diff --git a/Documentation/networking/devlink-health.txt b/Documentation/networking/devlink-health.txt new file mode 100644 index 0000000000000000000000000000000000000000..1db3fbea08313fb425326fcbc45fe236fa4fd513 --- /dev/null +++ b/Documentation/networking/devlink-health.txt @@ -0,0 +1,86 @@ +The health mechanism is targeted for Real Time Alerting, in order to know when +something bad had happened to a PCI device +- Provide alert debug information +- Self healing +- If problem needs vendor support, provide a way to gather all needed debugging + information. + +The main idea is to unify and centralize driver health reports in the +generic devlink instance and allow the user to set different +attributes of the health reporting and recovery procedures. + +The devlink health reporter: +Device driver creates a "health reporter" per each error/health type. +Error/Health type can be a known/generic (eg pci error, fw error, rx/tx error) +or unknown (driver specific). +For each registered health reporter a driver can issue error/health reports +asynchronously. All health reports handling is done by devlink. +Device driver can provide specific callbacks for each "health reporter", e.g. + - Recovery procedures + - Diagnostics and object dump procedures + - OOB initial parameters +Different parts of the driver can register different types of health reporters +with different handlers. + +Once an error is reported, devlink health will do the following actions: + * A log is being send to the kernel trace events buffer + * Health status and statistics are being updated for the reporter instance + * Object dump is being taken and saved at the reporter instance (as long as + there is no other dump which is already stored) + * Auto recovery attempt is being done. Depends on: + - Auto-recovery configuration + - Grace period vs. time passed since last recover + +The user interface: +User can access/change each reporter's parameters and driver specific callbacks +via devlink, e.g per error type (per health reporter) + - Configure reporter's generic parameters (like: disable/enable auto recovery) + - Invoke recovery procedure + - Run diagnostics + - Object dump + +The devlink health interface (via netlink): +DEVLINK_CMD_HEALTH_REPORTER_GET + Retrieves status and configuration info per DEV and reporter. +DEVLINK_CMD_HEALTH_REPORTER_SET + Allows reporter-related configuration setting. +DEVLINK_CMD_HEALTH_REPORTER_RECOVER + Triggers a reporter's recovery procedure. +DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE + Retrieves diagnostics data from a reporter on a device. +DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET + Retrieves the last stored dump. Devlink health + saves a single dump. If an dump is not already stored by the devlink + for this reporter, devlink generates a new dump. + dump output is defined by the reporter. +DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR + Clears the last saved dump file for the specified reporter. + + + netlink + +--------------------------+ + | | + | + | + | | | + +--------------------------+ + |request for ops + |(diagnose, + mlx5_core devlink |recover, + |dump) ++--------+ +--------------------------+ +| | | reporter| | +| | | +---------v----------+ | +| | ops execution | | | | +| <----------------------------------+ | | +| | | | | | +| | | + ^------------------+ | +| | | | request for ops | +| | | | (recover, dump) | +| | | | | +| | | +-+------------------+ | +| | health report | | health handler | | +| +-------------------------------> | | +| | | +--------------------+ | +| | health reporter create | | +| +----------------------------> | ++--------+ +--------------------------+ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 9de9abacf7f6113f0383f4177cb6257d57e63bed..6bb2a860b15b9f08484716fd991ab8699baf25e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -22,7 +22,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ # mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ - en_selftest.o en/port.o en/monitor_stats.o + en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8fa8fdd30b8509f73a27fe4d31b094dfceda5e5d..27e276c9bf84cb251ac23f3527eaae2851427696 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -388,10 +388,7 @@ struct mlx5e_txqsq { struct mlx5e_channel *channel; int txq_ix; u32 rate_limit; - struct mlx5e_txqsq_recover { - struct work_struct recover_work; - u64 last_recover; - } recover; + struct work_struct recover_work; } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { @@ -682,6 +679,13 @@ struct mlx5e_rss_params { u8 hfunc; }; +struct mlx5e_modify_sq_param { + int curr_state; + int next_state; + int rl_update; + int rl_index; +}; + struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -737,6 +741,7 @@ struct mlx5e_priv { #ifdef CONFIG_MLX5_EN_TLS struct mlx5e_tls *tls; #endif + struct devlink_health_reporter *tx_reporter; }; struct mlx5e_profile { @@ -866,6 +871,11 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p); +void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); +void mlx5e_tx_disable_queue(struct netdev_queue *txq); + static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h new file mode 100644 index 0000000000000000000000000000000000000000..2335c5b48820ca1405785619c87799612b52709d --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2018 Mellanox Technologies. */ + +#ifndef __MLX5E_EN_REPORTER_H +#define __MLX5E_EN_REPORTER_H + +#include +#include "en.h" + +int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); +void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv); +void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq); +void mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c new file mode 100644 index 0000000000000000000000000000000000000000..d9675afbb92422d496fd99005923f26102583c68 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -0,0 +1,356 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2018 Mellanox Technologies. */ + +#include +#include "reporter.h" +#include "lib/eq.h" + +#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256 + +struct mlx5e_tx_err_ctx { + int (*recover)(struct mlx5e_txqsq *sq); + struct mlx5e_txqsq *sq; +}; + +static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) +{ + unsigned long exp_time = jiffies + msecs_to_jiffies(2000); + + while (time_before(jiffies, exp_time)) { + if (sq->cc == sq->pc) + return 