From 57f35c93a2072c1f66ab1728a77a9ee4bc33bf42 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Thu, 25 May 2017 16:46:14 +0300 Subject: net/mlx5: Fix create vport flow table flow Send vport number to the create flow table inner method instead of ignoring the vport argument and sending always 0. Fixes: b3ba51498bdd ('net/mlx5: Refactor create flow table method to accept underlay QP') Signed-off-by: Mohamad Haj Yahia Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 0e487e8ca634..8f5125ccd8d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -862,7 +862,7 @@ struct mlx5_flow_table *mlx5_create_vport_flow_table(struct mlx5_flow_namespace ft_attr.level = level; ft_attr.prio = prio; - return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, 0); + return __mlx5_create_flow_table(ns, &ft_attr, FS_FT_OP_MOD_NORMAL, vport); } struct mlx5_flow_table* -- cgit v1.2.3 From 3fece5d676939f42f434c63dfe1bd42d7d94e6f0 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Sun, 9 Apr 2017 17:19:37 +0300 Subject: net/mlx5: Continue health polling until it is explicitly stopped The issue is that when we get an assert we will stop polling the health and thus we cant enter error state when we have a real health issue. Fixes: fd76ee4da55a ('net/mlx5_core: Fix internal error detection conditions') Signed-off-by: Mohamad Haj Yahia Reviewed-by: Daniel Jurgens Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 44f59b1d6f0f..f27f84ffbc85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -275,10 +275,8 @@ static void poll_health(unsigned long data) struct mlx5_core_health *health = &dev->priv.health; u32 count; - if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { - mod_timer(&health->timer, get_next_poll_jiffies()); - return; - } + if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto out; count = ioread32be(health->health_counter); if (count == health->prev) @@ -290,8 +288,6 @@ static void poll_health(unsigned long data) if (health->miss_counter == MAX_MISSES) { dev_err(&dev->pdev->dev, "device's health compromised - reached miss count\n"); print_health_info(dev); - } else { - mod_timer(&health->timer, get_next_poll_jiffies()); } if (in_fatal(dev) && !health->sick) { @@ -305,6 +301,9 @@ static void poll_health(unsigned long data) "new health works are not permitted at this stage\n"); spin_unlock(&health->wq_lock); } + +out: + mod_timer(&health->timer, get_next_poll_jiffies()); } void mlx5_start_health_poll(struct mlx5_core_dev *dev) -- cgit v1.2.3 From f729860a177d097ac44321fb2f7d927a0c54c5a3 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Mon, 8 May 2017 11:46:50 -0500 Subject: net/mlx5: Remove several module events out of ethtool stats Remove the following module event counters out of ethtool stats. The reason for removing these event counters is that these events do not occur without techinician's intervention. module_pwr_budget_exd module_long_range module_no_eeprom module_enforce_part module_unknown_id module_unknown_status module_plug Fixes: bedb7c909c19 ("net/mlx5e: Add port module event counters to ethtool stats") Signed-off-by: Huy Nguyen Reviewed by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 53e4992d6511..f81c3aa60b46 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -417,20 +417,13 @@ struct mlx5e_stats { }; static const struct counter_desc mlx5e_pme_status_desc[] = { - { "module_plug", 0 }, { "module_unplug", 8 }, }; static const struct counter_desc mlx5e_pme_error_desc[] = { - { "module_pwr_budget_exd", 0 }, /* power budget exceed */ - { "module_long_range", 8 }, /* long range for non MLNX cable */ - { "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */ - { "module_no_eeprom", 24 }, /* no eeprom/retry time out */ - { "module_enforce_part", 32 }, /* enforce part number list */ - { "module_unknown_id", 40 }, /* unknown identifier */ - { "module_high_temp", 48 }, /* high temperature */ + { "module_bus_stuck", 16 }, /* bus stuck (I2C or data shorted) */ + { "module_high_temp", 48 }, /* high temperature */ { "module_bad_shorted", 56 }, /* bad or shorted cable/module */ - { "module_unknown_status", 64 }, }; #endif /* __MLX5_EN_STATS_H__ */ -- cgit v1.2.3 From