=4) to use this new moderation method. Ethtool method: ethtool -C ethX rx-usecs 4 Signed-off-by: Jesse Brandeburg Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/e1000e/netdev.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) (limited to 'drivers/net/e1000e/netdev.c') diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 478c34a47d18..c5f65a29865a 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -52,7 +52,7 @@ #include "e1000.h" -#define DRV_VERSION "1.0.2-k2" +#define DRV_VERSION "1.0.2-k4" char e1000e_driver_name[] = "e1000e"; const char e1000e_driver_version[] = DRV_VERSION; @@ -4070,6 +4070,22 @@ link_up: } } + /* Simple mode for Interrupt Throttle Rate (ITR) */ + if (adapter->itr_setting == 4) { + /* + * Symmetric Tx/Rx gets a reduced ITR=2000; + * Total asymmetrical Tx or Rx gets ITR=8000; + * everyone else is between 2000-8000. + */ + u32 goc = (adapter->gotc + adapter->gorc) / 10000; + u32 dif = (adapter->gotc > adapter->gorc ? + adapter->gotc - adapter->gorc : + adapter->gorc - adapter->gotc) / 10000; + u32 itr = goc > 0 ? (dif * 6000 / goc + 2000) : 8000; + + ew32(ITR, 1000000000 / (itr * 256)); + } + /* Cause software interrupt to ensure Rx ring is cleaned */ if (adapter->msix_entries) ew32(ICS, adapter->rx_ring->ims_val); -- cgit v1.2.2