0; + + msleep(20); + } + + netdev_err(sq->channel->netdev, + "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", + sq->sqn, sq->cc, sq->pc); + + return -ETIMEDOUT; +} + +static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) +{ + WARN_ONCE(sq->cc != sq->pc, + "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", + sq->sqn, sq->cc, sq->pc); + sq->cc = 0; + sq->dma_fifo_cc = 0; + sq->pc = 0; +} + +static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) +{ + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + struct mlx5e_modify_sq_param msp = {0}; + int err; + + msp.curr_state = curr_state; + msp.next_state = MLX5_SQC_STATE_RST; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); + return err; + } + + memset(&msp, 0, sizeof(msp)); + msp.curr_state = MLX5_SQC_STATE_RST; + msp.next_state = MLX5_SQC_STATE_RDY; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); + return err; + } + + return 0; +} + +static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq) +{ + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + u8 state; + int err; + + if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) + return 0; + + err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); + if (err) { + netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", + sq->sqn, err); + return err; + } + + if (state != MLX5_RQC_STATE_ERR) { + netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); + return -EINVAL; + } + + mlx5e_tx_disable_queue(sq->txq); + + err = mlx5e_wait_for_sq_flush(sq); + if (err) + return err; + + /* At this point, no new packets will arrive from the stack as TXQ is + * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all + * pending WQEs. SQ can safely reset the SQ. + */ + + err = mlx5e_sq_to_ready(sq, state); + if (err) + return err; + + mlx5e_reset_txqsq_cc_pc(sq); + sq->stats->recover++; + mlx5e_activate_txqsq(sq); + + return 0; +} + +void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq) +{ + char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; + struct mlx5e_tx_err_ctx err_ctx = {0}; + + err_ctx.sq = sq; + err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; + sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn); + + devlink_health_report(sq->channel->priv->tx_reporter, err_str, + &err_ctx); +} + +static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq) +{ + struct mlx5_eq_comp *eq = sq->cq.mcq.eq; + u32 eqe_count; + + netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", + eq->core.eqn, eq->core.cons_index, eq->core.irqn); + + eqe_count = mlx5_eq_poll_irq_disabled(eq); + if (!eqe_count) { + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); + return 1; + } + + netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n", + eqe_count, eq->core.eqn); + sq->channel->stats->eq_rearm++; + return 0; +} + +void mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq) +{ + struct mlx5e_tx_err_ctx err_ctx; + char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; + + err_ctx.sq = sq; + err_ctx.recover = mlx5e_tx_reporter_timeout_recover; + sprintf(err_str, + "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", + sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, + jiffies_to_usecs(jiffies - sq->txq->trans_start)); + devlink_health_report(sq->channel->priv->tx_reporter, err_str, + &err_ctx); +} + +/* state lock cannot be grabbed within this function. + * It can cause a dead lock or a read-after-free. + */ +int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx) +{ + return err_ctx->recover(err_ctx->sq); +} + +static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv) +{ + int err; + + mutex_lock(&priv->state_lock); + mlx5e_close_locked(priv->netdev); + err = mlx5e_open_locked(priv->netdev); + mutex_unlock(&priv->state_lock); + + return err; +} + +static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, + void *context) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_tx_err_ctx *err_ctx = context; + + return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) : + mlx5e_tx_reporter_recover_all(priv); +} + +static int +mlx5e_tx_reporter_build_diagnose_output(struct devlink_health_buffer *buffer, + u32 sqn, u8 state, u8 stopped) +{ + int err, i; + int nest = 0; + char name[20]; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT); + if (err) + goto buffer_error; + nest++; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR); + if (err) + goto buffer_error; + nest++; + + sprintf(name, "SQ 0x%x", sqn); + err = devlink_health_buffer_put_object_name(buffer, name); + if (err) + goto buffer_error; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE); + if (err) + goto buffer_error; + nest++; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT); + if (err) + goto buffer_error; + nest++; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR); + if (err) + goto buffer_error; + nest++; + + err = devlink_health_buffer_put_object_name(buffer, "HW state"); + if (err) + goto buffer_error; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE); + if (err) + goto buffer_error; + nest++; + + err = devlink_health_buffer_put_value_u8(buffer, state); + if (err) + goto buffer_error; + + devlink_health_buffer_nest_end(buffer); /* DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE */ + nest--; + + devlink_health_buffer_nest_end(buffer); /* DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR */ + nest--; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR); + if (err) + goto buffer_error; + nest++; + + err = devlink_health_buffer_put_object_name(buffer, "stopped"); + if (err) + goto buffer_error; + + err = devlink_health_buffer_nest_start(buffer, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE); + if (err) + goto buffer_error; + nest++; + + err = devlink_health_buffer_put_value_u8(buffer, stopped); + if (err) + goto buffer_error; + + for (i = 0; i < nest; i++) + devlink_health_buffer_nest_end(buffer); + + return 0; + +buffer_error: + for (i = 0; i < nest; i++) + devlink_health_buffer_nest_cancel(buffer); + return err; +} + +static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_health_buffer **buffers_array, + unsigned int buffer_size, + unsigned int num_buffers) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + unsigned int buff = 0; + int i = 0, err = 0; + + if (buffer_size < MLX5E_TX_REPORTER_PER_SQ_MAX_LEN) + return -ENOMEM; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + mutex_unlock(&priv->state_lock); + return 0; + } + + while (i < priv->channels.num * priv->channels.params.num_tc) { + struct