diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-16 04:42:13 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-16 04:42:13 +0300 |
commit | 9ff9b0d392ea08090cd1780fb196f36dbb586529 (patch) | |
tree | 276a3a5c4525b84dee64eda30b423fc31bf94850 /drivers/net/ethernet/google | |
parent | 840e5bb326bbcb16ce82dd2416d2769de4839aea (diff) | |
parent | 105faa8742437c28815b2a3eb8314ebc5fd9288c (diff) | |
download | linux-9ff9b0d392ea08090cd1780fb196f36dbb586529.tar.xz |
Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
- Add redirect_neigh() BPF packet redirect helper, allowing to limit
stack traversal in common container configs and improving TCP
back-pressure.
Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain.
- Expand netlink policy support and improve policy export to user
space. (Ge)netlink core performs request validation according to
declared policies. Expand the expressiveness of those policies
(min/max length and bitmasks). Allow dumping policies for particular
commands. This is used for feature discovery by user space (instead
of kernel version parsing or trial and error).
- Support IGMPv3/MLDv2 multicast listener discovery protocols in
bridge.
- Allow more than 255 IPv4 multicast interfaces.
- Add support for Type of Service (ToS) reflection in SYN/SYN-ACK
packets of TCPv6.
- In Multi-patch TCP (MPTCP) support concurrent transmission of data on
multiple subflows in a load balancing scenario. Enhance advertising
addresses via the RM_ADDR/ADD_ADDR options.
- Support SMC-Dv2 version of SMC, which enables multi-subnet
deployments.
- Allow more calls to same peer in RxRPC.
- Support two new Controller Area Network (CAN) protocols - CAN-FD and
ISO 15765-2:2016.
- Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit
kernel problem.
- Add TC actions for implementing MPLS L2 VPNs.
- Improve nexthop code - e.g. handle various corner cases when nexthop
objects are removed from groups better, skip unnecessary
notifications and make it easier to offload nexthops into HW by
converting to a blocking notifier.
- Support adding and consuming TCP header options by BPF programs,
opening the doors for easy experimental and deployment-specific TCP
option use.
- Reorganize TCP congestion control (CC) initialization to simplify
life of TCP CC implemented in BPF.
- Add support for shipping BPF programs with the kernel and loading
them early on boot via the User Mode Driver mechanism, hence reusing
all the user space infra we have.
- Support sleepable BPF programs, initially targeting LSM and tracing.
- Add bpf_d_path() helper for returning full path for given 'struct
path'.
- Make bpf_tail_call compatible with bpf-to-bpf calls.
- Allow BPF programs to call map_update_elem on sockmaps.
- Add BPF Type Format (BTF) support for type and enum discovery, as
well as support for using BTF within the kernel itself (current use
is for pretty printing structures).
- Support listing and getting information about bpf_links via the bpf
syscall.
- Enhance kernel interfaces around NIC firmware update. Allow
specifying overwrite mask to control if settings etc. are reset
during update; report expected max time operation may take to users;
support firmware activation without machine reboot incl. limits of
how much impact reset may have (e.g. dropping link or not).
- Extend ethtool configuration interface to report IEEE-standard
counters, to limit the need for per-vendor logic in user space.
- Adopt or extend devlink use for debug, monitoring, fw update in many
drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx,
dpaa2-eth).
- In mlxsw expose critical and emergency SFP module temperature alarms.
Refactor port buffer handling to make the defaults more suitable and
support setting these values explicitly via the DCBNL interface.
- Add XDP support for Intel's igb driver.
- Support offloading TC flower classification and filtering rules to
mscc_ocelot switches.
- Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as
fixed interval period pulse generator and one-step timestamping in
dpaa-eth.
- Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3)
offload.
- Add Lynx PHY/PCS MDIO module, and convert various drivers which have
this HW to use it. Convert mvpp2 to split PCS.
- Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as
7-port Mediatek MT7531 IP.
- Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver,
and wcn3680 support in wcn36xx.
- Improve performance for packets which don't require much offloads on
recent Mellanox NICs by 20% by making multiple packets share a
descriptor entry.
- Move chelsio inline crypto drivers (for TLS and IPsec) from the
crypto subtree to drivers/net. Move MDIO drivers out of the phy
directory.
- Clean up a lot of W=1 warnings, reportedly the actively developed
subsections of networking drivers should now build W=1 warning free.
- Make sure drivers don't use in_interrupt() to dynamically adapt their
code. Convert tasklets to use new tasklet_setup API (sadly this
conversion is not yet complete).
* tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits)
Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH"
net, sockmap: Don't call bpf_prog_put() on NULL pointer
bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo
bpf, sockmap: Add locking annotations to iterator
netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements
net: fix pos incrementment in ipv6_route_seq_next
net/smc: fix invalid return code in smcd_new_buf_create()
net/smc: fix valid DMBE buffer sizes
net/smc: fix use-after-free of delayed events
bpfilter: Fix build error with CONFIG_BPFILTER_UMH
cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr
net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info
bpf: Fix register equivalence tracking.
rxrpc: Fix loss of final ack on shutdown
rxrpc: Fix bundle counting for exclusive connections
netfilter: restore NF_INET_NUMHOOKS
ibmveth: Identify ingress large send packets.
ibmveth: Switch order of ibmveth_helper calls.
cxgb4: handle 4-tuple PEDIT to NAT mode translation
selftests: Add VRF route leaking tests
...
Diffstat (limited to 'drivers/net/ethernet/google')
-rw-r--r-- | drivers/net/ethernet/google/gve/gve.h | 106 | ||||
-rw-r--r-- | drivers/net/ethernet/google/gve/gve_adminq.c | 315 | ||||
-rw-r--r-- | drivers/net/ethernet/google/gve/gve_adminq.h | 62 | ||||
-rw-r--r-- | drivers/net/ethernet/google/gve/gve_ethtool.c | 365 | ||||
-rw-r--r-- | drivers/net/ethernet/google/gve/gve_main.c | 301 | ||||
-rw-r--r-- | drivers/net/ethernet/google/gve/gve_register.h | 1 | ||||
-rw-r--r-- | drivers/net/ethernet/google/gve/gve_rx.c | 37 |
7 files changed, 1023 insertions, 164 deletions
