Merge tag 'irq-core-2020-12-23' of git://git.kernel.org/pub/scm/linux…

…/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "This is the second attempt after the first one failed miserably and
  got zapped to unblock the rest of the interrupt related patches.

  A treewide cleanup of interrupt descriptor (ab)use with all sorts of
  racy accesses, inefficient and disfunctional code. The goal is to
  remove the export of irq_to_desc() to prevent these things from
  creeping up again"

* tag 'irq-core-2020-12-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  genirq: Restrict export of irq_to_desc()
  xen/events: Implement irq distribution
  xen/events: Reduce irq_info:: Spurious_cnt storage size
  xen/events: Only force affinity mask for percpu interrupts
  xen/events: Use immediate affinity setting
  xen/events: Remove disfunct affinity spreading
  xen/events: Remove unused bind_evtchn_to_irq_lateeoi()
  net/mlx5: Use effective interrupt affinity
  net/mlx5: Replace irq_to_desc() abuse
  net/mlx4: Use effective interrupt affinity
  net/mlx4: Replace irq_to_desc() abuse
  PCI: mobiveil: Use irq_data_get_irq_chip_data()
  PCI: xilinx-nwl: Use irq_data_get_irq_chip_data()
  NTB/msi: Use irq_has_action()
  mfd: ab8500-debugfs: Remove the racy fiddling with irq_desc
  pinctrl: nomadik: Use irq_has_action()
  drm/i915/pmu: Replace open coded kstat_irqs() copy
  drm/i915/lpe_audio: Remove pointless irq_to_desc() usage
  s390/irq: Use irq_desc_kstat_cpu() in show_msi_interrupt()
  parisc/irq: Use irq_desc_kstat_cpu() in show_interrupts()
  ...

arch/alpha/kernel/sys_jensen.c

@@ -7,7 +7,7 @@
  *
  * Code supporting the Jensen.
  */
-
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/mm.h>

arch/arm/kernel/smp.c

@@ -549,7 +549,7 @@ void show_ipi_list(struct seq_file *p, int prec)
 		seq_printf(p, "%*s%u: ", prec - 1, "IPI", i);
 
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 
 		seq_printf(p, " %s\n", ipi_types[i]);
 	}

arch/arm64/kernel/smp.c

@@ -811,7 +811,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 		seq_printf(p, "      %s\n", ipi_types[i]);
 	}
 

arch/parisc/kernel/irq.c

@@ -216,12 +216,9 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (!action)
 			goto skip;
 		seq_printf(p, "%3d: ", i);
-#ifdef CONFIG_SMP
+
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-#else
-		seq_printf(p, "%10u ", kstat_irqs(i));
-#endif
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(desc, j));
 
 		seq_printf(p, " %14s", irq_desc_get_chip(desc)->name);
 #ifndef PARISC_IRQ_CR16_COUNTS

arch/s390/kernel/irq.c

@@ -124,7 +124,7 @@ static void show_msi_interrupt(struct seq_file *p, int irq)
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	seq_printf(p, "%3d: ", irq);
 	for_each_online_cpu(cpu)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+		seq_printf(p, "%10u ", irq_desc_kstat_cpu(desc, cpu));
 
 	if (desc->irq_data.chip)
 		seq_printf(p, " %8s", desc->irq_data.chip->name);

arch/x86/kernel/topology.c

@@ -25,6 +25,7 @@
  *
  * Send feedback to <[email protected]>
  */
+#include <linux/interrupt.h>
 #include <linux/nodemask.h>
 #include <linux/export.h>
 #include <linux/mmzone.h>

drivers/gpu/drm/i915/display/intel_lpe_audio.c

@@ -297,13 +297,9 @@ int intel_lpe_audio_init(struct drm_i915_private *dev_priv)
  */
 void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv)
 {
-	struct irq_desc *desc;
-
 	if (!HAS_LPE_AUDIO(dev_priv))
 		return;
 
-	desc = irq_to_desc(dev_priv->lpe_audio.irq);
-
 	lpe_audio_platdev_destroy(dev_priv);
 
 	irq_free_desc(dev_priv->lpe_audio.irq);

drivers/gpu/drm/i915/i915_irq.c

@@ -60,6 +60,24 @@
  * and related files, but that will be described in separate chapters.
  */
 
