irqchip/gic-v4.1: Plumb get/set_irqchip_state SGI callbacks

To implement the get/set_irqchip_state callbacks (limited to the
PENDING state), we have to use a particular set of hacks:

- Reading the pending state is done by using a pair of new redistributor
  registers (GICR_VSGIR, GICR_VSGIPENDR), which allow the 16 interrupts
  state to be retrieved.
- Setting the pending state is done by generating it as we'd otherwise do
  for a guest (writing to GITS_SGIR).
- Clearing the pending state is done by emitting a VSGI command with the
  "clear" bit set.

This requires some interesting locking though:
- When talking to the redistributor, we must make sure that the VPE
  affinity doesn't change, hence taking the VPE lock.
- At the same time, we must ensure that nobody accesses the same
  redistributor's GICR_VSGIR registers for a different VPE, which
  would corrupt the reading of the pending bits. We thus take the
  per-RD spinlock. Much fun.

Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Zenghui Yu <yuzenghui@huawei.com>
Link: https://lore.kernel.org/r/20200304203330.4967-12-maz@kernel.org

1 files changed, 77 insertions, 0 deletions

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index bc6666aed1cb..c614f0c19807 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -3972,11 +3972,88 @@ static int its_sgi_set_affinity(struct irq_data *d,
 	return IRQ_SET_MASK_OK;
 }
 
+static int its_sgi_set_irqchip_state(struct irq_data *d,
+				     enum irqchip_irq_state which,
+				     bool state)
+{
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	if (state) {
+		struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+		struct its_node *its = find_4_1_its();
+		u64 val;
+
+		val  = FIELD_PREP(GITS_SGIR_VPEID, vpe->vpe_id);
+		val |= FIELD_PREP(GITS_SGIR_VINTID, d->hwirq);
+		writeq_relaxed(val, its->sgir_base + GITS_SGIR - SZ_128K);
+	} else {
+		its_configure_sgi(d, true);
+	}
+
+	return 0;
+}
+
+static int its_sgi_get_irqchip_state(struct irq_data *d,
+				     enum irqchip_irq_state which, bool *val)
+{
+	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
+	void __iomem *base;
+	unsigned long flags;
+	u32 count = 1000000;	/* 1s! */
+	u32 status;
+	int cpu;
+
+	if (which != IRQCHIP_STATE_PENDING)
+		return -EINVAL;
+
+	/*
+	 * Locking galore! We can race against two different events:
+	 *
+	 * - Concurent vPE affinity change: we must make sure it cannot
+	 *   happen, or we'll talk to the wrong redistributor. This is
+	 *   identical to what happens with vLPIs.
+	 *
+	 * - Concurrent VSGIPENDR access: As it involves accessing two
+	 *   MMIO registers, this must be made atomic one way or another.
+	 */
+	cpu = vpe_to_cpuid_lock(vpe, &flags);
+	raw_spin_lock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	base = gic_data_rdist_cpu(cpu)->rd_base + SZ_128K;
+	writel_relaxed(vpe->vpe_id, base + GICR_VSGIR);
+	do {
+		status = readl_relaxed(base + GICR_VSGIPENDR);
+		if (!(status & GICR_VSGIPENDR_BUSY))
+			goto out;
+
+		count--;
+		if (!count) {
+			pr_err_ratelimited("Unable to get SGI status\n");
+			goto out;
+		}
+		cpu_relax();
+		udelay(1);
+	} while (count);
+
+out:
+	raw_spin_unlock(&gic_data_rdist_cpu(cpu)->rd_lock);
+	vpe_to_cpuid_unlock(vpe, flags);
+
+	if (!count)
+		return -ENXIO;
+
+	*val = !!(status & (1 << d->hwirq));
+
+	return 0;
+}
+
 static struct irq_chip its_sgi_irq_chip = {
 	.name			= "GICv4.1-sgi",
 	.irq_mask		= its_sgi_mask_irq,
 	.irq_unmask		= its_sgi_unmask_irq,
 	.irq_set_affinity	= its_sgi_set_affinity,
+	.irq_set_irqchip_state	= its_sgi_set_irqchip_state,
+	.irq_get_irqchip_state	= its_sgi_get_irqchip_state,
 };
 
 static int its_sgi_irq_domain_alloc(struct irq_domain *domain,