irqchip/gic: Work around broken Renesas integration

Geert reported that the GIC driver locks up on a Renesas system
since 005c34a ("irqchip/gic: Atomically update affinity")
fixed the driver to use writeb_relaxed() instead of writel_relaxed().

As it turns out, the interconnect used on this system mandates
32bit wide accesses for all MMIO transactions, even if the GIC
architecture specifically mandates for some registers to be byte
accessible. Gahhh...

Work around the issue by crudly detecting the offending system,
and falling back to an inefficient RMW+lock implementation.

Reported-by: Geert Uytterhoeven <[email protected]>
Signed-off-by: Marc Zyngier <[email protected]>
Link: https://lore.kernel.org/r/CAMuHMdV+Ev47K5NO8XHsanSq5YRMCHn2gWAQyV-q2LpJVy9HiQ@mail.gmail.com

Author: Marc Zyngier

drivers/irqchip/irq-gic.c

@@ -107,6 +107,8 @@ static DEFINE_RAW_SPINLOCK(cpu_map_lock);
 
 #endif
 
+static DEFINE_STATIC_KEY_FALSE(needs_rmw_access);
+
 /*
  * The GIC mapping of CPU interfaces does not necessarily match
  * the logical CPU numbering.  Let's use a mapping as returned
@@ -774,6 +776,25 @@ static int gic_pm_init(struct gic_chip_data *gic)
 #endif
 
 #ifdef CONFIG_SMP
+static void rmw_writeb(u8 bval, void __iomem *addr)
+{
+	static DEFINE_RAW_SPINLOCK(rmw_lock);
+	unsigned long offset = (unsigned long)addr & 3UL;
+	unsigned long shift = offset * 8;
+	unsigned long flags;
+	u32 val;
+
+	raw_spin_lock_irqsave(&rmw_lock, flags);
+
+	addr -= offset;
+	val = readl_relaxed(addr);
+	val &= ~GENMASK(shift + 7, shift);
+	val |= bval << shift;
+	writel_relaxed(val, addr);
+
+	raw_spin_unlock_irqrestore(&rmw_lock, flags);
+}
+
 static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
@@ -788,7 +809,10 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	if (cpu >= NR_GIC_CPU_IF || cpu >= nr_cpu_ids)
 		return -EINVAL;
 
-	writeb_relaxed(gic_cpu_map[cpu], reg);
+	if (static_branch_unlikely(&needs_rmw_access))
+		rmw_writeb(gic_cpu_map[cpu], reg);
+	else
+		writeb_relaxed(gic_cpu_map[cpu], reg);
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
 	return IRQ_SET_MASK_OK_DONE;
@@ -1375,6 +1399,30 @@ static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
 	return true;
 }
 
+static bool gic_enable_rmw_access(void *data)
+{
+	/*
+	 * The EMEV2 class of machines has a broken interconnect, and
+	 * locks up on accesses that are less than 32bit. So far, only
+	 * the affinity setting requires it.
+	 */
+	if (of_machine_is_compatible("renesas,emev2")) {
+		static_branch_enable(&needs_rmw_access);
+		return true;
+	}
+
+	return false;
+}
+
+static const struct gic_quirk gic_quirks[] = {
+	{
+		.desc		= "broken byte access",
+		.compatible	= "arm,pl390",
+		.init		= gic_enable_rmw_access,
+	},
+	{ },
+};
+
 static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
 {
 	if (!gic || !node)
@@ -1391,6 +1439,8 @@ static int gic_of_setup(struct gic_chip_data *gic, struct device_node *node)
 	if (of_property_read_u32(node, "cpu-offset", &gic->percpu_offset))
 		gic->percpu_offset = 0;
 
+	gic_enable_of_quirks(node, gic_quirks, gic);
+
 	return 0;
 
 error: