irqchip/gicv3: Workaround for Cavium ThunderX erratum 23154

This patch implements Cavium ThunderX erratum 23154.

The gicv3 of ThunderX requires a modified version for reading the IAR
status to ensure data synchronization. Since this is in the fast-path
and called with each interrupt, runtime patching is used using jump
label patching for smallest overhead (no-op). This is the same
technique as used for tracepoints.

Signed-off-by: Robert Richter <rrichter@cavium.com>
Reviewed-by: Marc Zygnier <marc.zyngier@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Tirumalesh Chalamarla <tchalamarla@cavium.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Jason Cooper <jason@lakedaemon.net>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/1442869119-1814-3-git-send-email-rric@kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 36ecfc8..eecec71 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -109,7 +109,7 @@
 }
 
 /* Low level accessors */
-static u64 __maybe_unused gic_read_iar(void)
+static u64 gic_read_iar_common(void)
 {
 	u64 irqstat;
 
@@ -117,6 +117,38 @@
 	return irqstat;
 }
 
+/*
+ * Cavium ThunderX erratum 23154
+ *
+ * The gicv3 of ThunderX requires a modified version for reading the
+ * IAR status to ensure data synchronization (access to icc_iar1_el1
+ * is not sync'ed before and after).
+ */
+static u64 gic_read_iar_cavium_thunderx(void)
+{
+	u64 irqstat;
+
+	asm volatile(
+		"nop;nop;nop;nop\n\t"
+		"nop;nop;nop;nop\n\t"
+		"mrs_s %0, " __stringify(ICC_IAR1_EL1) "\n\t"
+		"nop;nop;nop;nop"
+		: "=r" (irqstat));
+	mb();
+
+	return irqstat;
+}
+
+static struct static_key is_cavium_thunderx = STATIC_KEY_INIT_FALSE;
+
+static u64 __maybe_unused gic_read_iar(void)
+{
+	if (static_key_false(&is_cavium_thunderx))
+		return gic_read_iar_cavium_thunderx();
+	else
+		return gic_read_iar_common();
+}
+
 static void __maybe_unused gic_write_pmr(u64 val)
 {
 	asm volatile("msr_s " __stringify(ICC_PMR_EL1) ", %0" : : "r" (val));
@@ -836,6 +868,12 @@
 	.free = gic_irq_domain_free,
 };
 
+static void gicv3_enable_quirks(void)
+{
+	if (cpus_have_cap(ARM64_WORKAROUND_CAVIUM_23154))
+		static_key_slow_inc(&is_cavium_thunderx);
+}
+
 static int __init gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *dist_base;
@@ -901,6 +939,8 @@
 	gic_data.nr_redist_regions = nr_redist_regions;
 	gic_data.redist_stride = redist_stride;
 
+	gicv3_enable_quirks();
+
 	/*
 	 * Find out how many interrupts are supported.
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)