mlx5e_txqsq *sq = priv->txq2sq[i]; + u8 state; + + err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + if (err) + break; + + err = mlx5e_tx_reporter_build_diagnose_output(buffers_array[buff], + sq->sqn, state, + netif_xmit_stopped(sq->txq)); + if (err) { + if (++buff == num_buffers) + break; + } else { + i++; + } + } + + mutex_unlock(&priv->state_lock); + return err; +} + +static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { + .name = "TX", + .recover = mlx5e_tx_reporter_recover, + .diagnose_size = MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC * + MLX5E_TX_REPORTER_PER_SQ_MAX_LEN, + .diagnose = mlx5e_tx_reporter_diagnose, + .dump_size = 0, + .dump = NULL, +}; + +#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500 +int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct devlink *devlink = priv_to_devlink(mdev); + + priv->tx_reporter = + devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, + MLX5_REPORTER_TX_GRACEFUL_PERIOD, + true, priv); + return PTR_ERR_OR_ZERO(priv->tx_reporter); +} + +void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) +{ + devlink_health_reporter_destroy(priv->tx_reporter); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 8cfd2ec7c0a209afe424eca2a7be3301cf79223f..dee0c8f3d4e968940a73804087ddae0383229990 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -51,6 +51,7 @@ #include "en/xdp.h" #include "lib/eq.h" #include "en/monitor_stats.h" +#include "en/reporter.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; @@ -1160,7 +1161,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) return 0; } -static void mlx5e_sq_recover(struct work_struct *work); +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, @@ -1182,7 +1183,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; - INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover); + INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) @@ -1270,15 +1271,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, return err; } -struct mlx5e_modify_sq_param { - int curr_state; - int next_state; - bool rl_update; - int rl_index; -}; - -static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, - struct mlx5e_modify_sq_param *p) +int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p) { void *in; void *sqc; @@ -1376,17 +1370,7 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c, return err; } -static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) -{ - WARN_ONCE(sq->cc != sq->pc, - "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", - sq->sqn, sq->cc, sq->pc); - sq->cc = 0; - sq->dma_fifo_cc = 0; - sq->pc = 0; -} - -static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) +void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix); clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); @@ -1395,7 +1379,7 @@ static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) netif_tx_start_queue(sq->txq); } -static inline void netif_tx_disable_queue(struct netdev_queue *txq) +void mlx5e_tx_disable_queue(struct netdev_queue *txq) { __netif_tx_lock_bh(txq); netif_tx_stop_queue(txq); @@ -1411,7 +1395,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) /* prevent netif_tx_wake_queue */ napi_synchronize(&c->napi); - netif_tx_disable_queue(sq->txq); + mlx5e_tx_disable_queue(sq->txq); /* last doorbell out, godspeed .. */ if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) { @@ -1431,6 +1415,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) struct mlx5_rate_limit rl = {0}; cancel_work_sync(&sq->dim.work); + cancel_work_sync(&sq->recover_work); mlx5e_destroy_sq(mdev, sq->sqn); if (sq->rate_limit) { rl.rate = sq->rate_limit; @@ -1440,105 +1425,15 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) mlx5e_free_txqsq(sq); } -static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) -{ - unsigned long exp_time = jiffies + msecs_to_jiffies(2000); - - while (time_before(jiffies, exp_time)) { - if (sq->cc == sq->pc) - return 0; - - msleep(20); - } - - netdev_err(sq->channel->netdev, - "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", - sq->sqn, sq->cc, sq->pc); - - return -ETIMEDOUT; -} - -static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) { - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - struct mlx5e_modify_sq_param msp = {0}; - int err; + struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, + recover_work); - msp.curr_state = curr_state; - msp.next_state = MLX5_SQC_STATE_RST; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); - return err; - } - - memset(&msp, 0, sizeof(msp)); - msp.curr_state = MLX5_SQC_STATE_RST; - msp.next_state = MLX5_SQC_STATE_RDY; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); - return err; - } - - return 0; -} - -static void mlx5e_sq_recover(struct work_struct *work) -{ - struct mlx5e_txqsq_recover *recover = - container_of(work, struct mlx5e_txqsq_recover, - recover_work); - struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq, - recover); - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - u8 state; - int err; - - err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); - if (err) { - netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", - sq->sqn, err); - return; - } - - if (state != MLX5_RQC_STATE_ERR) { - netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); - return; - } - - netif_tx_disable_queue(sq->txq); - - if (mlx5e_wait_for_sq_flush(sq)) + if (!sq->channel->priv->tx_reporter) return; - /* If the interval between two consecutive recovers per SQ is too - * short, don't recover to avoid infinite loop of ERR_CQE -> recover. - * If we reached this state, there is probably a bug that needs to be - * fixed. let's keep the queue close and let tx timeout cleanup. - */ - if (jiffies_to_msecs(jiffies - recover->last_recover) < - MLX5E_SQ_RECOVER_MIN_INTERVAL) { - netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n", - sq->sqn); - return; - } - - /* At this point, no new packets will arrive from the stack as TXQ is - * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all - * pending WQEs. SQ can safely reset the SQ. - */ - if (mlx5e_sq_to_ready(sq, state)) - return; - - mlx5e_reset_txqsq_cc_pc(sq); - sq->stats->recover++; - recover->last_recover = jiffies; - mlx5e_activate_txqsq(sq); + mlx5e_tx_reporter_err_cqe(sq); } static int mlx5e_open_icosq(struct mlx5e_channel *c, @@ -3207,6 +3102,7 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { int tc; + mlx5e_tx_reporter_destroy(priv); for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); } @@ -4178,31 +4074,14 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, return features; } -static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev, - struct mlx5e_txqsq *sq) -{ - struct mlx5_eq_comp *eq = sq->cq.mcq.eq; - u32 eqe_count; - - netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", - eq->core.eqn, eq->core.cons_index, eq->core.irqn); - - eqe_count = mlx5_eq_poll_irq_disabled(eq); - if (!eqe_count) - return false; - - netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn); - sq->channel->stats->eq_rearm++; - return true; -} - static void mlx5e_tx_timeout_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, tx_timeout_work); - struct net_device *dev = priv->netdev; - bool reopen_channels = false; - int i, err; + int i; + + if (!priv->tx_reporter) + return; rtnl_lock(); mutex_lock(&priv->state_lock); @@ -4211,36 +4090,16 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) goto unlock; for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i); + struct netdev_queue *dev_queue = + netdev_get_tx_queue(priv->netdev, i); struct mlx5e_txqsq *sq = priv->txq2sq[i]; if (!netif_xmit_stopped(dev_queue)) continue; - netdev_err(dev, - "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", - i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, - jiffies_to_usecs(jiffies - dev_queue->trans_start)); - - /* If we recover a lost interrupt, most likely TX timeout will - * be resolved, skip reopening channels - */ - if (!mlx5e_tx_timeout_eq_recover(dev, sq)) { - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - reopen_channels = true; - } + mlx5e_tx_reporter_timeout(sq); } - if (!reopen_channels) - goto unlock; - - mlx5e_close_locked(dev); - err = mlx5e_open_locked(dev); - if (err) - netdev_err(priv->netdev, - "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n", - err); - unlock: mutex_unlock(&priv->state_lock); rtnl_unlock(); @@ -4908,6 +4767,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_initialize(priv); #endif + mlx5e_tx_reporter_create(priv); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 598ad7e4d5c97872c17fe4ae8387e82a2555c96e..a8e052a5ce3662c4c83e26a578d90bc62bc40074 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -514,7 +514,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) mlx5e_dump_error_cqe(sq, (struct mlx5_err_cqe *)cqe); queue_work(cq->channel->priv->wq, - &sq->recover.recover_work); + &sq->recover_work); } stats->cqe_err++; } diff --git a/include/net/devlink.h b/include/net/devlink.h index 67f4293bc9703f6f9b406882651aa7533783b581..a81a1b7a67d705e756e7536821e2be08e8711efa 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -30,6 +30,7 @@ struct devlink { struct list_head param_list; struct list_head region_list; u32 snapshot_id; + struct list_head reporter_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -423,6 +424,36 @@ struct devlink_region; typedef void devlink_snapshot_data_dest_t(const void *data); +struct devlink_health_buffer; +struct devlink_health_reporter; + +/** + * struct devlink_health_reporter_ops - Reporter operations + * @name: reporter name + * dump_size: dump buffer size allocated by the devlink + * diagnose_size: diagnose buffer size allocated by the devlink + * recover: callback to recover from reported error + * if priv_ctx is NULL, run a full recover + * dump: callback to dump an object + * if priv_ctx is NULL, run a full dump + * diagnose: callback to diagnose the current status + */ + +struct devlink_health_reporter_ops { + char *name; + unsigned int dump_size; + unsigned int diagnose_size; + int (*recover)(struct devlink_health_reporter *reporter, + void *priv_ctx); + int (*dump)(struct devlink_health_reporter *reporter, + struct devlink_health_buffer **buffers_array, + unsigned int buffer_size, unsigned int num_buffers, + void *priv_ctx); + int (*diagnose)(struct devlink_health_reporter *reporter, + struct devlink_health_buffer **buffers_array, + unsigned int buffer_size, unsigned int num_buffers); +}; + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -584,6 +615,34 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); +int devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, + int attrtype); +void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer); +void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer); +int devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, + char *name); +int devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, + u8 value); +int devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, + u32 value); +int devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, + u64 value); +int devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, + char *name); +int devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, + void *data, int len); +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv); +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter); +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx); #else static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, @@ -844,6 +903,91 @@ devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, return 0; } +static inline int +devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, + int attrtype) +{ + return 0; +} + +static inline void +devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer) +{ +} + +static inline void +devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer) +{ +} + +static inline int +devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, + char *name) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, + u8 value) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, + u32 value) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, + u64 value) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, + char *name) +{ + return 0; +} + +static inline int +devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, + void *data, int len) +{ + return 0; +} + +static inline struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv) +{ + return NULL; +} + +static inline void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ +} + +static inline void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return NULL; +} + +static inline int +devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + return 0; +} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 44acfbca12661d817a26ed6b2955ccdbbc60a9bf..7e39d2fc7c75af37d96f1539b8ed8f4b985609cd 