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index ebc37e256922..f5c80229ea96 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -27,6 +27,17 @@ /* 1 for management, 1 for rx, 1 for tx */ #define GVE_MIN_MSIX 3 +/* Numbers of gve tx/rx stats in stats report. */ +#define GVE_TX_STATS_REPORT_NUM 5 +#define GVE_RX_STATS_REPORT_NUM 2 + +/* Interval to schedule a stats report update, 20000ms. */ +#define GVE_STATS_REPORT_TIMER_PERIOD 20000 + +/* Numbers of NIC tx/rx stats in stats report. */ +#define NIC_TX_STATS_REPORT_NUM 0 +#define NIC_RX_STATS_REPORT_NUM 4 + /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */ struct gve_rx_desc_queue { struct gve_rx_desc *desc_ring; /* the descriptor ring */ @@ -71,6 +82,11 @@ struct gve_rx_ring { u32 cnt; /* free-running total number of completed packets */ u32 fill_cnt; /* free-running total number of descs and buffs posted */ u32 mask; /* masks the cnt and fill_cnt to the size of the ring */ + u64 rx_copybreak_pkt; /* free-running count of copybreak packets */ + u64 rx_copied_pkt; /* free-running total number of copied packets */ + u64 rx_skb_alloc_fail; /* free-running count of skb alloc fails */ + u64 rx_buf_alloc_fail; /* free-running count of buffer alloc fails */ + u64 rx_desc_err_dropped_pkt; /* free-running count of packets dropped by descriptor error */ u32 q_num; /* queue index */ u32 ntfy_id; /* notification block index */ struct gve_queue_resources *q_resources; /* head and tail pointer idx */ @@ -202,24 +218,63 @@ struct gve_priv { dma_addr_t adminq_bus_addr; u32 adminq_mask; /* masks prod_cnt to adminq size */ u32 adminq_prod_cnt; /* free-running count of AQ cmds executed */ - + u32 adminq_cmd_fail; /* free-running count of AQ cmds failed */ + u32 adminq_timeouts; /* free-running count of AQ cmds timeouts */ + /* free-running count of per AQ cmd executed */ + u32 adminq_describe_device_cnt; + u32 adminq_cfg_device_resources_cnt; + u32 adminq_register_page_list_cnt; + u32 adminq_unregister_page_list_cnt; + u32 adminq_create_tx_queue_cnt; + u32 adminq_create_rx_queue_cnt; + u32 adminq_destroy_tx_queue_cnt; + u32 adminq_destroy_rx_queue_cnt; + u32 adminq_dcfg_device_resources_cnt; + u32 adminq_set_driver_parameter_cnt; + u32 adminq_report_stats_cnt; + u32 adminq_report_link_speed_cnt; + + /* Global stats */ + u32 interface_up_cnt; /* count of times interface turned up since last reset */ + u32 interface_down_cnt; /* count of times interface turned down since last reset */ + u32 reset_cnt; /* count of reset */ + u32 page_alloc_fail; /* count of page alloc fails */ + u32 dma_mapping_error; /* count of dma mapping errors */ + u32 stats_report_trigger_cnt; /* count of device-requested stats-reports since last reset */ struct workqueue_struct *gve_wq; struct work_struct service_task; + struct work_struct stats_report_task; unsigned long service_task_flags; unsigned long state_flags; + + struct gve_stats_report *stats_report; + u64 stats_report_len; + dma_addr_t stats_report_bus; /* dma address for the stats report */ + unsigned long ethtool_flags; + + unsigned long stats_report_timer_period; + struct timer_list stats_report_timer; + + /* Gvnic device link speed from hypervisor. */ + u64 link_speed; }; -enum gve_service_task_flags { - GVE_PRIV_FLAGS_DO_RESET = BIT(1), - GVE_PRIV_FLAGS_RESET_IN_PROGRESS = BIT(2), - GVE_PRIV_FLAGS_PROBE_IN_PROGRESS = BIT(3), +enum gve_service_task_flags_bit { + GVE_PRIV_FLAGS_DO_RESET = 1, + GVE_PRIV_FLAGS_RESET_IN_PROGRESS = 2, + GVE_PRIV_FLAGS_PROBE_IN_PROGRESS = 3, + GVE_PRIV_FLAGS_DO_REPORT_STATS = 4, }; -enum gve_state_flags { - GVE_PRIV_FLAGS_ADMIN_QUEUE_OK = BIT(1), - GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK = BIT(2), - GVE_PRIV_FLAGS_DEVICE_RINGS_OK = BIT(3), - GVE_PRIV_FLAGS_NAPI_ENABLED = BIT(4), +enum gve_state_flags_bit { + GVE_PRIV_FLAGS_ADMIN_QUEUE_OK = 1, + GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK = 2, + GVE_PRIV_FLAGS_DEVICE_RINGS_OK = 3, + GVE_PRIV_FLAGS_NAPI_ENABLED = 4, +}; + +enum gve_ethtool_flags_bit { + GVE_PRIV_FLAGS_REPORT_STATS = 0, }; static inline bool gve_get_do_reset(struct gve_priv *priv) @@ -269,6 +324,22 @@ static inline void gve_clear_probe_in_progress(struct gve_priv *priv) clear_bit(GVE_PRIV_FLAGS_PROBE_IN_PROGRESS, &priv->service_task_flags); } +static inline bool gve_get_do_report_stats(struct gve_priv *priv) +{ + return test_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS, + &priv->service_task_flags); +} + +static inline void gve_set_do_report_stats(struct gve_priv *priv) +{ + set_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS, &priv->service_task_flags); +} + +static inline void gve_clear_do_report_stats(struct gve_priv *priv) +{ + clear_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS, &priv->service_task_flags); +} + static inline bool gve_get_admin_queue_ok(struct gve_priv *priv) { return test_bit(GVE_PRIV_FLAGS_ADMIN_QUEUE_OK, &priv->state_flags); @@ -329,6 +400,16 @@ static inline void gve_clear_napi_enabled(struct gve_priv *priv) clear_bit(GVE_PRIV_FLAGS_NAPI_ENABLED, &priv->state_flags); } +static inline bool gve_get_report_stats(struct gve_priv *priv) +{ + return test_bit(GVE_PRIV_FLAGS_REPORT_STATS, &priv->ethtool_flags); +} + +static inline void gve_clear_report_stats(struct gve_priv *priv) +{ + clear_bit(GVE_PRIV_FLAGS_REPORT_STATS, &priv->ethtool_flags); +} + /* Returns the address of the ntfy_blocks irq doorbell */ static inline __be32 __iomem *gve_irq_doorbell(struct gve_priv *priv, @@ -426,7 +507,8 @@ static inline bool gve_can_recycle_pages(struct net_device *dev) } /* buffers */ -int gve_alloc_page(struct device *dev, struct page **page, dma_addr_t *dma, +int gve_alloc_page(struct gve_priv *priv, struct device *dev, + struct page **page, dma_addr_t *dma, enum dma_data_direction); void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma, enum dma_data_direction); @@ -450,6 +532,8 @@ int gve_reset(struct gve_priv *priv, bool attempt_teardown); int gve_adjust_queues(struct gve_priv *priv, struct gve_queue_config new_rx_config, struct gve_queue_config new_tx_config); +/* report stats handling */ +void gve_handle_report_stats(struct gve_priv *priv); /* exported by ethtool.c */ extern const struct ethtool_ops gve_ethtool_ops; /* needed by ethtool */ diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index c3ba7baf0107..24ae6a28a806 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -23,6 +23,20 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv) priv->adminq_mask = (PAGE_SIZE / sizeof(union gve_adminq_command)) - 1; priv->adminq_prod_cnt = 0; + priv->adminq_cmd_fail = 0; + priv->adminq_timeouts = 0; + priv->adminq_describe_device_cnt = 0; + priv->adminq_cfg_device_resources_cnt = 0; + priv->adminq_register_page_list_cnt = 0; + priv->adminq_unregister_page_list_cnt = 0; + priv->adminq_create_tx_queue_cnt = 0; + priv->adminq_create_rx_queue_cnt = 0; + priv->adminq_destroy_tx_queue_cnt = 0; + priv->adminq_destroy_rx_queue_cnt = 0; + priv->adminq_dcfg_device_resources_cnt = 0; + priv->adminq_set_driver_parameter_cnt = 0; + priv->adminq_report_stats_cnt = 0; + priv->adminq_report_link_speed_cnt = 0; /* Setup Admin queue with the device */ iowrite32be(priv->adminq_bus_addr / PAGE_SIZE, @@ -81,17 +95,18 @@ static bool gve_adminq_wait_for_cmd(struct gve_priv *priv, u32 prod_cnt) return false; } -static int gve_adminq_parse_err(struct device *dev, u32 status) +static int gve_adminq_parse_err(struct gve_priv *priv, u32 status) { if (status != GVE_ADMINQ_COMMAND_PASSED && - status != GVE_ADMINQ_COMMAND_UNSET) - dev_err(dev, "AQ command failed with status %d\n", status); - + status != GVE_ADMINQ_COMMAND_UNSET) { + dev_err(&priv->pdev->dev, "AQ command failed with status %d\n", status); + priv->adminq_cmd_fail++; + } switch (status) { case GVE_ADMINQ_COMMAND_PASSED: return 0; case GVE_ADMINQ_COMMAND_UNSET: - dev_err(dev, "parse_aq_err: err and status both unset, this should not be possible.\n"); + dev_err(&priv->pdev->dev, "parse_aq_err: err and status both unset, this should not be possible.