LKML Archive on lore.kernel.org
 help / color / Atom feed
From: "tip-bot2 for Marc Zyngier" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: John Garry <john.garry@huawei.com>, Marc Zyngier <maz@kernel.org>,
	x86 <x86@kernel.org>, LKML <linux-kernel@vger.kernel.org>
Subject: [tip: irq/core] irqchip/gic-v3-its: Balance initial LPI affinity across CPUs
Date: Sat, 30 May 2020 07:46:37 -0000
Message-ID: <159082479727.17951.12803360401899580245.tip-bot2@tip-bot2> (raw)
In-Reply-To: <1575642904-58295-1-git-send-email-john.garry@huawei.com>

The following commit has been merged into the irq/core branch of tip:

Commit-ID:     c5d6082d35e0bcc20a26a067ffcfddcb5257e580
Gitweb:        https://git.kernel.org/tip/c5d6082d35e0bcc20a26a067ffcfddcb5257e580
Author:        Marc Zyngier <maz@kernel.org>
AuthorDate:    Fri, 15 May 2020 17:57:52 +01:00
Committer:     Marc Zyngier <maz@kernel.org>
CommitterDate: Wed, 20 May 2020 11:00:00 +01:00

irqchip/gic-v3-its: Balance initial LPI affinity across CPUs

When mapping a LPI, the ITS driver picks the first possible
affinity, which is in most cases CPU0, assuming that if
that's not suitable, someone will come and set the affinity
to something more interesting.

It apparently isn't the case, and people complain of poor
performance when many interrupts are glued to the same CPU.
So let's place the interrupts by finding the "least loaded"
CPU (that is, the one that has the fewer LPIs mapped to it).
So called 'managed' interrupts are an interesting case where
the affinity is actually dictated by the kernel itself, and
we should honor this.

Reported-by: John Garry <john.garry@huawei.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1575642904-58295-1-git-send-email-john.garry@huawei.com
Link: https://lore.kernel.org/r/20200515165752.121296-3-maz@kernel.org
---
 drivers/irqchip/irq-gic-v3-its.c | 127 +++++++++++++++++++++++-------
 1 file changed, 100 insertions(+), 27 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 4eb8441..cd685f5 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1541,15 +1541,104 @@ static void its_dec_lpi_count(struct irq_data *d, int cpu)
 		atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
 }
 
+static unsigned int cpumask_pick_least_loaded(struct irq_data *d,
+					      const struct cpumask *cpu_mask)
+{
+	unsigned int cpu = nr_cpu_ids, tmp;
+	int count = S32_MAX;
+
+	for_each_cpu(tmp, cpu_mask) {
+		int this_count = its_read_lpi_count(d, tmp);
+		if (this_count < count) {
+			cpu = tmp;
+		        count = this_count;
+		}
+	}
+
+	return cpu;
+}
+
+/*
+ * As suggested by Thomas Gleixner in:
+ * https://lore.kernel.org/r/87h80q2aoc.fsf@nanos.tec.linutronix.de
+ */
+static int its_select_cpu(struct irq_data *d,
+			  const struct cpumask *aff_mask)
+{
+	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
+	cpumask_var_t tmpmask;
+	int cpu, node;
+
+	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
+		return -ENOMEM;
+
+	node = its_dev->its->numa_node;
+
+	if (!irqd_affinity_is_managed(d)) {
+		/* First try the NUMA node */
+		if (node != NUMA_NO_NODE) {
+			/*
+			 * Try the intersection of the affinity mask and the
+			 * node mask (and the online mask, just to be safe).
+			 */
+			cpumask_and(tmpmask, cpumask_of_node(node), aff_mask);
+			cpumask_and(tmpmask, tmpmask, cpu_online_mask);
+
+			/*
+			 * Ideally, we would check if the mask is empty, and
+			 * try again on the full node here.
+			 *
+			 * But it turns out that the way ACPI describes the
+			 * affinity for ITSs only deals about memory, and
+			 * not target CPUs, so it cannot describe a single
+			 * ITS placed next to two NUMA nodes.
+			 *
+			 * Instead, just fallback on the online mask. This
+			 * diverges from Thomas' suggestion above.
+			 */
+			cpu = cpumask_pick_least_loaded(d, tmpmask);
+			if (cpu < nr_cpu_ids)
+				goto out;
+
+			/* If we can't cross sockets, give up */
+			if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144))
+				goto out;
+
+			/* If the above failed, expand the search */
+		}
+
+		/* Try the intersection of the affinity and online masks */
+		cpumask_and(tmpmask, aff_mask, cpu_online_mask);
+
+		/* If that doesn't fly, the online mask is the last resort */
+		if (cpumask_empty(tmpmask))
+			cpumask_copy(tmpmask, cpu_online_mask);
+
+		cpu = cpumask_pick_least_loaded(d, tmpmask);
+	} else {
+		cpumask_and(tmpmask, irq_data_get_affinity_mask(d), cpu_online_mask);
+
+		/* If we cannot cross sockets, limit the search to that node */
+		if ((its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) &&
+		    node != NUMA_NO_NODE)
+			cpumask_and(tmpmask, tmpmask, cpumask_of_node(node));
+
+		cpu = cpumask_pick_least_loaded(d, tmpmask);
+	}
+out:
+	free_cpumask_var(tmpmask);
+
+	pr_debug("IRQ%d -> %*pbl CPU%d\n", d->irq, cpumask_pr_args(aff_mask), cpu);
+	return cpu;
+}
+
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
-	unsigned int cpu;
-	const struct cpumask *cpu_mask = cpu_online_mask;
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
-	int prev_cpu;
+	int cpu, prev_cpu;
 
