diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-10 20:01:30 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-02-10 20:01:30 -0800 |
| commit | c5ce28df0e7c01a1de23c36ebdefcd803f2b6cbb (patch) | |
| tree | 9830baf38832769e1cf621708889111bbe3c93df /drivers/net/ethernet/intel | |
| parent | 29afc4e9a408f2304e09c6dd0dbcfbd2356d0faa (diff) | |
| parent | 9399f0c51489ae8c16d6559b82a452fdc1895e91 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) More iov_iter conversion work from Al Viro.
[ The "crypto: switch af_alg_make_sg() to iov_iter" commit was
wrong, and this pull actually adds an extra commit on top of the
branch I'm pulling to fix that up, so that the pre-merge state is
ok. - Linus ]
2) Various optimizations to the ipv4 forwarding information base trie
lookup implementation. From Alexander Duyck.
3) Remove sock_iocb altogether, from CHristoph Hellwig.
4) Allow congestion control algorithm selection via routing metrics.
From Daniel Borkmann.
5) Make ipv4 uncached route list per-cpu, from Eric Dumazet.
6) Handle rfs hash collisions more gracefully, also from Eric Dumazet.
7) Add xmit_more support to r8169, e1000, and e1000e drivers. From
Florian Westphal.
8) Transparent Ethernet Bridging support for GRO, from Jesse Gross.
9) Add BPF packet actions to packet scheduler, from Jiri Pirko.
10) Add support for uniqu flow IDs to openvswitch, from Joe Stringer.
11) New NetCP ethernet driver, from Muralidharan Karicheri and Wingman
Kwok.
12) More sanely handle out-of-window dupacks, which can result in
serious ACK storms. From Neal Cardwell.
13) Various rhashtable bug fixes and enhancements, from Herbert Xu,
Patrick McHardy, and Thomas Graf.
14) Support xmit_more in be2net, from Sathya Perla.
15) Group Policy extensions for vxlan, from Thomas Graf.
16) Remove Checksum Offload support for vxlan, from Tom Herbert.
17) Like ipv4, support lockless transmit over ipv6 UDP sockets. From
Vlad Yasevich.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1494+1 commits)
crypto: fix af_alg_make_sg() conversion to iov_iter
ipv4: Namespecify TCP PMTU mechanism
i40e: Fix for stats init function call in Rx setup
tcp: don't include Fast Open option in SYN-ACK on pure SYN-data
openvswitch: Only set TUNNEL_VXLAN_OPT if VXLAN-GBP metadata is set
ipv6: Make __ipv6_select_ident static
ipv6: Fix fragment id assignment on LE arches.
bridge: Fix inability to add non-vlan fdb entry
net: Mellanox: Delete unnecessary checks before the function call "vunmap"
cxgb4: Add support in cxgb4 to get expansion rom version via ethtool
ethtool: rename reserved1 memeber in ethtool_drvinfo for expansion ROM version
net: dsa: Remove redundant phy_attach()
IB/mlx4: Reset flow support for IB kernel ULPs
IB/mlx4: Always use the correct port for mirrored multicast attachments
net/bonding: Fix potential bad memory access during bonding events
tipc: remove tipc_snprintf
tipc: nl compat add noop and remove legacy nl framework
tipc: convert legacy nl stats show to nl compat
tipc: convert legacy nl net id get to nl compat
tipc: convert legacy nl net id set to nl compat
...
Diffstat (limited to 'drivers/net/ethernet/intel')
47 files changed, 1752 insertions, 550 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 4d61ef50b465..f4ff465584a0 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -192,6 +192,17 @@ config IXGBE To compile this driver as a module, choose M here. The module will be called ixgbe. +config IXGBE_VXLAN + bool "Virtual eXtensible Local Area Network Support" + default n + depends on IXGBE && VXLAN && !(IXGBE=y && VXLAN=m) + ---help--- + This allows one to create VXLAN virtual interfaces that provide + Layer 2 Networks over Layer 3 Networks. VXLAN is often used + to tunnel virtual network infrastructure in virtualized environments. + Say Y here if you want to use Virtual eXtensible Local Area Network + (VXLAN) in the driver. + config IXGBE_HWMON bool "Intel(R) 10GbE PCI Express adapters HWMON support" default y diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index b691eb4f6376..4270ad2d4ddf 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -24,6 +24,7 @@ /* ethtool support for e1000 */ #include "e1000.h" +#include <linux/jiffies.h> #include <linux/uaccess.h> enum {NETDEV_STATS, E1000_STATS}; @@ -1460,7 +1461,7 @@ static int e1000_run_loopback_test(struct e1000_adapter *adapter) ret_val = 13; /* ret_val is the same as mis-compare */ break; } - if (jiffies >= (time + 2)) { + if (time_after_eq(jiffies, time + 2)) { ret_val = 14; /* error code for time out error */ break; } diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 83140cbb5f01..7f997d36948f 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2977,7 +2977,6 @@ static void e1000_tx_queue(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring, int tx_flags, int count) { - struct e1000_hw *hw = &adapter->hw; struct e1000_tx_desc *tx_desc = NULL; struct e1000_tx_buffer *buffer_info; u32 txd_upper = 0, txd_lower = E1000_TXD_CMD_IFCS; @@ -3031,11 +3030,6 @@ static void e1000_tx_queue(struct e1000_adapter *adapter, wmb(); tx_ring->next_to_use = i; - writel(i, hw->hw_addr + tx_ring->tdt); - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } /* 82547 workaround to avoid controller hang in half-duplex environment. @@ -3226,9 +3220,10 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, return NETDEV_TX_BUSY; } - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { tx_flags |= E1000_TX_FLAGS_VLAN; - tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT); + tx_flags |= (skb_vlan_tag_get(skb) << + E1000_TX_FLAGS_VLAN_SHIFT); } first = tx_ring->next_to_use; @@ -3263,6 +3258,15 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, /* Make sure there is space in the ring for the next send. */ e1000_maybe_stop_tx(netdev, tx_ring, MAX_SKB_FRAGS + 2); + if (!skb->xmit_more || + netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { + writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt); + /* we need this if more than one processor can write to + * our tail at a time, it synchronizes IO on IA64/Altix + * systems + */ + mmiowb(); + } } else { dev_kfree_skb_any(skb); tx_ring->buffer_info[first].time_stamp = 0; diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 7785240a0da1..9416e5a7e0c8 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -34,7 +34,7 @@ #include <linux/pci-aspm.h> #include <linux/crc32.h> #include <linux/if_vlan.h> -#include <linux/clocksource.h> +#include <linux/timecounter.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> #include <linux/ptp_classify.h> diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e14fd85f64eb..1e8c40fd5c3d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4189,7 +4189,7 @@ static int e1000_sw_init(struct e1000_adapter *adapter) /* Setup hardware time stamping cyclecounter */ if (adapter->flags & FLAG_HAS_HW_TIMESTAMP) { adapter->cc.read = e1000e_cyclecounter_read; - adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.mask = CYCLECOUNTER_MASK(64); adapter->cc.mult = 1; /* cc.shift set in e1000e_get_base_tininca() */ @@ -5444,16 +5444,6 @@ static void e1000_tx_queue(struct e1000_ring *tx_ring, int tx_flags, int count) wmb(); tx_ring->next_to_use = i; - - if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) - e1000e_update_tdt_wa(tx_ring, i); - else - writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } #define MINIMUM_DHCP_PACKET_SIZE 282 @@ -5463,8 +5453,8 @@ static int e1000_transfer_dhcp_info(struct e1000_adapter *adapter, struct e1000_hw *hw = &adapter->hw; u16 length, offset; - if (vlan_tx_tag_present(skb) && - !((vlan_tx_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) && + if (skb_vlan_tag_present(skb) && + !((skb_vlan_tag_get(skb) == adapter->hw.mng_cookie.vlan_id) && (adapter->hw.mng_cookie.status & E1000_MNG_DHCP_COOKIE_STATUS_VLAN))) return 0; @@ -5603,9 +5593,10 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, if (e1000_maybe_stop_tx(tx_ring, count + 2)) return NETDEV_TX_BUSY; - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { tx_flags |= E1000_TX_FLAGS_VLAN; - tx_flags |= (vlan_tx_tag_get(skb) << E1000_TX_FLAGS_VLAN_SHIFT); + tx_flags |= (skb_vlan_tag_get(skb) << + E1000_TX_FLAGS_VLAN_SHIFT); } first = tx_ring->next_to_use; @@ -5635,8 +5626,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, count = e1000_tx_map(tx_ring, skb, first, adapter->tx_fifo_limit, nr_frags); if (count) { - if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - !adapter->tx_hwtstamp_skb)) { + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + (adapter->flags & FLAG_HAS_HW_TIMESTAMP) && + !adapter->tx_hwtstamp_skb) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= E1000_TX_FLAGS_HWTSTAMP; adapter->tx_hwtstamp_skb = skb_get(skb); @@ -5653,6 +5645,21 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, (MAX_SKB_FRAGS * DIV_ROUND_UP(PAGE_SIZE, adapter->tx_fifo_limit) + 2)); + + if (!skb->xmit_more || + netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { + if (adapter->flags2 & FLAG2_PCIM2PCI_ARBITER_WA) + e1000e_update_tdt_wa(tx_ring, + tx_ring->next_to_use); + else + writel(tx_ring->next_to_use, tx_ring->tail); + + /* we need this if more than one processor can write + * to our tail at a time, it synchronizes IO on + *IA64/Altix systems + */ + mmiowb(); + } } else { dev_kfree_skb_any(skb); tx_ring->buffer_info[first].time_stamp = 0; diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index fb1a914a3ad4..978ef9c4a043 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -90,12 +90,9 @@ static int e1000e_phc_adjtime(struct ptp_clock_info *ptp, s64 delta) struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, ptp_clock_info); unsigned long flags; - s64 now; spin_lock_irqsave(&adapter->systim_lock, flags); - now = timecounter_read(&adapter->tc); - now += delta; - timecounter_init(&adapter->tc, &adapter->cc, now); + timecounter_adjtime(&adapter->tc, delta); spin_unlock_irqrestore(&adapter->systim_lock, flags); return 0; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index eb088b129bc7..84ab9eea2768 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -97,7 +97,6 @@ static bool fm10k_alloc_mapped_page(struct fm10k_ring *rx_ring, */ if (dma_mapping_error(rx_ring->dev, dma)) { __free_page(page); - bi->page = NULL; rx_ring->rx_stats.alloc_failed++; return false; @@ -147,8 +146,8 @@ void fm10k_alloc_rx_buffers(struct fm10k_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } - /* clear the hdr_addr for the next_to_use descriptor */ - rx_desc->q.hdr_addr = 0; + /* clear the status bits for the next_to_use descriptor */ + rx_desc->d.staterr = 0; cleaned_count--; } while (cleaned_count); @@ -194,7 +193,7 @@ static void fm10k_reuse_rx_page(struct fm10k_ring *rx_ring, rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; /* transfer page from old buffer to new buffer */ - memcpy(new_buff, old_buff, sizeof(struct fm10k_rx_buffer)); + *new_buff = *old_buff; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, old_buff->dma, @@ -203,12 +202,17 @@ static void fm10k_reuse_rx_page(struct fm10k_ring *rx_ring, DMA_FROM_DEVICE); } +static inline bool fm10k_page_is_reserved(struct page *page) +{ + return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc; +} + static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer, struct page *page, unsigned int truesize) { /* avoid re-using remote pages */ - if (unlikely(page_to_nid(page) != numa_mem_id())) + if (unlikely(fm10k_page_is_reserved(page))) return false; #if (PAGE_SIZE < 8192) @@ -218,22 +222,19 @@ static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer, /* flip page offset to other buffer */ rx_buffer->page_offset ^= FM10K_RX_BUFSZ; - - /* Even if we own the page, we are not allowed to use atomic_set() - * This would break get_page_unless_zero() users. - */ - atomic_inc(&page->_count); #else /* move offset up to the next cache line */ rx_buffer->page_offset += truesize; if (rx_buffer->page_offset > (PAGE_SIZE - FM10K_RX_BUFSZ)) return false; - - /* bump ref count on page before it is given to the stack */ - get_page(page); #endif + /* Even if we own the page, we are not allowed to use atomic_set() + * This would break get_page_unless_zero() users. + */ + atomic_inc(&page->_count); + return true; } @@ -270,12 +271,12 @@ static bool fm10k_add_rx_frag(struct fm10k_ring *rx_ring, memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - /* we can reuse buffer as-is, just make sure it is local */ - if (likely(page_to_nid(page) == numa_mem_id())) + /* page is not reserved, we can reuse buffer as-is */ + if (likely(!fm10k_page_is_reserved(page))) return true; /* this page cannot be reused so discard it */ - put_page(page); + __free_page(page); return false; } @@ -293,7 +294,6 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, struct page *page; rx_buffer = &rx_ring->rx_buffer[rx_ring->next_to_clean]; - page = rx_buffer->page; prefetchw(page); @@ -727,6 +727,12 @@ static __be16 fm10k_tx_encap_offload(struct sk_buff *skb) struct ethhdr *eth_hdr; u8 l4_hdr = 0; +/* fm10k supports 184 octets of outer+inner headers. Minus 20 for inner L4. */ +#define FM10K_MAX_ENCAP_TRANSPORT_OFFSET 164 + if (skb_inner_transport_header(skb) - skb_mac_header(skb) > + FM10K_MAX_ENCAP_TRANSPORT_OFFSET) + return 0; + switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): l4_hdr = ip_hdr(skb)->protocol; @@ -965,8 +971,8 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring, tx_desc = FM10K_TX_DESC(tx_ring, i); /* add HW VLAN tag */ - if (vlan_tx_tag_present(skb)) - tx_desc->vlan = cpu_to_le16(vlan_tx_tag_get(skb)); + if (skb_vlan_tag_present(skb)) + tx_desc->vlan = cpu_to_le16(skb_vlan_tag_get(skb)); else tx_desc->vlan = 0; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 14a4ea795c01..9f5457c9e627 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1194,12 +1194,11 @@ static s32 fm10k_mbx_process_disconnect(struct fm10k_hw *hw, { const enum fm10k_mbx_state state = mbx->state; const u32 *hdr = &mbx->mbx_hdr; - u16 head, tail; + u16 head; s32 err; - /* we will need to pull all of the fields for verification */ + /* we will need to pull the header field for verification */ head = FM10K_MSG_HDR_FIELD_GET(*hdr, HEAD); - tail = FM10K_MSG_HDR_FIELD_GET(*hdr, TAIL); /* We should not be receiving disconnect if Rx is incomplete */ if (mbx->pushed) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 8811364b91cb..cfde8bac1aeb 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -609,7 +609,7 @@ static netdev_tx_t fm10k_xmit_frame(struct sk_buff *skb, struct net_device *dev) int err; if ((skb->protocol == htons(ETH_P_8021Q)) && - !vlan_tx_tag_present(skb)) { + !skb_vlan_tag_present(skb)) { /* FM10K only supports hardware tagging, any tags in frame * are considered 2nd level or "outer" tags */ @@ -1414,13 +1414,12 @@ struct net_device *fm10k_alloc_netdev(void) dev->vlan_features |= dev->features; /* configure tunnel offloads */ - dev->hw_enc_features = NETIF_F_IP_CSUM | - NETIF_F_TSO | - NETIF_F_TSO6 | - NETIF_F_TSO_ECN | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_IPV6_CSUM | - NETIF_F_SG; + dev->hw_enc_features |= NETIF_F_IP_CSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_TSO_ECN | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_IPV6_CSUM; /* we want to leave these both on as we cannot disable VLAN tag * insertion or stripping on the hardware since it is contained diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 275423d4f777..7e4711958e46 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -330,13 +330,10 @@ static s32 fm10k_update_xc_addr_pf(struct fm10k_hw *hw, u16 glort, struct fm10k_mac_update mac_update; u32 msg[5]; - /* if glort is not valid return error */ - if (!fm10k_glort_valid_pf(hw, glort)) + /* if glort or vlan are not valid return error */ + if (!fm10k_glort_valid_pf(hw, glort) || vid >= FM10K_VLAN_TABLE_VID_MAX) return FM10K_ERR_PARAM; - /* drop upper 4 bits of VLAN ID */ - vid = (vid << 4) >> 4; - /* record fields */ mac_update.mac_lower = cpu_to_le32(((u32)mac[2] << 24) | ((u32)mac[3] << 16) | diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c b/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c index 7822809436a3..d966044e017a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ptp.c @@ -57,7 +57,6 @@ void fm10k_ts_tx_enqueue(struct fm10k_intfc *interface, struct sk_buff *skb) struct sk_buff_head *list = &interface->ts_tx_skb_queue; struct sk_buff *clone; unsigned long flags; - __le16 dglort; /* create clone for us to return on the Tx path */ clone = skb_clone_sk(skb); @@ -65,8 +64,6 @@ void fm10k_ts_tx_enqueue(struct fm10k_intfc *interface, struct sk_buff *skb) return; FM10K_CB(clone)->ts_tx_timeout = jiffies + FM10K_TS_TX_TIMEOUT; - dglort = FM10K_CB(clone)->fi.w.dglort; - spin_lock_irqsave(&list->lock, flags); /* attempt to locate any buffers with the same dglort, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 280296f29154..7c6d9d5a8ae5 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -354,7 +354,7 @@ struct fm10k_hw; /* Define timeouts for resets and disables */ #define FM10K_QUEUE_DISABLE_TIMEOUT 100 -#define FM10K_RESET_TIMEOUT 100 +#define FM10K_RESET_TIMEOUT 150 /* VF registers */ #define FM10K_VFCTRL 0x00000 diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index fc50f6461b13..2b65cdcad6ba 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -87,11 +87,12 @@ #define I40E_MINIMUM_FCOE 1 /* minimum number of QPs for FCoE */ #endif /* I40E_FCOE */ #define I40E_MAX_AQ_BUF_SIZE 4096 -#define I40E_AQ_LEN 128 -#define I40E_AQ_WORK_LIMIT 16 +#define I40E_AQ_LEN 256 +#define I40E_AQ_WORK_LIMIT 32 #define I40E_MAX_USER_PRIORITY 8 #define I40E_DEFAULT_MSG_ENABLE 4 #define I40E_QUEUE_WAIT_RETRY_LIMIT 10 +#define I40E_INT_NAME_STR_LEN (IFNAMSIZ + 9) #define I40E_NVM_VERSION_LO_SHIFT 0 #define I40E_NVM_VERSION_LO_MASK (0xff << I40E_NVM_VERSION_LO_SHIFT) @@ -147,6 +148,7 @@ enum i40e_state_t { __I40E_FD_FLUSH_REQUESTED, __I40E_RESET_FAILED, __I40E_PORT_TX_SUSPENDED, + __I40E_VF_DISABLE, }; enum i40e_interrupt_policy { @@ -268,7 +270,7 @@ struct i40e_pf { u16 rx_itr_default; u16 tx_itr_default; u16 msg_enable; - char misc_int_name[IFNAMSIZ + 9]; + char int_name[I40E_INT_NAME_STR_LEN]; u16 adminq_work_limit; /* num of admin receive queue desc to process */ unsigned long service_timer_period; unsigned long service_timer_previous; @@ -524,7 +526,7 @@ struct i40e_q_vector { cpumask_t affinity_mask; struct rcu_head rcu; /* to avoid race with update stats on free */ - char name[IFNAMSIZ + 9]; + char name[I40E_INT_NAME_STR_LEN]; } ____cacheline_internodealigned_in_smp; /* lan device */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h index 564d0b0192f7..de17b6fbcc4e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h @@ -148,7 +148,7 @@ static inline int i40e_aq_rc_to_posix(u32 aq_ret, u16 aq_rc) /* general information */ #define I40E_AQ_LARGE_BUF 512 -#define I40E_ASQ_CMD_TIMEOUT 100 /* msecs */ +#define I40E_ASQ_CMD_TIMEOUT 250 /* msecs */ void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 8835aeeff23e..929e3d72a01e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -256,6 +256,8 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_lldp_stop = 0x0A05, i40e_aqc_opc_lldp_start = 0x0A06, i40e_aqc_opc_get_cee_dcb_cfg = 0x0A07, + i40e_aqc_opc_lldp_set_local_mib = 0x0A08, + i40e_aqc_opc_lldp_stop_start_spec_agent = 0x0A09, /* Tunnel commands */ i40e_aqc_opc_add_udp_tunnel = 0x0B00, @@ -268,6 +270,8 @@ enum i40e_admin_queue_opc { /* OEM commands */ i40e_aqc_opc_oem_parameter_change = 0xFE00, i40e_aqc_opc_oem_device_status_change = 0xFE01, + i40e_aqc_opc_oem_ocsd_initialize = 0xFE02, + i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, /* debug commands */ i40e_aqc_opc_debug_get_deviceid = 0xFF00, @@ -276,7 +280,6 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_debug_write_reg = 0xFF04, i40e_aqc_opc_debug_modify_reg = 0xFF07, i40e_aqc_opc_debug_dump_internals = 0xFF08, - i40e_aqc_opc_debug_modify_internals = 0xFF09, }; /* command structures and indirect data structures */ @@ -410,6 +413,7 @@ struct i40e_aqc_list_capabilities_element_resp { #define I40E_AQ_CAP_ID_VSI 0x0017 #define I40E_AQ_CAP_ID_DCB 0x0018 #define I40E_AQ_CAP_ID_FCOE 0x0021 +#define I40E_AQ_CAP_ID_ISCSI 0x0022 #define I40E_AQ_CAP_ID_RSS 0x0040 #define I40E_AQ_CAP_ID_RXQ 0x0041 #define I40E_AQ_CAP_ID_TXQ 0x0042 @@ -454,8 +458,11 @@ struct i40e_aqc_arp_proxy_data { __le32 pfpm_proxyfc; __le32 ip_addr; u8 mac_addr[6]; + u8 reserved[2]; }; +I40E_CHECK_STRUCT_LEN(0x14, i40e_aqc_arp_proxy_data); + /* Set NS Proxy Table Entry Command (indirect 0x0105) */ struct i40e_aqc_ns_proxy_data { __le16 table_idx_mac_addr_0; @@ -481,6 +488,8 @@ struct i40e_aqc_ns_proxy_data { u8 ipv6_addr_1[16]; }; +I40E_CHECK_STRUCT_LEN(0x3c, i40e_aqc_ns_proxy_data); + /* Manage LAA Command (0x0106) - obsolete */ struct i40e_aqc_mng_laa { __le16 command_flags; @@ -491,6 +500,8 @@ struct i40e_aqc_mng_laa { u8 reserved2[6]; }; +I40E_CHECK_CMD_LENGTH(i40e_aqc_mng_laa); + /* Manage MAC Address Read Command (indirect 0x0107) */ struct i40e_aqc_mac_address_read { __le16 command_flags; @@ -562,6 +573,8 @@ struct i40e_aqc_get_switch_config_header_resp { u8 reserved[12]; }; +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_config_header_resp); + struct i40e_aqc_switch_config_element_resp { u8 element_type; #define I40E_AQ_SW_ELEM_TYPE_MAC 1 @@ -587,6 +600,8 @@ struct i40e_aqc_switch_config_element_resp { __le16 element_info; }; +I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_config_element_resp); + /* Get Switch Configuration (indirect 0x0200) * an array of elements are returned in the response buffer * the first in the array is the header, remainder are elements @@ -596,6 +611,8 @@ struct i40e_aqc_get_switch_config_resp { struct i40e_aqc_switch_config_element_resp element[1]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_switch_config_resp); + /* Add Statistics (direct 0x0201) * Remove Statistics (direct 0x0202) */ @@ -661,6 +678,8 @@ struct i40e_aqc_switch_resource_alloc_element_resp { u8 reserved2[6]; }; +I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); + /* Add VSI (indirect 0x0210) * this indirect command uses struct i40e_aqc_vsi_properties_data * as the indirect buffer (128 bytes) @@ -1092,6 +1111,8 @@ struct i40e_aqc_remove_tag { u8 reserved[12]; }; +I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_tag); + /* Add multicast E-Tag (direct 0x0257) * del multicast E-Tag (direct 0x0258) only uses pv_seid and etag fields * and no external data @@ -1207,7 +1228,7 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { } ipaddr; __le16 flags; #define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \ +#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \ I40E_AQC_ADD_CLOUD_FILTER_SHIFT) /* 0x0000 reserved */ #define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001 @@ -1240,7 +1261,7 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { u8 reserved[4]; __le16 queue_number; #define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x3F << \ +#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x7FF << \ I40E_AQC_ADD_CLOUD_QUEUE_SHIFT) u8 reserved2[14]; /* response section */ @@ -1359,6 +1380,8 @@ struct i40e_aqc_configure_vsi_ets_sla_bw_data { u8 reserved1[28]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_configure_vsi_ets_sla_bw_data); + /* Configure VSI Bandwidth Allocation per Traffic Type (indirect 0x0407) * responds with i40e_aqc_qs_handles_resp */ @@ -1370,6 +1393,8 @@ struct i40e_aqc_configure_vsi_tc_bw_data { __le16 qs_handles[8]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_vsi_tc_bw_data); + /* Query vsi bw configuration (indirect 0x0408) */ struct i40e_aqc_query_vsi_bw_config_resp { u8 tc_valid_bits; @@ -1383,6 +1408,8 @@ struct i40e_aqc_query_vsi_bw_config_resp { u8 reserved3[23]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_vsi_bw_config_resp); + /* Query VSI Bandwidth Allocation per Traffic Type (indirect 0x040A) */ struct i40e_aqc_query_vsi_ets_sla_config_resp { u8 tc_valid_bits; @@ -1394,6 +1421,8 @@ struct i40e_aqc_query_vsi_ets_sla_config_resp { __le16 tc_bw_max[2]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_vsi_ets_sla_config_resp); + /* Configure Switching Component Bandwidth Limit (direct 0x0410) */ struct i40e_aqc_configure_switching_comp_bw_limit { __le16 seid; @@ -1421,6 +1450,8 @@ struct i40e_aqc_configure_switching_comp_ets_data { u8 reserved2[96]; }; +I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_configure_switching_comp_ets_data); + /* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */ struct i40e_aqc_configure_switching_comp_ets_bw_limit_data { u8 tc_valid_bits; @@ -1432,6 +1463,9 @@ struct i40e_aqc_configure_switching_comp_ets_bw_limit_data { u8 reserved1[28]; }; +I40E_CHECK_STRUCT_LEN(0x40, + i40e_aqc_configure_switching_comp_ets_bw_limit_data); + /* Configure Switching Component Bandwidth Allocation per Tc * (indirect 0x0417) */ @@ -1443,6 +1477,8 @@ struct i40e_aqc_configure_switching_comp_bw_config_data { u8 reserved1[20]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_switching_comp_bw_config_data); + /* Query Switching Component Configuration (indirect 0x0418) */ struct i40e_aqc_query_switching_comp_ets_config_resp { u8 tc_valid_bits; @@ -1453,6 +1489,8 @@ struct i40e_aqc_query_switching_comp_ets_config_resp { u8 reserved2[23]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_switching_comp_ets_config_resp); + /* Query PhysicalPort ETS Configuration (indirect 0x0419) */ struct i40e_aqc_query_port_ets_config_resp { u8 reserved[4]; @@ -1468,6 +1506,8 @@ struct i40e_aqc_query_port_ets_config_resp { u8 reserved3[32]; }; +I40E_CHECK_STRUCT_LEN(0x44, i40e_aqc_query_port_ets_config_resp); + /* Query Switching Component Bandwidth Allocation per Traffic Type * (indirect 0x041A) */ @@ -1482,6 +1522,8 @@ struct i40e_aqc_query_switching_comp_bw_config_resp { __le16 tc_bw_max[2]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_switching_comp_bw_config_resp); + /* Suspend/resume port TX traffic * (direct 0x041B and 0x041C) uses the generic SEID struct */ @@ -1495,6 +1537,8 @@ struct i40e_aqc_configure_partition_bw_data { u8 max_bw[16]; /* bandwidth limit */ }; +I40E_CHECK_STRUCT_LEN(0x22, i40e_aqc_configure_partition_bw_data); + /* Get and set the active HMC resource profile and status. * (direct 0x0500) and (direct 0x0501) */ @@ -1577,6 +1621,8 @@ struct i40e_aqc_module_desc { u8 reserved2[8]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_module_desc); + struct i40e_aq_get_phy_abilities_resp { __le32 phy_type; /* bitmap using the above enum for offsets */ u8 link_speed; /* bitmap using the above enum bit patterns */ @@ -1605,6 +1651,8 @@ struct i40e_aq_get_phy_abilities_resp { struct i40e_aqc_module_desc qualified_module[I40E_AQ_PHY_MAX_QMS]; }; +I40E_CHECK_STRUCT_LEN(0x218, i40e_aq_get_phy_abilities_resp); + /* Set PHY Config (direct 0x0601) */ struct i40e_aq_set_phy_config { /* same bits as above in all */ __le32 phy_type; @@ -1788,12 +1836,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update); /* NVM Config Read (indirect 0x0704) */ struct i40e_aqc_nvm_config_read { __le16 cmd_flags; -#define ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK 1 -#define ANVM_READ_SINGLE_FEATURE 0 -#define ANVM_READ_MULTIPLE_FEATURES 1 +#define I40E_AQ_ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK 1 +#define I40E_AQ_ANVM_READ_SINGLE_FEATURE 0 +#define I40E_AQ_ANVM_READ_MULTIPLE_FEATURES 1 __le16 element_count; - __le16 element_id; /* Feature/field ID */ - u8 reserved[2]; + __le16 element_id; /* Feature/field ID */ + __le16 element_id_msw; /* MSWord of field ID */ __le32 address_high; __le32 address_low; }; @@ -1811,21 +1859,32 @@ struct i40e_aqc_nvm_config_write { I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write); +/* Used for 0x0704 as well as for 0x0705 commands */ +#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT 1 +#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_MASK \ + (1 << I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT) +#define I40E_AQ_ANVM_FEATURE 0 +#define I40E_AQ_ANVM_IMMEDIATE_FIELD (1 << FEATURE_OR_IMMEDIATE_SHIFT) struct i40e_aqc_nvm_config_data_feature { __le16 feature_id; - __le16 instance_id; +#define I40E_AQ_ANVM_FEATURE_OPTION_OEM_ONLY 0x01 +#define I40E_AQ_ANVM_FEATURE_OPTION_DWORD_MAP 0x08 +#define I40E_AQ_ANVM_FEATURE_OPTION_POR_CSR 0x10 __le16 feature_options; __le16 feature_selection; }; +I40E_CHECK_STRUCT_LEN(0x6, i40e_aqc_nvm_config_data_feature); + struct i40e_aqc_nvm_config_data_immediate_field { -#define ANVM_FEATURE_OR_IMMEDIATE_MASK 0x2 - __le16 field_id; - __le16 instance_id; + __le32 field_id; + __le32 field_value; __le16 field_options; - __le16 field_value; + __le16 reserved; }; +I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field); + /* Send to PF command (indirect 0x0801) id is only used by PF * Send to VF command (indirect 0x0802) id is only used by PF * Send to Peer PF command (indirect 0x0803) @@ -2026,12 +2085,54 @@ struct i40e_aqc_get_cee_dcb_cfg_resp { u8 oper_tc_bw[8]; u8 oper_pfc_en; __le16 oper_app_prio; +#define I40E_AQC_CEE_APP_FCOE_SHIFT 0x0 +#define I40E_AQC_CEE_APP_FCOE_MASK (0x7 << I40E_AQC_CEE_APP_FCOE_SHIFT) +#define I40E_AQC_CEE_APP_ISCSI_SHIFT 0x3 +#define I40E_AQC_CEE_APP_ISCSI_MASK (0x7 << I40E_AQC_CEE_APP_ISCSI_SHIFT) +#define I40E_AQC_CEE_APP_FIP_SHIFT 0x8 +#define I40E_AQC_CEE_APP_FIP_MASK (0x7 << I40E_AQC_CEE_APP_FIP_SHIFT) +#define I40E_AQC_CEE_APP_FIP_MASK (0x7 << I40E_AQC_CEE_APP_FIP_SHIFT) __le32 tlv_status; +#define I40E_AQC_CEE_PG_STATUS_SHIFT 0x0 +#define I40E_AQC_CEE_PG_STATUS_MASK (0x7 << I40E_AQC_CEE_PG_STATUS_SHIFT) +#define I40E_AQC_CEE_PFC_STATUS_SHIFT 0x3 +#define I40E_AQC_CEE_PFC_STATUS_MASK (0x7 << I40E_AQC_CEE_PFC_STATUS_SHIFT) +#define I40E_AQC_CEE_APP_STATUS_SHIFT 0x8 +#define I40E_AQC_CEE_APP_STATUS_MASK (0x7 << I40E_AQC_CEE_APP_STATUS_SHIFT) u8 reserved[12]; }; I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_cee_dcb_cfg_resp); +/* Set Local LLDP MIB (indirect 0x0A08) + * Used to replace the local MIB of a given LLDP agent. e.g. DCBx + */ +struct i40e_aqc_lldp_set_local_mib { +#define SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT 0 +#define SET_LOCAL_MIB_AC_TYPE_DCBX_MASK (1 << SET_LOCAL_MIB_AC_TYPE_DCBX_SHIFT) + u8 type; + u8 reserved0; + __le16 length; + u8 reserved1[4]; + __le32 address_high; + __le32 address_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_set_local_mib); + +/* Stop/Start LLDP Agent (direct 0x0A09) + * Used for stopping/starting specific LLDP agent. e.g. DCBx + */ +struct i40e_aqc_lldp_stop_start_specific_agent { +#define I40E_AQC_START_SPECIFIC_AGENT_SHIFT 0 +#define I40E_AQC_START_SPECIFIC_AGENT_MASK \ + (1 << I40E_AQC_START_SPECIFIC_AGENT_SHIFT) + u8 command; + u8 reserved[15]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop_start_specific_agent); + /* Add Udp Tunnel command and completion (direct 0x0B00) */ struct i40e_aqc_add_udp_tunnel { __le16 udp_port; @@ -2106,7 +2207,8 @@ struct i40e_aqc_oem_param_change { #define I40E_AQ_OEM_PARAM_TYPE_BW_CTL 1 #define I40E_AQ_OEM_PARAM_MAC 2 __le32 param_value1; - u8 param_value2[8]; + __le16 param_value2; + u8 reserved[6]; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change); @@ -2120,6 +2222,28 @@ struct i40e_aqc_oem_state_change { I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_state_change); +/* Initialize OCSD (0xFE02, direct) */ +struct i40e_aqc_opc_oem_ocsd_initialize { + u8 type_status; + u8 reserved1[3]; + __le32 ocsd_memory_block_addr_high; + __le32 ocsd_memory_block_addr_low; + __le32 requested_update_interval; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocsd_initialize); + +/* Initialize OCBB (0xFE03, direct) */ +struct i40e_aqc_opc_oem_ocbb_initialize { + u8 type_status; + u8 reserved1[3]; + __le32 ocbb_memory_block_addr_high; + __le32 ocbb_memory_block_addr_low; + u8 reserved2[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocbb_initialize); + /* debug commands */ /* get device id (0xFF00) uses the generic structure */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 3d741ee99a2c..11a9ffebf8d8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -742,6 +742,65 @@ i40e_status i40e_get_san_mac_addr(struct i40e_hw *hw, u8 *mac_addr) #endif /** + * i40e_read_pba_string - Reads part number string from EEPROM + * @hw: pointer to hardware structure + * @pba_num: stores the part number string from the EEPROM + * @pba_num_size: part number string buffer length + * + * Reads the part number string from the EEPROM. + **/ +i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, + u32 pba_num_size) +{ + i40e_status status = 0; + u16 pba_word = 0; + u16 pba_size = 0; + u16 pba_ptr = 0; + u16 i = 0; + + status = i40e_read_nvm_word(hw, I40E_SR_PBA_FLAGS, &pba_word); + if (status || (pba_word != 0xFAFA)) { + hw_dbg(hw, "Failed to read PBA flags or flag is invalid.\n"); + return status; + } + + status = i40e_read_nvm_word(hw, I40E_SR_PBA_BLOCK_PTR, &pba_ptr); + if (status) { + hw_dbg(hw, "Failed to read PBA Block pointer.\n"); + return status; + } + + status = i40e_read_nvm_word(hw, pba_ptr, &pba_size); + if (status) { + hw_dbg(hw, "Failed to read PBA Block size.\n"); + return status; + } + + /* Subtract one to get PBA word count (PBA Size word is included in + * total size) + */ + pba_size--; + if (pba_num_size < (((u32)pba_size * 2) + 1)) { + hw_dbg(hw, "Buffer to small for PBA data.\n"); + return I40E_ERR_PARAM; + } + + for (i = 0; i < pba_size; i++) { + status = i40e_read_nvm_word(hw, (pba_ptr + 1) + i, &pba_word); + if (status) { + hw_dbg(hw, "Failed to read PBA Block word %d.\n", i); + return status; + } + + pba_num[(i * 2)] = (pba_word >> 8) & 0xFF; + pba_num[(i * 2) + 1] = pba_word & 0xFF; + } + pba_num[(pba_size * 2)] = '\0'; + + return status; +} + +/** * i40e_get_media_type - Gets media type * @hw: pointer to the hardware structure **/ @@ -1083,8 +1142,10 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink) if (mode == I40E_LINK_ACTIVITY) blink = false; - gpio_val |= (blink ? 1 : 0) << - I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT; + if (blink) + gpio_val |= (1 << I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT); + else + gpio_val &= ~(1 << I40E_GLGEN_GPIO_CTL_LED_BLINK_SHIFT); wr32(hw, I40E_GLGEN_GPIO_CTL(i), gpio_val); break; @@ -2035,6 +2096,43 @@ i40e_status i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, } /** + * i40e_aq_debug_read_register + * @hw: pointer to the hw struct + * @reg_addr: register address + * @reg_val: register value + * @cmd_details: pointer to command details structure or NULL + * + * Read the register using the admin queue commands + **/ +i40e_status i40e_aq_debug_read_register(struct i40e_hw *hw, + u32 reg_addr, u64 *reg_val, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_debug_reg_read_write *cmd_resp = + (struct i40e_aqc_debug_reg_read_write *)&desc.params.raw; + i40e_status status; + + if (reg_val == NULL) + return I40E_ERR_PARAM; + + i40e_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_debug_read_reg); + + cmd_resp->address = cpu_to_le32(reg_addr); + + status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); + + if (!status) { + *reg_val = ((u64)cmd_resp->value_high << 32) | + (u64)cmd_resp->value_low; + *reg_val = le64_to_cpu(*reg_val); + } + + return status; +} + +/** * i40e_aq_debug_write_register * @hw: pointer to the hw struct * @reg_addr: register address @@ -2264,6 +2362,7 @@ i40e_aq_erase_nvm_exit: #define I40E_DEV_FUNC_CAP_VSI 0x17 #define I40E_DEV_FUNC_CAP_DCB 0x18 #define I40E_DEV_FUNC_CAP_FCOE 0x21 +#define I40E_DEV_FUNC_CAP_ISCSI 0x22 #define I40E_DEV_FUNC_CAP_RSS 0x40 #define I40E_DEV_FUNC_CAP_RX_QUEUES 0x41 #define I40E_DEV_FUNC_CAP_TX_QUEUES 0x42 @@ -2292,6 +2391,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, enum i40e_admin_queue_opc list_type_opc) { struct i40e_aqc_list_capabilities_element_resp *cap; + u32 valid_functions, num_functions; u32 number, logical_id, phys_id; struct i40e_hw_capabilities *p; u32 i = 0; @@ -2362,6 +2462,10 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, if (number == 1) p->fcoe = true; break; + case I40E_DEV_FUNC_CAP_ISCSI: + if (number == 1) + p->iscsi = true; + break; case I40E_DEV_FUNC_CAP_RSS: p->rss = true; p->rss_table_size = number; @@ -2427,6 +2531,34 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, if (p->npar_enable || p->mfp_mode_1) p->fcoe = false; + /* count the enabled ports (aka the "not disabled" ports) */ + hw->num_ports = 0; + for (i = 0; i < 4; i++) { + u32 port_cfg_reg = I40E_PRTGEN_CNF + (4 * i); + u64 port_cfg = 0; + + /* use AQ read to get the physical register offset instead + * of the port relative offset + */ + i40e_aq_debug_read_register(hw, port_cfg_reg, &port_cfg, NULL); + if (!(port_cfg & I40E_PRTGEN_CNF_PORT_DIS_MASK)) + hw->num_ports++; + } + + valid_functions = p->valid_functions; + num_functions = 0; + while (valid_functions) { + if (valid_functions & 1) + num_functions++; + valid_functions >>= 1; + } + + /* partition id is 1-based, and functions are evenly spread + * across the ports as partitions + */ + hw->partition_id = (hw->pf_id / hw->num_ports) + 1; + hw->num_partitions = num_functions / hw->num_ports; + /* additional HW specific goodies that might * someday be HW version specific */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index cb0de455683e..61236f983971 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1890,7 +1890,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, " dump desc tx <vsi_seid> <ring_id> [<desc_n>]\n"); dev_info(&pf->pdev->dev, " dump desc rx <vsi_seid> <ring_id> [<desc_n>]\n"); dev_info(&pf->pdev->dev, " dump desc aq\n"); - dev_info(&pf->pdev->dev, " dump stats\n"); dev_info(&pf->pdev->dev, " dump reset stats\n"); dev_info(&pf->pdev->dev, " msg_enable [level]\n"); dev_info(&pf->pdev->dev, " read <reg>\n"); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 951e8767fc50..b8230dc205ec 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -219,6 +219,16 @@ static const char i40e_gstrings_test[][ETH_GSTRING_LEN] = { #define I40E_TEST_LEN (sizeof(i40e_gstrings_test) / ETH_GSTRING_LEN) /** + * i40e_partition_setting_complaint - generic complaint for MFP restriction + * @pf: the PF struct + **/ +static void i40e_partition_setting_complaint(struct i40e_pf *pf) +{ + dev_info(&pf->pdev->dev, + "The link settings are allowed to be changed only from the first partition of a given port. Please switch to the first partition in order to change the setting.