\n"); return -EINVAL; case GVE_ADMINQ_COMMAND_ERROR_ABORTED: case GVE_ADMINQ_COMMAND_ERROR_CANCELLED: @@ -116,36 +131,145 @@ static int gve_adminq_parse_err(struct device *dev, u32 status) case GVE_ADMINQ_COMMAND_ERROR_UNIMPLEMENTED: return -ENOTSUPP; default: - dev_err(dev, "parse_aq_err: unknown status code %d\n", status); + dev_err(&priv->pdev->dev, "parse_aq_err: unknown status code %d\n", status); return -EINVAL; } } +/* Flushes all AQ commands currently queued and waits for them to complete. + * If there are failures, it will return the first error. + */ +static int gve_adminq_kick_and_wait(struct gve_priv *priv) +{ + u32 tail, head; + int i; + + tail = ioread32be(&priv->reg_bar0->adminq_event_counter); + head = priv->adminq_prod_cnt; + + gve_adminq_kick_cmd(priv, head); + if (!gve_adminq_wait_for_cmd(priv, head)) { + dev_err(&priv->pdev->dev, "AQ commands timed out, need to reset AQ\n"); + priv->adminq_timeouts++; + return -ENOTRECOVERABLE; + } + + for (i = tail; i < head; i++) { + union gve_adminq_command *cmd; + u32 status, err; + + cmd = &priv->adminq[i & priv->adminq_mask]; + status = be32_to_cpu(READ_ONCE(cmd->status)); + err = gve_adminq_parse_err(priv, status); + if (err) + // Return the first error if we failed. + return err; + } + + return 0; +} + /* This function is not threadsafe - the caller is responsible for any * necessary locks. */ -int gve_adminq_execute_cmd(struct gve_priv *priv, - union gve_adminq_command *cmd_orig) +static int gve_adminq_issue_cmd(struct gve_priv *priv, + union gve_adminq_command *cmd_orig) { union gve_adminq_command *cmd; - u32 status = 0; - u32 prod_cnt; + u32 opcode; + u32 tail; + + tail = ioread32be(&priv->reg_bar0->adminq_event_counter); + + // Check if next command will overflow the buffer. + if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) == tail) { + int err; + + // Flush existing commands to make room. + err = gve_adminq_kick_and_wait(priv); + if (err) + return err; + + // Retry. + tail = ioread32be(&priv->reg_bar0->adminq_event_counter); + if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) == tail) { + // This should never happen. We just flushed the + // command queue so there should be enough space. + return -ENOMEM; + } + } cmd = &priv->adminq[priv->adminq_prod_cnt & priv->adminq_mask]; priv->adminq_prod_cnt++; - prod_cnt = priv->adminq_prod_cnt; memcpy(cmd, cmd_orig, sizeof(*cmd_orig)); - - gve_adminq_kick_cmd(priv, prod_cnt); - if (!gve_adminq_wait_for_cmd(priv, prod_cnt)) { - dev_err(&priv->pdev->dev, "AQ command timed out, need to reset AQ\n"); - return -ENOTRECOVERABLE; + opcode = be32_to_cpu(READ_ONCE(cmd->opcode)); + + switch (opcode) { + case GVE_ADMINQ_DESCRIBE_DEVICE: + priv->adminq_describe_device_cnt++; + break; + case GVE_ADMINQ_CONFIGURE_DEVICE_RESOURCES: + priv->adminq_cfg_device_resources_cnt++; + break; + case GVE_ADMINQ_REGISTER_PAGE_LIST: + priv->adminq_register_page_list_cnt++; + break; + case GVE_ADMINQ_UNREGISTER_PAGE_LIST: + priv->adminq_unregister_page_list_cnt++; + break; + case GVE_ADMINQ_CREATE_TX_QUEUE: + priv->adminq_create_tx_queue_cnt++; + break; + case GVE_ADMINQ_CREATE_RX_QUEUE: + priv->adminq_create_rx_queue_cnt++; + break; + case GVE_ADMINQ_DESTROY_TX_QUEUE: + priv->adminq_destroy_tx_queue_cnt++; + break; + case GVE_ADMINQ_DESTROY_RX_QUEUE: + priv->adminq_destroy_rx_queue_cnt++; + break; + case GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES: + priv->adminq_dcfg_device_resources_cnt++; + break; + case GVE_ADMINQ_SET_DRIVER_PARAMETER: + priv->adminq_set_driver_parameter_cnt++; + break; + case GVE_ADMINQ_REPORT_STATS: + priv->adminq_report_stats_cnt++; + break; + case GVE_ADMINQ_REPORT_LINK_SPEED: + priv->adminq_report_link_speed_cnt++; + break; + default: + dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode); } - memcpy(cmd_orig, cmd, sizeof(*cmd)); - status = be32_to_cpu(READ_ONCE(cmd->status)); - return gve_adminq_parse_err(&priv->pdev->dev, status); + return 0; +} + +/* This function is not threadsafe - the caller is responsible for any + * necessary locks. + * The caller is also responsible for making sure there are no commands + * waiting to be executed. + */ +static int gve_adminq_execute_cmd(struct gve_priv *priv, union gve_adminq_command *cmd_orig) +{ + u32 tail, head; + int err; + + tail = ioread32be(&priv->reg_bar0->adminq_event_counter); + head = priv->adminq_prod_cnt; + if (tail != head) + // This is not a valid path + return -EINVAL; + + err = gve_adminq_issue_cmd(priv, cmd_orig); + if (err) + return err; + + return gve_adminq_kick_and_wait(priv); } /* The device specifies that the management vector can either be the first irq @@ -190,29 +314,50 @@ int gve_adminq_deconfigure_device_resources(struct gve_priv *priv) return gve_adminq_execute_cmd(priv, &cmd); } -int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index) +static int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index) { struct gve_tx_ring *tx = &priv->tx[queue_index]; union gve_adminq_command cmd; + int err; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_TX_QUEUE); cmd.create_tx_queue = (struct gve_adminq_create_tx_queue) { .queue_id = cpu_to_be32(queue_index), .reserved = 0, - .queue_resources_addr = cpu_to_be64(tx->q_resources_bus), + .queue_resources_addr = + cpu_to_be64(tx->q_resources_bus), .tx_ring_addr = cpu_to_be64(tx->bus), .queue_page_list_id = cpu_to_be32(tx->tx_fifo.qpl->id), .ntfy_id = cpu_to_be32(tx->ntfy_id), }; - return gve_adminq_execute_cmd(priv, &cmd); + err = gve_adminq_issue_cmd(priv, &cmd); + if (err) + return err; + + return 0; +} + +int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues) +{ + int err; + int i; + + for (i = 0; i < num_queues; i++) { + err = gve_adminq_create_tx_queue(priv, i); + if (err) + return err; + } + + return gve_adminq_kick_and_wait(priv); } -int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) +static int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) { struct gve_rx_ring *rx = &priv->rx[queue_index]; union gve_adminq_command cmd; + int err; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE); @@ -227,12 +372,31 @@ int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index) .queue_page_list_id = cpu_to_be32(rx->data.qpl->id), }; - return gve_adminq_execute_cmd(priv, &cmd); + err = gve_adminq_issue_cmd(priv, &cmd); + if (err) + return err; + + return 0; } -int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index) +int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues) +{ + int err; + int i; + + for (i = 0; i < num_queues; i++) { + err = gve_adminq_create_rx_queue(priv, i); + if (err) + return err; + } + + return gve_adminq_kick_and_wait(priv); +} + +static int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index) { union gve_adminq_command cmd; + int err; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_TX_QUEUE); @@ -240,12 +404,31 @@ int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index) .queue_id = cpu_to_be32(queue_index), }; - return gve_adminq_execute_cmd(priv, &cmd); + err = gve_adminq_issue_cmd(priv, &cmd); + if (err) + return err; + + return 0; +} + +int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 num_queues) +{ + int err; + int i; + + for (i = 0; i < num_queues; i++) { + err = gve_adminq_destroy_tx_queue(priv, i); + if (err) + return err; + } + + return gve_adminq_kick_and_wait(priv); } -int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index) +static int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index) { union gve_adminq_command cmd; + int err; memset(&cmd, 0, sizeof(cmd)); cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_RX_QUEUE); @@ -253,7 +436,25 @@ int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index) .queue_id = cpu_to_be32(queue_index), }; - return gve_adminq_execute_cmd(priv, &cmd); + err = gve_adminq_issue_cmd(priv, &cmd); + if (err) + return err; + + return 0; +} + +int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues) +{ + int err; + int i; + + for (i = 0; i < num_queues; i++) { + err = gve_adminq_destroy_rx_queue(priv, i); + if (err) + return err; + } + + return gve_adminq_kick_and_wait(priv); } int gve_adminq_describe_device(struct gve_priv *priv) @@ -283,8 +484,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries); if (priv->tx_desc_cnt * sizeof(priv->tx->desc[0]) < PAGE_SIZE) { - netif_err(priv, drv, priv->dev, "Tx desc count %d too low\n", - priv->tx_desc_cnt); + dev_err(&priv->pdev->dev, "Tx desc count %d too low\n", priv->tx_desc_cnt); err = -EINVAL; goto free_device_descriptor; } @@ -293,8 +493,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) < PAGE_SIZE || priv->rx_desc_cnt * sizeof(priv->rx->data.data_ring[0]) < PAGE_SIZE) { - netif_err(priv, drv, priv->dev, "Rx desc count %d too low\n", - priv->rx_desc_cnt); + dev_err(&priv->pdev->dev, "Rx desc count %d too low\n", priv->rx_desc_cnt); err = -EINVAL; goto free_device_descriptor; } @@ -302,8 +501,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) be64_to_cpu(descriptor->max_registered_pages); mtu = be16_to_cpu(descriptor->mtu); if (mtu < ETH_MIN_MTU) { - netif_err(priv, drv, priv->dev, "MTU %d below minimum MTU\n", - mtu); + dev_err(&priv->pdev->dev, "MTU %d below minimum MTU\n", mtu); err = -EINVAL; goto free_device_descriptor; } @@ -311,12 +509,12 @@ int gve_adminq_describe_device(struct gve_priv *priv) priv->num_event_counters = be16_to_cpu(descriptor->counters); ether_addr_copy(priv->dev->dev_addr, descriptor->mac); mac = descriptor->mac; - netif_info(priv, drv, priv->dev, "MAC addr: %pM\n", mac); + dev_info(&priv->pdev->dev, "MAC addr: %pM\n", mac); priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl); priv->rx_pages_per_qpl = be16_to_cpu(descriptor->rx_pages_per_qpl); if (priv->rx_pages_per_qpl < priv->rx_desc_cnt) { - netif_err(priv, drv, priv->dev, "rx_pages_per_qpl cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n", - priv->rx_pages_per_qpl); + dev_err(&priv->pdev->dev, "rx_pages_per_qpl cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n", + priv->rx_pages_per_qpl); priv->rx_desc_cnt = priv->rx_pages_per_qpl; } priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues); @@ -385,3 +583,46 @@ int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu) return gve_adminq_execute_cmd(priv, &cmd); } + +int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, + dma_addr_t stats_report_addr, u64 interval) +{ + union gve_adminq_command cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_STATS); + cmd.report_stats = (struct gve_adminq_report_stats) { + .stats_report_len = cpu_to_be64(stats_report_len), + .stats_report_addr = cpu_to_be64(stats_report_addr), + .interval = cpu_to_be64(interval), + }; + + return gve_adminq_execute_cmd(priv, &cmd); +} + +int gve_adminq_report_link_speed(struct gve_priv *priv) +{ + union gve_adminq_command gvnic_cmd; + dma_addr_t link_speed_region_bus; + __be64 *link_speed_region; + int err; + + link_speed_region = + dma_alloc_coherent(&priv->pdev->dev, sizeof(*link_speed_region), + &link_speed_region_bus, GFP_KERNEL); + + if (!link_speed_region) + return -ENOMEM; + + memset(&gvnic_cmd, 0, sizeof(gvnic_cmd)); + gvnic_cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_LINK_SPEED); + gvnic_cmd.report_link_speed.link_speed_address = + cpu_to_be64(link_speed_region_bus); + + err = gve_adminq_execute_cmd(priv, &gvnic_cmd); + + priv->link_speed = be64_to_cpu(*link_speed_region); + dma_free_coherent(&priv->pdev->dev, sizeof(*link_speed_region), link_speed_region, + link_speed_region_bus); + return err; +} diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h index 4dfa06edc0f8..281de8326bc5 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.h +++ b/drivers/net/ethernet/google/gve/gve_adminq.h @@ -21,6 +21,8 @@ enum gve_adminq_opcodes { GVE_ADMINQ_DESTROY_RX_QUEUE = 0x8, GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES = 0x9, GVE_ADMINQ_SET_DRIVER_PARAMETER = 0xB, + GVE_ADMINQ_REPORT_STATS = 0xC, + GVE_ADMINQ_REPORT_LINK_SPEED = 0xD }; /* Admin queue status codes */ @@ -172,6 +174,51 @@ struct gve_adminq_set_driver_parameter { static_assert(sizeof(struct gve_adminq_set_driver_parameter) == 16); +struct gve_adminq_report_stats { + __be64 stats_report_len; + __be64 stats_report_addr; + __be64 interval; +}; + +static_assert(sizeof(struct gve_adminq_report_stats) == 24); + +struct gve_adminq_report_link_speed { + __be64 link_speed_address; +}; + +static_assert(sizeof(struct gve_adminq_report_link_speed) == 8); + +struct stats { + __be32 stat_name; + __be32 queue_id; + __be64 value; +}; + +static_assert(sizeof(struct stats) == 16); + +struct gve_stats_report { + __be64 written_count; + struct stats stats[0]; +}; + +static_assert(sizeof(struct gve_stats_report) == 8); + +enum gve_stat_names { + // stats from gve + TX_WAKE_CNT = 1, + TX_STOP_CNT = 2, + TX_FRAMES_SENT = 3, + TX_BYTES_SENT = 4, + TX_LAST_COMPLETION_PROCESSED = 5, + RX_NEXT_EXPECTED_SEQUENCE = 6, + RX_BUFFERS_POSTED = 7, + // stats from NIC + RX_QUEUE_DROP_CNT = 65, + RX_NO_BUFFERS_POSTED = 66, + RX_DROPS_PACKET_OVER_MRU = 67, + RX_DROPS_INVALID_CHECKSUM = 68, +}; + union gve_adminq_command { struct { __be32 opcode; @@ -187,6 +234,8 @@ union gve_adminq_command { struct gve_adminq_register_page_list reg_page_list; struct gve_adminq_unregister_page_list unreg_page_list; struct gve_adminq_set_driver_parameter set_driver_param; + struct gve_adminq_report_stats report_stats; + struct gve_adminq_report_link_speed report_link_speed; }; }; u8 reserved[64]; @@ -197,8 +246,6 @@ static_assert(sizeof(union gve_adminq_command) == 64); int gve_adminq_alloc(struct device *dev, struct gve_priv *priv); void gve_adminq_free(struct device *dev, struct gve_priv *priv); void gve_adminq_release(struct gve_priv *priv); -int gve_adminq_execute_cmd(struct gve_priv *priv, - union gve_adminq_command *cmd_orig); int gve_adminq_describe_device(struct gve_priv *priv); int gve_adminq_configure_device_resources(struct gve_priv *priv, dma_addr_t counter_array_bus_addr, @@ -206,12 +253,15 @@ int gve_adminq_configure_device_resources(struct gve_priv *priv, dma_addr_t db_array_bus_addr, u32 num_ntfy_blks); int gve_adminq_deconfigure_device_resources(struct gve_priv *priv); -int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_id); -int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_id); -int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_id); -int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_id); +int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues); +int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 queue_id); +int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues); +int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id); int gve_adminq_register_page_list(struct gve_priv *priv, struct gve_queue_page_list *qpl); int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id); int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu); +int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len, + dma_addr_t stats_report_addr, u64 interval); +int gve_adminq_report_link_speed(struct gve_priv *priv); #endif /* _GVE_ADMINQ_H */ diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index d8fa816f4473..7b44769bd87c 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -6,6 +6,7 @@ #include <linux/rtnetlink.h> #include "gve.h" +#include "gve_adminq.h" static void gve_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info) @@ -34,41 +35,84 @@ static u32 gve_get_msglevel(struct net_device *netdev) static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = { "rx_packets", "tx_packets", "rx_bytes", "tx_bytes", "rx_dropped", "tx_dropped", "tx_timeouts", + "rx_skb_alloc_fail", "rx_buf_alloc_fail", "rx_desc_err_dropped_pkt", + "interface_up_cnt", "interface_down_cnt", "reset_cnt", + "page_alloc_fail", "dma_mapping_error", "stats_report_trigger_cnt", +}; + +static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = { + "rx_posted_desc[%u]", "rx_completed_desc[%u]", "rx_bytes[%u]", + "rx_dropped_pkt[%u]", "rx_copybreak_pkt[%u]", "rx_copied_pkt[%u]", + "rx_queue_drop_cnt[%u]", "rx_no_buffers_posted[%u]", + "rx_drops_packet_over_mru[%u]", "rx_drops_invalid_checksum[%u]", +}; + +static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = { + "tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_bytes[%u]", + "tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]", +}; + +static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = { + "adminq_prod_cnt", "adminq_cmd_fail", "adminq_timeouts", + "adminq_describe_device_cnt", "adminq_cfg_device_resources_cnt", + "adminq_register_page_list_cnt", "adminq_unregister_page_list_cnt", + "adminq_create_tx_queue_cnt", "adminq_create_rx_queue_cnt", + "adminq_destroy_tx_queue_cnt", "adminq_destroy_rx_queue_cnt", + "adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt", + "adminq_report_stats_cnt", "adminq_report_link_speed_cnt" +}; + +static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = { + "report-stats", }; #define GVE_MAIN_STATS_LEN ARRAY_SIZE(gve_gstrings_main_stats) -#define NUM_GVE_TX_CNTS 5 -#define NUM_GVE_RX_CNTS 2 +#define GVE_ADMINQ_STATS_LEN ARRAY_SIZE(gve_gstrings_adminq_stats) +#define NUM_GVE_TX_CNTS ARRAY_SIZE(gve_gstrings_tx_stats) +#define NUM_GVE_RX_CNTS ARRAY_SIZE(gve_gstrings_rx_stats) +#define GVE_PRIV_FLAGS_STR_LEN ARRAY_SIZE(gve_gstrings_priv_flags) static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data) { struct gve_priv *priv = netdev_priv(netdev); char *s = (char *)data; - int i; + int i, j; - if (stringset != ETH_SS_STATS) - return; + switch (stringset) { + case ETH_SS_STATS: + memcpy(s, *gve_gstrings_main_stats, + sizeof(gve_gstrings_main_stats)); + s += sizeof(gve_gstrings_main_stats); + + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + for (j = 0; j < NUM_GVE_RX_CNTS; j++) { + snprintf(s, ETH_GSTRING_LEN, + gve_gstrings_rx_stats[j], i); + s += ETH_GSTRING_LEN; + } + } - memcpy(s, *gve_gstrings_main_stats, - sizeof(gve_gstrings_main_stats)); - s += sizeof(gve_gstrings_main_stats); - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - snprintf(s, ETH_GSTRING_LEN, "rx_desc_cnt[%u]", i); - s += ETH_GSTRING_LEN; - snprintf(s, ETH_GSTRING_LEN, "rx_desc_fill_cnt[%u]", i); - s += ETH_GSTRING_LEN; - } - for (i = 0; i < priv->tx_cfg.num_queues; i++) { - snprintf(s, ETH_GSTRING_LEN, "tx_req[%u]", i); - s += ETH_GSTRING_LEN; - snprintf(s, ETH_GSTRING_LEN, "tx_done[%u]", i); - s += ETH_GSTRING_LEN; - snprintf(s, ETH_GSTRING_LEN, "tx_wake[%u]", i); - s += ETH_GSTRING_LEN; - snprintf(s, ETH_GSTRING_LEN, "tx_stop[%u]", i); - s += ETH_GSTRING_LEN; - snprintf(s, ETH_GSTRING_LEN, "tx_event_counter[%u]", i); - s += ETH_GSTRING_LEN; + for (i = 0; i < priv->tx_cfg.num_queues; i++) { + for (j = 0; j < NUM_GVE_TX_CNTS; j++) { + snprintf(s, ETH_GSTRING_LEN, + gve_gstrings_tx_stats[j], i); + s += ETH_GSTRING_LEN; + } + } + + memcpy(s, *gve_gstrings_adminq_stats, + sizeof(gve_gstrings_adminq_stats)); + s += sizeof(gve_gstrings_adminq_stats); + break; + + case ETH_SS_PRIV_FLAGS: + memcpy(s, *gve_gstrings_priv_flags, + sizeof(gve_gstrings_priv_flags)); + s += sizeof(gve_gstrings_priv_flags); + break; + + default: + break; } } @@ -78,9 +122,11 @@ static int gve_get_sset_count(struct net_device *netdev, int sset) switch (sset) { case ETH_SS_STATS: - return GVE_MAIN_STATS_LEN + + return GVE_MAIN_STATS_LEN + GVE_ADMINQ_STATS_LEN + (priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS) + (priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS); + case ETH_SS_PRIV_FLAGS: + return GVE_PRIV_FLAGS_STR_LEN; default: return -EOPNOTSUPP; } @@ -90,24 +136,56 @@ static void gve_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { - struct gve_priv *priv = netdev_priv(netdev); - u64 rx_pkts, rx_bytes, tx_pkts, tx_bytes; + u64 tmp_rx_pkts, tmp_rx_bytes, tmp_rx_skb_alloc_fail, tmp_rx_buf_alloc_fail, + tmp_rx_desc_err_dropped_pkt, tmp_tx_pkts, tmp_tx_bytes; + u64 rx_buf_alloc_fail, rx_desc_err_dropped_pkt, rx_pkts, + rx_skb_alloc_fail, rx_bytes, tx_pkts, tx_bytes; + int stats_idx, base_stats_idx, max_stats_idx; + struct stats *report_stats; + int *rx_qid_to_stats_idx; + int *tx_qid_to_stats_idx; + struct gve_priv *priv; + bool skip_nic_stats; unsigned int start; int ring; - int i; + int i, j; ASSERT_RTNL(); - for (rx_pkts = 0, rx_bytes = 0, ring = 0; + priv = netdev_priv(netdev); + report_stats = priv->stats_report->stats; + rx_qid_to_stats_idx = kmalloc_array(priv->rx_cfg.num_queues, + sizeof(int), GFP_KERNEL); + if (!rx_qid_to_stats_idx) + return; + tx_qid_to_stats_idx = kmalloc_array(priv->tx_cfg.num_queues, + sizeof(int), GFP_KERNEL); + if (!tx_qid_to_stats_idx) { + kfree(rx_qid_to_stats_idx); + return; + } + for (rx_pkts = 0, rx_bytes = 0, rx_skb_alloc_fail = 0, + rx_buf_alloc_fail = 0, rx_desc_err_dropped_pkt = 0, ring = 0; ring < priv->rx_cfg.num_queues; ring++) { if (priv->rx) { do { + struct gve_rx_ring *rx = &priv->rx[ring]; + start = u64_stats_fetch_begin(&priv->rx[ring].statss); - rx_pkts += priv->rx[ring].rpackets; - rx_bytes += priv->rx[ring].rbytes; + tmp_rx_pkts = rx->rpackets; + tmp_rx_bytes = rx->rbytes; + tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; + tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; + tmp_rx_desc_err_dropped_pkt = + rx->rx_desc_err_dropped_pkt; } while (u64_stats_fetch_retry(&priv->rx[ring].statss, start)); + rx_pkts += tmp_rx_pkts; + rx_bytes += tmp_rx_bytes; + rx_skb_alloc_fail += tmp_rx_skb_alloc_fail; + rx_buf_alloc_fail += tmp_rx_buf_alloc_fail; + rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt; } } for (tx_pkts = 0, tx_bytes = 0, ring = 0; @@ -116,10 +194,12 @@ gve_get_ethtool_stats(struct net_device *netdev, do { start = u64_stats_fetch_begin(&priv->tx[ring].statss); - tx_pkts += priv->tx[ring].pkt_done; - tx_bytes += priv->tx[ring].bytes_done; + tmp_tx_pkts = priv->tx[ring].pkt_done; + tmp_tx_bytes = priv->tx[ring].bytes_done; } while (u64_stats_fetch_retry(&priv->tx[ring].statss, start)); + tx_pkts += tmp_tx_pkts; + tx_bytes += tmp_tx_bytes; } } @@ -128,22 +208,102 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = tx_pkts; data[i++] = rx_bytes; data[i++] = tx_bytes; - /* Skip rx_dropped and tx_dropped */ - i += 2; + /* total rx dropped packets */ + data[i++] = rx_skb_alloc_fail + rx_buf_alloc_fail + + rx_desc_err_dropped_pkt; + /* Skip tx_dropped */ + i++; + data[i++] = priv->tx_timeo_cnt; + data[i++] = rx_skb_alloc_fail; + data[i++] = rx_buf_alloc_fail; + data[i++] = rx_desc_err_dropped_pkt; + data[i++] = priv->interface_up_cnt; + data[i++] = priv->interface_down_cnt; + data[i++] = priv->reset_cnt; + data[i++] = priv->page_alloc_fail; + data[i++] = priv->dma_mapping_error; + data[i++] = priv->stats_report_trigger_cnt; i = GVE_MAIN_STATS_LEN; + /* For rx cross-reporting stats, start from nic rx stats in report */ + base_stats_idx = GVE_TX_STATS_REPORT_NUM * priv->tx_cfg.num_queues + + GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues; + max_stats_idx = NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues + + base_stats_idx; + /* Preprocess the stats report for rx, map queue id to start index */ + skip_nic_stats = false; + for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + stats_idx += NIC_RX_STATS_REPORT_NUM) { + u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); + u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); + + if (stat_name == 0) { + /* no stats written by NIC yet */ + skip_nic_stats = true; + break; + } + rx_qid_to_stats_idx[queue_id] = stats_idx; + } /* walk RX rings */ if (priv->rx) { for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) { struct gve_rx_ring *rx = &priv->rx[ring]; - data[i++] = rx->cnt; data[i++] = rx->fill_cnt; + data[i++] = rx->cnt; + do { + start = + u64_stats_fetch_begin(&priv->rx[ring].statss); + tmp_rx_bytes = rx->rbytes; + tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; + tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; + tmp_rx_desc_err_dropped_pkt = + rx->rx_desc_err_dropped_pkt; + } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + start)); + data[i++] = tmp_rx_bytes; + /* rx dropped packets */ + data[i++] = tmp_rx_skb_alloc_fail + + tmp_rx_buf_alloc_fail + + tmp_rx_desc_err_dropped_pkt; + data[i++] = rx->rx_copybreak_pkt; + data[i++] = rx->rx_copied_pkt; + /* stats from NIC */ + if (skip_nic_stats) { + /* skip NIC rx stats */ + i += NIC_RX_STATS_REPORT_NUM; + continue; + } + for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) { + u64 value = + be64_to_cpu(report_stats[rx_qid_to_stats_idx[ring] + j].value); + + data[i++] = value; + } } } else { i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS; } + + /* For tx cross-reporting stats, start from nic tx stats in report */ + base_stats_idx = max_stats_idx; + max_stats_idx = NIC_TX_STATS_REPORT_NUM * priv->tx_cfg.num_queues + + max_stats_idx; + /* Preprocess the stats report for tx, map queue id to start index */ + skip_nic_stats = false; + for (stats_idx = base_stats_idx; stats_idx < max_stats_idx; + stats_idx += NIC_TX_STATS_REPORT_NUM) { + u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name); + u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id); + + if (stat_name == 0) { + /* no stats written by NIC yet */ + skip_nic_stats = true; + break; + } + tx_qid_to_stats_idx[queue_id] = stats_idx; + } /* walk TX rings */ if (priv->tx) { for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) { @@ -151,14 +311,51 @@ gve_get_ethtool_stats(struct net_device *netdev, data[i++] = tx->req; data[i++] = tx->done; + do { + start = + u64_stats_fetch_begin(&priv->tx[ring].statss); + tmp_tx_bytes = tx->bytes_done; + } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + start)); + data[i++] = tmp_tx_bytes; data[i++] = tx->wake_queue; data[i++] = tx->stop_queue; data[i++] = be32_to_cpu(gve_tx_load_event_counter(priv, tx)); + /* stats from NIC */ + if (skip_nic_stats) { + /* skip NIC tx stats */ + i += NIC_TX_STATS_REPORT_NUM; + continue; + } + for (j = 0; j < NIC_TX_STATS_REPORT_NUM; j++) { + u64 value = + be64_to_cpu(report_stats[tx_qid_to_stats_idx[ring] + j].value); + data[i++] = value; + } } } else { i += priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS; } + + kfree(rx_qid_to_stats_idx); + kfree(tx_qid_to_stats_idx); + /* AQ Stats */ + data[i++] = priv->adminq_prod_cnt; + data[i++] = priv->adminq_cmd_fail; + data[i++] = priv->adminq_timeouts; + data[i++] = priv->adminq_describe_device_cnt; + data[i++] = priv->adminq_cfg_device_resources_cnt; + data[i++] = priv->adminq_register_page_list_cnt; + data[i++] = priv->adminq_unregister_page_list_cnt; + data[i++] = priv->adminq_create_tx_queue_cnt; + data[i++] = priv->adminq_create_rx_queue_cnt; + data[i++] = priv->adminq_destroy_tx_queue_cnt; + data[i++] = priv->adminq_destroy_rx_queue_cnt; + data[i++] = priv->adminq_dcfg_device_resources_cnt; + data[i++] = priv->adminq_set_driver_parameter_cnt; + data[i++] = priv->adminq_report_stats_cnt; + data[i++] = priv->adminq_report_link_speed_cnt; } static void gve_get_channels(struct net_device *netdev, @@ -230,6 +427,95 @@ static int gve_user_reset(struct net_device *netdev, u32 *flags) return -EOPNOTSUPP; } +static int gve_get_tunable(struct net_device *netdev, + const struct ethtool_tunable *etuna, void *value) +{ + struct gve_priv *priv = netdev_priv(netdev); + + switch (etuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)value = priv->rx_copybreak; + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int gve_set_tunable(struct net_device *netdev, + const struct ethtool_tunable *etuna, + const void *value) +{ + struct gve_priv *priv = netdev_priv(netdev); + u32 len; + + switch (etuna->id) { + case ETHTOOL_RX_COPYBREAK: + len = *(u32 *)value; + if (len > PAGE_SIZE / 2) + return -EINVAL; + priv->rx_copybreak = len; + return 0; + default: + return -EOPNOTSUPP; + } +} + +static u32 gve_get_priv_flags(struct net_device *netdev) +{ + struct gve_priv *priv = netdev_priv(netdev); + u32 ret_flags = 0; + + /* Only 1 flag exists currently: report-stats (BIT(O)), so set that flag. */ + if (priv->ethtool_flags & BIT(0)) + ret_flags |= BIT(0); + return ret_flags; +} + +static int gve_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct gve_priv *priv = netdev_priv(netdev); + u64 ori_flags, new_flags; + + ori_flags = READ_ONCE(priv->ethtool_flags); + new_flags = ori_flags; + + /* Only one priv flag exists: report-stats (BIT(0))*/ + if (flags & BIT(0)) + new_flags |= BIT(0); + else + new_flags &= ~(BIT(0)); + priv->ethtool_flags = new_flags; + /* start report-stats timer when user turns report stats on. */ + if (flags & BIT(0)) { + mod_timer(&priv->stats_report_timer, + round_jiffies(jiffies + + msecs_to_jiffies(priv->stats_report_timer_period))); + } + /* Zero off gve stats when report-stats turned off and */ + /* delete report stats timer. */ + if (!(flags & BIT(0)) && (ori_flags & BIT(0))) { + int tx_stats_num = GVE_TX_STATS_REPORT_NUM * + priv->tx_cfg.num_queues; + int rx_stats_num = GVE_RX_STATS_REPORT_NUM * + priv->rx_cfg.num_queues; + + memset(priv->stats_report->stats, 0, (tx_stats_num + rx_stats_num) * + sizeof(struct stats)); + del_timer_sync(&priv->stats_report_timer); + } + return 0; +} + +static int gve_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct gve_priv *priv = netdev_priv(netdev); + int err = gve_adminq_report_link_speed(priv); + + cmd->base.speed = priv->link_speed; + return err; +} + const struct ethtool_ops gve_ethtool_ops = { .get_drvinfo = gve_get_drvinfo, .get_strings = gve_get_strings, @@ -242,4 +528,9 @@ const struct ethtool_ops gve_ethtool_ops = { .get_link = ethtool_op_get_link, .get_ringparam = gve_get_ringparam, .reset = gve_user_reset, + .get_tunable = gve_get_tunable, + .set_tunable = gve_set_tunable, + .get_priv_flags = gve_get_priv_flags, + .set_priv_flags = gve_set_priv_flags, + .get_link_ksettings = gve_get_link_ksettings }; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index e032563ceefd..48a433154ce0 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -78,6 +78,66 @@ static void gve_free_counter_array(struct gve_priv *priv) priv->counter_array = NULL; } +/* NIC requests to report stats */ +static void gve_stats_report_task(struct work_struct *work) +{ + struct gve_priv *priv = container_of(work, struct gve_priv, + stats_report_task); + if (gve_get_do_report_stats(priv)) { + gve_handle_report_stats(priv); + gve_clear_do_report_stats(priv); + } +} + +static void gve_stats_report_schedule(struct gve_priv *priv) +{ + if (!gve_get_probe_in_progress(priv) && + !gve_get_reset_in_progress(priv)) { + gve_set_do_report_stats(priv); + queue_work(priv->gve_wq, &priv->stats_report_task); + } +} + +static void gve_stats_report_timer(struct timer_list *t) +{ + struct gve_priv *priv = from_timer(priv, t, stats_report_timer); + + mod_timer(&priv->stats_report_timer, + round_jiffies(jiffies + + msecs_to_jiffies(priv->stats_report_timer_period))); + gve_stats_report_schedule(priv); +} + +static int gve_alloc_stats_report(struct gve_priv *priv) +{ + int tx_stats_num, rx_stats_num; + + tx_stats_num = (GVE_TX_STATS_REPORT_NUM + NIC_TX_STATS_REPORT_NUM) * + priv->tx_cfg.num_queues; + rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) * + priv->rx_cfg.num_queues; + priv->stats_report_len = sizeof(struct gve_stats_report) + + (tx_stats_num + rx_stats_num) * + sizeof(struct stats); + priv->stats_report = + dma_alloc_coherent(&priv->pdev->dev, priv->stats_report_len, + &priv->stats_report_bus, GFP_KERNEL); + if (!priv->stats_report) + return -ENOMEM; + /* Set up timer for the report-stats task */ + timer_setup(&priv->stats_report_timer, gve_stats_report_timer, 0); + priv->stats_report_timer_period = GVE_STATS_REPORT_TIMER_PERIOD; + return 0; +} + +static void gve_free_stats_report(struct gve_priv *priv) +{ + del_timer_sync(&priv->stats_report_timer); + dma_free_coherent(&priv->pdev->dev, priv->stats_report_len, + priv->stats_report, priv->stats_report_bus); + priv->stats_report = NULL; +} + static irqreturn_t gve_mgmnt_intr(int irq, void *arg) { struct gve_priv *priv = arg; @@ -270,6 +330,9 @@ static int gve_setup_device_resources(struct gve_priv *priv) err = gve_alloc_notify_blocks(priv); if (err) goto abort_with_counter; + err = gve_alloc_stats_report(priv); + if (err) + goto abort_with_ntfy_blocks; err = gve_adminq_configure_device_resources(priv, priv->counter_array_bus, priv->num_event_counters, @@ -279,10 +342,18 @@ static int gve_setup_device_resources(struct gve_priv *priv) dev_err(&priv->pdev->dev, "could not setup device_resources: err=%d\n", err); err = -ENXIO; - goto abort_with_ntfy_blocks; + goto abort_with_stats_report; } + err = gve_adminq_report_stats(priv, priv->stats_report_len, + priv->stats_report_bus, + GVE_STATS_REPORT_TIMER_PERIOD); + if (err) + dev_err(&priv->pdev->dev, + "Failed to report stats: err=%d\n", err); gve_set_device_resources_ok(priv); return 0; +abort_with_stats_report: + gve_free_stats_report(priv); abort_with_ntfy_blocks: gve_free_notify_blocks(priv); abort_with_counter: @@ -298,6 +369,13 @@ static void gve_teardown_device_resources(struct gve_priv *priv) /* Tell device its resources are being freed */ if (gve_get_device_resources_ok(priv)) { + /* detach the stats report */ + err = gve_adminq_report_stats(priv, 0, 0x0, GVE_STATS_REPORT_TIMER_PERIOD); + if (err) { + dev_err(&priv->pdev->dev, + "Failed to detach stats report: err=%d\n", err); + gve_trigger_reset(priv); + } err = gve_adminq_deconfigure_device_resources(priv); if (err) { dev_err(&priv->pdev->dev, @@ -308,6 +386,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv) } gve_free_counter_array(priv); gve_free_notify_blocks(priv); + gve_free_stats_report(priv); gve_clear_device_resources_ok(priv); } @@ -371,36 +450,37 @@ static int gve_create_rings(struct gve_priv *priv) int err; int i; - for (i = 0; i < priv->tx_cfg.num_queues; i++) { - err = gve_adminq_create_tx_queue(priv, i); - if (err) { - netif_err(priv, drv, priv->dev, "failed to create tx queue %d\n", - i); - /* This failure will trigger a reset - no need to clean - * up - */ - return err; - } - netif_dbg(priv, drv, priv->dev, "created tx queue %d\n", i); + err = gve_adminq_create_tx_queues(priv, priv->tx_cfg.num_queues); + if (err) { + netif_err(priv, drv, priv->dev, "failed to create %d tx queues\n", + priv->tx_cfg.num_queues); + /* This failure will trigger a reset - no need to clean + * up + */ + return err; } - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - err = gve_adminq_create_rx_queue(priv, i); - if (err) { - netif_err(priv, drv, priv->dev, "failed to create rx queue %d\n", - i); - /* This failure will trigger a reset - no need to clean - * up - */ - return err; - } - /* Rx data ring has been prefilled with packet buffers at - * queue allocation time. - * Write the doorbell to provide descriptor slots and packet - * buffers to the NIC. + netif_dbg(priv, drv, priv->dev, "created %d tx queues\n", + priv->tx_cfg.num_queues); + + err = gve_adminq_create_rx_queues(priv, priv->rx_cfg.num_queues); + if (err) { + netif_err(priv, drv, priv->dev, "failed to create %d rx queues\n", + priv->rx_cfg.num_queues); + /* This failure will trigger a reset - no need to clean + * up */ - gve_rx_write_doorbell(priv, &priv->rx[i]); - netif_dbg(priv, drv, priv->dev, "created rx queue %d\n", i); + return err; } + netif_dbg(priv, drv, priv->dev, "created %d rx queues\n", + priv->rx_cfg.num_queues); + + /* Rx data ring has been prefilled with packet buffers at queue + * allocation time. + * Write the doorbell to provide descriptor slots and packet buffers + * to the NIC. + */ + for (i = 0; i < priv->rx_cfg.num_queues; i++) + gve_rx_write_doorbell(priv, &priv->rx[i]); return 0; } @@ -458,34 +538,23 @@ free_tx: static int gve_destroy_rings(struct gve_priv *priv) { int err; - int i; - for (i = 0; i < priv->tx_cfg.num_queues; i++) { - err = gve_adminq_destroy_tx_queue(priv, i); - if (err) { - netif_err(priv, drv, priv->dev, - "failed to destroy tx queue %d\n", - i); - /* This failure will trigger a reset - no need to clean - * up - */ - return err; - } - netif_dbg(priv, drv, priv->dev, "destroyed tx queue %d\n", i); + err = gve_adminq_destroy_tx_queues(priv, priv->tx_cfg.num_queues); + if (err) { + netif_err(priv, drv, priv->dev, + "failed to destroy tx queues\n"); + /* This failure will trigger a reset - no need to clean up */ + return err; } - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - err = gve_adminq_destroy_rx_queue(priv, i); - if (err) { - netif_err(priv, drv, priv->dev, - "failed to destroy rx queue %d\n", - i); - /* This failure will trigger a reset - no need to clean - * up - */ - return err; - } - netif_dbg(priv, drv, priv->dev, "destroyed rx queue %d\n", i); + netif_dbg(priv, drv, priv->dev, "destroyed tx queues\n"); + err = gve_adminq_destroy_rx_queues(priv, priv->rx_cfg.num_queues); + if (err) { + netif_err(priv, drv, priv->dev, + "failed to destroy rx queues\n"); + /* This failure will trigger a reset - no need to clean up */ + return err; } + netif_dbg(priv, drv, priv->dev, "destroyed rx queues\n"); return 0; } @@ -514,14 +583,18 @@ static void gve_free_rings(struct gve_priv *priv) } } -int gve_alloc_page(struct device *dev, struct page **page, dma_addr_t *dma, +int gve_alloc_page(struct gve_priv *priv, struct device *dev, + struct page **page, dma_addr_t *dma, enum dma_data_direction dir) { *page = alloc_page(GFP_KERNEL); - if (!*page) + if (!*page) { + priv->page_alloc_fail++; return -ENOMEM; + } *dma = dma_map_page(dev, *page, 0, PAGE_SIZE, dir); if (dma_mapping_error(dev, *dma)) { + priv->dma_mapping_error++; put_page(*page); return -ENOMEM; } @@ -556,7 +629,7 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id, return -ENOMEM; for (i = 0; i < pages; i++) { - err = gve_alloc_page(&priv->pdev->dev, &qpl->pages[i], + err = gve_alloc_page(priv, &priv->pdev->dev, &qpl->pages[i], &qpl->page_buses[i], gve_qpl_dma_dir(priv, id)); /* caller handles clean up */ @@ -695,8 +768,14 @@ static int gve_open(struct net_device *dev) goto reset; gve_set_device_rings_ok(priv); + if (gve_get_report_stats(priv)) + mod_timer(&priv->stats_report_timer, + round_jiffies(jiffies + + msecs_to_jiffies(priv->stats_report_timer_period))); + gve_turnup(priv); - netif_carrier_on(dev); + queue_work(priv->gve_wq, &priv->service_task); + priv->interface_up_cnt++; return 0; free_rings: @@ -735,9 +814,11 @@ static int gve_close(struct net_device *dev) goto err; gve_clear_device_rings_ok(priv); } + del_timer_sync(&priv->stats_report_timer); gve_free_rings(priv); gve_free_qpls(priv); + priv->interface_down_cnt++; return 0; err: @@ -817,6 +898,7 @@ static void gve_turndown(struct gve_priv *priv) netif_tx_disable(priv->dev); gve_clear_napi_enabled(priv); + gve_clear_report_stats(priv); } static void gve_turnup(struct gve_priv *priv) @@ -867,6 +949,10 @@ static void gve_handle_status(struct gve_priv *priv, u32 status) dev_info(&priv->pdev->dev, "Device requested reset.