MIPS: mm: Place per_cpu on different nodes, if NUMA is enabled

Implement placing of per_cpu into memory, which is local to the CPU.
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: Paul Burton <paulburton@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@vger.kernel.org
Cc: linux-kernel@vger.kernel.org

arch/mips/Kconfig

@@ -2696,6 +2696,14 @@ config NUMA
 config SYS_SUPPORTS_NUMA
 	bool
 
+config HAVE_SETUP_PER_CPU_AREA
+	def_bool y
+	depends on NUMA
+
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool y
+	depends on NUMA
+
 config RELOCATABLE
 	bool "Relocatable kernel"
 	depends on SYS_SUPPORTS_RELOCATABLE && (CPU_MIPS32_R2 || CPU_MIPS64_R2 || CPU_MIPS32_R6 || CPU_MIPS64_R6 || CAVIUM_OCTEON_SOC)

arch/mips/mm/init.c

@@ -508,6 +508,51 @@ void __ref free_initmem(void)
 		free_initmem_default(POISON_FREE_INITMEM);
 }
 
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+	return node_distance(cpu_to_node(from), cpu_to_node(to));
+}
+
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
+				       size_t align)
+{
+	return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS),
+				      MEMBLOCK_ALLOC_ACCESSIBLE,
+				      cpu_to_node(cpu));
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+	memblock_free_early(__pa(ptr), size);
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
+
+	/*
+	 * Always reserve area for module percpu variables.  That's
+	 * what the legacy allocator did.
+	 */
+	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+				    pcpu_cpu_distance,
+				    pcpu_fc_alloc, pcpu_fc_free);
+	if (rc < 0)
+		panic("Failed to initialize percpu areas.");
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+}
+#endif
+
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
 unsigned long pgd_current[NR_CPUS];
 #endif