linux-kernel - [PATCH 4/4 net-next] net: mana: Assigning IRQ affinity on HT cores

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Tue,  9 Jan 2024 02:51:18 -0800
From: Souradeep Chakrabarti <schakrabarti@...ux.microsoft.com>
To: kys@...rosoft.com,
	haiyangz@...rosoft.com,
	wei.liu@...nel.org,
	decui@...rosoft.com,
	davem@...emloft.net,
	edumazet@...gle.com,
	kuba@...nel.org,
	pabeni@...hat.com,
	longli@...rosoft.com,
	yury.norov@...il.com,
	leon@...nel.org,
	cai.huoqing@...ux.dev,
	ssengar@...ux.microsoft.com,
	vkuznets@...hat.com,
	tglx@...utronix.de,
	linux-hyperv@...r.kernel.org,
	netdev@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-rdma@...r.kernel.org
Cc: schakrabarti@...rosoft.com,
	paulros@...rosoft.com,
	Souradeep Chakrabarti <schakrabarti@...ux.microsoft.com>
Subject: [PATCH 4/4 net-next] net: mana: Assigning IRQ affinity on HT cores

Existing MANA design assigns IRQ to every CPU, including sibling
hyper-threads. This may cause multiple IRQs to be active simultaneously
in the same core and may reduce the network performance.

Improve the performance by assigning IRQ to non sibling CPUs in local
NUMA node. The performance improvement we are getting using ntttcp with
following patch is around 15 percent against existing design and
approximately 11 percent, when trying to assign one IRQ in each core
across NUMA nodes, if enough cores are present.

Signed-off-by: Souradeep Chakrabarti <schakrabarti@...ux.microsoft.com>
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 58 +++++++++++++++----
 1 file changed, 48 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 6a967d6be01e..6715d6939bc7 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1274,13 +1274,16 @@ static __maybe_unused int irq_setup(unsigned int *irqs, unsigned int len, int no
 
 static int mana_gd_setup_irqs(struct pci_dev *pdev)
 {
-	unsigned int max_queues_per_port = num_online_cpus();
 	struct gdma_context *gc = pci_get_drvdata(pdev);
+	unsigned int max_queues_per_port;
 	struct gdma_irq_context *gic;
 	unsigned int max_irqs, cpu;
-	int nvec, irq;
+	int start_irq_index = 1;
+	int nvec, *irqs, irq;
 	int err, i = 0, j;
 
+	cpus_read_lock();
+	max_queues_per_port = num_online_cpus();
 	if (max_queues_per_port > MANA_MAX_NUM_QUEUES)
 		max_queues_per_port = MANA_MAX_NUM_QUEUES;
 
@@ -1288,8 +1291,18 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 	max_irqs = max_queues_per_port + 1;
 
 	nvec = pci_alloc_irq_vectors(pdev, 2, max_irqs, PCI_IRQ_MSIX);
-	if (nvec < 0)
+	if (nvec < 0) {
+		cpus_read_unlock();
 		return nvec;
+	}
+	if (nvec <= num_online_cpus())
+		start_irq_index = 0;
+
+	irqs = kmalloc_array((nvec - start_irq_index), sizeof(int), GFP_KERNEL);
+	if (!irqs) {
+		err = -ENOMEM;
+		goto free_irq_vector;
+	}
 
 	gc->irq_contexts = kcalloc(nvec, sizeof(struct gdma_irq_context),
 				   GFP_KERNEL);
@@ -1316,21 +1329,44 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 			goto free_irq;
 		}
 
-		err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);
-		if (err)
-			goto free_irq;
-
-		cpu = cpumask_local_spread(i, gc->numa_node);
-		irq_set_affinity_and_hint(irq, cpumask_of(cpu));
+		if (!i) {
+			err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);
+			if (err)
+				goto free_irq;
+
+			/* If number of IRQ is one extra than number of online CPUs,
+			 * then we need to assign IRQ0 (hwc irq) and IRQ1 to
+			 * same CPU.
+			 * Else we will use different CPUs for IRQ0 and IRQ1.
+			 * Also we are using cpumask_local_spread instead of
+			 * cpumask_first for the node, because the node can be
+			 * mem only.
+			 */
+			if (start_irq_index) {
+				cpu = cpumask_local_spread(i, gc->numa_node);
+				irq_set_affinity_and_hint(irq, cpumask_of(cpu));
+			} else {
+				irqs[start_irq_index] = irq;
+			}
+		} else {
+			irqs[i - start_irq_index] = irq;
+			err = request_irq(irqs[i - start_irq_index], mana_gd_intr, 0,
+					  gic->name, gic);
+			if (err)
+				goto free_irq;
+		}
 	}
 
+	err = irq_setup(irqs, (nvec - start_irq_index), gc->numa_node);
+	if (err)
+		goto free_irq;
 	err = mana_gd_alloc_res_map(nvec, &gc->msix_resource);
 	if (err)
 		goto free_irq;
 
 	gc->max_num_msix = nvec;
 	gc->num_msix_usable = nvec;
-
+	cpus_read_unlock();
 	return 0;
 
 free_irq:
@@ -1343,8 +1379,10 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev)
 	}
 
 	kfree(gc->irq_contexts);
+	kfree(irqs);
 	gc->irq_contexts = NULL;
 free_irq_vector:
+	cpus_read_unlock();
 	pci_free_irq_vectors(pdev);
 	return err;
 }
-- 
2.34.1