c3164d2fc48fd4fa0477ab658b644559c3fe9073 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Mon, 15 May 2017 14:13:16 +0300 Subject: net/mlx5e: Added BW check for DIM decision mechanism DIM (Dynamically-tuned Interrupt Moderation) is a mechanism designed for changing the channel interrupt moderation values in order to reduce CPU overhead for all traffic types. Until now only interrupt and packet rate were sampled. We found a scenario on which we get a false indication since a change in DIM caused more aggregation and reduced packet rate while increasing BW. We now regard a change as succesfull iff: current_BW > (prev_BW + threshold) or current_BW ~= prev_BW and current_PR > (prev_PR + threshold) or current_BW ~= prev_BW and current_PR ~= prev_PR and current_IR < (prev_IR - threshold) Where BW = Bandwidth, PR = Packet rate and IR = Interrupt rate Improvements (ConnectX-4Lx 25GbE, single RX queue, LRO off) -------------------------------------------------- packet size | before[Mb/s] | after[Mb/s] | gain | 2B | 343.4 | 359.4 | 4.5% | 16B | 2739.7 | 2814.8 | 2.7% | 64B | 9739 | 10185.3 | 4.5% | Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing") Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 ++ drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 37 ++++++++++++---------- 2 files changed, 22 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 2fd044b23875..429da21a583d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -458,12 +458,14 @@ struct mlx5e_mpw_info { struct mlx5e_rx_am_stats { int ppms; /* packets per msec */ + int bpms; /* bytes per msec */ int epms; /* events per msec */ }; struct mlx5e_rx_am_sample { ktime_t time; unsigned int pkt_ctr; + unsigned int byte_ctr; u16 event_ctr; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c index 02dd3a95ed8f..54cdda957f9a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c @@ -183,28 +183,27 @@ static void mlx5e_am_exit_parking(struct mlx5e_rx_am *am) mlx5e_am_step(am); } +#define IS_SIGNIFICANT_DIFF(val, ref) \ + (((100 * abs((val) - (ref))) / (ref)) > 10) /* more than 10% difference */ + static int mlx5e_am_stats_compare(struct mlx5e_rx_am_stats *curr, struct mlx5e_rx_am_stats *prev) { - int diff; - - if (!prev->ppms) - return curr->ppms ? MLX5E_AM_STATS_BETTER : + if (!prev->bpms) + return curr->bpms ? MLX5E_AM_STATS_BETTER : MLX5E_AM_STATS_SAME; - diff = curr->ppms - prev->ppms; - if (((100 * abs(diff)) / prev->ppms) > 10) /* more than 10% diff */ - return (diff > 0) ? MLX5E_AM_STATS_BETTER : - MLX5E_AM_STATS_WORSE; + if (IS_SIGNIFICANT_DIFF(curr->bpms, prev->bpms)) + return (curr->bpms > prev->bpms) ? MLX5E_AM_STATS_BETTER : + MLX5E_AM_STATS_WORSE; - if (!prev->epms) - return curr->epms ? MLX5E_AM_STATS_WORSE : - MLX5E_AM_STATS_SAME; + if (IS_SIGNIFICANT_DIFF(curr->ppms, prev->ppms)) + return (curr->ppms > prev->ppms) ? MLX5E_AM_STATS_BETTER : + MLX5E_AM_STATS_WORSE; - diff = curr->epms - prev->epms; - if (((100 * abs(diff)) / prev->epms) > 10) /* more than 10% diff */ - return (diff < 0) ? MLX5E_AM_STATS_BETTER : - MLX5E_AM_STATS_WORSE; + if (IS_SIGNIFICANT_DIFF(curr->epms, prev->epms)) + return (curr->epms < prev->epms) ? MLX5E_AM_STATS_BETTER : + MLX5E_AM_STATS_WORSE; return MLX5E_AM_STATS_SAME; } @@ -266,6 +265,7 @@ static void mlx5e_am_sample(struct mlx5e_rq *rq, { s->time = ktime_get(); s->pkt_ctr = rq->stats.packets; + s->byte_ctr = rq->stats.bytes; s->event_ctr = rq->cq.event_ctr; } @@ -278,12 +278,15 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start, /* u32 holds up to 71 minutes, should be enough */ u32 delta_us = ktime_us_delta(end->time, start->time); unsigned int npkts = end->pkt_ctr - start->pkt_ctr; + unsigned int nbytes = end->byte_ctr - start->byte_ctr; if (!delta_us) return; - curr_stats->ppms = (npkts * USEC_PER_MSEC) / delta_us; - curr_stats->epms = (MLX5E_AM_NEVENTS * USEC_PER_MSEC) / delta_us; + curr_stats->ppms = DIV_ROUND_UP(npkts * USEC_PER_MSEC, delta_us); + curr_stats->bpms = DIV_ROUND_UP(nbytes * USEC_PER_MSEC, delta_us); + curr_stats->epms = DIV_ROUND_UP(MLX5E_AM_NEVENTS * USEC_PER_MSEC, + delta_us); } void mlx5e_rx_am_work(struct work_struct *work) -- cgit v1.2.3 From 53acd76ce571e3b71f9205f2d49ab285a9f1aad8 