+/*
+ * Interrupt statistic for PMU. Increments the counter only if the
+ * interrupt originated from the the GPU so interrupts from a device which
+ * shares the interrupt line are not accounted.
+ */
+static inline void pmu_irq_stats(struct drm_i915_private *i915,
+				 irqreturn_t res)
+{
+	if (unlikely(res != IRQ_HANDLED))
+		return;
+
+	/*
+	 * A clever compiler translates that into INC. A not so clever one
+	 * should at least prevent store tearing.
+	 */
+	WRITE_ONCE(i915->pmu.irq_count, i915->pmu.irq_count + 1);
+}
+
 typedef bool (*long_pulse_detect_func)(enum hpd_pin pin, u32 val);
 typedef u32 (*hotplug_enables_func)(struct drm_i915_private *i915,
 				    enum hpd_pin pin);
@@ -1668,6 +1686,8 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -1745,6 +1765,8 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 		valleyview_pipestat_irq_handler(dev_priv, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -2155,6 +2177,8 @@ static irqreturn_t ilk_irq_handler(int irq, void *arg)
 	if (sde_ier)
 		raw_reg_write(regs, SDEIER, sde_ier);
 
+	pmu_irq_stats(i915, ret);
+
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	enable_rpm_wakeref_asserts(&i915->runtime_pm);
 
@@ -2541,6 +2565,8 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg)
 
 	gen8_master_intr_enable(regs);
 
+	pmu_irq_stats(dev_priv, IRQ_HANDLED);
+
 	return IRQ_HANDLED;
 }
 
@@ -2636,6 +2662,8 @@ __gen11_irq_handler(struct drm_i915_private * const i915,
 
 	gen11_gu_misc_irq_handler(gt, gu_misc_iir);
 
+	pmu_irq_stats(i915, IRQ_HANDLED);
+
 	return IRQ_HANDLED;
 }
 
@@ -3934,6 +3962,8 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		i8xx_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -4043,6 +4073,8 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		i915_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, ret);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
@@ -4189,6 +4221,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		i965_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
 
+	pmu_irq_stats(dev_priv, IRQ_HANDLED);
+
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;

drivers/gpu/drm/i915/i915_pmu.c

@@ -4,7 +4,6 @@
  * Copyright © 2017-2018 Intel Corporation
  */
 
-#include <linux/irq.h>
 #include <linux/pm_runtime.h>
 
 #include "gt/intel_engine.h"
@@ -424,22 +423,6 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static u64 count_interrupts(struct drm_i915_private *i915)
-{
-	/* open-coded kstat_irqs() */
-	struct irq_desc *desc = irq_to_desc(i915->drm.pdev->irq);
-	u64 sum = 0;
-	int cpu;
-
-	if (!desc || !desc->kstat_irqs)
-		return 0;
-
-	for_each_possible_cpu(cpu)
-		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
-
-	return sum;
-}
-
 static void i915_pmu_event_destroy(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
@@ -590,7 +573,7 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_INTERRUPTS:
-			val = count_interrupts(i915);
+			val = READ_ONCE(pmu->irq_count);
 			break;
 		case I915_PMU_RC6_RESIDENCY:
 			val = get_rc6(&i915->gt);

drivers/gpu/drm/i915/i915_pmu.h

@@ -111,6 +111,14 @@ struct i915_pmu {
 	 * @sleep_last: Last time GT parked for RC6 estimation.
 	 */
 	ktime_t sleep_last;
+	/**
+	 * @irq_count: Number of interrupts
+	 *
+	 * Intentionally unsigned long to avoid atomics or heuristics on 32bit.
+	 * 4e9 interrupts are a lot and postprocessing can really deal with an
+	 * occasional wraparound easily. It's 32bit after all.
+	 */
+	unsigned long irq_count;
 	/**
 	 * @events_attr_group: Device events attribute group.
 	 */

drivers/mfd/ab8500-debugfs.c

@@ -1513,24 +1513,14 @@ static int ab8500_interrupts_show(struct seq_file *s, void *p)
 {
 	int line;
 
-	seq_puts(s, "name: number:  number of: wake:\n");
+	seq_puts(s, "name: number: irq: number of: wake:\n");
 
 	for (line = 0; line < num_interrupt_lines; line++) {
-		struct irq_desc *desc = irq_to_desc(line + irq_first);
-
-		seq_printf(s, "%3i:  %6i %4i",
+		seq_printf(s, "%3i:  %4i %6i %4i\n",
 			   line,
+			   line + irq_first,
 			   num_interrupts[line],
 			   num_wake_interrupts[line]);
-
-		if (desc && desc->name)
-			seq_printf(s, "-%-8s", desc->name);
-		if (desc && desc->action) {
-			struct irqaction *action = desc->action;
-
-			seq_printf(s, "  %s", action->name);
-			while ((action = action->next) != NULL)
-				seq_printf(s, ", %s", action->name);
 		}
 		seq_putc(s, '\n');
 	}

drivers/net/ethernet/mellanox/mlx4/en_cq.c

@@ -90,7 +90,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 			int cq_idx)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int err = 0;
+	int irq, err = 0;
 	int timestamp_en = 0;
 	bool assigned_eq = false;
 
@@ -116,10 +116,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 
 			assigned_eq = true;
 		}
-
-		cq->irq_desc =
-			irq_to_desc(mlx4_eq_get_irq(mdev->dev,
-						    cq->vector));
+		irq = mlx4_eq_get_irq(mdev->dev, cq->vector);
+		cq->aff_mask = irq_get_effective_affinity_mask(irq);
 	} else {
 		/* For TX we use the same irq per
 		ring we assigned for the RX    */

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -958,18 +958,14 @@ 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 || !clean_complete) {
-		const struct cpumask *aff;
-		struct irq_data *idata;
 		int cpu_curr;
 
 		/* in case we got here because of !clean_complete */
 		done = budget;
 
 		cpu_curr = smp_processor_id();
-		idata = irq_desc_get_irq_data(cq->irq_desc);
-		aff = irq_data_get_affinity_mask(idata);
 
-		if (likely(cpumask_test_cpu(cpu_curr, aff)))
+		if (likely(cpumask_test_cpu(cpu_curr, cq->aff_mask)))
 			return budget;
 
 		/* Current cpu is not according to smp_irq_affinity -

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -47,6 +47,7 @@
 #endif
 #include <linux/cpu_rmap.h>
 #include <linux/ptp_clock_kernel.h>
+#include <linux/irq.h>
 #include <net/xdp.h>
 
 #include <linux/mlx4/device.h>
@@ -365,7 +366,7 @@ struct mlx4_en_cq {
 	struct mlx4_cqe *buf;
 #define MLX4_EN_OPCODE_ERROR	0x1e
 
-	struct irq_desc *irq_desc;
+	const struct cpumask *aff_mask;
 };
 
 struct mlx4_en_port_profile {

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -684,7 +684,7 @@ struct mlx5e_channel {
 	spinlock_t                 async_icosq_lock;
 
 	/* data path - accessed per napi poll */
-	struct irq_desc *irq_desc;
+	const struct cpumask	  *aff_mask;
 	struct mlx5e_ch_stats     *stats;
 
 	/* control */

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c

@@ -479,7 +479,6 @@ int mlx5e_port_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
 	c->num_tc   = params->num_tc;
 	c->stats    = &priv->port_ptp_stats.ch;
-	c->irq_desc = irq_to_desc(irq);
 	c->lag_port = lag_port;
 
 	netif_napi_add(netdev, &c->napi, mlx5e_ptp_napi_poll, 64);

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h

@@ -28,7 +28,6 @@ struct mlx5e_port_ptp {
 	u8                         lag_port;
 
 	/* data path - accessed per napi poll */
-	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
 
 	/* control */

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -1987,7 +1987,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->num_tc   = params->num_tc;
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
-	c->irq_desc = irq_to_desc(irq);
+	c->aff_mask = irq_get_effective_affinity_mask(irq);
 	c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix);
 
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);

drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c

@@ -40,12 +40,8 @@
 static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
 	int current_cpu = smp_processor_id();
-	const struct cpumask *aff;
-	struct irq_data *idata;
 
-	idata = irq_desc_get_irq_data(c->irq_desc);
-	aff = irq_data_get_affinity_mask(idata);
-	return cpumask_test_cpu(current_cpu, aff);
+	return cpumask_test_cpu(current_cpu, c->aff_mask);
 }
 
 static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq)

drivers/ntb/msi.c

@@ -282,15 +282,13 @@ int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler,
 				  struct ntb_msi_desc *msi_desc)
 {
 	struct msi_desc *entry;
-	struct irq_desc *desc;
 	int ret;
 
 	if (!ntb->msi)
 		return -EINVAL;
 
 	for_each_pci_msi_entry(entry, ntb->pdev) {
-		desc = irq_to_desc(entry->irq);
-		if (desc->action)
+		if (irq_has_action(entry->irq))
 			continue;
 
 		ret = devm_request_threaded_irq(&ntb->dev, entry->irq, handler,