 	/* A forwarded interrupt should use irq_set_vcpu_affinity */
 	if (irqd_is_forwarded_to_vcpu(d))
@@ -1558,18 +1647,12 @@ static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	prev_cpu = its_dev->event_map.col_map[id];
 	its_dec_lpi_count(d, prev_cpu);
 
-       /* lpi cannot be routed to a redistributor that is on a foreign node */
-	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
-		if (its_dev->its->numa_node >= 0) {
-			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
-			if (!cpumask_intersects(mask_val, cpu_mask))
-				goto err;
-		}
-	}
-
-	cpu = cpumask_any_and(mask_val, cpu_mask);
+	if (!force)
+		cpu = its_select_cpu(d, mask_val);
+	else
+		cpu = cpumask_pick_least_loaded(d, mask_val);
 
-	if (cpu >= nr_cpu_ids)
+	if (cpu < 0 || cpu >= nr_cpu_ids)
 		goto err;
 
 	/* don't set the affinity when the target cpu is same as current one */
@@ -3473,21 +3556,11 @@ static int its_irq_domain_activate(struct irq_domain *domain,
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
-	const struct cpumask *cpu_mask = cpu_online_mask;
 	int cpu;
 
-	/* get the cpu_mask of local node */
-	if (its_dev->its->numa_node >= 0)
-		cpu_mask = cpumask_of_node(its_dev->its->numa_node);
-
-	/* Bind the LPI to the first possible CPU */
-	cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
-	if (cpu >= nr_cpu_ids) {
-		if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144)
-			return -EINVAL;
-
-		cpu = cpumask_first(cpu_online_mask);
-	}
+	cpu = its_select_cpu(d, cpu_online_mask);
+	if (cpu < 0 || cpu >= nr_cpu_ids)
+		return -EINVAL;
 
 	its_inc_lpi_count(d, cpu);
 	its_dev->event_map.col_map[event] = cpu;

      parent reply index

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-06 14:35 [PATCH RFC 0/1] Threaded handler uses irq affinity for when the interrupt is managed John Garry
2019-12-06 14:35 ` [PATCH RFC 1/1] genirq: Make threaded handler use irq affinity for managed interrupt John Garry
2019-12-06 15:22   ` Marc Zyngier
2019-12-06 16:16     ` John Garry
2019-12-07  8:03   ` Ming Lei
2019-12-09 14:30     ` John Garry
2019-12-09 15:09       ` Hannes Reinecke
2019-12-09 15:17         ` Marc Zyngier
2019-12-09 15:25           ` Hannes Reinecke
2019-12-09 15:36             ` Marc Zyngier
2019-12-09 15:49           ` Qais Yousef
2019-12-09 15:55             ` Marc Zyngier
2019-12-10  1:43       ` Ming Lei
2019-12-10  9:45         ` John Garry
2019-12-10 10:06           ` Ming Lei
2019-12-10 10:28           ` Marc Zyngier
2019-12-10 10:59             ` John Garry
2019-12-10 11:36               ` Marc Zyngier
2019-12-10 12:05                 ` John Garry
2019-12-10 18:32                   ` Marc Zyngier
2019-12-11  9:41                     ` John Garry
2019-12-13 10:07                       ` John Garry
2019-12-13 10:31                         ` Marc Zyngier
2019-12-13 12:08                           ` John Garry
2019-12-14 10:59                             ` Marc Zyngier
2019-12-11 17:09         ` John Garry
2019-12-12 22:38           ` Ming Lei
2019-12-13 11:12             ` John Garry
2019-12-13 13:18               ` Ming Lei
2019-12-13 15:43                 ` John Garry
2019-12-13 17:12                   ` Ming Lei
2019-12-13 17:50                     ` John Garry
2019-12-14 13:56                   ` Marc Zyngier
2019-12-16 10:47                     ` John Garry
2019-12-16 11:40                       ` Marc Zyngier
2019-12-16 14:17                         ` John Garry
2019-12-16 18:00                           ` Marc Zyngier
2019-12-16 18:50                             ` John Garry
2019-12-20 11:30                               ` John Garry
2019-12-20 14:43                                 ` Marc Zyngier
2019-12-20 15:38                                   ` John Garry
2019-12-20 16:16                                     ` Marc Zyngier
2019-12-20 23:31                                     ` Ming Lei
2019-12-23  9:07                                       ` Marc Zyngier
2019-12-23 10:26                                         ` John Garry
2019-12-23 10:47                                           ` Marc Zyngier
2019-12-23 11:35                                             ` John Garry
2019-12-24  1:59                                             ` Ming Lei
2019-12-24 11:20                                               ` Marc Zyngier
2019-12-25  0:48                                                 ` Ming Lei
2020-01-02 10:35                                                   ` John Garry
2020-01-03  0:46                                                     ` Ming Lei
2020-01-03 10:41                                                       ` John Garry
2020-01-03 11:29                                                         ` Ming Lei
2020-01-03 11:50                                                           ` John Garry
2020-01-04 12:03                                                             ` Ming Lei
2020-05-30  7:46 ` tip-bot2 for Marc Zyngier [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=159082479727.17951.12803360401899580245.tip-bot2@tip-bot2 \
    --to=tip-bot2@linutronix.de \
    --cc=john.garry@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git