\n"); +} + +/** * i40e_get_settings - Get Link Speed and Duplex settings * @netdev: network interface device structure * @ecmd: ethtool command @@ -485,6 +495,14 @@ static int i40e_set_settings(struct net_device *netdev, u8 autoneg; u32 advertise; + /* Changing port settings is not supported if this isn't the + * port's controlling PF + */ + if (hw->partition_id != 1) { + i40e_partition_setting_complaint(pf); + return -EOPNOTSUPP; + } + if (vsi != pf->vsi[pf->lan_vsi]) return -EOPNOTSUPP; @@ -687,6 +705,14 @@ static int i40e_set_pauseparam(struct net_device *netdev, u8 aq_failures; int err = 0; + /* Changing the port's flow control is not supported if this isn't the + * port's controlling PF + */ + if (hw->partition_id != 1) { + i40e_partition_setting_complaint(pf); + return -EOPNOTSUPP; + } + if (vsi != pf->vsi[pf->lan_vsi]) return -EOPNOTSUPP; @@ -1503,7 +1529,7 @@ static void i40e_get_wol(struct net_device *netdev, /* NVM bit on means WoL disabled for the port */ i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits); - if ((1 << hw->port) & wol_nvm_bits) { + if ((1 << hw->port) & wol_nvm_bits || hw->partition_id != 1) { wol->supported = 0; wol->wolopts = 0; } else { @@ -1512,13 +1538,28 @@ static void i40e_get_wol(struct net_device *netdev, } } +/** + * i40e_set_wol - set the WakeOnLAN configuration + * @netdev: the netdev in question + * @wol: the ethtool WoL setting data + **/ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; + struct i40e_vsi *vsi = np->vsi; struct i40e_hw *hw = &pf->hw; u16 wol_nvm_bits; + /* WoL not supported if this isn't the controlling PF on the port */ + if (hw->partition_id != 1) { + i40e_partition_setting_complaint(pf); + return -EOPNOTSUPP; + } + + if (vsi != pf->vsi[pf->lan_vsi]) + return -EOPNOTSUPP; + /* NVM bit on means WoL disabled for the port */ i40e_read_nvm_word(hw, I40E_SR_NVM_WAKE_ON_LAN, &wol_nvm_bits); if (((1 << hw->port) & wol_nvm_bits)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c index a8b8bd95108d..27c206e62da7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c +++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c @@ -39,15 +39,6 @@ #include "i40e_fcoe.h" /** - * i40e_rx_is_fip - returns true if the rx packet type is FIP - * @ptype: the packet type field from rx descriptor write-back - **/ -static inline bool i40e_rx_is_fip(u16 ptype) -{ - return ptype == I40E_RX_PTYPE_L2_FIP_PAY2; -} - -/** * i40e_rx_is_fcoe - returns true if the rx packet type is FCoE * @ptype: the packet type field from rx descriptor write-back **/ @@ -404,6 +395,7 @@ int i40e_fcoe_vsi_init(struct i40e_vsi *vsi, struct i40e_vsi_context *ctxt) I40E_AQ_VSI_PROP_INGRESS_UP_VALID | I40E_AQ_VSI_PROP_EGRESS_UP_VALID)); + info->switch_id = cpu_to_le16(I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB); enabled_tc = i40e_get_fcoe_tc_map(pf); i40e_vsi_setup_queue_map(vsi, ctxt, enabled_tc, true); @@ -1511,12 +1503,16 @@ void i40e_fcoe_config_netdev(struct net_device *netdev, struct i40e_vsi *vsi) strlcpy(netdev->name, "fcoe%d", IFNAMSIZ-1); netdev->mtu = FCOE_MTU; SET_NETDEV_DEV(netdev, &pf->pdev->dev); + /* set different dev_port value 1 for FCoE netdev than the default + * zero dev_port value for PF netdev, this helps biosdevname user + * tool to differentiate them correctly while both attached to the + * same PCI function. + */ + netdev->dev_port = 1; i40e_add_filter(vsi, hw->mac.san_addr, 0, false, false); i40e_add_filter(vsi, (u8[6]) FC_FCOE_FLOGI_MAC, 0, false, false); i40e_add_filter(vsi, FIP_ALL_FCOE_MACS, 0, false, false); i40e_add_filter(vsi, FIP_ALL_ENODE_MACS, 0, false, false); - i40e_add_filter(vsi, FIP_ALL_VN2VN_MACS, 0, false, false); - i40e_add_filter(vsi, FIP_ALL_P2P_MACS, 0, false, false); /* use san mac */ ether_addr_copy(netdev->dev_addr, hw->mac.san_addr); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index a5f2660d552d..cbe281be1c9f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,7 +39,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 2 -#define DRV_VERSION_BUILD 2 +#define DRV_VERSION_BUILD 6 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -2819,8 +2819,9 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) * i40e_enable_misc_int_causes - enable the non-queue interrupts * @hw: ptr to the hardware info **/ -static void i40e_enable_misc_int_causes(struct i40e_hw *hw) +static void i40e_enable_misc_int_causes(struct i40e_pf *pf) { + struct i40e_hw *hw = &pf->hw; u32 val; /* clear things first */ @@ -2832,11 +2833,13 @@ static void i40e_enable_misc_int_causes(struct i40e_hw *hw) I40E_PFINT_ICR0_ENA_GRST_MASK | I40E_PFINT_ICR0_ENA_PCI_EXCEPTION_MASK | I40E_PFINT_ICR0_ENA_GPIO_MASK | - I40E_PFINT_ICR0_ENA_TIMESYNC_MASK | I40E_PFINT_ICR0_ENA_HMC_ERR_MASK | I40E_PFINT_ICR0_ENA_VFLR_MASK | I40E_PFINT_ICR0_ENA_ADMINQ_MASK; + if (pf->flags & I40E_FLAG_PTP) + val |= I40E_PFINT_ICR0_ENA_TIMESYNC_MASK; + wr32(hw, I40E_PFINT_ICR0_ENA, val); /* SW_ITR_IDX = 0, but don't change INTENA */ @@ -2866,7 +2869,7 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi) q_vector->tx.latency_range = I40E_LOW_LATENCY; wr32(hw, I40E_PFINT_ITR0(I40E_TX_ITR), q_vector->tx.itr); - i40e_enable_misc_int_causes(hw); + i40e_enable_misc_int_causes(pf); /* FIRSTQ_INDX = 0, FIRSTQ_TYPE = 0 (rx) */ wr32(hw, I40E_PFINT_LNKLST0, 0); @@ -2937,7 +2940,7 @@ void i40e_irq_dynamic_enable(struct i40e_vsi *vsi, int vector) /** * i40e_irq_dynamic_disable - Disable default interrupt generation settings * @vsi: pointer to a vsi - * @vector: enable a particular Hw Interrupt vector + * @vector: disable a particular Hw Interrupt vector **/ void i40e_irq_dynamic_disable(struct i40e_vsi *vsi, int vector) { @@ -3402,10 +3405,10 @@ static int i40e_vsi_request_irq(struct i40e_vsi *vsi, char *basename) err = i40e_vsi_request_irq_msix(vsi, basename); else if (pf->flags & I40E_FLAG_MSI_ENABLED) err = request_irq(pf->pdev->irq, i40e_intr, 0, - pf->misc_int_name, pf); + pf->int_name, pf); else err = request_irq(pf->pdev->irq, i40e_intr, IRQF_SHARED, - pf->misc_int_name, pf); + pf->int_name, pf); if (err) dev_info(&pf->pdev->dev, "request_irq failed, Error %d\n", err); @@ -3999,6 +4002,35 @@ static int i40e_pf_wait_txq_disabled(struct i40e_pf *pf) #endif /** + * i40e_get_iscsi_tc_map - Return TC map for iSCSI APP + * @pf: pointer to pf + * + * Get TC map for ISCSI PF type that will include iSCSI TC + * and LAN TC. + **/ +static u8 i40e_get_iscsi_tc_map(struct i40e_pf *pf) +{ + struct i40e_dcb_app_priority_table app; + struct i40e_hw *hw = &pf->hw; + u8 enabled_tc = 1; /* TC0 is always enabled */ + u8 tc, i; + /* Get the iSCSI APP TLV */ + struct i40e_dcbx_config *dcbcfg = &hw->local_dcbx_config; + + for (i = 0; i < dcbcfg->numapps; i++) { + app = dcbcfg->app[i]; + if (app.selector == I40E_APP_SEL_TCPIP && + app.protocolid == I40E_APP_PROTOID_ISCSI) { + tc = dcbcfg->etscfg.prioritytable[app.priority]; + enabled_tc |= (1 << tc); + break; + } + } + + return enabled_tc; +} + +/** * i40e_dcb_get_num_tc - Get the number of TCs from DCBx config * @dcbcfg: the corresponding DCBx configuration structure * @@ -4061,18 +4093,23 @@ static u8 i40e_pf_get_num_tc(struct i40e_pf *pf) if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return 1; + /* SFP mode will be enabled for all TCs on port */ + if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) + return i40e_dcb_get_num_tc(dcbcfg); + /* MFP mode return count of enabled TCs for this PF */ - if (pf->flags & I40E_FLAG_MFP_ENABLED) { + if (pf->hw.func_caps.iscsi) + enabled_tc = i40e_get_iscsi_tc_map(pf); + else enabled_tc = pf->hw.func_caps.enabled_tcmap; - for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { - if (enabled_tc & (1 << i)) - num_tc++; - } - return num_tc; - } - /* SFP mode will be enabled for all TCs on port */ - return i40e_dcb_get_num_tc(dcbcfg); + /* At least have TC0 */ + enabled_tc = (enabled_tc ? enabled_tc : 0x1); + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (enabled_tc & (1 << i)) + num_tc++; + } + return num_tc; } /** @@ -4110,12 +4147,15 @@ static u8 i40e_pf_get_tc_map(struct i40e_pf *pf) if (!(pf->flags & I40E_FLAG_DCB_ENABLED)) return i40e_pf_get_default_tc(pf); - /* MFP mode will have enabled TCs set by FW */ - if (pf->flags & I40E_FLAG_MFP_ENABLED) - return pf->hw.func_caps.enabled_tcmap; - /* SFP mode we want PF to be enabled for all TCs */ - return i40e_dcb_get_enabled_tc(&pf->hw.local_dcbx_config); + if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) + return i40e_dcb_get_enabled_tc(&pf->hw.local_dcbx_config); + + /* MPF enabled and iSCSI PF type */ + if (pf->hw.func_caps.iscsi) + return i40e_get_iscsi_tc_map(pf); + else + return pf->hw.func_caps.enabled_tcmap; } /** @@ -4505,9 +4545,6 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) struct i40e_hw *hw = &pf->hw; int err = 0; - if (pf->hw.func_caps.npar_enable) - goto out; - /* Get the initial DCB configuration */ err = i40e_init_dcb(hw); if (!err) { @@ -4533,7 +4570,8 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) "DCBX offload is supported for this PF.\n"); } } else { - dev_info(&pf->pdev->dev, "AQ Querying DCB configuration failed: %d\n", + dev_info(&pf->pdev->dev, + "AQ Querying DCB configuration failed: aq_err %d\n", pf->hw.aq.asq_last_status); } @@ -4557,6 +4595,15 @@ static void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) return; } + /* Warn user if link speed on NPAR enabled partition is not at + * least 10GB + */ + if (vsi->back->hw.func_caps.npar_enable && + (vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_1GB || + vsi->back->hw.phy.link_info.link_speed == I40E_LINK_SPEED_100MB)) + netdev_warn(vsi->netdev, + "The partition detected link speed that is less than 10Gbps\n"); + switch (vsi->back->hw.phy.link_info.link_speed) { case I40E_LINK_SPEED_40GB: strlcpy(speed, "40 Gbps", SPEED_SIZE); @@ -4836,7 +4883,7 @@ static int i40e_open(struct net_device *netdev) int i40e_vsi_open(struct i40e_vsi *vsi) { struct i40e_pf *pf = vsi->back; - char int_name[IFNAMSIZ]; + char int_name[I40E_INT_NAME_STR_LEN]; int err; /* allocate descriptors */ @@ -4870,7 +4917,7 @@ int i40e_vsi_open(struct i40e_vsi *vsi) goto err_set_queues; } else if (vsi->type == I40E_VSI_FDIR) { - snprintf(int_name, sizeof(int_name) - 1, "%s-%s-fdir", + snprintf(int_name, sizeof(int_name) - 1, "%s-%s:fdir", dev_driver_string(&pf->pdev->dev), dev_name(&pf->pdev->dev)); err = i40e_vsi_request_irq(vsi, int_name); @@ -5494,14 +5541,18 @@ static void i40e_link_event(struct i40e_pf *pf) { bool new_link, old_link; struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; + u8 new_link_speed, old_link_speed; /* set this to force the get_link_status call to refresh state */ pf->hw.phy.get_link_info = true; old_link = (pf->hw.phy.link_info_old.link_info & I40E_AQ_LINK_UP); new_link = i40e_get_link_status(&pf->hw); + old_link_speed = pf->hw.phy.link_info_old.link_speed; + new_link_speed = pf->hw.phy.link_info.link_speed; if (new_link == old_link && + new_link_speed == old_link_speed && (test_bit(__I40E_DOWN, &vsi->state) || new_link == netif_carrier_ok(vsi->netdev))) return; @@ -6175,8 +6226,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit) #ifdef CONFIG_I40E_DCB ret = i40e_init_pf_dcb(pf); if (ret) { - dev_info(&pf->pdev->dev, "init_pf_dcb failed: %d\n", ret); - goto end_core_reset; + dev_info(&pf->pdev->dev, "DCB init failed %d, disabled\n", ret); + pf->flags &= ~I40E_FLAG_DCB_CAPABLE; + /* Continue without DCB enabled */ } #endif /* CONFIG_I40E_DCB */ #ifdef I40E_FCOE @@ -6881,17 +6933,17 @@ static int i40e_init_msix(struct i40e_pf *pf) if (pf->flags & I40E_FLAG_FD_SB_ENABLED) other_vecs++; + /* Scale down if necessary, and the rings will share vectors */ + pf->num_lan_msix = min_t(int, pf->num_lan_msix, + (hw->func_caps.num_msix_vectors - other_vecs)); + v_budget = pf->num_lan_msix + other_vecs; + #ifdef I40E_FCOE if (pf->flags & I40E_FLAG_FCOE_ENABLED) { pf->num_fcoe_msix = pf->num_fcoe_qps; v_budget += pf->num_fcoe_msix; } - #endif - /* Scale down if necessary, and the rings will share vectors */ - pf->num_lan_msix = min_t(int, pf->num_lan_msix, - (hw->func_caps.num_msix_vectors - other_vecs)); - v_budget = pf->num_lan_msix + other_vecs; pf->msix_entries = kcalloc(v_budget, sizeof(struct msix_entry), GFP_KERNEL); @@ -7113,16 +7165,16 @@ static int i40e_setup_misc_vector(struct i40e_pf *pf) */ if (!test_bit(__I40E_RESET_RECOVERY_PENDING, &pf->state)) { err = request_irq(pf->msix_entries[0].vector, - i40e_intr, 0, pf->misc_int_name, pf); + i40e_intr, 0, pf->int_name, pf); if (err) { dev_info(&pf->pdev->dev, "request_irq for %s failed: %d\n", - pf->misc_int_name, err); + pf->int_name, err); return -EFAULT; } } - i40e_enable_misc_int_causes(hw); + i40e_enable_misc_int_causes(pf); /* associate no queues to the misc vector */ wr32(hw, I40E_PFINT_LNKLST0, I40E_QUEUE_END_OF_LIST); @@ -7306,7 +7358,7 @@ static int i40e_sw_init(struct i40e_pf *pf) #endif /* I40E_FCOE */ #ifdef CONFIG_PCI_IOV - if (pf->hw.func_caps.num_vfs) { + if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) { pf->num_vf_qps = I40E_DEFAULT_QUEUES_PER_VF; pf->flags |= I40E_FLAG_SRIOV_ENABLED; pf->num_req_vfs = min_t(int, @@ -7766,7 +7818,8 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) enabled_tc = i40e_pf_get_tc_map(pf); /* MFP mode setup queue map and update VSI */ - if (pf->flags & I40E_FLAG_MFP_ENABLED) { + if ((pf->flags & I40E_FLAG_MFP_ENABLED) && + !(pf->hw.func_caps.iscsi)) { /* NIC type PF */ memset(&ctxt, 0, sizeof(ctxt)); ctxt.seid = pf->main_vsi_seid; ctxt.pf_num = pf->hw.pf_id; @@ -7787,6 +7840,8 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) /* Default/Main VSI is only enabled for TC0 * reconfigure it to enable all TCs that are * available on the port in SFP mode. + * For MFP case the iSCSI PF would use this + * flow to enable LAN+iSCSI TC. */ ret = i40e_vsi_config_tc(vsi, enabled_tc); if (ret) { @@ -9164,7 +9219,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->aq.asq_buf_size = I40E_MAX_AQ_BUF_SIZE; pf->adminq_work_limit = I40E_AQ_WORK_LIMIT; - snprintf(pf->misc_int_name, sizeof(pf->misc_int_name) - 1, + snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc", dev_driver_string(&pf->pdev->dev), dev_name(&pdev->dev)); @@ -9227,6 +9282,16 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_configure_lan_hmc; } + /* Disable LLDP for NICs that have firmware versions lower than v4.3. + * Ignore error return codes because if it was already disabled via + * hardware settings this will fail + */ + if (((pf->hw.aq.fw_maj_ver == 4) && (pf->hw.aq.fw_min_ver < 3)) || + (pf->hw.aq.fw_maj_ver < 4)) { + dev_info(&pdev->dev, "Stopping firmware LLDP agent.\n"); + i40e_aq_stop_lldp(hw, true, NULL); + } + i40e_get_mac_addr(hw, hw->mac.addr); if (!is_valid_ether_addr(hw->mac.addr)) { dev_info(&pdev->dev, "invalid MAC address %pM\n", hw->mac.addr); @@ -9256,7 +9321,7 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) #ifdef CONFIG_I40E_DCB err = i40e_init_pf_dcb(pf); if (err) { - dev_info(&pdev->dev, "init_pf_dcb failed: %d\n", err); + dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err); pf->flags &= ~I40E_FLAG_DCB_CAPABLE; /* Continue without DCB enabled */ } @@ -9671,6 +9736,8 @@ static int i40e_suspend(struct pci_dev *pdev, pm_message_t state) set_bit(__I40E_SUSPENDED, &pf->state); set_bit(__I40E_DOWN, &pf->state); + del_timer_sync(&pf->service_timer); + cancel_work_sync(&pf->service_task); rtnl_lock(); i40e_prep_for_reset(pf); rtnl_unlock(); diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 2fb4306597e8..68e852a96680 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -71,6 +71,9 @@ i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw, i40e_status i40e_aq_debug_write_register(struct i40e_hw *hw, u32 reg_addr, u64 reg_val, struct i40e_asq_cmd_details *cmd_details); +i40e_status i40e_aq_debug_read_register(struct i40e_hw *hw, + u32 reg_addr, u64 *reg_val, + struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, struct i40e_asq_cmd_details *cmd_details); i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw, u16 vsi_id, @@ -245,6 +248,8 @@ void i40e_clear_pxe_mode(struct i40e_hw *hw); bool i40e_get_link_status(struct i40e_hw *hw); i40e_status i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr); i40e_status i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr); +i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, + u32 pba_num_size); i40e_status i40e_validate_mac_addr(u8 *mac_addr); void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable); #ifdef I40E_FCOE diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 6d1ec926aa37..fabcfa1b45b2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -247,7 +247,12 @@ void i40e_ptp_rx_hang(struct i40e_vsi *vsi) u32 prttsyn_stat; int n; - if (!(pf->flags & I40E_FLAG_PTP)) + /* Since we cannot turn off the Rx timestamp logic if the device is + * configured for Tx timestamping, we check if Rx timestamping is + * configured. We don't want to spuriously warn about Rx timestamp + * hangs if we don't care about the timestamps. + */ + if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_rx) return; prttsyn_stat = rd32(hw, I40E_PRTTSYN_STAT_1); @@ -305,6 +310,13 @@ void i40e_ptp_tx_hwtstamp(struct i40e_pf *pf) u32 hi, lo; u64 ns; + if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_tx) + return; + + /* don't attempt to timestamp if we don't have an skb */ + if (!pf->ptp_tx_skb) + return; + lo = rd32(hw, I40E_PRTTSYN_TXTIME_L); hi = rd32(hw, I40E_PRTTSYN_TXTIME_H); @@ -338,7 +350,7 @@ void i40e_ptp_rx_hwtstamp(struct i40e_pf *pf, struct sk_buff *skb, u8 index) /* Since we cannot turn off the Rx timestamp logic if the device is * doing Tx timestamping, check if Rx timestamping is configured. */ - if (!pf->ptp_rx) + if (!