Mon Sep 17 00:00:00 2001 From: Tal Gilboa Date: Mon, 29 May 2017 17:02:55 +0300 Subject: net/mlx5e: Fix wrong indications in DIM due to counter wraparound DIM (Dynamically-tuned Interrupt Moderation) is a mechanism designed for changing the channel interrupt moderation values in order to reduce CPU overhead for all traffic types. Each iteration of the algorithm, DIM calculates the difference in throughput, packet rate and interrupt rate from last iteration in order to make a decision. DIM relies on counters for each metric. When these counters get to their type's max value they wraparound. In this case the delta between 'end' and 'start' samples is negative and when translated to unsigned integers - very high. This results in a false indication to the algorithm and might result in a wrong decision. The fix calculates the 'distance' between 'end' and 'start' samples in a cyclic way around the relevant type's max value. It can also be viewed as an absolute value around the type's max value instead of around 0. Testing show higher stability in DIM profile selection and no wraparound issues. Fixes: cb3c7fd4f839 ("net/mlx5e: Support adaptive RX coalescing") Signed-off-by: Tal Gilboa Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 8 ++++---- drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c | 10 +++++++--- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 429da21a583d..944fc1742464 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -463,10 +463,10 @@ struct mlx5e_rx_am_stats { }; struct mlx5e_rx_am_sample { - ktime_t time; - unsigned int pkt_ctr; - unsigned int byte_ctr; - u16 event_ctr; + ktime_t time; + u32 pkt_ctr; + u32 byte_ctr; + u16 event_ctr; }; struct mlx5e_rx_am { /* Adaptive Moderation */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c index 54cdda957f9a..acf32fe952cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx_am.c @@ -270,6 +270,8 @@ static void mlx5e_am_sample(struct mlx5e_rq *rq, } #define MLX5E_AM_NEVENTS 64 +#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) +#define BIT_GAP(bits, end, start) ((((end) - (start)) + BIT_ULL(bits)) & (BIT_ULL(bits) - 1)) static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start, struct mlx5e_rx_am_sample *end, @@ -277,8 +279,9 @@ static void mlx5e_am_calc_stats(struct mlx5e_rx_am_sample *start, { /* u32 holds up to 71 minutes, should be enough */ u32 delta_us = ktime_us_delta(end->time, start->time); - unsigned int npkts = end->pkt_ctr - start->pkt_ctr; - unsigned int nbytes = end->byte_ctr - start->byte_ctr; + u32 npkts = BIT_GAP(BITS_PER_TYPE(u32), end->pkt_ctr, start->pkt_ctr); + u32 nbytes = BIT_GAP(BITS_PER_TYPE(u32), end->byte_ctr, + start->byte_ctr); if (!delta_us) return; @@ -311,7 +314,8 @@ void mlx5e_rx_am(struct mlx5e_rq *rq) switch (am->state) { case MLX5E_AM_MEASURE_IN_PROGRESS: - nevents = rq->cq.event_ctr - am->start_sample.event_ctr; + nevents = BIT_GAP(BITS_PER_TYPE(u16), rq->cq.event_ctr, + am->start_sample.event_ctr); if (nevents < MLX5E_AM_NEVENTS) break; mlx5e_am_sample(rq, &end_sample); -- cgit v1.2.3 From 91828bd89940e8145f91751a015bc11bc486aad0 Mon Sep 17 00:00:00 2001 From: Majd Dibbiny Date: Sun, 28 May 2017 14:47:56 +0300 Subject: net/mlx5: Enable 4K UAR only when page size is bigger than 4K When the page size isn't bigger than 4K, there is no added value of enabling 4K UAR feature in the Firmware. Modified the condition of enabling the 4K UAR accordingly. Fixes: f502d834950a ("net/mlx5: Activate support for 4K UARs") Signed-off-by: Majd Dibbiny Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index af945edfee19..4f577a5abf88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -537,8 +537,10 @@ static int handle_hca_cap(struct mlx5_core_dev *dev) /* disable cmdif checksum */ MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0); - /* If the HCA supports 4K UARs use it */ - if (MLX5_CAP_GEN_MAX(dev, uar_4k)) + /* Enable 4K UAR only when HCA supports it and page size is bigger + * than 4K. + */ + if (MLX5_CAP_GEN_MAX(dev, uar_4k) && PAGE_SIZE > 4096) MLX5_SET(cmd_hca_cap, set_hca_cap, uar_4k, 1); MLX5_SET(cmd_hca_cap, set_hca_cap, log_uar_page_sz, PAGE_SHIFT - 12); -- cgit v1.2.3