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -46,6 +46,65 @@ TRACE_EVENT(devlink_hwmsg, (int) __entry->len, __get_dynamic_array(buf), __entry->len) ); +TRACE_EVENT(devlink_health_report, + TP_PROTO(const struct devlink *devlink, const char *reporter_name, + const char *msg), + + TP_ARGS(devlink, reporter_name, msg), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __string(reporter_name, msg) + __string(msg, msg) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(reporter_name, reporter_name); + __assign_str(msg, msg); + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __get_str(reporter_name), + __get_str(msg)) +); + +TRACE_EVENT(devlink_health_recover_aborted, + TP_PROTO(const struct devlink *devlink, const char *reporter_name, + bool health_state, u64 time_since_last_recover), + + TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __string(reporter_name, reporter_name) + __field(bool, health_state) + __field(u64, time_since_last_recover) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(reporter_name, reporter_name); + __entry->health_state = health_state; + __entry->time_since_last_recover = time_since_last_recover; + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover = %llu recover aborted", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __get_str(reporter_name), + __entry->health_state, + __entry->time_since_last_recover) +); + #endif /* _TRACE_DEVLINK_H */ /* This part must be outside protection */ @@ -64,6 +123,9 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink, { } +static inline void trace_devlink_health(const char *msg) +{ +} #endif /* _TRACE_DEVLINK_H */ #endif diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6e52d3660654dd031ad1c9d7ab91fd9a64f91bee..6b26bb2ce4dcb0839e20ea5a91c8caea8033f5a5 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -89,6 +89,13 @@ enum devlink_command { DEVLINK_CMD_REGION_DEL, DEVLINK_CMD_REGION_READ, + DEVLINK_CMD_HEALTH_REPORTER_GET, + DEVLINK_CMD_HEALTH_REPORTER_SET, + DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -285,6 +292,24 @@ enum devlink_attr { DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME, /* string */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY, /* nested */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, /* u8 */ + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, /* dynamic */ + + DEVLINK_ATTR_HEALTH_REPORTER, /* nested */ + DEVLINK_ATTR_HEALTH_REPORTER_NAME, /* string */ + DEVLINK_ATTR_HEALTH_REPORTER_STATE, /* u8 */ + DEVLINK_ATTR_HEALTH_REPORTER_ERR, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL, /* u8 */ + DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, /* u8 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index abb0da9d7b4b7c8a21a91341f56852db41f06c67..60248a53c0ad08ff676d4dd497148c86204f2bc5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3597,6 +3597,1012 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, return 0; } +#define DEVLINK_HEALTH_BUFFER_SIZE (4096 - GENL_HDRLEN) +#define DEVLINK_HEALTH_BUFFER_DATA_SIZE (DEVLINK_HEALTH_BUFFER_SIZE / 2) +#define DEVLINK_HEALTH_SIZE_TO_BUFFERS(size) DIV_ROUND_UP(size, DEVLINK_HEALTH_BUFFER_DATA_SIZE) +#define DEVLINK_HEALTH_BUFFER_MAX_CHUNK 1024 + +struct devlink_health_buffer { + void *data; + u64 offset; + u64 bytes_left; + u64 bytes_left_metadata; + u64 max_nested_depth; + u64 curr_nest; +}; + +struct devlink_health_buffer_desc { + int attrtype; + u16 len; + u8 nla_type; + u8 nest_end; + int value[0]; +}; + +static void +devlink_health_buffers_reset(struct devlink_health_buffer **buffers_list, + u64 num_of_buffers) +{ + u64 i; + + for (i = 0; i < num_of_buffers; i++) { + memset(buffers_list[i]->data, 0, DEVLINK_HEALTH_BUFFER_SIZE); + buffers_list[i]->offset = 0; + buffers_list[i]->bytes_left = DEVLINK_HEALTH_BUFFER_DATA_SIZE; + buffers_list[i]->bytes_left_metadata = + DEVLINK_HEALTH_BUFFER_DATA_SIZE; + buffers_list[i]->max_nested_depth = 0; + buffers_list[i]->curr_nest = 0; + } +} + +static void +devlink_health_buffers_destroy(struct devlink_health_buffer **buffers_list, + u64 size); + +static struct devlink_health_buffer ** +devlink_health_buffers_create(u64 size) +{ + struct devlink_health_buffer **buffers_list; + u64 num_of_buffers = DEVLINK_HEALTH_SIZE_TO_BUFFERS(size); + u64 i; + + buffers_list = kcalloc(num_of_buffers, + sizeof(struct devlink_health_buffer *), + GFP_KERNEL); + if (!buffers_list) + return NULL; + + for (i = 0; i < num_of_buffers; i++) { + struct devlink_health_buffer *buffer; + void *data; + + buffer = kzalloc(sizeof(*buffer), GFP_KERNEL); + data = kzalloc(DEVLINK_HEALTH_BUFFER_SIZE, GFP_KERNEL); + if (!buffer || !data) { + kfree(buffer); + kfree(data); + goto buffers_cleanup; + } + buffers_list[i] = buffer; + buffer->data = data; + } + devlink_health_buffers_reset(buffers_list, num_of_buffers); + + return buffers_list; + +buffers_cleanup: + devlink_health_buffers_destroy(buffers_list, --i); + kfree(buffers_list); + return NULL; +} + +static void +devlink_health_buffers_destroy(struct devlink_health_buffer **buffers_list, + u64 num_of_buffers) +{ + u64 i; + + for (i = 0; i < num_of_buffers; i++) { + kfree(buffers_list[i]->data); + kfree(buffers_list[i]); + } +} + +void +devlink_health_buffer_offset_inc(struct devlink_health_buffer *buffer, + int len) +{ + buffer->offset += len; +} + +/* In order to store a nest, need two descriptors, for start and end */ +#define DEVLINK_HEALTH_BUFFER_NEST_SIZE (sizeof(struct devlink_health_buffer_desc) * 2) + +int devlink_health_buffer_verify_len(struct devlink_health_buffer *buffer, + int len, int metadata_len) +{ + if (len > DEVLINK_HEALTH_BUFFER_DATA_SIZE) + return -EINVAL; + + if (buffer->bytes_left < len || + buffer->bytes_left_metadata < metadata_len) + return -ENOMEM; + + return 0; +} + +static struct devlink_health_buffer_desc * +devlink_health_buffer_get_desc_from_offset(struct devlink_health_buffer *buffer) +{ + return buffer->data + buffer->offset; +} + +int +devlink_health_buffer_nest_start(struct devlink_health_buffer *buffer, + int attrtype) +{ + struct devlink_health_buffer_desc *desc; + int err; + + err = devlink_health_buffer_verify_len(buffer, 0, + DEVLINK_HEALTH_BUFFER_NEST_SIZE); + if (err) + return err; + + if (attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT && + attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR && + attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE && + attrtype != DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY) + return -EINVAL; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + + desc->attrtype = attrtype; + buffer->bytes_left_metadata -= DEVLINK_HEALTH_BUFFER_NEST_SIZE; + devlink_health_buffer_offset_inc(buffer, sizeof(*desc)); + + buffer->curr_nest++; + buffer->max_nested_depth = max(buffer->max_nested_depth, + buffer->curr_nest); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_start); + +enum devlink_health_buffer_nest_end_cancel { + DEVLINK_HEALTH_BUFFER_NEST_END = 1, + DEVLINK_HEALTH_BUFFER_NEST_CANCEL, +}; + +static void +devlink_health_buffer_nest_end_cancel(struct devlink_health_buffer *buffer, + enum devlink_health_buffer_nest_end_cancel nest) +{ + struct devlink_health_buffer_desc *desc; + + WARN_ON(!buffer->curr_nest); + buffer->curr_nest--; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc->nest_end = nest; + devlink_health_buffer_offset_inc(buffer, sizeof(*desc)); +} + +void devlink_health_buffer_nest_end(struct devlink_health_buffer *buffer) +{ + devlink_health_buffer_nest_end_cancel(buffer, + DEVLINK_HEALTH_BUFFER_NEST_END); +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_end); + +void devlink_health_buffer_nest_cancel(struct devlink_health_buffer *buffer) +{ + devlink_health_buffer_nest_end_cancel(buffer, + DEVLINK_HEALTH_BUFFER_NEST_CANCEL); +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_nest_cancel); + +int +devlink_health_buffer_put_object_name(struct devlink_health_buffer *buffer, + char *name) +{ + struct devlink_health_buffer_desc *desc; + int err; + + err = devlink_health_buffer_verify_len(buffer, strlen(name) + 1, + sizeof(*desc)); + if (err) + return err; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc->attrtype = DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME; + desc->nla_type = NLA_NUL_STRING; + desc->len = strlen(name) + 1; + memcpy(&desc->value, name, desc->len); + devlink_health_buffer_offset_inc(buffer, sizeof(*desc) + desc->len); + + buffer->bytes_left_metadata -= sizeof(*desc); + buffer->bytes_left -= (strlen(name) + 1); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_object_name); + +static int +devlink_health_buffer_put_value(struct devlink_health_buffer *buffer, + u8 nla_type, void *value, int len) +{ + struct devlink_health_buffer_desc *desc; + int err; + + err = devlink_health_buffer_verify_len(buffer, len, sizeof(*desc)); + if (err) + return err; + + desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc->attrtype = DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA; + desc->nla_type = nla_type; + desc->len = len; + memcpy(&desc->value, value, len); + devlink_health_buffer_offset_inc(buffer, sizeof(*desc) + desc->len); + + buffer->bytes_left_metadata -= sizeof(*desc); + buffer->bytes_left -= len; + + return 0; +} + +int +devlink_health_buffer_put_value_u8(struct devlink_health_buffer *buffer, + u8 value) +{ + int err; + + err = devlink_health_buffer_put_value(buffer, NLA_U8, &value, + sizeof(value)); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u8); + +int +devlink_health_buffer_put_value_u32(struct devlink_health_buffer *buffer, + u32 value) +{ + int err; + + err = devlink_health_buffer_put_value(buffer, NLA_U32, &value, + sizeof(value)); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u32); + +int +devlink_health_buffer_put_value_u64(struct devlink_health_buffer *buffer, + u64 value) +{ + int err; + + err = devlink_health_buffer_put_value(buffer, NLA_U64, &value, + sizeof(value)); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_u64); + +int +devlink_health_buffer_put_value_string(struct devlink_health_buffer *buffer, + char *name) +{ + int err; + + if (strlen(name) + 1 > DEVLINK_HEALTH_BUFFER_MAX_CHUNK) + return -EINVAL; + + err = devlink_health_buffer_put_value(buffer, NLA_NUL_STRING, name, + strlen(name) + 1); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_string); + +int +devlink_health_buffer_put_value_data(struct devlink_health_buffer *buffer, + void *data, int len) +{ + int err; + + if (len > DEVLINK_HEALTH_BUFFER_MAX_CHUNK) + return -EINVAL; + + err = devlink_health_buffer_put_value(buffer, NLA_BINARY, data, len); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_buffer_put_value_data); + +static int +devlink_health_buffer_fill_data(struct sk_buff *skb, + struct devlink_health_buffer_desc *desc) +{ + int err = -EINVAL; + + switch (desc->nla_type) { + case NLA_U8: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + *(u8 *)desc->value); + break; + case NLA_U32: + err = nla_put_u32(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + *(u32 *)desc->value); + break; + case NLA_U64: + err = nla_put_u64_64bit(skb, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + *(u64 *)desc->value, DEVLINK_ATTR_PAD); + break; + case NLA_NUL_STRING: + err = nla_put_string(skb, + DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + (char *)&desc->value); + break; + case NLA_BINARY: + err = nla_put(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA, + desc->len, (void *)&desc->value); + break; + } + + return err; +} + +static int +devlink_health_buffer_fill_type(struct sk_buff *skb, + struct devlink_health_buffer_desc *desc) +{ + int err = -EINVAL; + + switch (desc->nla_type) { + case NLA_U8: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_U8); + break; + case NLA_U32: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_U32); + break; + case NLA_U64: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_U64); + break; + case NLA_NUL_STRING: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_NUL_STRING); + break; + case NLA_BINARY: + err = nla_put_u8(skb, DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_TYPE, + NLA_BINARY); + break; + } + + return err; +} + +static inline struct devlink_health_buffer_desc * +devlink_health_buffer_get_next_desc(struct devlink_health_buffer_desc *desc) +{ + return (void *)&desc->value + desc->len; +} + +static int +devlink_health_buffer_prepare_skb(struct sk_buff *skb, + struct devlink_health_buffer *buffer) +{ + struct devlink_health_buffer_desc *last_desc, *desc; + struct nlattr **buffer_nlattr; + int err; + int i = 0; + + buffer_nlattr = kcalloc(buffer->max_nested_depth, + sizeof(*buffer_nlattr), GFP_KERNEL); + if (!buffer_nlattr) + return -EINVAL; + + last_desc = devlink_health_buffer_get_desc_from_offset(buffer); + desc = buffer->data; + while (desc != last_desc) { + switch (desc->attrtype) { + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT: + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_PAIR: + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE: + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_ARRAY: + buffer_nlattr[i] = nla_nest_start(skb, desc->attrtype); + if (!buffer_nlattr[i]) + goto nla_put_failure; + i++; + break; + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_VALUE_DATA: + err = devlink_health_buffer_fill_data(skb, desc); + if (err) + goto nla_put_failure; + err = devlink_health_buffer_fill_type(skb, desc); + if (err) + goto nla_put_failure; + break; + case DEVLINK_ATTR_HEALTH_BUFFER_OBJECT_NAME: + err = nla_put_string(skb, desc->attrtype, + (char *)&desc->value); + if (err) + goto nla_put_failure; + break; + default: + WARN_ON(!desc->nest_end); + WARN_ON(i <= 0); + if (desc->nest_end == DEVLINK_HEALTH_BUFFER_NEST_END) + nla_nest_end(skb, buffer_nlattr[--i]); + else + nla_nest_cancel(skb, buffer_nlattr[--i]); + break; + } + desc = devlink_health_buffer_get_next_desc(desc); + } + + return 0; + +nla_put_failure: + kfree(buffer_nlattr); + return err; +} + +static int +devlink_health_buffer_snd(struct genl_info *info, + enum devlink_command cmd, int flags, + struct devlink_health_buffer **buffers_array, + u64 num_of_buffers) +{ + struct sk_buff *skb; + struct nlmsghdr *nlh; + void *hdr; + int err; + u64 i; + + for (i = 0; i < num_of_buffers; i++) { + /* Skip buffer if driver did not fill it up with any data */ + if (!buffers_array[i]->offset) + continue; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, NLM_F_MULTI, cmd); + if (!hdr) + goto nla_put_failure; + + err = devlink_health_buffer_prepare_skb(skb, buffers_array[i]); + if (err) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + err = genlmsg_reply(skb, info); + if (err) + return err; + } + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + err = genlmsg_reply(skb, info); + if (err) + return err; + + return 0; + +nla_put_failure: + err = -EIO; + nlmsg_free(skb); + return err; +} + +struct devlink_health_reporter { + struct list_head list; + struct devlink_health_buffer **dump_buffers_array; + struct mutex dump_lock; /* lock parallel read/write from dump buffers */ + struct devlink_health_buffer **diagnose_buffers_array; + struct mutex diagnose_lock; /* lock parallel read/write from diagnose buffers */ + void *priv; + const struct devlink_health_reporter_ops *ops; + struct devlink *devlink; + u64 graceful_period; + bool auto_recover; + u8 health_state; + u8 dump_avail; + u64 dump_ts; + u64 error_count; + u64 recovery_count; + u64 last_recovery_ts; +}; + +enum devlink_health_reporter_state { + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY, + DEVLINK_HEALTH_REPORTER_STATE_ERROR, +}; + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return reporter->priv; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); + +static struct devlink_health_reporter * +devlink_health_reporter_find_by_name(struct devlink *devlink, + const char *reporter_name) +{ + struct devlink_health_reporter *reporter; + + list_for_each_entry(reporter, &devlink->reporter_list, list) + if (!strcmp(reporter->ops->name, reporter_name)) + return reporter; + return NULL; +} + +/** + * devlink_health_reporter_create - create devlink health reporter + * + * @devlink: devlink + * @ops: ops + * @graceful_period: to avoid recovery loops, in msecs + * @auto_recover: auto recover when error occurs + * @priv: priv + */ +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv) +{ + struct devlink_health_reporter *reporter; + + mutex_lock(&devlink->lock); + if (devlink_health_reporter_find_by_name(devlink, ops->name)) { + reporter = ERR_PTR(-EEXIST); + goto unlock; + } + + if (WARN_ON(ops->dump && !ops->dump_size) || + WARN_ON(ops->diagnose && !ops->diagnose_size) || + WARN_ON(auto_recover && !ops->recover) || + WARN_ON(graceful_period && !ops->recover)) { + reporter = ERR_PTR(-EINVAL); + goto unlock; + } + + reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); + if (!reporter) { + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + + if (ops->dump) { + reporter->dump_buffers_array = + devlink_health_buffers_create(ops->dump_size); + if (!reporter->dump_buffers_array) { + kfree(reporter); + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + } + + if (ops->diagnose) { + reporter->diagnose_buffers_array = + devlink_health_buffers_create(ops->diagnose_size); + if (!reporter->diagnose_buffers_array) { + devlink_health_buffers_destroy(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(ops->dump_size)); + kfree(reporter); + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + } + + list_add_tail(&reporter->list, &devlink->reporter_list); + mutex_init(&reporter->dump_lock); + mutex_init(&reporter->diagnose_lock); + + reporter->priv = priv; + reporter->ops = ops; + reporter->devlink = devlink; + reporter->graceful_period = graceful_period; + reporter->auto_recover = auto_recover; +unlock: + mutex_unlock(&devlink->lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_create); + +/** + * devlink_health_reporter_destroy - destroy devlink health reporter + * + * @reporter: devlink health reporter to destroy + */ +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + mutex_lock(&reporter->devlink->lock); + list_del(&reporter->list); + devlink_health_buffers_destroy(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); + devlink_health_buffers_destroy(reporter->diagnose_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->diagnose_size)); + kfree(reporter); + mutex_unlock(&reporter->devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); + +static int +devlink_health_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->recover) + return -EOPNOTSUPP; + + err = reporter->ops->recover(reporter, priv_ctx); + if (err) + return err; + + reporter->recovery_count++; + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; + reporter->last_recovery_ts = jiffies; + + return 0; +} + +static int devlink_health_do_dump(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->dump) + return 0; + + if (reporter->dump_avail) + return 0; + + devlink_health_buffers_reset(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); + err = reporter->ops->dump(reporter, reporter->dump_buffers_array, + DEVLINK_HEALTH_BUFFER_SIZE, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size), + priv_ctx); + if (!err) { + reporter->dump_avail = true; + reporter->dump_ts = jiffies; + } + + return err; +} + +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + struct devlink *devlink = reporter->devlink; + int err = 0; + + /* write a log message of the current error */ + WARN_ON(!msg); + trace_devlink_health_report(devlink, reporter->ops->name, msg); + reporter->error_count++; + + /* abort if the previous error wasn't recovered */ + if (reporter->auto_recover && + (reporter->health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || + jiffies - reporter->last_recovery_ts < + msecs_to_jiffies(reporter->graceful_period))) { + trace_devlink_health_recover_aborted(devlink, + reporter->ops->name, + reporter->health_state, + jiffies - + reporter->last_recovery_ts); + return -ECANCELED; + } + + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; + + mutex_lock(&reporter->dump_lock); + /* store current dump of current error, for later analysis */ + devlink_health_do_dump(reporter, priv_ctx); + mutex_unlock(&reporter->dump_lock); + + if (reporter->auto_recover) + err = devlink_health_reporter_recover(reporter, priv_ctx); + + return err; +} +EXPORT_SYMBOL_GPL(devlink_health_report); + +static struct devlink_health_reporter * +devlink_health_reporter_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *reporter_name; + + if (!info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) + return NULL; + + reporter_name = + nla_data(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); + return devlink_health_reporter_find_by_name(devlink, reporter_name); +} + +static int +devlink_nl_health_reporter_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_health_reporter *reporter, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *reporter_attr; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER); + if (!reporter_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, + reporter->ops->name)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, + reporter->health_state)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR, + reporter->error_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, + reporter->recovery_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, + reporter->graceful_period, + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, + reporter->auto_recover)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_AVAIL, + reporter->dump_avail)) + goto reporter_nest_cancel; + if (reporter->dump_avail && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, + jiffies_to_msecs(reporter->dump_ts), + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + + nla_nest_end(msg, reporter_attr); + genlmsg_end(msg, hdr); + return 0; + +reporter_nest_cancel: + nla_nest_end(msg, reporter_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct sk_buff *msg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_health_reporter_fill(msg, devlink, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + info->snd_portid, info->snd_seq, + 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_health_reporter *reporter; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(reporter, &devlink->reporter_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill(msg, devlink, + reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int +devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->recover && + (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) + return -EINVAL; + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) + reporter->graceful_period = + nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) + reporter->auto_recover = + nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); + + return 0; +} + +static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + return devlink_health_reporter_recover(reporter, NULL); +} + +static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + u64 num_of_buffers; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->diagnose) + return -EOPNOTSUPP; + + num_of_buffers = + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->diagnose_size); + + mutex_lock(&reporter->diagnose_lock); + devlink_health_buffers_reset(reporter->diagnose_buffers_array, + num_of_buffers); + + err = reporter->ops->diagnose(reporter, + reporter->diagnose_buffers_array, + DEVLINK_HEALTH_BUFFER_SIZE, + num_of_buffers); + if (err) + goto out; + + err = devlink_health_buffer_snd(info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + 0, reporter->diagnose_buffers_array, + num_of_buffers); + if (err) + goto out; + + mutex_unlock(&reporter->diagnose_lock); + return 0; + +out: + mutex_unlock(&reporter->diagnose_lock); + return err; +} + +static void +devlink_health_dump_clear(struct devlink_health_reporter *reporter) +{ + reporter->dump_avail = false; + reporter->dump_ts = 0; + devlink_health_buffers_reset(reporter->dump_buffers_array, + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size)); +} + +static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + u64 num_of_buffers; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) + return -EOPNOTSUPP; + + num_of_buffers = + DEVLINK_HEALTH_SIZE_TO_BUFFERS(reporter->ops->dump_size); + + mutex_lock(&reporter->dump_lock); + err = devlink_health_do_dump(reporter, NULL); + if (err) + goto out; + + err = devlink_health_buffer_snd(info, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + 0, reporter->dump_buffers_array, + num_of_buffers); + +out: + mutex_unlock(&reporter->dump_lock); + return err; +} + +static int +devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + mutex_lock(&reporter->dump_lock); + devlink_health_dump_clear(reporter); + mutex_unlock(&reporter->dump_lock); + return 0; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -3622,6 +4628,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -3842,6 +4851,51 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, + .doit = devlink_nl_cmd_health_reporter_get_doit, + .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, + .doit = devlink_nl_cmd_health_reporter_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + .doit = devlink_nl_cmd_health_reporter_recover_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + .doit = devlink_nl_cmd_health_reporter_diagnose_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + .doit = devlink_nl_cmd_health_reporter_dump_get_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -3882,6 +4936,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->resource_list); INIT_LIST_HEAD(&devlink->param_list); INIT_LIST_HEAD(&devlink->region_list); + INIT_LIST_HEAD(&devlink->reporter_list); mutex_init(&devlink->lock); return devlink; }