Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
Date:   Fri, 22 Apr 2022 04:35:32 +0000
Message-Id: <20220422043532.146946-1-nathan@nathanrossi.com>
From:   Nathan Rossi <nathan@nathanrossi.com>
To:     linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org
Cc:     Nathan Rossi <nathan@nathanrossi.com>,
        Nathan Rossi <nathan.rossi@digi.com>,
        Andrew Lunn <andrew@lunn.ch>,
        Gregory Clement <gregory.clement@bootlin.com>,
        Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Marc Zyngier <maz@kernel.org>
Subject: [PATCH v2] irqchip/armada-370-xp: Enable MSI affinity configuration
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 8bit
MIME-Version: 1.0
Precedence: bulk

From: Nathan Rossi <nathan.rossi@digi.com>

With multiple devices attached via PCIe to an Armada 385 it is possible
to overwhelm a single CPU with MSI interrupts. Under certain scenarios
configuring the interrupts to be handled by more than one CPU would
prevent the system from being overwhelmed. However the
irqchip-aramada-370-xp driver is configured to only handle MSIs on the
boot CPU, and provides no affinity configuration.

This change adds support to the armada-370-xp driver to allow for
configuring the affinity of specific MSI irqs and to generate the
interrupts on secondary CPUs. This is done by enabling the private
doorbell for all online CPUs and configures all CPUs to unmask MSI
specific private doorbell bits. The CPU affinity selection of the
interrupt is handled by the target list of the software triggered
interrupt value, which is provided as the MSI message. The message has
the associated CPU bit set for the target CPU. For private doorbell
interrupts only one bit can be set otherwise all CPUs will receive the
interrupt, so the lowest CPU in the affinity mask is used. This means
that by default the first CPU will handle all the interrupts as was the
case before.

Signed-off-by: Nathan Rossi <nathan.rossi@digi.com>
---
Changes in v2:
- Use BIT()
- Remove added #ifdef CONFIG_SMP within compose_msi_msg/msi_set_affinity
- Refactor duplication of per cpu doorbell mask and interrupt enable
  configuration
---
 drivers/irqchip/irq-armada-370-xp.c | 45 +++++++++++++++++++++++++++----------
 1 file changed, 33 insertions(+), 12 deletions(-)

diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 5b8d571c04..c877285d70 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -209,15 +209,29 @@ static struct msi_domain_info armada_370_xp_msi_domain_info = {
 
 static void armada_370_xp_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
+	unsigned int cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
+
 	msg->address_lo = lower_32_bits(msi_doorbell_addr);
 	msg->address_hi = upper_32_bits(msi_doorbell_addr);
-	msg->data = 0xf00 | (data->hwirq + PCI_MSI_DOORBELL_START);
+	msg->data = BIT(cpu + 8) | (data->hwirq + PCI_MSI_DOORBELL_START);
 }
 
 static int armada_370_xp_msi_set_affinity(struct irq_data *irq_data,
 					  const struct cpumask *mask, bool force)
 {
-	 return -EINVAL;
+	unsigned int cpu;
+
+	if (!force)
+		cpu = cpumask_any_and(mask, cpu_online_mask);
+	else
+		cpu = cpumask_first(mask);
+
+	if (cpu >= nr_cpu_ids)
+		return -EINVAL;
+
+	irq_data_update_effective_affinity(irq_data, cpumask_of(cpu));
+
+	return IRQ_SET_MASK_OK;
 }
 
 static struct irq_chip armada_370_xp_msi_bottom_irq_chip = {
@@ -264,11 +278,21 @@ static const struct irq_domain_ops armada_370_xp_msi_domain_ops = {
 	.free	= armada_370_xp_msi_free,
 };
 
-static int armada_370_xp_msi_init(struct device_node *node,
-				  phys_addr_t main_int_phys_base)
+static void armada_370_xp_msi_reenable_percpu(void)
 {
 	u32 reg;
 
+	/* Enable MSI doorbell mask and combined cpu local interrupt */
+	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS)
+		| PCI_MSI_DOORBELL_MASK;
+	writel(reg, per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
+	/* Unmask local doorbell interrupt */
+	writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+}
+
+static int armada_370_xp_msi_init(struct device_node *node,
+				  phys_addr_t main_int_phys_base)
+{
 	msi_doorbell_addr = main_int_phys_base +
 		ARMADA_370_XP_SW_TRIG_INT_OFFS;
 
@@ -287,18 +311,13 @@ static int armada_370_xp_msi_init(struct device_node *node,
 		return -ENOMEM;
 	}
 
-	reg = readl(per_cpu_int_base + ARMADA_370_XP_IN_DRBEL_MSK_OFFS)
-		| PCI_MSI_DOORBELL_MASK;
-
-	writel(reg, per_cpu_int_base +
-	       ARMADA_370_XP_IN_DRBEL_MSK_OFFS);
-
-	/* Unmask IPI interrupt */
-	writel(1, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS);
+	armada_370_xp_msi_reenable_percpu();
 
 	return 0;
 }
 #else
+static void armada_370_xp_msi_reenable_percpu(void) {}
+
 static inline int armada_370_xp_msi_init(struct device_node *node,
 					 phys_addr_t main_int_phys_base)
 {
@@ -501,6 +520,8 @@ static void armada_xp_mpic_reenable_percpu(void)
 	}
 
 	ipi_resume();
+
+	armada_370_xp_msi_reenable_percpu();
 }
 
 static int armada_xp_mpic_starting_cpu(unsigned int cpu)
---
2.35.2