irqchip/gicv3-its: numa: Enable workaround for Cavium thunderx erratum 23144

The erratum fixes the hang of ITS SYNC command by avoiding inter node
io and collections/cpu mapping on thunderx dual-socket platform.

This fix is only applicable for Cavium's ThunderX dual-socket platform.

Reviewed-by: Robert Richter <rrichter@cavium.com>
Signed-off-by: Ganapatrao Kulkarni <gkulkarni@caviumnetworks.com>
Signed-off-by: Robert Richter <rrichter@cavium.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

3 files changed, 57 insertions, 2 deletions

diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index c6938e50e71f..4da60b463995 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -56,6 +56,7 @@ stable kernels.
 | ARM            | MMU-500         | #841119,#826419 | N/A                     |
 |                |                 |                 |                         |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375    |
+| Cavium         | ThunderX ITS    | #23144          | CAVIUM_ERRATUM_23144    |
 | Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
 | Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456    |
 | Cavium         | ThunderX SMMUv2 | #27704          | N/A                     |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 76747d92bc72..57a9f67971d3 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -426,6 +426,15 @@ config CAVIUM_ERRATUM_22375
 
           If unsure, say Y.
 
+config CAVIUM_ERRATUM_23144
+        bool "Cavium erratum 23144: ITS SYNC hang on dual socket system"
+        depends on NUMA
+        default y
+        help
+          ITS SYNC command hang for cross node io and collections/cpu mapping.
+
+          If unsure, say Y.
+
 config CAVIUM_ERRATUM_23154
         bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed"
         default y
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 6bd881be24ea..5eb1f9e17a98 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -41,6 +41,7 @@
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING           (1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375       (1ULL << 1)
+#define ITS_FLAGS_WORKAROUND_CAVIUM_23144       (1ULL << 2)
 
 #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING     (1 << 0)
 
@@ -82,6 +83,7 @@ struct its_node {
         u64                     flags;
         u32                     ite_size;
         u32                     device_ids;
+        int                     numa_node;
 };
 
 #define ITS_ITT_ALIGN           SZ_256
@@ -613,11 +615,23 @@ static void its_unmask_irq(struct irq_data *d)
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
                             bool force)
 {
-        unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask);
+        unsigned int cpu;
+        const struct cpumask *cpu_mask = cpu_online_mask;
         struct its_device *its_dev = irq_data_get_irq_chip_data(d);
         struct its_collection *target_col;
         u32 id = its_get_event_id(d);
 
+       /* lpi cannot be routed to a redistributor that is on a foreign node */
+        if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+                if (its_dev->its->numa_node >= 0) {
+                        cpu_mask = cpumask_of_node(its_dev->its->numa_node);
+                        if (!cpumask_intersects(mask_val, cpu_mask))
+                                return -EINVAL;
+                }
+        }
+
+        cpu = cpumask_any_and(mask_val, cpu_mask);
+
         if (cpu >= nr_cpu_ids)
                 return -EINVAL;
 
@@ -1101,6 +1115,16 @@ static void its_cpu_init_collection(void)
         list_for_each_entry(its, &its_nodes, entry) {
                 u64 target;
 
+                /* avoid cross node collections and its mapping */
+                if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
+                        struct device_node *cpu_node;
+
+                        cpu_node = of_get_cpu_node(cpu, NULL);
+                        if (its->numa_node != NUMA_NO_NODE &&
+                                its->numa_node != of_node_to_nid(cpu_node))
+                                continue;
+                }
+
                 /*
                  * We now have to bind each collection to its target
                  * redistributor.
@@ -1351,9 +1375,14 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 {
         struct its_device *its_dev = irq_data_get_irq_chip_data(d);
         u32 event = its_get_event_id(d);
+        const struct cpumask *cpu_mask = cpu_online_mask;
+
+        /* get the cpu_mask of local node */
+        if (its_dev->its->numa_node >= 0)
+                cpu_mask = cpumask_of_node(its_dev->its->numa_node);
 
         /* Bind the LPI to the first possible CPU */
-        its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+        its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
 
         /* Map the GIC IRQ and event to the device */
         its_send_mapvi(its_dev, d->hwirq, event);
@@ -1443,6 +1472,13 @@ static void __maybe_unused its_enable_quirk_cavium_22375(void *data)
         its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375;
 }
 
+static void __maybe_unused its_enable_quirk_cavium_23144(void *data)
+{
+        struct its_node *its = data;
+
+        its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144;
+}
+
 static const struct gic_quirk its_quirks[] = {
 #ifdef CONFIG_CAVIUM_ERRATUM_22375
         {
@@ -1452,6 +1488,14 @@ static const struct gic_quirk its_quirks[] = {
                 .init   = its_enable_quirk_cavium_22375,
         },
 #endif
+#ifdef CONFIG_CAVIUM_ERRATUM_23144
+        {
+                .desc   = "ITS: Cavium erratum 23144",
+                .iidr   = 0xa100034c,   /* ThunderX pass 1.x */
+                .mask   = 0xffff0fff,
+                .init   = its_enable_quirk_cavium_23144,
+        },
+#endif
         {
         }
 };
@@ -1514,6 +1558,7 @@ static int __init its_probe(struct device_node *node,
         its->base = its_base;
         its->phys_base = res.start;
         its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
+        its->numa_node = of_node_to_nid(node);
 
         its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
         if (!its->cmd_base) {