From: Amir Vadai Date: Sun, 29 Jun 2014 08:54:55 +0000 (+0300) Subject: net/mlx4_en: Don't use irq_affinity_notifier to track changes in IRQ affinity map X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=35f6f45;p=linux-beck.git net/mlx4_en: Don't use irq_affinity_notifier to track changes in IRQ affinity map IRQ affinity notifier can only have a single notifier - cpu_rmap notifier. Can't use it to track changes in IRQ affinity map. Detect IRQ affinity changes by comparing CPU to current IRQ affinity map during NAPI poll thread. CC: Thomas Gleixner CC: Ben Hutchings Fixes: 2eacc23 ("net/mlx4_core: Enforce irq affinity changes immediatly") Signed-off-by: Amir Vadai Signed-off-by: David S. Miller --- diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index 80f725228f5b..56022d647837 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -294,8 +294,6 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, init_completion(&cq->free); cq->irq = priv->eq_table.eq[cq->vector].irq; - cq->irq_affinity_change = false; - return 0; err_radix: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 4b2130760eed..1213cc71348c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -128,6 +128,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq, mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n", name); } + + cq->irq_desc = + irq_to_desc(mlx4_eq_get_irq(mdev->dev, + cq->vector)); } } else { cq->vector = (cq->ring + 1 + priv->port) % diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index d2d415732d99..96724170308a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -40,6 +40,7 @@ #include #include #include +#include #include "mlx4_en.h" @@ -896,16 +897,25 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget) /* If we used up all the quota - we're probably not done yet... */ if (done == budget) { + int cpu_curr; + const struct cpumask *aff; + INC_PERF_COUNTER(priv->pstats.napi_quota); - if (unlikely(cq->mcq.irq_affinity_change)) { - cq->mcq.irq_affinity_change = false; + + cpu_curr = smp_processor_id(); + aff = irq_desc_get_irq_data(cq->irq_desc)->affinity; + + if (unlikely(!cpumask_test_cpu(cpu_curr, aff))) { + /* Current cpu is not according to smp_irq_affinity - + * probably affinity changed. need to stop this NAPI + * poll, and restart it on the right CPU + */ napi_complete(napi); mlx4_en_arm_cq(priv, cq); return 0; } } else { /* Done for now */ - cq->mcq.irq_affinity_change = false; napi_complete(napi); mlx4_en_arm_cq(priv, cq); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8be7483f8236..ac3dead3792c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -474,15 +474,9 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget) /* If we used up all the quota - we're probably not done yet... */ if (done < budget) { /* Done for now */ - cq->mcq.irq_affinity_change = false; napi_complete(napi); mlx4_en_arm_cq(priv, cq); return done; - } else if (unlikely(cq->mcq.irq_affinity_change)) { - cq->mcq.irq_affinity_change = false; - napi_complete(napi); - mlx4_en_arm_cq(priv, cq); - return 0; } return budget; } diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index d954ec1eac17..2a004b347e1d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -53,11 +53,6 @@ enum { MLX4_EQ_ENTRY_SIZE = 0x20 }; -struct mlx4_irq_notify { - void *arg; - struct irq_affinity_notify notify; -}; - #define MLX4_EQ_STATUS_OK ( 0 << 28) #define MLX4_EQ_STATUS_WRITE_FAIL (10 << 28) #define MLX4_EQ_OWNER_SW ( 0 << 24) @@ -1088,57 +1083,6 @@ static void mlx4_unmap_clr_int(struct mlx4_dev *dev) iounmap(priv->clr_base); } -static void mlx4_irq_notifier_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct mlx4_irq_notify *n = container_of(notify, - struct mlx4_irq_notify, - notify); - struct mlx4_priv *priv = (struct mlx4_priv *)n->arg; - struct radix_tree_iter iter; - void **slot; - - radix_tree_for_each_slot(slot, &priv->cq_table.tree, &iter, 0) { - struct mlx4_cq *cq = (struct mlx4_cq *)(*slot); - - if (cq->irq == notify->irq) - cq->irq_affinity_change = true; - } -} - -static void mlx4_release_irq_notifier(struct kref *ref) -{ - struct mlx4_irq_notify *n = container_of(ref, struct mlx4_irq_notify, - notify.kref); - kfree(n); -} - -static void mlx4_assign_irq_notifier(struct mlx4_priv *priv, - struct mlx4_dev *dev, int irq) -{ - struct mlx4_irq_notify *irq_notifier = NULL; - int err = 0; - - irq_notifier = kzalloc(sizeof(*irq_notifier), GFP_KERNEL); - if (!irq_notifier) { - mlx4_warn(dev, "Failed to allocate irq notifier. irq %d\n", - irq); - return; - } - - irq_notifier->notify.irq = irq; - irq_notifier->notify.notify = mlx4_irq_notifier_notify; - irq_notifier->notify.release = mlx4_release_irq_notifier; - irq_notifier->arg = priv; - err = irq_set_affinity_notifier(irq, &irq_notifier->notify); - if (err) { - kfree(irq_notifier); - irq_notifier = NULL; - mlx4_warn(dev, "Failed to set irq notifier. irq %d\n", irq); - } -} - - int mlx4_alloc_eq_table(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -1409,8 +1353,6 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, continue; /*we dont want to break here*/ } - mlx4_assign_irq_notifier(priv, dev, - priv->eq_table.eq[vec].irq); eq_set_ci(&priv->eq_table.eq[vec], 1); } @@ -1427,6 +1369,14 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, } EXPORT_SYMBOL(mlx4_assign_eq); +int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec) +{ + struct mlx4_priv *priv = mlx4_priv(dev); + + return priv->eq_table.eq[vec].irq; +} +EXPORT_SYMBOL(mlx4_eq_get_irq); + void mlx4_release_eq(struct mlx4_dev *dev, int vec) { struct mlx4_priv *priv = mlx4_priv(dev); @@ -1438,9 +1388,6 @@ void mlx4_release_eq(struct mlx4_dev *dev, int vec) Belonging to a legacy EQ*/ mutex_lock(&priv->msix_ctl.pool_lock); if (priv->msix_ctl.pool_bm & 1ULL << i) { - irq_set_affinity_notifier( - priv->eq_table.eq[vec].irq, - NULL); free_irq(priv->eq_table.eq[vec].irq, &priv->eq_table.eq[vec]); priv->msix_ctl.pool_bm &= ~(1ULL << i); diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 0e15295bedd6..624e1939e9ee 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -343,6 +343,7 @@ struct mlx4_en_cq { #define CQ_USER_PEND (MLX4_EN_CQ_STATE_POLL | MLX4_EN_CQ_STATE_POLL_YIELD) spinlock_t poll_lock; /* protects from LLS/napi conflicts */ #endif /* CONFIG_NET_RX_BUSY_POLL */ + struct irq_desc *irq_desc; }; struct mlx4_en_port_profile { diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b12f4bbd064c..35b51e7af886 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -578,8 +578,6 @@ struct mlx4_cq { u32 cons_index; u16 irq; - bool irq_affinity_change; - __be32 *set_ci_db; __be32 *arm_db; int arm_sn; @@ -1167,6 +1165,8 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); +int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec); + int mlx4_get_phys_port_id(struct mlx4_dev *dev); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);