(pf->flags & I40E_FLAG_PTP) || !pf->ptp_rx) return; hw = &pf->hw; @@ -467,7 +479,12 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: pf->ptp_rx = false; - tsyntype = 0; + /* We set the type to V1, but do not enable UDP packet + * recognition. In this way, we should be as close to + * disabling PTP Rx timestamps as possible since V1 packets + * are always UDP, since L2 packets are a V2 feature. + */ + tsyntype = I40E_PRTTSYN_CTL1_TSYNTYPE_V1; break; case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: @@ -521,17 +538,18 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, regval &= ~I40E_PFINT_ICR0_ENA_TIMESYNC_MASK; wr32(hw, I40E_PFINT_ICR0_ENA, regval); - /* There is no simple on/off switch for Rx. To "disable" Rx support, - * ignore any received timestamps, rather than turn off the clock. + /* Although there is no simple on/off switch for Rx, we "disable" Rx + * timestamps by setting to V1 only mode and clear the UDP + * recognition. This ought to disable all PTP Rx timestamps as V1 + * packets are always over UDP. Note that software is configured to + * ignore Rx timestamps via the pf->ptp_rx flag. */ - if (pf->ptp_rx) { - regval = rd32(hw, I40E_PRTTSYN_CTL1); - /* clear everything but the enable bit */ - regval &= I40E_PRTTSYN_CTL1_TSYNENA_MASK; - /* now enable bits for desired Rx timestamps */ - regval |= tsyntype; - wr32(hw, I40E_PRTTSYN_CTL1, regval); - } + regval = rd32(hw, I40E_PRTTSYN_CTL1); + /* clear everything but the enable bit */ + regval &= I40E_PRTTSYN_CTL1_TSYNENA_MASK; + /* now enable bits for desired Rx timestamps */ + regval |= tsyntype; + wr32(hw, I40E_PRTTSYN_CTL1, regval); return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index cecb340898fe..2206d2d36f0f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -836,8 +836,8 @@ static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { u32 val = I40E_PFINT_DYN_CTLN_INTENA_MASK | I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK | - I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK - /* allow 00 to be written to the index */; + I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK; + /* allow 00 to be written to the index */ wr32(&vsi->back->hw, I40E_PFINT_DYN_CTLN(q_vector->v_idx + vsi->base_vector - 1), @@ -1098,6 +1098,8 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) goto err; + u64_stats_init(&rx_ring->syncp); + /* Round up to nearest 4K */ rx_ring->size = ring_is_16byte_desc_enabled(rx_ring) ? rx_ring->count * sizeof(union i40e_16byte_rx_desc) @@ -1815,8 +1817,8 @@ static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, u32 tx_flags = 0; /* if we have a HW VLAN tag being added, default to the HW one */ - if (vlan_tx_tag_present(skb)) { - tx_flags |= vlan_tx_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT; + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT; tx_flags |= I40E_TX_FLAGS_HW_VLAN; /* else if it is a SW VLAN, check the next protocol and store the tag */ } else if (protocol == htons(ETH_P_8021Q)) { @@ -1939,6 +1941,9 @@ static int i40e_tsyn(struct i40e_ring *tx_ring, struct sk_buff *skb, * we are not already transmitting a packet to be timestamped */ pf = i40e_netdev_to_pf(tx_ring->netdev); + if (!(pf->flags & I40E_FLAG_PTP)) + return 0; + if (pf->ptp_tx && !test_and_set_bit_lock(__I40E_PTP_TX_IN_PROGRESS, &pf->state)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index c1f2eb963357..e9901ef06a63 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -211,6 +211,7 @@ struct i40e_hw_capabilities { bool evb_802_1_qbh; /* Bridge Port Extension */ bool dcb; bool fcoe; + bool iscsi; /* Indicates iSCSI enabled */ bool mfp_mode_1; bool mgmt_cem; bool ieee_1588; @@ -431,7 +432,7 @@ struct i40e_hw { u8 __iomem *hw_addr; void *back; - /* function pointer structs */ + /* subsystem structs */ struct i40e_phy_info phy; struct i40e_mac_info mac; struct i40e_bus_info bus; @@ -458,6 +459,11 @@ struct i40e_hw { u8 pf_id; u16 main_vsi_seid; + /* for multi-function MACs */ + u16 partition_id; + u16 num_partitions; + u16 num_ports; + /* Closest numa node to the device */ u16 numa_node; @@ -1135,6 +1141,8 @@ struct i40e_hw_port_stats { /* Checksum and Shadow RAM pointers */ #define I40E_SR_NVM_CONTROL_WORD 0x00 #define I40E_SR_EMP_MODULE_PTR 0x0F +#define I40E_SR_PBA_FLAGS 0x15 +#define I40E_SR_PBA_BLOCK_PTR 0x16 #define I40E_SR_NVM_IMAGE_VERSION 0x18 #define I40E_SR_NVM_WAKE_ON_LAN 0x19 #define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR 0x27 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 5bae89550657..40f042af4131 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -647,6 +647,9 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) int i; u32 reg; + if (test_and_set_bit(__I40E_VF_DISABLE, &pf->state)) + return; + /* warn the VF */ clear_bit(I40E_VF_STAT_ACTIVE, &vf->vf_states); @@ -668,13 +671,13 @@ void i40e_reset_vf(struct i40e_vf *vf, bool flr) /* poll VPGEN_VFRSTAT reg to make sure * that reset is complete */ - for (i = 0; i < 100; i++) { - /* vf reset requires driver to first reset the - * vf and then poll the status register to make sure - * that the requested op was completed - * successfully + for (i = 0; i < 10; i++) { + /* VF reset requires driver to first reset the VF and then + * poll the status register to make sure that the reset + * completed successfully. Due to internal HW FIFO flushes, + * we must wait 10ms before the register will be valid. */ - usleep_range(10, 20); + usleep_range(10000, 20000); reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id)); if (reg & I40E_VPGEN_VFRSTAT_VFRD_MASK) { rsd = true; @@ -706,6 +709,7 @@ complete_reset: /* tell the VF the reset is done */ wr32(hw, I40E_VFGEN_RSTAT1(vf->vf_id), I40E_VFR_VFACTIVE); i40e_flush(hw); + clear_bit(__I40E_VF_DISABLE, &pf->state); } /** @@ -790,11 +794,18 @@ void i40e_free_vfs(struct i40e_pf *pf) if (!pf->vf) return; + while (test_and_set_bit(__I40E_VF_DISABLE, &pf->state)) + usleep_range(1000, 2000); - /* Disable interrupt 0 so we don't try to handle the VFLR. */ - i40e_irq_dynamic_disable_icr0(pf); + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); + + msleep(20); /* let any messages in transit get finished up */ - mdelay(10); /* let any messages in transit get finished up */ /* free up vf resources */ tmp = pf->num_alloc_vfs; pf->num_alloc_vfs = 0; @@ -813,7 +824,6 @@ void i40e_free_vfs(struct i40e_pf *pf) * before this function ever gets called. */ if (!pci_vfs_assigned(pf->pdev)) { - pci_disable_sriov(pf->pdev); /* Acknowledge VFLR for all VFS. Without this, VFs will fail to * work correctly when SR-IOV gets re-enabled. */ @@ -827,9 +837,7 @@ void i40e_free_vfs(struct i40e_pf *pf) dev_warn(&pf->pdev->dev, "unable to disable SR-IOV because VFs are assigned.\n"); } - - /* Re-enable interrupt 0. */ - i40e_irq_dynamic_enable_icr0(pf); + clear_bit(__I40E_VF_DISABLE, &pf->state); } #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h index 6c31bf22c2c3..60f04e96a80e 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h @@ -148,7 +148,7 @@ static inline int i40e_aq_rc_to_posix(u32 aq_ret, u16 aq_rc) /* general information */ #define I40E_AQ_LARGE_BUF 512 -#define I40E_ASQ_CMD_TIMEOUT 100 /* msecs */ +#define I40E_ASQ_CMD_TIMEOUT 250 /* msecs */ void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index ff1b16370da9..e715bccfb5d2 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -268,6 +268,8 @@ enum i40e_admin_queue_opc { /* OEM commands */ i40e_aqc_opc_oem_parameter_change = 0xFE00, i40e_aqc_opc_oem_device_status_change = 0xFE01, + i40e_aqc_opc_oem_ocsd_initialize = 0xFE02, + i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, /* debug commands */ i40e_aqc_opc_debug_get_deviceid = 0xFF00, @@ -276,7 +278,6 @@ enum i40e_admin_queue_opc { i40e_aqc_opc_debug_write_reg = 0xFF04, i40e_aqc_opc_debug_modify_reg = 0xFF07, i40e_aqc_opc_debug_dump_internals = 0xFF08, - i40e_aqc_opc_debug_modify_internals = 0xFF09, }; /* command structures and indirect data structures */ @@ -410,6 +411,7 @@ struct i40e_aqc_list_capabilities_element_resp { #define I40E_AQ_CAP_ID_VSI 0x0017 #define I40E_AQ_CAP_ID_DCB 0x0018 #define I40E_AQ_CAP_ID_FCOE 0x0021 +#define I40E_AQ_CAP_ID_ISCSI 0x0022 #define I40E_AQ_CAP_ID_RSS 0x0040 #define I40E_AQ_CAP_ID_RXQ 0x0041 #define I40E_AQ_CAP_ID_TXQ 0x0042 @@ -454,8 +456,11 @@ struct i40e_aqc_arp_proxy_data { __le32 pfpm_proxyfc; __le32 ip_addr; u8 mac_addr[6]; + u8 reserved[2]; }; +I40E_CHECK_STRUCT_LEN(0x14, i40e_aqc_arp_proxy_data); + /* Set NS Proxy Table Entry Command (indirect 0x0105) */ struct i40e_aqc_ns_proxy_data { __le16 table_idx_mac_addr_0; @@ -481,6 +486,8 @@ struct i40e_aqc_ns_proxy_data { u8 ipv6_addr_1[16]; }; +I40E_CHECK_STRUCT_LEN(0x3c, i40e_aqc_ns_proxy_data); + /* Manage LAA Command (0x0106) - obsolete */ struct i40e_aqc_mng_laa { __le16 command_flags; @@ -491,6 +498,8 @@ struct i40e_aqc_mng_laa { u8 reserved2[6]; }; +I40E_CHECK_CMD_LENGTH(i40e_aqc_mng_laa); + /* Manage MAC Address Read Command (indirect 0x0107) */ struct i40e_aqc_mac_address_read { __le16 command_flags; @@ -562,6 +571,8 @@ struct i40e_aqc_get_switch_config_header_resp { u8 reserved[12]; }; +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_config_header_resp); + struct i40e_aqc_switch_config_element_resp { u8 element_type; #define I40E_AQ_SW_ELEM_TYPE_MAC 1 @@ -587,6 +598,8 @@ struct i40e_aqc_switch_config_element_resp { __le16 element_info; }; +I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_config_element_resp); + /* Get Switch Configuration (indirect 0x0200) * an array of elements are returned in the response buffer * the first in the array is the header, remainder are elements @@ -596,6 +609,8 @@ struct i40e_aqc_get_switch_config_resp { struct i40e_aqc_switch_config_element_resp element[1]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_switch_config_resp); + /* Add Statistics (direct 0x0201) * Remove Statistics (direct 0x0202) */ @@ -661,6 +676,8 @@ struct i40e_aqc_switch_resource_alloc_element_resp { u8 reserved2[6]; }; +I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); + /* Add VSI (indirect 0x0210) * this indirect command uses struct i40e_aqc_vsi_properties_data * as the indirect buffer (128 bytes) @@ -1092,6 +1109,8 @@ struct i40e_aqc_remove_tag { u8 reserved[12]; }; +I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_tag); + /* Add multicast E-Tag (direct 0x0257) * del multicast E-Tag (direct 0x0258) only uses pv_seid and etag fields * and no external data @@ -1207,7 +1226,7 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { } ipaddr; __le16 flags; #define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \ +#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \ I40E_AQC_ADD_CLOUD_FILTER_SHIFT) /* 0x0000 reserved */ #define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001 @@ -1240,7 +1259,7 @@ struct i40e_aqc_add_remove_cloud_filters_element_data { u8 reserved[4]; __le16 queue_number; #define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x3F << \ +#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x7FF << \ I40E_AQC_ADD_CLOUD_QUEUE_SHIFT) u8 reserved2[14]; /* response section */ @@ -1359,6 +1378,8 @@ struct i40e_aqc_configure_vsi_ets_sla_bw_data { u8 reserved1[28]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_configure_vsi_ets_sla_bw_data); + /* Configure VSI Bandwidth Allocation per Traffic Type (indirect 0x0407) * responds with i40e_aqc_qs_handles_resp */ @@ -1370,6 +1391,8 @@ struct i40e_aqc_configure_vsi_tc_bw_data { __le16 qs_handles[8]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_vsi_tc_bw_data); + /* Query vsi bw configuration (indirect 0x0408) */ struct i40e_aqc_query_vsi_bw_config_resp { u8 tc_valid_bits; @@ -1383,6 +1406,8 @@ struct i40e_aqc_query_vsi_bw_config_resp { u8 reserved3[23]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_vsi_bw_config_resp); + /* Query VSI Bandwidth Allocation per Traffic Type (indirect 0x040A) */ struct i40e_aqc_query_vsi_ets_sla_config_resp { u8 tc_valid_bits; @@ -1394,6 +1419,8 @@ struct i40e_aqc_query_vsi_ets_sla_config_resp { __le16 tc_bw_max[2]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_vsi_ets_sla_config_resp); + /* Configure Switching Component Bandwidth Limit (direct 0x0410) */ struct i40e_aqc_configure_switching_comp_bw_limit { __le16 seid; @@ -1421,6 +1448,8 @@ struct i40e_aqc_configure_switching_comp_ets_data { u8 reserved2[96]; }; +I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_configure_switching_comp_ets_data); + /* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */ struct i40e_aqc_configure_switching_comp_ets_bw_limit_data { u8 tc_valid_bits; @@ -1432,6 +1461,9 @@ struct i40e_aqc_configure_switching_comp_ets_bw_limit_data { u8 reserved1[28]; }; +I40E_CHECK_STRUCT_LEN(0x40, + i40e_aqc_configure_switching_comp_ets_bw_limit_data); + /* Configure Switching Component Bandwidth Allocation per Tc * (indirect 0x0417) */ @@ -1443,6 +1475,8 @@ struct i40e_aqc_configure_switching_comp_bw_config_data { u8 reserved1[20]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_switching_comp_bw_config_data); + /* Query Switching Component Configuration (indirect 0x0418) */ struct i40e_aqc_query_switching_comp_ets_config_resp { u8 tc_valid_bits; @@ -1453,6 +1487,8 @@ struct i40e_aqc_query_switching_comp_ets_config_resp { u8 reserved2[23]; }; +I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_switching_comp_ets_config_resp); + /* Query PhysicalPort ETS Configuration (indirect 0x0419) */ struct i40e_aqc_query_port_ets_config_resp { u8 reserved[4]; @@ -1468,6 +1504,8 @@ struct i40e_aqc_query_port_ets_config_resp { u8 reserved3[32]; }; +I40E_CHECK_STRUCT_LEN(0x44, i40e_aqc_query_port_ets_config_resp); + /* Query Switching Component Bandwidth Allocation per Traffic Type * (indirect 0x041A) */ @@ -1482,6 +1520,8 @@ struct i40e_aqc_query_switching_comp_bw_config_resp { __le16 tc_bw_max[2]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_switching_comp_bw_config_resp); + /* Suspend/resume port TX traffic * (direct 0x041B and 0x041C) uses the generic SEID struct */ @@ -1495,6 +1535,8 @@ struct i40e_aqc_configure_partition_bw_data { u8 max_bw[16]; /* bandwidth limit */ }; +I40E_CHECK_STRUCT_LEN(0x22, i40e_aqc_configure_partition_bw_data); + /* Get and set the active HMC resource profile and status. * (direct 0x0500) and (direct 0x0501) */ @@ -1577,6 +1619,8 @@ struct i40e_aqc_module_desc { u8 reserved2[8]; }; +I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_module_desc); + struct i40e_aq_get_phy_abilities_resp { __le32 phy_type; /* bitmap using the above enum for offsets */ u8 link_speed; /* bitmap using the above enum bit patterns */ @@ -1605,6 +1649,8 @@ struct i40e_aq_get_phy_abilities_resp { struct i40e_aqc_module_desc qualified_module[I40E_AQ_PHY_MAX_QMS]; }; +I40E_CHECK_STRUCT_LEN(0x218, i40e_aq_get_phy_abilities_resp); + /* Set PHY Config (direct 0x0601) */ struct i40e_aq_set_phy_config { /* same bits as above in all */ __le32 phy_type; @@ -1788,12 +1834,12 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update); /* NVM Config Read (indirect 0x0704) */ struct i40e_aqc_nvm_config_read { __le16 cmd_flags; -#define ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK 1 -#define ANVM_READ_SINGLE_FEATURE 0 -#define ANVM_READ_MULTIPLE_FEATURES 1 +#define I40E_AQ_ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK 1 +#define I40E_AQ_ANVM_READ_SINGLE_FEATURE 0 +#define I40E_AQ_ANVM_READ_MULTIPLE_FEATURES 1 __le16 element_count; - __le16 element_id; /* Feature/field ID */ - u8 reserved[2]; + __le16 element_id; /* Feature/field ID */ + __le16 element_id_msw; /* MSWord of field ID */ __le32 address_high; __le32 address_low; }; @@ -1811,21 +1857,32 @@ struct i40e_aqc_nvm_config_write { I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write); +/* Used for 0x0704 as well as for 0x0705 commands */ +#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT 1 +#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_MASK \ + (1 << I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT) +#define I40E_AQ_ANVM_FEATURE 0 +#define I40E_AQ_ANVM_IMMEDIATE_FIELD (1 << FEATURE_OR_IMMEDIATE_SHIFT) struct i40e_aqc_nvm_config_data_feature { __le16 feature_id; - __le16 instance_id; +#define I40E_AQ_ANVM_FEATURE_OPTION_OEM_ONLY 0x01 +#define I40E_AQ_ANVM_FEATURE_OPTION_DWORD_MAP 0x08 +#define I40E_AQ_ANVM_FEATURE_OPTION_POR_CSR 0x10 __le16 feature_options; __le16 feature_selection; }; +I40E_CHECK_STRUCT_LEN(0x6, i40e_aqc_nvm_config_data_feature); + struct i40e_aqc_nvm_config_data_immediate_field { -#define ANVM_FEATURE_OR_IMMEDIATE_MASK 0x2 - __le16 field_id; - __le16 instance_id; + __le32 field_id; + __le32 field_value; __le16 field_options; - __le16 field_value; + __le16 reserved; }; +I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field); + /* Send to PF command (indirect 0x0801) id is only used by PF * Send to VF command (indirect 0x0802) id is only used by PF * Send to Peer PF command (indirect 0x0803) @@ -2082,7 +2139,8 @@ struct i40e_aqc_oem_param_change { #define I40E_AQ_OEM_PARAM_TYPE_BW_CTL 1 #define I40E_AQ_OEM_PARAM_MAC 2 __le32 param_value1; - u8 param_value2[8]; + __le16 param_value2; + u8 reserved[6]; }; I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change); @@ -2096,6 +2154,28 @@ struct i40e_aqc_oem_state_change { I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_state_change); +/* Initialize OCSD (0xFE02, direct) */ +struct i40e_aqc_opc_oem_ocsd_initialize { + u8 type_status; + u8 reserved1[3]; + __le32 ocsd_memory_block_addr_high; + __le32 ocsd_memory_block_addr_low; + __le32 requested_update_interval; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocsd_initialize); + +/* Initialize OCBB (0xFE03, direct) */ +struct i40e_aqc_opc_oem_ocbb_initialize { + u8 type_status; + u8 reserved1[3]; + __le32 ocbb_memory_block_addr_high; + __le32 ocbb_memory_block_addr_low; + u8 reserved2[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocbb_initialize); + /* debug commands */ /* get device id (0xFF00) uses the generic structure */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 04c7c1557a0c..29004382f462 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -192,6 +192,8 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring) return le32_to_cpu(*(volatile __le32 *)head); } +#define WB_STRIDE 0x3 + /** * i40e_clean_tx_irq - Reclaim resources after transmit completes * @tx_ring: tx ring to clean @@ -293,6 +295,14 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; + if (budget && + !((i & WB_STRIDE) == WB_STRIDE) && + !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && + (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + tx_ring->arm_wb = true; + else + tx_ring->arm_wb = false; + if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) { /* schedule immediate reset if we believe we hung */ dev_info(tx_ring->dev, "Detected Tx Unit Hang\n" @@ -344,6 +354,24 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) } /** + * i40e_force_wb -Arm hardware to do a wb on noncache aligned descriptors + * @vsi: the VSI we care about + * @q_vector: the vector on which to force writeback + * + **/ +static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +{ + u32 val = I40E_VFINT_DYN_CTLN_INTENA_MASK | + I40E_VFINT_DYN_CTLN_SWINT_TRIG_MASK | + I40E_VFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK; + /* allow 00 to be written to the index */ + + wr32(&vsi->back->hw, + I40E_VFINT_DYN_CTLN1(q_vector->v_idx + vsi->base_vector - 1), + val); +} + +/** * i40e_set_new_dynamic_itr - Find new ITR level * @rc: structure containing ring performance data * @@ -568,6 +596,8 @@ int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) goto err; + u64_stats_init(&rx_ring->syncp); + /* Round up to nearest 4K */ rx_ring->size = ring_is_16byte_desc_enabled(rx_ring) ? rx_ring->count * sizeof(union i40e_16byte_rx_desc) @@ -1065,6 +1095,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) struct i40e_vsi *vsi = q_vector->vsi; struct i40e_ring *ring; bool clean_complete = true; + bool arm_wb = false; int budget_per_ring; if (test_bit(__I40E_DOWN, &vsi->state)) { @@ -1075,8 +1106,10 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ - i40e_for_each_ring(ring, q_vector->tx) + i40e_for_each_ring(ring, q_vector->tx) { clean_complete &= i40e_clean_tx_irq(ring, vsi->work_limit); + arm_wb |= ring->arm_wb; + } /* We attempt to distribute budget to each Rx queue fairly, but don't * allow the budget to go below 1 because that would exit polling early. @@ -1087,8 +1120,11 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) clean_complete &= i40e_clean_rx_irq(ring, budget_per_ring); /* If work not completed, return budget and polling will return */ - if (!clean_complete) + if (!clean_complete) { + if (arm_wb) + i40e_force_wb(vsi, q_vector); return budget; + } /* Work is done so exit the polling mode and re-enable the interrupt */ napi_complete(napi); @@ -1122,8 +1158,8 @@ static int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, u32 tx_flags = 0; /* if we have a HW VLAN tag being added, default to the HW one */ - if (vlan_tx_tag_present(skb)) { - tx_flags |= vlan_tx_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT; + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT; tx_flags |= I40E_TX_FLAGS_HW_VLAN; /* else if it is a SW VLAN, check the next protocol and store the tag */ } else if (protocol == htons(ETH_P_8021Q)) { diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index c7f29626eada..4e15903b2b6d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -238,6 +238,7 @@ struct i40e_ring { u8 atr_count; bool ring_active; /* is ring online or not */ + bool arm_wb; /* do something to arm write back */ /* stats structs */ struct i40e_queue_stats stats; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 68aec11f6523..3d0fdaab5cc8 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -211,6 +211,7 @@ struct i40e_hw_capabilities { bool evb_802_1_qbh; /* Bridge Port Extension */ bool dcb; bool fcoe; + bool iscsi; /* Indicates iSCSI enabled */ bool mfp_mode_1; bool mgmt_cem; bool ieee_1588; @@ -425,7 +426,7 @@ struct i40e_hw { u8 __iomem *hw_addr; void *back; - /* function pointer structs */ + /* subsystem structs */ struct i40e_phy_info phy; struct i40e_mac_info mac; struct i40e_bus_info bus; @@ -452,6 +453,11 @@ struct i40e_hw { u8 pf_id; u16 main_vsi_seid; + /* for multi-function MACs */ + u16 partition_id; + u16 num_partitions; + u16 num_ports; + /* Closest numa node to the device */ u16 numa_node; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index cabaf599f562..8d8c201c63c1 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -36,7 +36,7 @@ char i40evf_driver_name[] = "i40evf"; static const char i40evf_driver_string[] = "Intel(R) XL710/X710 Virtual Function Network Driver"; -#define DRV_VERSION "1.0.6" +#define DRV_VERSION "1.2.0" const char i40evf_driver_version[] = DRV_VERSION; static const char i40evf_copyright[] = "Copyright (c) 2013 - 2014 Intel Corporation."; @@ -313,10 +313,6 @@ static irqreturn_t i40evf_msix_aq(int irq, void *data) val = val | I40E_PFINT_DYN_CTL0_CLEARPBA_MASK; wr32(hw, I40E_VFINT_DYN_CTL01, val); - /* re-enable interrupt causes */ - wr32(hw, I40E_VFINT_ICR0_ENA1, ena_mask); - wr32(hw, I40E_VFINT_DYN_CTL01, I40E_VFINT_DYN_CTL01_INTENA_MASK); - /* schedule work on the private workqueue */ schedule_work(&adapter->adminq_task); @@ -947,30 +943,6 @@ static int i40evf_up_complete(struct i40evf_adapter *adapter) } /** - * i40evf_clean_all_rx_rings - Free Rx Buffers for all queues - * @adapter: board private structure - **/ -static void i40evf_clean_all_rx_rings(struct i40evf_adapter *adapter) -{ - int i; - - for (i = 0; i < adapter->num_active_queues; i++) - i40evf_clean_rx_ring(adapter->rx_rings[i]); -} - -/** - * i40evf_clean_all_tx_rings - Free Tx Buffers for all queues - * @adapter: board private structure - **/ -static void i40evf_clean_all_tx_rings(struct i40evf_adapter *adapter) -{ - int i; - - for (i = 0; i < adapter->num_active_queues; i++) - i40evf_clean_tx_ring(adapter->tx_rings[i]); -} - -/** * i40e_down - Shutdown the connection processing * @adapter: board private structure **/ @@ -982,6 +954,12 @@ void i40evf_down(struct i40evf_adapter *adapter) if (adapter->state == __I40EVF_DOWN) return; + while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + &adapter->crit_section)) + usleep_range(500, 1000); + + i40evf_irq_disable(adapter); + /* remove all MAC filters */ list_for_each_entry(f, &adapter->mac_filter_list, list) { f->remove = true; @@ -992,25 +970,27 @@ void i40evf_down(struct i40evf_adapter *adapter) } if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) && adapter->state != __I40EVF_RESETTING) { - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; + /* cancel any current operation */ + adapter->current_op = I40E_VIRTCHNL_OP_UNKNOWN; + adapter->aq_pending = 0; + /* Schedule operations to close down the HW. Don't wait + * here for this to complete. The watchdog is still running + * and it will take care of this. + */ + adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER; adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; - /* disable receives */ adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; - mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); - msleep(20); } netif_tx_disable(netdev); netif_tx_stop_all_queues(netdev); - i40evf_irq_disable(adapter); - i40evf_napi_disable_all(adapter); - netif_carrier_off(netdev); + msleep(20); - i40evf_clean_all_tx_rings(adapter); - i40evf_clean_all_rx_rings(adapter); + netif_carrier_off(netdev); + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); } /** @@ -1356,8 +1336,13 @@ static void i40evf_watchdog_task(struct work_struct *work) /* Process admin queue tasks. After init, everything gets done * here so we don't race on the admin queue. */ - if (adapter->aq_pending) + if (adapter->aq_pending) { + if (!i40evf_asq_done(hw)) { + dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n"); + i40evf_send_api_ver(adapter); + } goto watchdog_done; + } if (adapter->aq_required & I40EVF_FLAG_AQ_MAP_VECTORS) { i40evf_map_queues(adapter); @@ -1401,11 +1386,14 @@ static void i40evf_watchdog_task(struct work_struct *work) if (adapter->state == __I40EVF_RUNNING) i40evf_request_stats(adapter); - - i40evf_irq_enable(adapter, true); - i40evf_fire_sw_int(adapter, 0xFF); - watchdog_done: + if (adapter->state == __I40EVF_RUNNING) { + i40evf_irq_enable_queues(adapter, ~0); + i40evf_fire_sw_int(adapter, 0xFF); + } else { + i40evf_fire_sw_int(adapter, 0x1); + } + clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); restart_watchdog: if (adapter->state == __I40EVF_REMOVE) @@ -1633,17 +1621,17 @@ static void i40evf_adminq_task(struct work_struct *work) u16 pending; if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) - return; + goto out; event.buf_len = I40EVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) - return; + goto out; v_msg = (struct i40e_virtchnl_msg *)&event.desc; do { ret = i40evf_clean_arq_element(hw, &event, &pending); - if (ret) + if (ret || !v_msg->v_opcode) break; /* No event to process or error cleaning ARQ */ i40evf_virtchnl_completion(adapter, v_msg->v_opcode, @@ -1688,10 +1676,10 @@ static void i40evf_adminq_task(struct work_struct *work) if (oldval != val) wr32(hw, hw->aq.asq.len, val); + kfree(event.msg_buf); +out: /* re-enable Admin queue interrupt cause */ i40evf_misc_irq_enable(adapter); - - kfree(event.msg_buf); } /** @@ -2053,12 +2041,8 @@ static void i40evf_init_task(struct work_struct *work) /* aq msg sent, awaiting reply */ err = i40evf_verify_api_ver(adapter); if (err) { - dev_info(&pdev->dev, "Unable to verify API version (%d), retrying\n", - err); - if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) { - dev_info(&pdev->dev, "Resending request\n"); + if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) err = i40evf_send_api_ver(adapter); - } goto err; } err = i40evf_send_vf_config_msg(adapter); @@ -2081,7 +2065,6 @@ static void i40evf_init_task(struct work_struct *work) } err = i40evf_get_vf_config(adapter); if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) { - dev_info(&pdev->dev, "Resending VF config request\n"); err = i40evf_send_vf_config_msg(adapter); goto err; } @@ -2230,12 +2213,18 @@ err: static void i40evf_shutdown(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); + struct i40evf_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); if (netif_running(netdev)) i40evf_close(netdev); + /* Prevent the watchdog from running. */ + adapter->state = __I40EVF_REMOVE; + adapter->aq_required = 0; + adapter->aq_pending = 0; + #ifdef CONFIG_PM pci_save_state(pdev); @@ -2448,7 +2437,18 @@ static void i40evf_remove(struct pci_dev *pdev) unregister_netdev(netdev); adapter->netdev_registered = false; } + + /* Shut down all the garbage mashers on the detention level */ adapter->state = __I40EVF_REMOVE; + adapter->aq_required = 0; + adapter->aq_pending = 0; + i40evf_request_reset(adapter); + msleep(20); + /* If the FW isn't responding, kick it once, but only once. */ + if (!i40evf_asq_done(hw)) { + i40evf_request_reset(adapter); + msleep(20); + } if (adapter->msix_entries) { i40evf_misc_irq_disable(adapter); @@ -2477,6 +2477,10 @@ static void i40evf_remove(struct pci_dev *pdev) list_del(&f->list); kfree(f); } + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + list_del(&f->list); + kfree(f); + } free_netdev(netdev); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 5fde5a7f4591..3f0c85ecbca6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -715,14 +715,14 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } return; } - if (v_opcode != adapter->current_op) - dev_info(&adapter->pdev->dev, "Pending op is %d, received %d\n", - adapter->current_op, v_opcode); if (v_retval) { dev_err(&adapter->pdev->dev, "%s: PF returned error %d to our request %d\n", __func__, v_retval, v_opcode); } switch (v_opcode) { + case I40E_VIRTCHNL_OP_VERSION: + /* no action, but also not an error */ + break; case I40E_VIRTCHNL_OP_GET_STATS: { struct i40e_eth_stats *stats = (struct i40e_eth_stats *)msg; diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 82d891e183b1..c2bd4f98a837 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -29,7 +29,7 @@ #include "e1000_mac.h" #include "e1000_82575.h" -#include <linux/clocksource.h> +#include <linux/timecounter.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> #include <linux/bitops.h> @@ -343,6 +343,9 @@ struct hwmon_buff { }; #endif +#define IGB_N_EXTTS 2 +#define IGB_N_PEROUT 2 +#define IGB_N_SDP 4 #define IGB_RETA_SIZE 128 /* board specific private data structure */ @@ -439,6 +442,12 @@ struct igb_adapter { u32 tx_hwtstamp_timeouts; u32 rx_hwtstamp_cleared; + struct ptp_pin_desc sdp_config[IGB_N_SDP]; + struct { + struct timespec start; + struct timespec period; + } perout[IGB_N_PEROUT]; + char fw_version[32]; #ifdef CONFIG_IGB_HWMON struct hwmon_buff *igb_hwmon_buff; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index ff59897a9463..f366b3b96d03 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -5035,9 +5035,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, skb_tx_timestamp(skb); - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { tx_flags |= IGB_TX_FLAGS_VLAN; - tx_flags |= (vlan_tx_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT); + tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT); } /* record initial flags and protocol */ @@ -5384,6 +5384,80 @@ void igb_update_stats(struct igb_adapter *adapter, } } +static void igb_tsync_interrupt(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + struct ptp_clock_event event; + struct timespec ts; + u32 ack = 0, tsauxc, sec, nsec, tsicr = rd32(E1000_TSICR); + + if (tsicr & TSINTR_SYS_WRAP) { + event.type = PTP_CLOCK_PPS; + if (adapter->ptp_caps.pps) + ptp_clock_event(adapter->ptp_clock, &event); + else + dev_err(&adapter->pdev->dev, "unexpected SYS WRAP"); + ack |= TSINTR_SYS_WRAP; + } + + if (tsicr & E1000_TSICR_TXTS) { + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + ack |= E1000_TSICR_TXTS; + } + + if (tsicr & TSINTR_TT0) { + spin_lock(&adapter->tmreg_lock); + ts = timespec_add(adapter->perout[0].start, + adapter->perout[0].period); + wr32(E1000_TRGTTIML0, ts.tv_nsec); + wr32(E1000_TRGTTIMH0, ts.tv_sec); + tsauxc = rd32(E1000_TSAUXC); + tsauxc |= TSAUXC_EN_TT0; + wr32(E1000_TSAUXC, tsauxc); + adapter->perout[0].start = ts; + spin_unlock(&adapter->tmreg_lock); + ack |= TSINTR_TT0; + } + + if (tsicr & TSINTR_TT1) { + spin_lock(&adapter->tmreg_lock); + ts = timespec_add(adapter->perout[1].start, + adapter->perout[1].period); + wr32(E1000_TRGTTIML1, ts.tv_nsec); + wr32(E1000_TRGTTIMH1, ts.tv_sec); + tsauxc = rd32(E1000_TSAUXC); + tsauxc |= TSAUXC_EN_TT1; + wr32(E1000_TSAUXC, tsauxc); + adapter->perout[1].start = ts; + spin_unlock(&adapter->tmreg_lock); + ack |= TSINTR_TT1; + } + + if (tsicr & TSINTR_AUTT0) { + nsec = rd32(E1000_AUXSTMPL0); + sec = rd32(E1000_AUXSTMPH0); + event.type = PTP_CLOCK_EXTTS; + event.index = 0; + event.timestamp = sec * 1000000000ULL + nsec; + ptp_clock_event(adapter->ptp_clock, &event); + ack |= TSINTR_AUTT0; + } + + if (tsicr & TSINTR_AUTT1) { + nsec = rd32(E1000_AUXSTMPL1); + sec = rd32(E1000_AUXSTMPH1); + event.type = PTP_CLOCK_EXTTS; + event.index = 1; + event.timestamp = sec * 1000000000ULL + nsec; + ptp_clock_event(adapter->ptp_clock, &event); + ack |= TSINTR_AUTT1; + } + + /* acknowledge the interrupts */ + wr32(E1000_TSICR, ack); +} + static irqreturn_t igb_msix_other(int irq, void *data) { struct igb_adapter *adapter = data; @@ -5415,16 +5489,8 @@ static irqreturn_t igb_msix_other(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } - if (icr & E1000_ICR_TS) { - u32 tsicr = rd32(E1000_TSICR); - - if (tsicr & E1000_TSICR_TXTS) { - /* acknowledge the interrupt */ - wr32(E1000_TSICR, E1000_TSICR_TXTS); - /* retrieve hardware timestamp */ - schedule_work(&adapter->ptp_tx_work); - } - } + if (icr & E1000_ICR_TS) + igb_tsync_interrupt(adapter); wr32(E1000_EIMS, adapter->eims_other); @@ -6011,8 +6077,12 @@ static void igb_vf_reset_msg(struct igb_adapter *adapter, u32 vf) adapter->vf_data[vf].flags |= IGB_VF_FLAG_CTS; /* reply to reset with ack and vf mac address */ - msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK; - memcpy(addr, vf_mac, ETH_ALEN); + if (!is_zero_ether_addr(vf_mac)) { + msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_ACK; + memcpy(addr, vf_mac, ETH_ALEN); + } else { + msgbuf[0] = E1000_VF_RESET | E1000_VT_MSGTYPE_NACK; + } igb_write_mbx(hw, msgbuf, 3, vf); } @@ -6203,16 +6273,8 @@ static irqreturn_t igb_intr_msi(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } - if (icr & E1000_ICR_TS) { - u32 tsicr = rd32(E1000_TSICR); - - if (tsicr & E1000_TSICR_TXTS) { - /* acknowledge the interrupt */ - wr32(E1000_TSICR, E1000_TSICR_TXTS); - /* retrieve hardware timestamp */ - schedule_work(&adapter->ptp_tx_work); - } - } + if (icr & E1000_ICR_TS) + igb_tsync_interrupt(adapter); napi_schedule(&q_vector->napi); @@ -6257,16 +6319,8 @@ static irqreturn_t igb_intr(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } - if (icr & E1000_ICR_TS) { - u32 tsicr = rd32(E1000_TSICR); - - if (tsicr & E1000_TSICR_TXTS) { - /* acknowledge the interrupt */ - wr32(E1000_TSICR, E1000_TSICR_TXTS); - /* retrieve hardware timestamp */ - schedule_work(&adapter->ptp_tx_work); - } - } + if (icr & E1000_ICR_TS) + igb_tsync_interrupt(adapter); napi_schedule(&q_vector->napi); @@ -6527,15 +6581,17 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, DMA_FROM_DEVICE); } +static inline bool igb_page_is_reserved(struct page *page) +{ + return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc; +} + static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, struct page *page, unsigned int truesize) { /* avoid re-using remote pages */ - if (unlikely(page_to_nid(page) != numa_node_id())) - return false; - - if (unlikely(page->pfmemalloc)) + if (unlikely(igb_page_is_reserved(page))) return false; #if (PAGE_SIZE < 8192) @@ -6545,22 +6601,19 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, /* flip page offset to other buffer */ rx_buffer->page_offset ^= IGB_RX_BUFSZ; - - /* Even if we own the page, we are not allowed to use atomic_set() - * This would break get_page_unless_zero() users. - */ - atomic_inc(&page->_count); #else /* move offset up to the next cache line */ rx_buffer->page_offset += truesize; if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) return false; - - /* bump ref count on page before it is given to the stack */ - get_page(page); #endif + /* Even if we own the page, we are not allowed to use atomic_set() + * This would break get_page_unless_zero() users. + */ + atomic_inc(&page->_count); + return true; } @@ -6603,13 +6656,12 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - /* we can reuse buffer as-is, just make sure it is local */ - if (likely((page_to_nid(page) == numa_node_id()) && - !page->pfmemalloc)) + /* page is not reserved, we can reuse buffer as-is */ + if (likely(!igb_page_is_reserved(page))) return true; /* this page cannot be reused so discard it */ - put_page(page); + __free_page(page); return false; } @@ -6627,7 +6679,6 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, struct page *page; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; prefetchw(page); @@ -7042,8 +7093,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } - /* clear the hdr_addr for the next_to_use descriptor */ - rx_desc->read.hdr_addr = 0; + /* clear the status bits for the next_to_use descriptor */ + rx_desc->wb.upper.status_error = 0; cleaned_count--; } while (cleaned_count); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 794c139f0cc0..d20fc8ed11f1 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -256,14 +256,9 @@ static int igb_ptp_adjtime_82576(struct ptp_clock_info *ptp, s64 delta) struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); unsigned long flags; - s64 now; spin_lock_irqsave(&igb->tmreg_lock, flags); - - now = timecounter_read(&igb->tc); - now += delta; - timecounter_init(&igb->tc, &igb->cc, now); - + timecounter_adjtime(&igb->tc, delta); spin_unlock_irqrestore(&igb->tmreg_lock, flags); return 0; @@ -360,12 +355,239 @@ static int igb_ptp_settime_i210(struct ptp_clock_info *ptp, return 0; } +static void igb_pin_direction(int pin, int input, u32 *ctrl, u32 *ctrl_ext) +{ + u32 *ptr = pin < 2 ? ctrl : ctrl_ext; + u32 mask[IGB_N_SDP] = { + E1000_CTRL_SDP0_DIR, + E1000_CTRL_SDP1_DIR, + E1000_CTRL_EXT_SDP2_DIR, + E1000_CTRL_EXT_SDP3_DIR, + }; + + if (input) + *ptr &= ~mask[pin]; + else + *ptr |= mask[pin]; +} + +static void igb_pin_extts(struct igb_adapter *igb, int chan, int pin) +{ + struct e1000_hw *hw = &igb->hw; + u32 aux0_sel_sdp[IGB_N_SDP] = { + AUX0_SEL_SDP0, AUX0_SEL_SDP1, AUX0_SEL_SDP2, AUX0_SEL_SDP3, + }; + u32 aux1_sel_sdp[IGB_N_SDP] = { + AUX1_SEL_SDP0, AUX1_SEL_SDP1, AUX1_SEL_SDP2, AUX1_SEL_SDP3, + }; + u32 ts_sdp_en[IGB_N_SDP] = { + TS_SDP0_EN, TS_SDP1_EN, TS_SDP2_EN, TS_SDP3_EN, + }; + u32 ctrl, ctrl_ext, tssdp = 0; + + ctrl = rd32(E1000_CTRL); + ctrl_ext = rd32(E1000_CTRL_EXT); + tssdp = rd32(E1000_TSSDP); + + igb_pin_direction(pin, 1, &ctrl, &ctrl_ext); + + /* Make sure this pin is not enabled as an output. */ + tssdp &= ~ts_sdp_en[pin]; + + if (chan == 1) { + tssdp &= ~AUX1_SEL_SDP3; + tssdp |= aux1_sel_sdp[pin] | AUX1_TS_SDP_EN; + } else { + tssdp &= ~AUX0_SEL_SDP3; + tssdp |= aux0_sel_sdp[pin] | AUX0_TS_SDP_EN; + } + + wr32(E1000_TSSDP, tssdp); + wr32(E1000_CTRL, ctrl); + wr32(E1000_CTRL_EXT, ctrl_ext); +} + +static void igb_pin_perout(struct igb_adapter *igb, int chan, int pin) +{ + struct e1000_hw *hw = &igb->hw; + u32 aux0_sel_sdp[IGB_N_SDP] = { + AUX0_SEL_SDP0, AUX0_SEL_SDP1, AUX0_SEL_SDP2, AUX0_SEL_SDP3, + }; + u32 aux1_sel_sdp[IGB_N_SDP] = { + AUX1_SEL_SDP0, AUX1_SEL_SDP1, AUX1_SEL_SDP2, AUX1_SEL_SDP3, + }; + u32 ts_sdp_en[IGB_N_SDP] = { + TS_SDP0_EN, TS_SDP1_EN, TS_SDP2_EN, TS_SDP3_EN, + }; + u32 ts_sdp_sel_tt0[IGB_N_SDP] = { + TS_SDP0_SEL_TT0, TS_SDP1_SEL_TT0, + TS_SDP2_SEL_TT0, TS_SDP3_SEL_TT0, + }; + u32 ts_sdp_sel_tt1[IGB_N_SDP] = { + TS_SDP0_SEL_TT1, TS_SDP1_SEL_TT1, + TS_SDP2_SEL_TT1, TS_SDP3_SEL_TT1, + }; + u32 ts_sdp_sel_clr[IGB_N_SDP] = { + TS_SDP0_SEL_FC1, TS_SDP1_SEL_FC1, + TS_SDP2_SEL_FC1, TS_SDP3_SEL_FC1, + }; + u32 ctrl, ctrl_ext, tssdp = 0; + + ctrl = rd32(E1000_CTRL); + ctrl_ext = rd32(E1000_CTRL_EXT); + tssdp = rd32(E1000_TSSDP); + + igb_pin_direction(pin, 0, &ctrl, &ctrl_ext); + + /* Make sure this pin is not enabled as an input. */ + if ((tssdp & AUX0_SEL_SDP3) == aux0_sel_sdp[pin]) + tssdp &= ~AUX0_TS_SDP_EN; + + if ((tssdp & AUX1_SEL_SDP3) == aux1_sel_sdp[pin]) + tssdp &= ~AUX1_TS_SDP_EN; + + tssdp &= ~ts_sdp_sel_clr[pin]; + if (chan == 1) + tssdp |= ts_sdp_sel_tt1[pin]; + else + tssdp |= ts_sdp_sel_tt0[pin]; + + tssdp |= ts_sdp_en[pin]; + + wr32(E1000_TSSDP, tssdp); + wr32(E1000_CTRL, ctrl); + wr32(E1000_CTRL_EXT, ctrl_ext); +} + +static int igb_ptp_feature_enable_i210(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct igb_adapter *igb = + container_of(ptp, struct igb_adapter, ptp_caps); + struct e1000_hw *hw = &igb->hw; + u32 tsauxc, tsim, tsauxc_mask, tsim_mask, trgttiml, trgttimh; + unsigned long flags; + struct timespec ts; + int pin; + s64 ns; + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + if (on) { + pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS, + rq->extts.index); + if (pin < 0) + return -EBUSY; + } + if (rq->extts.index == 1) { + tsauxc_mask = TSAUXC_EN_TS1; + tsim_mask = TSINTR_AUTT1; + } else { + tsauxc_mask = TSAUXC_EN_TS0; + tsim_mask = TSINTR_AUTT0; + } + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsauxc = rd32(E1000_TSAUXC); + tsim = rd32(E1000_TSIM); + if (on) { + igb_pin_extts(igb, rq->extts.index, pin); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } else { + tsauxc &= ~tsauxc_mask; + tsim &= ~tsim_mask; + } + wr32(E1000_TSAUXC, tsauxc); + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PEROUT: + if (on) { + pin = ptp_find_pin(igb->ptp_clock, PTP_PF_PEROUT, + rq->perout.index); + if (pin < 0) + return -EBUSY; + } + ts.tv_sec = rq->perout.period.sec; + ts.tv_nsec = rq->perout.period.nsec; + ns = timespec_to_ns(&ts); + ns = ns >> 1; + if (on && ns < 500000LL) { + /* 2k interrupts per second is an awful lot. */ + return -EINVAL; + } + ts = ns_to_timespec(ns); + if (rq->perout.index == 1) { + tsauxc_mask = TSAUXC_EN_TT1; + tsim_mask = TSINTR_TT1; + trgttiml = E1000_TRGTTIML1; + trgttimh = E1000_TRGTTIMH1; + } else { + tsauxc_mask = TSAUXC_EN_TT0; + tsim_mask = TSINTR_TT0; + trgttiml = E1000_TRGTTIML0; + trgttimh = E1000_TRGTTIMH0; + } + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsauxc = rd32(E1000_TSAUXC); + tsim = rd32(E1000_TSIM); + if (on) { + int i = rq->perout.index; + + igb_pin_perout(igb, i, pin); + igb->perout[i].start.tv_sec = rq->perout.start.sec; + igb->perout[i].start.tv_nsec = rq->perout.start.nsec; + igb->perout[i].period.tv_sec = ts.tv_sec; + igb->perout[i].period.tv_nsec = ts.tv_nsec; + wr32(trgttiml, rq->perout.start.sec); + wr32(trgttimh, rq->perout.start.nsec); + tsauxc |= tsauxc_mask; + tsim |= tsim_mask; + } else { + tsauxc &= ~tsauxc_mask; + tsim &= ~tsim_mask; + } + wr32(E1000_TSAUXC, tsauxc); + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + + case PTP_CLK_REQ_PPS: + spin_lock_irqsave(&igb->tmreg_lock, flags); + tsim = rd32(E1000_TSIM); + if (on) + tsim |= TSINTR_SYS_WRAP; + else + tsim &= ~TSINTR_SYS_WRAP; + wr32(E1000_TSIM, tsim); + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + return 0; + } + + return -EOPNOTSUPP; +} + static int igb_ptp_feature_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { return -EOPNOTSUPP; } +static int igb_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + switch (func) { + case PTP_PF_NONE: + case PTP_PF_EXTTS: + case PTP_PF_PEROUT: + break; + case PTP_PF_PHYSYNC: + return -1; + } + return 0; +} + /** * igb_ptp_tx_work * @work: pointer to work struct @@ -756,6 +978,7 @@ void igb_ptp_init(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct net_device *netdev = adapter->netdev; + int i; switch (hw->mac.type) { case e1000_82576: @@ -770,7 +993,7 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.settime = igb_ptp_settime_82576; adapter->ptp_caps.enable = igb_ptp_feature_enable; adapter->cc.read = igb_ptp_read_82576; - adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.mask = CYCLECOUNTER_MASK(64); adapter->cc.mult = 1; adapter->cc.shift = IGB_82576_TSYNC_SHIFT; /* Dial the nominal frequency. */ @@ -790,7 +1013,7 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.settime = igb_ptp_settime_82576; adapter->ptp_caps.enable = igb_ptp_feature_enable; adapter->cc.read = igb_ptp_read_82580; - adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580); + adapter->cc.mask = CYCLECOUNTER_MASK(IGB_NBITS_82580); adapter->cc.mult = 1; adapter->cc.shift = 0; /* Enable the timer functions by clearing bit 31. */ @@ -798,16 +1021,27 @@ void igb_ptp_init(struct igb_adapter *adapter) break; case e1000_i210: case e1000_i211: + for (i = 0; i < IGB_N_SDP; i++) { + struct ptp_pin_desc *ppd = &adapter->sdp_config[i]; + + snprintf(ppd->name, sizeof(ppd->name), "SDP%d", i); + ppd->index = i; + ppd->func = PTP_PF_NONE; + } snprintf(adapter->ptp_caps.name, 16, "%pm", netdev->dev_addr); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 62499999; - adapter->ptp_caps.n_ext_ts = 0; - adapter->ptp_caps.pps = 0; + adapter->ptp_caps.n_ext_ts = IGB_N_EXTTS; + adapter->ptp_caps.n_per_out = IGB_N_PEROUT; + adapter->ptp_caps.n_pins = IGB_N_SDP; + adapter->ptp_caps.pps = 1; + adapter->ptp_caps.pin_config = adapter->sdp_config; adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210; adapter->ptp_caps.gettime = igb_ptp_gettime_i210; adapter->ptp_caps.settime = igb_ptp_settime_i210; - adapter->ptp_caps.enable = igb_ptp_feature_enable; + adapter->ptp_caps.enable = igb_ptp_feature_enable_i210; + adapter->ptp_caps.verify = igb_ptp_verify_pin; /* Enable the timer functions by clearing bit 31. */ wr32(E1000_TSAUXC, 0x0); break; @@ -905,6 +1139,7 @@ void igb_ptp_stop(struct igb_adapter *adapter) void igb_ptp_reset(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; + unsigned long flags; if (!(adapter->flags & IGB_FLAG_PTP)) return; @@ -912,6 +1147,8 @@ void igb_ptp_reset(struct igb_adapter *adapter) /* reset the tstamp_config */ igb_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config); + spin_lock_irqsave(&adapter->tmreg_lock, flags); + switch (adapter->hw.mac.type) { case e1000_82576: /* Dial the nominal frequency. */ @@ -922,23 +1159,25 @@ void igb_ptp_reset(struct igb_adapter *adapter) case e1000_i350: case e1000_i210: case e1000_i211: - /* Enable the timer functions and interrupts. */ wr32(E1000_TSAUXC, 0x0); + wr32(E1000_TSSDP, 0x0); wr32(E1000_TSIM, TSYNC_INTERRUPTS); wr32(E1000_IMS, E1000_IMS_TS); break; default: /* No work to do. */ - return; + goto out; } /* Re-initialize the timer. */ if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211)) { struct timespec ts = ktime_to_timespec(ktime_get_real()); - igb_ptp_settime_i210(&adapter->ptp_caps, &ts); + igb_ptp_write_i210(adapter, &ts); } else { timecounter_init(&adapter->tc, &adapter->cc, ktime_to_ns(ktime_get_real())); } +out: + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); } diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index edea13b0ee85..ebf9d4a42fdd 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2237,9 +2237,10 @@ static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb, return NETDEV_TX_BUSY; } - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { tx_flags |= IGBVF_TX_FLAGS_VLAN; - tx_flags |= (vlan_tx_tag_get(skb) << IGBVF_TX_FLAGS_VLAN_SHIFT); + tx_flags |= (skb_vlan_tag_get(skb) << + IGBVF_TX_FLAGS_VLAN_SHIFT); } if (protocol == htons(ETH_P_IP)) diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index aa87605b144a..11a1bdbe3fd9 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -1532,9 +1532,9 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) DESC_NEEDED))) return NETDEV_TX_BUSY; - if (vlan_tx_tag_present(skb)) { + if (skb_vlan_tag_present(skb)) { tx_flags |= IXGB_TX_FLAGS_VLAN; - vlan_id = vlan_tx_tag_get(skb); + vlan_id = skb_vlan_tag_get(skb); } first = adapter->tx_ring.next_to_use; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index b6137be43920..7dcbbec09a70 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -38,7 +38,7 @@ #include <linux/if_vlan.h> #include <linux/jiffies.h> -#include <linux/clocksource.h> +#include <linux/timecounter.h> #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> @@ -76,6 +76,8 @@ #define IXGBE_MAX_RXD 4096 #define IXGBE_MIN_RXD 64 +#define IXGBE_ETH_P_LLDP 0x88CC + /* flow control */ #define IXGBE_MIN_FCRTL 0x40 #define IXGBE_MAX_FCRTL 0x7FF80 @@ -753,6 +755,7 @@ struct ixgbe_adapter { u32 timer_event_accumulator; u32 vferr_refcount; struct ixgbe_mac_addr *mac_table; + u16 vxlan_port; struct kobject *info_kobj; #ifdef CONFIG_IXGBE_HWMON struct hwmon_buff *ixgbe_hwmon_buff; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 67b02bde179e..70cc4c5c0a01 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -50,6 +50,7 @@ #include <linux/if_bridge.h> #include <linux/prefetch.h> #include <scsi/fc/fc_fcoe.h> +#include <net/vxlan.h> #ifdef CONFIG_OF #include <linux/of_net.h> @@ -1396,12 +1397,23 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + __le16 hdr_info = rx_desc->wb.lower.lo_dword.hs_rss.hdr_info; + bool encap_pkt = false; + skb_checksum_none_assert(skb); /* Rx csum disabled */ if (!(ring->netdev->features & NETIF_F_RXCSUM)) return; + if ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_VXLAN)) && + (hdr_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_TUNNEL >> 16))) { + encap_pkt = true; + skb->encapsulation = 1; + skb->ip_summed = CHECKSUM_NONE; + } + /* if IP and error */ if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) && ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) { @@ -1413,8 +1425,6 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring, return; if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) { - __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; - /* * 82599 errata, UDP frames with a 0 checksum can be marked as * checksum errors. @@ -1429,6 +1439,17 @@ static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring, /* It must be a TCP or UDP packet with a valid checksum */ skb->ip_summed = CHECKSUM_UNNECESSARY; + if (encap_pkt) { + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_OUTERIPCS)) + return; + + if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_OUTERIPER)) { + ring->rx_stats.csum_err++; + return; + } + /* If we checked the outer header let the stack know */ + skb->csum_level = 1; + } } static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, @@ -3564,10 +3585,24 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) /* Enable MAC Anti-Spoofing */ hw->mac.ops.set_mac_anti_spoofing(hw, (adapter->num_vfs != 0), adapter->num_vfs); + + /* Ensure LLDP is set for Ethertype Antispoofing if we will be + * calling set_ethertype_anti_spoofing for each VF in loop below + */ + if (hw->mac.ops.set_ethertype_anti_spoofing) + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_LLDP), + (IXGBE_ETQF_FILTER_EN | /* enable filter */ + IXGBE_ETQF_TX_ANTISPOOF | /* tx antispoof */ + IXGBE_ETH_P_LLDP)); /* LLDP eth type */ + /* For VFs that have spoof checking turned off */ for (i = 0; i < adapter->num_vfs; i++) { if (!adapter->vfinfo[i].spoofchk_enabled) ixgbe_ndo_set_vf_spoofchk(adapter->netdev, i, false); + + /* enable ethertype anti spoofing if hw supports it */ + if (hw->mac.ops.set_ethertype_anti_spoofing) + hw->mac.ops.set_ethertype_anti_spoofing(hw, true, i); } } @@ -5627,6 +5662,10 @@ static int ixgbe_open(struct net_device *netdev) ixgbe_up_complete(adapter); +#if IS_ENABLED(CONFIG_IXGBE_VXLAN) + vxlan_get_rx_port(netdev); + +#endif return 0; err_set_queues: @@ -7217,8 +7256,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, first->gso_segs = 1; /* if we have a HW VLAN tag being added default to the HW one */ - if (vlan_tx_tag_present(skb)) { - tx_flags |= vlan_tx_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT; + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_HW_VLAN; /* else if it is a SW VLAN check the next protocol and store the tag */ } else if (protocol == htons(ETH_P_8021Q)) { @@ -7771,6 +7810,64 @@ static int ixgbe_set_features(struct net_device *netdev, return 0; } +/** + * ixgbe_add_vxlan_port - Get notifications about VXLAN ports that come up + * @dev: The port's netdev + * @sa_family: Socket Family that VXLAN is notifiying us about + * @port: New UDP port number that VXLAN started listening to + **/ +static void ixgbe_add_vxlan_port(struct net_device *dev, sa_family_t sa_family, + __be16 port) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + u16 new_port = ntohs(port); + + if (sa_family == AF_INET6) + return; + + if (adapter->vxlan_port == new_port) { + netdev_info(dev, "Port %d already offloaded\n", new_port); + return; + } + + if (adapter->vxlan_port) { + netdev_info(dev, + "Hit Max num of UDP ports, not adding port %d\n", + new_port); + return; + } + + adapter->vxlan_port = new_port; + IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, new_port); +} + +/** + * ixgbe_del_vxlan_port - Get notifications about VXLAN ports that go away + * @dev: The port's netdev + * @sa_family: Socket Family that VXLAN is notifying us about + * @port: UDP port number that VXLAN stopped listening to + **/ +static void ixgbe_del_vxlan_port(struct net_device *dev, sa_family_t sa_family, + __be16 port) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + u16 new_port = ntohs(port); + + if (sa_family == AF_INET6) + return; + + if (adapter->vxlan_port != new_port) { + netdev_info(dev, "Port %d was not found, not deleting\n", + new_port); + return; + } + + adapter->vxlan_port = 0; + IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, 0); +} + static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, @@ -7786,7 +7883,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } static int ixgbe_ndo_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh) + struct nlmsghdr *nlh, u16 flags) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct nlattr *attr, *br_spec; @@ -7982,6 +8079,8 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_bridge_getlink = ixgbe_ndo_bridge_getlink, .ndo_dfwd_add_station = ixgbe_fwd_add, .ndo_dfwd_del_station = ixgbe_fwd_del, + .ndo_add_vxlan_port = ixgbe_add_vxlan_port, + .ndo_del_vxlan_port = ixgbe_del_vxlan_port, }; /** @@ -8339,6 +8438,15 @@ skip_sriov: netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; + switch (adapter->hw.mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + netdev->hw_enc_features |= NETIF_F_RXCSUM; + break; + default: + break; + } + #ifdef CONFIG_IXGBE_DCB netdev->dcbnl_ops = &dcbnl_ops; #endif diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 5fd4b5271f9a..79c00f57d3e7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -261,18 +261,9 @@ static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); unsigned long flags; - u64 now; spin_lock_irqsave(&adapter->tmreg_lock, flags); - - now = timecounter_read(&adapter->tc); - now += delta; - - /* reset the timecounter */ - timecounter_init(&adapter->tc, - &adapter->cc, - now); - + timecounter_adjtime(&adapter->tc, delta); spin_unlock_irqrestore(&adapter->tmreg_lock, flags); ixgbe_ptp_setup_sdp(adapter); @@ -802,7 +793,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) memset(&adapter->cc, 0, sizeof(adapter->cc)); adapter->cc.read = ixgbe_ptp_read; - adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.mask = CYCLECOUNTER_MASK(64); adapter->cc.shift = shift; adapter->cc.mult = 1; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index c76ba90ecc6e..7f37fe7269a7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -101,9 +101,6 @@ static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter) adapter->dcb_cfg.num_tcs.pfc_tcs = 1; } - /* We do not support RSS w/ SR-IOV */ - adapter->ring_feature[RING_F_RSS].limit = 1; - /* Disable RSC when in SR-IOV mode */ adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | IXGBE_FLAG2_RSC_ENABLED); @@ -1097,14 +1094,12 @@ static int ixgbe_enable_port_vlan(struct ixgbe_adapter *adapter, int vf, u16 vlan, u8 qos) { struct ixgbe_hw *hw = &adapter->hw; - int err = 0; + int err; - if (adapter->vfinfo[vf].pf_vlan) - err = ixgbe_set_vf_vlan(adapter, false, - adapter->vfinfo[vf].pf_vlan, - vf); + err = ixgbe_set_vf_vlan(adapter, true, vlan, vf); if (err) goto out; + ixgbe_set_vmvir(adapter, vlan, qos, vf); ixgbe_set_vmolr(hw, vf, false); if (adapter->vfinfo[vf].spoofchk_enabled) @@ -1143,6 +1138,11 @@ static int ixgbe_disable_port_vlan(struct ixgbe_adapter *adapter, int vf) hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf); if (adapter->vfinfo[vf].vlan_count) adapter->vfinfo[vf].vlan_count--; + + /* disable hide VLAN on X550 */ + if (hw->mac.type >= ixgbe_mac_X550) + ixgbe_write_qde(adapter, vf, IXGBE_QDE_ENABLE); + adapter->vfinfo[vf].pf_vlan = 0; adapter->vfinfo[vf].pf_qos = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index d101b25dc4b6..fc5ecee56ca8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -378,6 +378,8 @@ struct ixgbe_thermal_sensor_data { #define IXGBE_SPOOF_MACAS_MASK 0xFF #define IXGBE_SPOOF_VLANAS_MASK 0xFF00 #define IXGBE_SPOOF_VLANAS_SHIFT 8 +#define IXGBE_SPOOF_ETHERTYPEAS 0xFF000000 +#define IXGBE_SPOOF_ETHERTYPEAS_SHIFT 16 #define IXGBE_PFVFSPOOF_REG_COUNT 8 #define IXGBE_DCA_TXCTRL(_i) (0x07200 + ((_i) * 4)) /* 16 of these (0-15) */ @@ -399,6 +401,7 @@ struct ixgbe_thermal_sensor_data { #define IXGBE_WUPL 0x05900 #define IXGBE_WUPM 0x05A00 /* wake up pkt memory 0x5A00-0x5A7C */ +#define IXGBE_VXLANCTRL 0x0000507C /* Rx filter VXLAN UDPPORT Register */ #define IXGBE_FHFT(_n) (0x09000 + ((_n) * 0x100)) /* Flex host filter table */ #define IXGBE_FHFT_EXT(_n) (0x09800 + ((_n) * 0x100)) /* Ext Flexible Host * Filter Table */ @@ -1540,6 +1543,7 @@ enum { #define IXGBE_MAX_ETQF_FILTERS 8 #define IXGBE_ETQF_FCOE 0x08000000 /* bit 27 */ #define IXGBE_ETQF_BCN 0x10000000 /* bit 28 */ +#define IXGBE_ETQF_TX_ANTISPOOF 0x20000000 /* bit 29 */ #define IXGBE_ETQF_1588 0x40000000 /* bit 30 */ #define IXGBE_ETQF_FILTER_EN 0x80000000 /* bit 31 */ #define IXGBE_ETQF_POOL_ENABLE (1 << 26) /* bit 26 */ @@ -1565,6 +1569,9 @@ enum { #define IXGBE_ETQF_FILTER_FCOE 2 #define IXGBE_ETQF_FILTER_1588 3 #define IXGBE_ETQF_FILTER_FIP 4 +#define IXGBE_ETQF_FILTER_LLDP 5 +#define IXGBE_ETQF_FILTER_LACP 6 + /* VLAN Control Bit Masks */ #define IXGBE_VLNCTRL_VET 0x0000FFFF /* bits 0-15 */ #define IXGBE_VLNCTRL_CFI 0x10000000 /* bit 28 */ @@ -2122,6 +2129,7 @@ enum { #define IXGBE_RXD_STAT_IPCS 0x40 /* IP xsum calculated */ #define IXGBE_RXD_STAT_PIF 0x80 /* passed in-exact filter */ #define IXGBE_RXD_STAT_CRCV 0x100 /* Speculative CRC Valid */ +#define IXGBE_RXD_STAT_OUTERIPCS 0x100 /* Cloud IP xsum calculated */ #define IXGBE_RXD_STAT_VEXT 0x200 /* 1st VLAN found */ #define IXGBE_RXD_STAT_UDPV 0x400 /* Valid UDP checksum */ #define IXGBE_RXD_STAT_DYNINT 0x800 /* Pkt caused INT via DYNINT */ @@ -2139,6 +2147,7 @@ enum { #define IXGBE_RXD_ERR_IPE 0x80 /* IP Checksum Error */ #define IXGBE_RXDADV_ERR_MASK 0xfff00000 /* RDESC.ERRORS mask */ #define IXGBE_RXDADV_ERR_SHIFT 20 /* RDESC.ERRORS shift */ +#define IXGBE_RXDADV_ERR_OUTERIPER 0x04000000 /* CRC IP Header error */ #define IXGBE_RXDADV_ERR_FCEOFE 0x80000000 /* FCoEFe/IPE */ #define IXGBE_RXDADV_ERR_FCERR 0x00700000 /* FCERR/FDIRERR */ #define IXGBE_RXDADV_ERR_FDIR_LEN 0x00100000 /* FDIR Length error */ @@ -2227,6 +2236,8 @@ enum { #define IXGBE_RXDADV_PKTTYPE_UDP 0x00000200 /* UDP hdr present */ #define IXGBE_RXDADV_PKTTYPE_SCTP 0x00000400 /* SCTP hdr present */ #define IXGBE_RXDADV_PKTTYPE_NFS 0x00000800 /* NFS hdr present */ +#define IXGBE_RXDADV_PKTTYPE_VXLAN 0x00000800 /* VXLAN hdr present */ +#define IXGBE_RXDADV_PKTTYPE_TUNNEL 0x00010000 /* Tunnel type */ #define IXGBE_RXDADV_PKTTYPE_IPSEC_ESP 0x00001000 /* IPSec ESP */ #define IXGBE_RXDADV_PKTTYPE_IPSEC_AH 0x00002000 /* IPSec AH */ #define IXGBE_RXDADV_PKTTYPE_LINKSEC 0x00004000 /* LinkSec Encap */ @@ -3056,6 +3067,7 @@ struct ixgbe_mac_operations { s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8); s32 (*get_thermal_sensor_data)(struct ixgbe_hw *); s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw); + void (*set_ethertype_anti_spoofing)(struct ixgbe_hw *, bool, int); /* DMA Coalescing */ s32 (*dmac_config)(struct ixgbe_hw *hw); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index ba54ff07b438..49395420c9b3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -55,9 +55,6 @@ s32 ixgbe_get_invariants_X540(struct ixgbe_hw *hw) { struct ixgbe_mac_info *mac = &hw->mac; - /* Call PHY identify routine to get the phy type */ - ixgbe_identify_phy_generic(hw); - mac->mcft_size = IXGBE_X540_MC_TBL_SIZE; mac->vft_size = IXGBE_X540_VFT_TBL_SIZE; mac->num_rar_entries = IXGBE_X540_RAR_ENTRIES; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index ffdd1231f419..50bf81908dd6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -80,7 +80,7 @@ static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, * Initializes the EEPROM parameters ixgbe_eeprom_info within the * ixgbe_hw struct in order to set up EEPROM access. **/ -s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw) +static s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw) { struct ixgbe_eeprom_info *eeprom = &hw->eeprom; u32 eec; @@ -110,8 +110,8 @@ s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw) * @device_type: 3 bit device type * @phy_data: Pointer to read data from the register **/ -s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, - u32 device_type, u32 *data) +static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u32 *data) { u32 i, command, error; @@ -158,7 +158,8 @@ s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, * * Reads a 16 bit word from the EEPROM using the hostif. **/ -s32 ixgbe_read_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, u16 *data) +static s32 ixgbe_read_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, + u16 *data) { s32 status; struct ixgbe_hic_read_shadow_ram buffer; @@ -193,8 +194,8 @@ s32 ixgbe_read_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, u16 *data) * * Reads a 16 bit word(s) from the EEPROM using the hostif. **/ -s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, - u16 offset, u16 words, u16 *data) +static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, + u16 offset, u16 words, u16 *data) { struct ixgbe_hic_read_shadow_ram buffer; u32 current_word = 0; @@ -331,7 +332,8 @@ static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, * * Returns a negative error code on error, or the 16-bit checksum **/ -s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer, u32 buffer_size) +static s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer, + u32 buffer_size) { u16 eeprom_ptrs[IXGBE_EEPROM_LAST_WORD + 1]; u16 *local_buffer; @@ -407,7 +409,7 @@ s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer, u32 buffer_size) * * Returns a negative error code on error, or the 16-bit checksum **/ -s32 ixgbe_calc_eeprom_checksum_X550(struct ixgbe_hw *hw) +static s32 ixgbe_calc_eeprom_checksum_X550(struct ixgbe_hw *hw) { return ixgbe_calc_checksum_X550(hw, NULL, 0); } @@ -419,7 +421,7 @@ s32 ixgbe_calc_eeprom_checksum_X550(struct ixgbe_hw *hw) * * Reads a 16 bit word from the EEPROM using the hostif. **/ -s32 ixgbe_read_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 *data) +static s32 ixgbe_read_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 *data) { s32 status = 0; @@ -440,7 +442,8 @@ s32 ixgbe_read_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 *data) * Performs checksum calculation and validates the EEPROM checksum. If the * caller does not need checksum_val, the value can be NULL. **/ -s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw, u16 *checksum_val) +static s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw, + u16 *checksum_val) { s32 status; u16 checksum; @@ -489,7 +492,8 @@ s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw, u16 *checksum_val) * * Write a 16 bit word to the EEPROM using the hostif. **/ -s32 ixgbe_write_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, u16 data) +static s32 ixgbe_write_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, + u16 data) { s32 status; struct ixgbe_hic_write_shadow_ram buffer; @@ -517,7 +521,7 @@ s32 ixgbe_write_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, u16 data) * * Write a 16 bit word to the EEPROM using the hostif. **/ -s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data) +static s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data) { s32 status = 0; @@ -537,7 +541,7 @@ s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data) * * Issue a shadow RAM dump to FW to copy EEPROM from shadow RAM to the flash. **/ -s32 ixgbe_update_flash_X550(struct ixgbe_hw *hw) +static s32 ixgbe_update_flash_X550(struct ixgbe_hw *hw) { s32 status = 0; union ixgbe_hic_hdr2 buffer; @@ -560,7 +564,7 @@ s32 ixgbe_update_flash_X550(struct ixgbe_hw *hw) * checksum and updates the EEPROM and instructs the hardware to update * the flash. **/ -s32 ixgbe_update_eeprom_checksum_X550(struct ixgbe_hw *hw) +static s32 ixgbe_update_eeprom_checksum_X550(struct ixgbe_hw *hw) { s32 status; u16 checksum = 0; @@ -600,8 +604,9 @@ s32 ixgbe_update_eeprom_checksum_X550(struct ixgbe_hw *hw) * * Write a 16 bit word(s) to the EEPROM using the hostif. **/ -s32 ixgbe_write_ee_hostif_buffer_X550(struct ixgbe_hw *hw, - u16 offset, u16 words, u16 *data) +static s32 ixgbe_write_ee_hostif_buffer_X550(struct ixgbe_hw *hw, + u16 offset, u16 words, + u16 *data) { s32 status = 0; u32 i = 0; @@ -630,7 +635,7 @@ s32 ixgbe_write_ee_hostif_buffer_X550(struct ixgbe_hw *hw, /** ixgbe_init_mac_link_ops_X550em - init mac link function pointers * @hw: pointer to hardware structure **/ -void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) +static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) { struct ixgbe_mac_info *mac = &hw->mac; @@ -647,7 +652,7 @@ void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) /** ixgbe_setup_sfp_modules_X550em - Setup SFP module * @hw: pointer to hardware structure */ -s32 ixgbe_setup_sfp_modules_X550em(struct ixgbe_hw *hw) +static s32 ixgbe_setup_sfp_modules_X550em(struct ixgbe_hw *hw) { bool setup_linear; u16 reg_slice, edc_mode; @@ -703,9 +708,9 @@ s32 ixgbe_setup_sfp_modules_X550em(struct ixgbe_hw *hw) * @speed: pointer to link speed * @autoneg: true when autoneg or autotry is enabled **/ -s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, - ixgbe_link_speed *speed, - bool *autoneg) +static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg) { /* SFP */ if (hw->phy.media_type == ixgbe_media_type_fiber) { @@ -740,8 +745,8 @@ s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, * @device_type: 3 bit device type * @data: Data to write to the register **/ -s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, - u32 device_type, u32 data) +static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u32 data) { u32 i, command, error; @@ -904,7 +909,7 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) * * Configures the integrated KX4 PHY. **/ -s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw) +static s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw) { s32 status; u32 reg_val; @@ -942,7 +947,7 @@ s32 ixgbe_setup_kx4_x550em(struct ixgbe_hw *hw) * * Configures the integrated KR PHY. **/ -s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw) +static s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw) { s32 status; u32 reg_val; @@ -987,7 +992,7 @@ s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw) * A return of a non-zero value indicates an error, and the base driver should * not report link up. **/ -s32 ixgbe_setup_internal_phy_x550em(struct ixgbe_hw *hw) +static s32 ixgbe_setup_internal_phy_x550em(struct ixgbe_hw *hw) { u32 status; u16 lasi, autoneg_status, speed; @@ -1049,7 +1054,7 @@ s32 ixgbe_setup_internal_phy_x550em(struct ixgbe_hw *hw) * set during init_shared_code because the PHY/SFP type was * not known. Perform the SFP init if necessary. **/ -s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) +static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) { struct ixgbe_phy_info *phy = &hw->phy; s32 ret_val; @@ -1102,7 +1107,7 @@ s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) * Returns the media type (fiber, copper, backplane) * */ -enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw) +static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw) { enum ixgbe_media_type media_type; @@ -1129,7 +1134,7 @@ enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw) /** ixgbe_init_ext_t_x550em - Start (unstall) the external Base T PHY. ** @hw: pointer to hardware structure **/ -s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw) +static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw) { u32 status; u16 reg; @@ -1202,7 +1207,7 @@ s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw) ** and clears all interrupts, perform a PHY reset, and perform a link (MAC) ** reset. **/ -s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) +static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) { ixgbe_link_speed link_speed; s32 status; @@ -1295,6 +1300,28 @@ mac_reset_top: return status; } +/** ixgbe_set_ethertype_anti_spoofing_X550 - Enable/Disable Ethertype + * anti-spoofing + * @hw: pointer to hardware structure + * @enable: enable or disable switch for Ethertype anti-spoofing + * @vf: Virtual Function pool - VF Pool to set for Ethertype anti-spoofing + **/ +void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw, bool enable, + int vf) +{ + int vf_target_reg = vf >> 3; + int vf_target_shift = vf % 8 + IXGBE_SPOOF_ETHERTYPEAS_SHIFT; + u32 pfvfspoof; + + pfvfspoof = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg)); + if (enable) + pfvfspoof |= (1 << vf_target_shift); + else + pfvfspoof &= ~(1 << vf_target_shift); + + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof); +} + #define X550_COMMON_MAC \ .init_hw = &ixgbe_init_hw_generic, \ .start_hw = &ixgbe_start_hw_X540, \ @@ -1329,6 +1356,8 @@ mac_reset_top: .init_uta_tables = &ixgbe_init_uta_tables_generic, \ .set_mac_anti_spoofing = &ixgbe_set_mac_anti_spoofing, \ .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, \ + .set_ethertype_anti_spoofing = \ + &ixgbe_set_ethertype_anti_spoofing_X550, \ .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X540, \ .release_swfw_sync = &ixgbe_release_swfw_sync_X540, \ .disable_rx_buff = &ixgbe_disable_rx_buff_generic, \ @@ -1345,7 +1374,6 @@ static struct ixgbe_mac_operations mac_ops_X550 = { .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic, .get_wwn_prefix = &ixgbe_get_wwn_prefix_generic, .setup_link = &ixgbe_setup_mac_link_X540, - .set_rxpba = &ixgbe_set_rxpba_generic, .get_link_capabilities = &ixgbe_get_copper_link_capabilities_generic, .setup_sfp = NULL, }; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 8c44ab25f3fa..3a9b356dff01 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -43,6 +43,13 @@ #define BP_EXTENDED_STATS #endif +#define IXGBE_MAX_TXD_PWR 14 +#define IXGBE_MAX_DATA_PER_TXD BIT(IXGBE_MAX_TXD_PWR) + +/* Tx Descriptors needed, worst case */ +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) + /* wrapper around a pointer to a socket buffer, * so a DMA handle can be stored along with the buffer */ struct ixgbevf_tx_buffer { @@ -85,6 +92,18 @@ struct ixgbevf_rx_queue_stats { u64 csum_err; }; +enum ixgbevf_ring_state_t { + __IXGBEVF_TX_DETECT_HANG, + __IXGBEVF_HANG_CHECK_ARMED, +}; + +#define check_for_tx_hang(ring) \ + test_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define set_check_for_tx_hang(ring) \ + set_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define clear_check_for_tx_hang(ring) \ + clear_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) + struct ixgbevf_ring { struct ixgbevf_ring *next; struct net_device *netdev; @@ -101,7 +120,7 @@ struct ixgbevf_ring { struct ixgbevf_tx_buffer *tx_buffer_info; struct ixgbevf_rx_buffer *rx_buffer_info; }; - + unsigned long state; struct ixgbevf_stats stats; struct u64_stats_sync syncp; union { @@ -124,6 +143,7 @@ struct ixgbevf_ring { #define MAX_RX_QUEUES IXGBE_VF_MAX_RX_QUEUES #define MAX_TX_QUEUES IXGBE_VF_MAX_TX_QUEUES +#define IXGBEVF_MAX_RSS_QUEUES 2 #define IXGBEVF_DEFAULT_TXD 1024 #define IXGBEVF_DEFAULT_RXD 512 @@ -347,8 +367,6 @@ struct ixgbevf_adapter { /* this field must be first, see ixgbevf_process_skb_fields */ unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - struct timer_list watchdog_timer; - struct work_struct reset_task; struct ixgbevf_q_vector *q_vector[MAX_MSIX_Q_VECTORS]; /* Interrupt Throttle Rate */ @@ -378,8 +396,7 @@ struct ixgbevf_adapter { * thus the additional *_CAPABLE flags. */ u32 flags; -#define IXGBE_FLAG_IN_WATCHDOG_TASK (u32)(1) - +#define IXGBEVF_FLAG_RESET_REQUESTED (u32)(1) #define IXGBEVF_FLAG_QUEUE_RESET_REQUESTED (u32)(1 << 2) struct msix_entry *msix_entries; @@ -415,9 +432,11 @@ struct ixgbevf_adapter { u32 link_speed; bool link_up; - spinlock_t mbx_lock; + struct timer_list service_timer; + struct work_struct service_task; - struct work_struct watchdog_task; + spinlock_t mbx_lock; + unsigned long last_reset; }; enum ixbgevf_state_t { @@ -426,7 +445,8 @@ enum ixbgevf_state_t { __IXGBEVF_DOWN, __IXGBEVF_DISABLED, __IXGBEVF_REMOVING, - __IXGBEVF_WORK_INIT, + __IXGBEVF_SERVICE_SCHED, + __IXGBEVF_SERVICE_INITED, }; enum ixgbevf_boards { diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 38c7a0be8197..4186981e562d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -98,6 +98,23 @@ static int debug = -1; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); +static void ixgbevf_service_event_schedule(struct ixgbevf_adapter *adapter) +{ + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state) && + !test_and_set_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state)) + schedule_work(&adapter->service_task); +} + +static void ixgbevf_service_event_complete(struct ixgbevf_adapter *adapter) +{ + BUG_ON(!test_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state)); + + /* flush memory to make sure state is correct before next watchdog */ + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state); +} + /* forward decls */ static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter); static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector); @@ -111,8 +128,8 @@ static void ixgbevf_remove_adapter(struct ixgbe_hw *hw) return; hw->hw_addr = NULL; dev_err(&adapter->pdev->dev, "Adapter removed\n"); - if (test_bit(__IXGBEVF_WORK_INIT, &adapter->state)) - schedule_work(&adapter->watchdog_task); + if (test_bit(__IXGBEVF_SERVICE_INITED, &adapter->state)) + ixgbevf_service_event_schedule(adapter); } static void ixgbevf_check_remove(struct ixgbe_hw *hw, u32 reg) @@ -199,14 +216,72 @@ static void ixgbevf_unmap_and_free_tx_resource(struct ixgbevf_ring *tx_ring, /* tx_buffer must be completely set up in the transmit path */ } -#define IXGBE_MAX_TXD_PWR 14 -#define IXGBE_MAX_DATA_PER_TXD (1 << IXGBE_MAX_TXD_PWR) +static u64 ixgbevf_get_tx_completed(struct ixgbevf_ring *ring) +{ + return ring->stats.packets; +} + +static u32 ixgbevf_get_tx_pending(struct ixgbevf_ring *ring) +{ + struct ixgbevf_adapter *adapter = netdev_priv(ring->netdev); + struct ixgbe_hw *hw = &adapter->hw; + + u32 head = IXGBE_READ_REG(hw, IXGBE_VFTDH(ring->reg_idx)); + u32 tail = IXGBE_READ_REG(hw, IXGBE_VFTDT(ring->reg_idx)); + + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + + return 0; +} + +static inline bool ixgbevf_check_tx_hang(struct ixgbevf_ring *tx_ring) +{ + u32 tx_done = ixgbevf_get_tx_completed(tx_ring); + u32 tx_done_old = tx_ring->tx_stats.tx_done_old; + u32 tx_pending = ixgbevf_get_tx_pending(tx_ring); + + clear_check_for_tx_hang(tx_ring); + + /* Check for a hung queue, but be thorough. This verifies + * that a transmit has been completed since the previous + * check AND there is at least one packet pending. The + * ARMED bit is set to indicate a potential hang. + */ + if ((tx_done_old == tx_done) && tx_pending) { + /* make sure it is true for two checks in a row */ + return test_and_set_bit(__IXGBEVF_HANG_CHECK_ARMED, + &tx_ring->state); + } + /* reset the countdown */ + clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &tx_ring->state); + + /* update completed stats and continue */ + tx_ring->tx_stats.tx_done_old = tx_done; + + return false; +} + +static void ixgbevf_tx_timeout_reset(struct ixgbevf_adapter *adapter) +{ + /* Do the reset outside of interrupt context */ + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) { + adapter->flags |= IXGBEVF_FLAG_RESET_REQUESTED; + ixgbevf_service_event_schedule(adapter); + } +} -/* Tx Descriptors needed, worst case */ -#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD) -#define DESC_NEEDED (MAX_SKB_FRAGS + 4) +/** + * ixgbevf_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + **/ +static void ixgbevf_tx_timeout(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); -static void ixgbevf_tx_timeout(struct net_device *netdev); + ixgbevf_tx_timeout_reset(adapter); +} /** * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes @@ -311,6 +386,37 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, q_vector->tx.total_bytes += total_bytes; q_vector->tx.total_packets += total_packets; + if (check_for_tx_hang(tx_ring) && ixgbevf_check_tx_hang(tx_ring)) { + struct ixgbe_hw *hw = &adapter->hw; + union ixgbe_adv_tx_desc *eop_desc; + + eop_desc = tx_ring->tx_buffer_info[i].next_to_watch; + + pr_err("Detected Tx Unit Hang\n" + " Tx Queue <%d>\n" + " TDH, TDT <%x>, <%x>\n" + " next_to_use <%x>\n" + " next_to_clean <%x>\n" + "tx_buffer_info[next_to_clean]\n" + " next_to_watch <%p>\n" + " eop_desc->wb.status <%x>\n" + " time_stamp <%lx>\n" + " jiffies <%lx>\n", + tx_ring->queue_index, + IXGBE_READ_REG(hw, IXGBE_VFTDH(tx_ring->reg_idx)), + IXGBE_READ_REG(hw, IXGBE_VFTDT(tx_ring->reg_idx)), + tx_ring->next_to_use, i, + eop_desc, (eop_desc ? eop_desc->wb.status : 0), + tx_ring->tx_buffer_info[i].time_stamp, jiffies); + + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + + /* schedule immediate reset if we believe we hung */ + ixgbevf_tx_timeout_reset(adapter); + + return true; + } + #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && (ixgbevf_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) { @@ -1158,9 +1264,7 @@ static irqreturn_t ixgbevf_msix_other(int irq, void *data) hw->mac.get_link_status = 1; - if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && - !test_bit(__IXGBEVF_REMOVING, &adapter->state)) - mod_timer(&adapter->watchdog_timer, jiffies); + ixgbevf_service_event_schedule(adapter); IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other); @@ -1479,6 +1583,8 @@ static void ixgbevf_configure_tx_ring(struct ixgbevf_adapter *adapter, txdctl |= (1 << 8) | /* HTHRESH = 1 */ 32; /* PTHRESH = 32 */ + clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &ring->state); + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), txdctl); /* poll to verify queue is enabled */ @@ -1584,6 +1690,39 @@ static void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter, reg_idx); } +static void ixgbevf_setup_vfmrqc(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vfmrqc = 0, vfreta = 0; + u32 rss_key[10]; + u16 rss_i = adapter->num_rx_queues; + int i, j; + + /* Fill out hash function seeds */ + netdev_rss_key_fill(rss_key, sizeof(rss_key)); + for (i = 0; i < 10; i++) + IXGBE_WRITE_REG(hw, IXGBE_VFRSSRK(i), rss_key[i]); + + /* Fill out redirection table */ + for (i = 0, j = 0; i < 64; i++, j++) { + if (j == rss_i) + j = 0; + vfreta = (vfreta << 8) | (j * 0x1); + if ((i & 3) == 3) + IXGBE_WRITE_REG(hw, IXGBE_VFRETA(i >> 2), vfreta); + } + + /* Perform hash on these packet types */ + vfmrqc |= IXGBE_VFMRQC_RSS_FIELD_IPV4 | + IXGBE_VFMRQC_RSS_FIELD_IPV4_TCP | + IXGBE_VFMRQC_RSS_FIELD_IPV6 | + IXGBE_VFMRQC_RSS_FIELD_IPV6_TCP; + + vfmrqc |= IXGBE_VFMRQC_RSSEN; + + IXGBE_WRITE_REG(hw, IXGBE_VFMRQC, vfmrqc); +} + static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, struct ixgbevf_ring *ring) { @@ -1640,6 +1779,8 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) struct net_device *netdev = adapter->netdev; ixgbevf_setup_psrtype(adapter); + if (hw->mac.type >= ixgbe_mac_X550_vf) + ixgbevf_setup_vfmrqc(adapter); /* notify the PF of our intent to use this size of frame */ ixgbevf_rlpml_set_vf(hw, netdev->mtu + ETH_HLEN + ETH_FCS_LEN); @@ -1794,7 +1935,8 @@ static int ixgbevf_configure_dcb(struct ixgbevf_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; unsigned int def_q = 0; unsigned int num_tcs = 0; - unsigned int num_rx_queues = 1; + unsigned int num_rx_queues = adapter->num_rx_queues; + unsigned int num_tx_queues = adapter->num_tx_queues; int err; spin_lock_bh(&adapter->mbx_lock); @@ -1808,6 +1950,9 @@ static int ixgbevf_configure_dcb(struct ixgbevf_adapter *adapter) return err; if (num_tcs > 1) { + /* we need only one Tx queue */ + num_tx_queues = 1; + /* update default Tx ring register index */ adapter->tx_ring[0]->reg_idx = def_q; @@ -1816,7 +1961,8 @@ static int ixgbevf_configure_dcb(struct ixgbevf_adapter *adapter) } /* if we have a bad config abort request queue reset */ - if (adapter->num_rx_queues != num_rx_queues) { + if ((adapter->num_rx_queues != num_rx_queues) || + (adapter->num_tx_queues != num_tx_queues)) { /* force mailbox timeout to prevent further messages */ hw->mbx.timeout = 0; @@ -1917,6 +2063,10 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) clear_bit(__IXGBEVF_DOWN, &adapter->state); ixgbevf_napi_enable_all(adapter); + /* clear any pending interrupts, may auto mask */ + IXGBE_READ_REG(hw, IXGBE_VTEICR); + ixgbevf_irq_enable(adapter); + /* enable transmits */ netif_tx_start_all_queues(netdev); @@ -1924,21 +2074,14 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) ixgbevf_init_last_counter_stats(adapter); hw->mac.get_link_status = 1; - mod_timer(&adapter->watchdog_timer, jiffies); + mod_timer(&adapter->service_timer, jiffies); } void ixgbevf_up(struct ixgbevf_adapter *adapter) { - struct ixgbe_hw *hw = &adapter->hw; - ixgbevf_configure(adapter); ixgbevf_up_complete(adapter); - - /* clear any pending interrupts, may auto mask */ - IXGBE_READ_REG(hw, IXGBE_VTEICR); - - ixgbevf_irq_enable(adapter); } /** @@ -2045,22 +2188,19 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) ixgbevf_disable_rx_queue(adapter, adapter->rx_ring[i]); - netif_tx_disable(netdev); - - msleep(10); + usleep_range(10000, 20000); netif_tx_stop_all_queues(netdev); + /* call carrier off first to avoid false dev_watchdog timeouts */ + netif_carrier_off(netdev); + netif_tx_disable(netdev); + ixgbevf_irq_disable(adapter); ixgbevf_napi_disable_all(adapter); - del_timer_sync(&adapter->watchdog_timer); - /* can't call flush scheduled work here because it can deadlock - * if linkwatch_event tries to acquire the rtnl_lock which we are - * holding */ - while (adapter->flags & IXGBE_FLAG_IN_WATCHDOG_TASK) - msleep(1); + del_timer_sync(&adapter->service_timer); /* disable transmits in the hardware now that interrupts are off */ for (i = 0; i < adapter->num_tx_queues; i++) { @@ -2070,8 +2210,6 @@ void ixgbevf_down(struct ixgbevf_adapter *adapter) IXGBE_TXDCTL_SWFLSH); } - netif_carrier_off(netdev); - if (!pci_channel_offline(adapter->pdev)) ixgbevf_reset(adapter); @@ -2110,6 +2248,8 @@ void ixgbevf_reset(struct ixgbevf_adapter *adapter) memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len); } + + adapter->last_reset = jiffies; } static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, @@ -2181,8 +2321,19 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) return; /* we need as many queues as traffic classes */ - if (num_tcs > 1) + if (num_tcs > 1) { adapter->num_rx_queues = num_tcs; + } else { + u16 rss = min_t(u16, num_online_cpus(), IXGBEVF_MAX_RSS_QUEUES); + + switch (hw->api_version) { + case ixgbe_mbox_api_11: + adapter->num_rx_queues = rss; + adapter->num_tx_queues = rss; + default: + break; + } + } } /** @@ -2552,7 +2703,8 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; int i; - if (!adapter->link_up) + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) return; UPDATE_VF_COUNTER_32bit(IXGBE_VFGPRC, adapter->stats.last_vfgprc, @@ -2576,79 +2728,176 @@ void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) } /** - * ixgbevf_watchdog - Timer Call-back + * ixgbevf_service_timer - Timer Call-back * @data: pointer to adapter cast into an unsigned long **/ -static void ixgbevf_watchdog(unsigned long data) +static void ixgbevf_service_timer(unsigned long data) { struct ixgbevf_adapter *adapter = (struct ixgbevf_adapter *)data; + + /* Reset the timer */ + mod_timer(&adapter->service_timer, (HZ * 2) + jiffies); + + ixgbevf_service_event_schedule(adapter); +} + +static void ixgbevf_reset_subtask(struct ixgbevf_adapter *adapter) +{ + if (!(adapter->flags & IXGBEVF_FLAG_RESET_REQUESTED)) + return; + + adapter->flags &= ~IXGBEVF_FLAG_RESET_REQUESTED; + + /* If we're already down or resetting, just bail */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; + + adapter->tx_timeout_count++; + + ixgbevf_reinit_locked(adapter); +} + +/* ixgbevf_check_hang_subtask - check for hung queues and dropped interrupts + * @adapter - pointer to the device adapter structure + * + * This function serves two purposes. First it strobes the interrupt lines + * in order to make certain interrupts are occurring. Secondly it sets the + * bits needed to check for TX hangs. As a result we should immediately + * determine if a hang has occurred. + */ +static void ixgbevf_check_hang_subtask(struct ixgbevf_adapter *adapter) +{ struct ixgbe_hw *hw = &adapter->hw; u32 eics = 0; int i; - /* - * Do the watchdog outside of interrupt context due to the lovely - * delays that some of the newer hardware requires - */ + /* If we're down or resetting, just bail */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; - if (test_bit(__IXGBEVF_DOWN, &adapter->state)) - goto watchdog_short_circuit; + /* Force detection of hung controller */ + if (netif_carrier_ok(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + set_check_for_tx_hang(adapter->tx_ring[i]); + } /* get one bit for every active tx/rx interrupt vector */ for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) { struct ixgbevf_q_vector *qv = adapter->q_vector[i]; + if (qv->rx.ring || qv->tx.ring) eics |= 1 << i; } + /* Cause software interrupt to ensure rings are cleaned */ IXGBE_WRITE_REG(hw, IXGBE_VTEICS, eics); +} -watchdog_short_circuit: - schedule_work(&adapter->watchdog_task); +/** + * ixgbevf_watchdog_update_link - update the link status + * @adapter - pointer to the device adapter structure + **/ +static void ixgbevf_watchdog_update_link(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 link_speed = adapter->link_speed; + bool link_up = adapter->link_up; + s32 err; + + spin_lock_bh(&adapter->mbx_lock); + + err = hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + + spin_unlock_bh(&adapter->mbx_lock); + + /* if check for link returns error we will need to reset */ + if (err && time_after(jiffies, adapter->last_reset + (10 * HZ))) { + adapter->flags |= IXGBEVF_FLAG_RESET_REQUESTED; + link_up = false; + } + + adapter->link_up = link_up; + adapter->link_speed = link_speed; } /** - * ixgbevf_tx_timeout - Respond to a Tx Hang - * @netdev: network interface device structure + * ixgbevf_watchdog_link_is_up - update netif_carrier status and + * print link up message + * @adapter - pointer to the device adapter structure **/ -static void ixgbevf_tx_timeout(struct net_device *netdev) +static void ixgbevf_watchdog_link_is_up(struct ixgbevf_adapter *adapter) { - struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct net_device *netdev = adapter->netdev; - /* Do the reset outside of interrupt context */ - schedule_work(&adapter->reset_task); + /* only continue if link was previously down */ + if (netif_carrier_ok(netdev)) + return; + + dev_info(&adapter->pdev->dev, "NIC Link is Up %s\n", + (adapter->link_speed == IXGBE_LINK_SPEED_10GB_FULL) ? + "10 Gbps" : + (adapter->link_speed == IXGBE_LINK_SPEED_1GB_FULL) ? + "1 Gbps" : + (adapter->link_speed == IXGBE_LINK_SPEED_100_FULL) ? + "100 Mbps" : + "unknown speed"); + + netif_carrier_on(netdev); } -static void ixgbevf_reset_task(struct work_struct *work) +/** + * ixgbevf_watchdog_link_is_down - update netif_carrier status and + * print link down message + * @adapter - pointer to the adapter structure + **/ +static void ixgbevf_watchdog_link_is_down(struct ixgbevf_adapter *adapter) { - struct ixgbevf_adapter *adapter; - adapter = container_of(work, struct ixgbevf_adapter, reset_task); + struct net_device *netdev = adapter->netdev; - /* If we're already down or resetting, just bail */ + adapter->link_speed = 0; + + /* only continue if link was up previously */ + if (!netif_carrier_ok(netdev)) + return; + + dev_info(&adapter->pdev->dev, "NIC Link is Down\n"); + + netif_carrier_off(netdev); +} + +/** + * ixgbevf_watchdog_subtask - worker thread to bring link up + * @work: pointer to work_struct containing our data + **/ +static void ixgbevf_watchdog_subtask(struct ixgbevf_adapter *adapter) +{ + /* if interface is down do nothing */ if (test_bit(__IXGBEVF_DOWN, &adapter->state) || - test_bit(__IXGBEVF_REMOVING, &adapter->state) || test_bit(__IXGBEVF_RESETTING, &adapter->state)) return; - adapter->tx_timeout_count++; + ixgbevf_watchdog_update_link(adapter); - ixgbevf_reinit_locked(adapter); + if (adapter->link_up) + ixgbevf_watchdog_link_is_up(adapter); + else + ixgbevf_watchdog_link_is_down(adapter); + + ixgbevf_update_stats(adapter); } /** - * ixgbevf_watchdog_task - worker thread to bring link up + * ixgbevf_service_task - manages and runs subtasks * @work: pointer to work_struct containing our data **/ -static void ixgbevf_watchdog_task(struct work_struct *work) +static void ixgbevf_service_task(struct work_struct *work) { struct ixgbevf_adapter *adapter = container_of(work, struct ixgbevf_adapter, - watchdog_task); - struct net_device *netdev = adapter->netdev; + service_task); struct ixgbe_hw *hw = &adapter->hw; - u32 link_speed = adapter->link_speed; - bool link_up = adapter->link_up; - s32 need_reset; if (IXGBE_REMOVED(hw->hw_addr)) { if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) { @@ -2658,73 +2907,13 @@ static void ixgbevf_watchdog_task(struct work_struct *work) } return; } - ixgbevf_queue_reset_subtask(adapter); - - adapter->flags |= IXGBE_FLAG_IN_WATCHDOG_TASK; - - /* - * Always check the link on the watchdog because we have - * no LSC interrupt - */ - spin_lock_bh(&adapter->mbx_lock); - - need_reset = hw->mac.ops.check_link(hw, &link_speed, &link_up, false); - - spin_unlock_bh(&adapter->mbx_lock); - - if (need_reset) { - adapter->link_up = link_up; - adapter->link_speed = link_speed; - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); - schedule_work(&adapter->reset_task); - goto pf_has_reset; - } - adapter->link_up = link_up; - adapter->link_speed = link_speed; - - if (link_up) { - if (!netif_carrier_ok(netdev)) { - char *link_speed_string; - switch (link_speed) { - case IXGBE_LINK_SPEED_10GB_FULL: - link_speed_string = "10 Gbps"; - break; - case IXGBE_LINK_SPEED_1GB_FULL: - link_speed_string = "1 Gbps"; - break; - case IXGBE_LINK_SPEED_100_FULL: - link_speed_string = "100 Mbps"; - break; - default: - link_speed_string = "unknown speed"; - break; - } - dev_info(&adapter->pdev->dev, - "NIC Link is Up, %s\n", link_speed_string); - netif_carrier_on(netdev); - netif_tx_wake_all_queues(netdev); - } - } else { - adapter->link_up = false; - adapter->link_speed = 0; - if (netif_carrier_ok(netdev)) { - dev_info(&adapter->pdev->dev, "NIC Link is Down\n"); - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); - } - } - ixgbevf_update_stats(adapter); - -pf_has_reset: - /* Reset the timer */ - if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && - !test_bit(__IXGBEVF_REMOVING, &adapter->state)) - mod_timer(&adapter->watchdog_timer, - round_jiffies(jiffies + (2 * HZ))); + ixgbevf_queue_reset_subtask(adapter); + ixgbevf_reset_subtask(adapter); + ixgbevf_watchdog_subtask(adapter); + ixgbevf_check_hang_subtask(adapter); - adapter->flags &= ~IXGBE_FLAG_IN_WATCHDOG_TASK; + ixgbevf_service_event_complete(adapter); } /** @@ -2944,10 +3133,6 @@ static int ixgbevf_open(struct net_device *netdev) if (!adapter->num_msix_vectors) return -ENOMEM; - /* disallow open during test */ - if (test_bit(__IXGBEVF_TESTING, &adapter->state)) - return -EBUSY; - if (hw->adapter_stopped) { ixgbevf_reset(adapter); /* if adapter is still stopped then PF isn't up and @@ -2960,6 +3145,12 @@ static int ixgbevf_open(struct net_device *netdev) } } + /* disallow open during test */ + if (test_bit(__IXGBEVF_TESTING, &adapter->state)) + return -EBUSY; + + netif_carrier_off(netdev); + /* allocate transmit descriptors */ err = ixgbevf_setup_all_tx_resources(adapter); if (err) @@ -2979,15 +3170,11 @@ static int ixgbevf_open(struct net_device *netdev) */ ixgbevf_map_rings_to_vectors(adapter); - ixgbevf_up_complete(adapter); - - /* clear any pending interrupts, may auto mask */ - IXGBE_READ_REG(hw, IXGBE_VTEICR); err = ixgbevf_request_irq(adapter); if (err) goto err_req_irq; - ixgbevf_irq_enable(adapter); + ixgbevf_up_complete(adapter); return 0; @@ -3452,8 +3639,8 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) first->bytecount = skb->len; first->gso_segs = 1; - if (vlan_tx_tag_present(skb)) { - tx_flags |= vlan_tx_tag_get(skb); + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb); tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_VLAN; } @@ -3822,28 +4009,28 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; - netdev->vlan_features |= NETIF_F_TSO; - netdev->vlan_features |= NETIF_F_TSO6; - netdev->vlan_features |= NETIF_F_IP_CSUM; - netdev->vlan_features |= NETIF_F_IPV6_CSUM; - netdev->vlan_features |= NETIF_F_SG; + netdev->vlan_features |= NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_SG; if (pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; netdev->priv_flags |= IFF_UNICAST_FLT; - init_timer(&adapter->watchdog_timer); - adapter->watchdog_timer.function = ixgbevf_watchdog; - adapter->watchdog_timer.data = (unsigned long)adapter; - if (IXGBE_REMOVED(hw->hw_addr)) { err = -EIO; goto err_sw_init; } - INIT_WORK(&adapter->reset_task, ixgbevf_reset_task); - INIT_WORK(&adapter->watchdog_task, ixgbevf_watchdog_task); - set_bit(__IXGBEVF_WORK_INIT, &adapter->state); + + setup_timer(&adapter->service_timer, &ixgbevf_service_timer, + (unsigned long)adapter); + + INIT_WORK(&adapter->service_task, ixgbevf_service_task); + set_bit(__IXGBEVF_SERVICE_INITED, &adapter->state); + clear_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state); err = ixgbevf_init_interrupt_scheme(adapter); if (err) @@ -3917,11 +4104,7 @@ static void ixgbevf_remove(struct pci_dev *pdev) adapter = netdev_priv(netdev); set_bit(__IXGBEVF_REMOVING, &adapter->state); - - del_timer_sync(&adapter->watchdog_timer); - - cancel_work_sync(&adapter->reset_task); - cancel_work_sync(&adapter->watchdog_task); + cancel_work_sync(&adapter->service_task); if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); @@ -3955,7 +4138,7 @@ static pci_ers_result_t ixgbevf_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct ixgbevf_adapter *adapter = netdev_priv(netdev); - if (!test_bit(__IXGBEVF_WORK_INIT, &adapter->state)) + if (!test_bit(__IXGBEVF_SERVICE_INITED, &adapter->state)) return PCI_ERS_RESULT_DISCONNECT; rtnl_lock(); diff --git a/drivers/net/ethernet/intel/ixgbevf/regs.h b/drivers/net/ethernet/intel/ixgbevf/regs.h index 09dd8f698bea..3e712fd6e695 100644 --- a/drivers/net/ethernet/intel/ixgbevf/regs.h +++ b/drivers/net/ethernet/intel/ixgbevf/regs.h @@ -69,6 +69,16 @@ #define IXGBE_VFGOTC_LSB 0x02020 #define IXGBE_VFGOTC_MSB 0x02024 #define IXGBE_VFMPRC 0x01034 +#define IXGBE_VFMRQC 0x3000 +#define IXGBE_VFRSSRK(x) (0x3100 + ((x) * 4)) +#define IXGBE_VFRETA(x) (0x3200 + ((x) * 4)) + +/* VFMRQC bits */ +#define IXGBE_VFMRQC_RSSEN 0x00000001 /* RSS Enable */ +#define IXGBE_VFMRQC_RSS_FIELD_IPV4_TCP 0x00010000 +#define IXGBE_VFMRQC_RSS_FIELD_IPV4 0x00020000 +#define IXGBE_VFMRQC_RSS_FIELD_IPV6 0x00100000 +#define IXGBE_VFMRQC_RSS_FIELD_IPV6_TCP 0x00200000 #define IXGBE_WRITE_FLUSH(a) (IXGBE_READ_REG(a, IXGBE_VFSTATUS)) |