riscv: Enable pcpu page first chunk allocator

As explained in commit 6ea529a203 ("percpu: make embedding first chunk
allocator check vmalloc space size"), the embedding first chunk allocator
needs the vmalloc space to be larger than the maximum distance between
units which are grouped into NUMA nodes.

On a very sparse NUMA configurations and a small vmalloc area (for example,
it is 64GB in sv39), the allocation of dynamic percpu data in the vmalloc
area could fail.

So provide the pcpu page allocator as a fallback in case we fall into
such a sparse configuration (which happened in arm64 as shown by
commit 09cea61950 ("arm64: support page mapping percpu first chunk
allocator")).

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>

arch/riscv/Kconfig

@@ -414,7 +414,9 @@ config NUMA
 	depends on SMP && MMU
 	select ARCH_SUPPORTS_NUMA_BALANCING
 	select GENERIC_ARCH_NUMA
+	select HAVE_SETUP_PER_CPU_AREA
 	select NEED_PER_CPU_EMBED_FIRST_CHUNK
+	select NEED_PER_CPU_PAGE_FIRST_CHUNK
 	select OF_NUMA
 	select USE_PERCPU_NUMA_NODE_ID
 	help

arch/riscv/mm/kasan_init.c

@@ -438,6 +438,14 @@ static void __init kasan_shallow_populate(void *start, void *end)
 	kasan_shallow_populate_pgd(vaddr, vend);
 }
 
+#ifdef CONFIG_KASAN_VMALLOC
+void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size)
+{
+	kasan_populate(kasan_mem_to_shadow(start),
+		       kasan_mem_to_shadow(start + size));
+}
+#endif
+
 static void __init create_tmp_mapping(void)
 {
 	void *ptr;