\n"); gve_set_do_reset(priv); } + if (GVE_DEVICE_STATUS_REPORT_STATS_MASK & status) { + priv->stats_report_trigger_cnt++; + gve_set_do_report_stats(priv); + } } static void gve_handle_reset(struct gve_priv *priv) @@ -885,16 +971,95 @@ static void gve_handle_reset(struct gve_priv *priv) } } -/* Handle NIC status register changes and reset requests */ +void gve_handle_report_stats(struct gve_priv *priv) +{ + int idx, stats_idx = 0, tx_bytes; + unsigned int start = 0; + struct stats *stats = priv->stats_report->stats; + + if (!gve_get_report_stats(priv)) + return; + + be64_add_cpu(&priv->stats_report->written_count, 1); + /* tx stats */ + if (priv->tx) { + for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) { + do { + start = u64_stats_fetch_begin(&priv->tx[idx].statss); + tx_bytes = priv->tx[idx].bytes_done; + } while (u64_stats_fetch_retry(&priv->tx[idx].statss, start)); + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_WAKE_CNT), + .value = cpu_to_be64(priv->tx[idx].wake_queue), + .queue_id = cpu_to_be32(idx), + }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_STOP_CNT), + .value = cpu_to_be64(priv->tx[idx].stop_queue), + .queue_id = cpu_to_be32(idx), + }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_FRAMES_SENT), + .value = cpu_to_be64(priv->tx[idx].req), + .queue_id = cpu_to_be32(idx), + }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_BYTES_SENT), + .value = cpu_to_be64(tx_bytes), + .queue_id = cpu_to_be32(idx), + }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(TX_LAST_COMPLETION_PROCESSED), + .value = cpu_to_be64(priv->tx[idx].done), + .queue_id = cpu_to_be32(idx), + }; + } + } + /* rx stats */ + if (priv->rx) { + for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) { + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(RX_NEXT_EXPECTED_SEQUENCE), + .value = cpu_to_be64(priv->rx[idx].desc.seqno), + .queue_id = cpu_to_be32(idx), + }; + stats[stats_idx++] = (struct stats) { + .stat_name = cpu_to_be32(RX_BUFFERS_POSTED), + .value = cpu_to_be64(priv->rx[0].fill_cnt), + .queue_id = cpu_to_be32(idx), + }; + } + } +} + +static void gve_handle_link_status(struct gve_priv *priv, bool link_status) +{ + if (!gve_get_napi_enabled(priv)) + return; + + if (link_status == netif_carrier_ok(priv->dev)) + return; + + if (link_status) { + netdev_info(priv->dev, "Device link is up.\n"); + netif_carrier_on(priv->dev); + } else { + netdev_info(priv->dev, "Device link is down.\n"); + netif_carrier_off(priv->dev); + } +} + +/* Handle NIC status register changes, reset requests and report stats */ static void gve_service_task(struct work_struct *work) { struct gve_priv *priv = container_of(work, struct gve_priv, service_task); + u32 status = ioread32be(&priv->reg_bar0->device_status); - gve_handle_status(priv, - ioread32be(&priv->reg_bar0->device_status)); + gve_handle_status(priv, status); gve_handle_reset(priv); + gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status); } static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) @@ -924,7 +1089,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) priv->dev->max_mtu = PAGE_SIZE; err = gve_adminq_set_mtu(priv, priv->dev->mtu); if (err) { - netif_err(priv, drv, priv->dev, "Could not set mtu"); + dev_err(&priv->pdev->dev, "Could not set mtu"); goto err; } } @@ -964,10 +1129,10 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) priv->rx_cfg.num_queues); } - netif_info(priv, drv, priv->dev, "TX queues %d, RX queues %d\n", - priv->tx_cfg.num_queues, priv->rx_cfg.num_queues); - netif_info(priv, drv, priv->dev, "Max TX queues %d, Max RX queues %d\n", - priv->tx_cfg.max_queues, priv->rx_cfg.max_queues); + dev_info(&priv->pdev->dev, "TX queues %d, RX queues %d\n", + priv->tx_cfg.num_queues, priv->rx_cfg.num_queues); + dev_info(&priv->pdev->dev, "Max TX queues %d, Max RX queues %d\n", + priv->tx_cfg.max_queues, priv->rx_cfg.max_queues); setup_device: err = gve_setup_device_resources(priv); @@ -1047,6 +1212,10 @@ int gve_reset(struct gve_priv *priv, bool attempt_teardown) /* Set it all back up */ err = gve_reset_recovery(priv, was_up); gve_clear_reset_in_progress(priv); + priv->reset_cnt++; + priv->interface_up_cnt = 0; + priv->interface_down_cnt = 0; + priv->stats_report_trigger_cnt = 0; return err; } @@ -1149,6 +1318,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) priv->db_bar2 = db_bar; priv->service_task_flags = 0x0; priv->state_flags = 0x0; + priv->ethtool_flags = 0x0; gve_set_probe_in_progress(priv); priv->gve_wq = alloc_ordered_workqueue("gve", 0); @@ -1158,6 +1328,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto abort_with_netdev; } INIT_WORK(&priv->service_task, gve_service_task); + INIT_WORK(&priv->stats_report_task, gve_stats_report_task); priv->tx_cfg.max_queues = max_tx_queues; priv->rx_cfg.max_queues = max_rx_queues; diff --git a/drivers/net/ethernet/google/gve/gve_register.h b/drivers/net/ethernet/google/gve/gve_register.h index 84ab8893aadd..fb655463c357 100644 --- a/drivers/net/ethernet/google/gve/gve_register.h +++ b/drivers/net/ethernet/google/gve/gve_register.h @@ -23,5 +23,6 @@ struct gve_registers { enum gve_device_status_flags { GVE_DEVICE_STATUS_RESET_MASK = BIT(1), GVE_DEVICE_STATUS_LINK_STATUS_MASK = BIT(2), + GVE_DEVICE_STATUS_REPORT_STATS_MASK = BIT(3), }; #endif /* _GVE_REGISTER_H_ */ diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 9f52e72ff641..008fa897a3e6 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -225,7 +225,8 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags) return PKT_HASH_TYPE_L2; } -static struct sk_buff *gve_rx_copy(struct net_device *dev, +static struct sk_buff *gve_rx_copy(struct gve_rx_ring *rx, + struct net_device *dev, struct napi_struct *napi, struct gve_rx_slot_page_info *page_info, u16 len) @@ -242,6 +243,11 @@ static struct sk_buff *gve_rx_copy(struct net_device *dev, skb_copy_to_linear_data(skb, va, len); skb->protocol = eth_type_trans(skb, dev); + + u64_stats_update_begin(&rx->statss); + rx->rx_copied_pkt++; + u64_stats_update_end(&rx->statss); + return skb; } @@ -284,8 +290,12 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, u16 len; /* drop this packet */ - if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) + if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) { + u64_stats_update_begin(&rx->statss); + rx->rx_desc_err_dropped_pkt++; + u64_stats_update_end(&rx->statss); return true; + } len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD; page_info = &rx->data.page_info[idx]; @@ -300,11 +310,14 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, if (PAGE_SIZE == 4096) { if (len <= priv->rx_copybreak) { /* Just copy small packets */ - skb = gve_rx_copy(dev, napi, page_info, len); + skb = gve_rx_copy(rx, dev, napi, page_info, len); + u64_stats_update_begin(&rx->statss); + rx->rx_copybreak_pkt++; + u64_stats_update_end(&rx->statss); goto have_skb; } if (unlikely(!gve_can_recycle_pages(dev))) { - skb = gve_rx_copy(dev, napi, page_info, len); + skb = gve_rx_copy(rx, dev, napi, page_info, len); goto have_skb; } pagecount = page_count(page_info->page); @@ -314,8 +327,12 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, * stack. */ skb = gve_rx_add_frags(dev, napi, page_info, len); - if (!skb) + if (!skb) { + u64_stats_update_begin(&rx->statss); + rx->rx_skb_alloc_fail++; + u64_stats_update_end(&rx->statss); return true; + } /* Make sure the kernel stack can't release the page */ get_page(page_info->page); /* "flip" to other packet buffer on this page */ @@ -324,21 +341,25 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc, /* We have previously passed the other half of this * page up the stack, but it has not yet been freed. */ - skb = gve_rx_copy(dev, napi, page_info, len); + skb = gve_rx_copy(rx, dev, napi, page_info, len); } else { WARN(pagecount < 1, "Pagecount should never be < 1"); return false; } } else { - skb = gve_rx_copy(dev, napi, page_info, len); + skb = gve_rx_copy(rx, dev, napi, page_info, len); } have_skb: /* We didn't manage to allocate an skb but we haven't had any * reset worthy failures. */ - if (!skb) + if (!skb) { + u64_stats_update_begin(&rx->statss); + rx->rx_skb_alloc_fail++; + u64_stats_update_end(&rx->statss); return true; + } if (likely(feat & NETIF_F_RXCSUM)) { /* NIC passes up the partial sum */ |