riscv: Add numa support for riscv64 platform

Use the generic numa implementation to add NUMA support for RISC-V.
This is based on Greentime's patch[1] but modified to use generic NUMA
implementation and few more fixes.

[1] https://lkml.org/lkml/2020/1/10/233

Co-developed-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Signed-off-by: Atish Patra <atish.patra@wdc.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Reviewed-by: Palmer Dabbelt <palmerdabbelt@google.com>
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>

7 files changed, 87 insertions, 5 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 81b76d44725d..2ef05ef921b5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -143,7 +143,7 @@ config PAGE_OFFSET
 	default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
 
 config ARCH_FLATMEM_ENABLE
-	def_bool y
+	def_bool !NUMA
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
@@ -298,6 +298,35 @@ config TUNE_GENERIC
 
 endchoice
 
+# Common NUMA Features
+config NUMA
+	bool "NUMA Memory Allocation and Scheduler Support"
+	select GENERIC_ARCH_NUMA
+	select OF_NUMA
+	select ARCH_SUPPORTS_NUMA_BALANCING
+	help
+	  Enable NUMA (Non-Uniform Memory Access) support.
+
+	  The kernel will try to allocate memory used by a CPU on the
+	  local memory of the CPU and add some more NUMA awareness to the kernel.
+
+config NODES_SHIFT
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 1 10
+	default "2"
+	depends on NEED_MULTIPLE_NODES
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accommodate various tables.
+
+config USE_PERCPU_NUMA_NODE_ID
+	def_bool y
+	depends on NUMA
+
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool y
+	depends on NUMA
+
 config RISCV_ISA_C
 	bool "Emit compressed instructions when building Linux"
 	default y
diff --git a/arch/riscv/include/asm/mmzone.h b/arch/riscv/include/asm/mmzone.h
new file mode 100644
index 000000000000..fa17e01d9ab2
--- /dev/null
+++ b/arch/riscv/include/asm/mmzone.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_MMZONE_H
+#define __ASM_MMZONE_H
+
+#ifdef CONFIG_NUMA
+
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)		(node_data[(nid)])
+
+#endif /* CONFIG_NUMA */
+#endif /* __ASM_MMZONE_H */
diff --git a/arch/riscv/include/asm/numa.h b/arch/riscv/include/asm/numa.h
new file mode 100644
index 000000000000..8c8cf4297cc3
--- /dev/null
+++ b/arch/riscv/include/asm/numa.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_NUMA_H
+#define __ASM_NUMA_H
+
+#include <asm/topology.h>
+#include <asm-generic/numa.h>
+
+#endif	/* __ASM_NUMA_H */
diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h
index 1c473a1bd986..658e112c3ce7 100644
--- a/arch/riscv/include/asm/pci.h
+++ b/arch/riscv/include/asm/pci.h
@@ -32,6 +32,20 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 	/* always show the domain in /proc */
 	return 1;
 }
+
+#ifdef	CONFIG_NUMA
+
+static inline int pcibus_to_node(struct pci_bus *bus)
+{
+	return dev_to_node(&bus->dev);
+}
+#ifndef cpumask_of_pcibus
+#define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
+				 cpu_all_mask :				\
+				 cpumask_of_node(pcibus_to_node(bus)))
+#endif
+#endif	/* CONFIG_NUMA */
+
 #endif  /* CONFIG_PCI */
 
 #endif  /* _ASM_RISCV_PCI_H */
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 9cd81d4df031..90a4e06886a6 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -273,13 +273,19 @@ void __init setup_arch(char **cmdline_p)
 
 static int __init topology_init(void)
 {
-	int i;
+	int i, ret;
+
+	for_each_online_node(i)
+		register_one_node(i);
 
 	for_each_possible_cpu(i) {
 		struct cpu *cpu = &per_cpu(cpu_devices, i);
 
 		cpu->hotpluggable = cpu_has_hotplug(i);
-		register_cpu(cpu, i);
+		ret = register_cpu(cpu, i);
+		if (unlikely(ret))
+			pr_warn("Warning: %s: register_cpu %d failed (%d)\n",
+			       __func__, i, ret);
 	}
 
 	return 0;
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 96167d55ed98..5e276c25646f 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -27,6 +27,7 @@
 #include <asm/cpu_ops.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
+#include <asm/numa.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/sbi.h>
@@ -45,13 +46,18 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
 	int ret;
+	unsigned int curr_cpuid;
+
+	curr_cpuid = smp_processor_id();
+	numa_store_cpu_info(curr_cpuid);
+	numa_add_cpu(curr_cpuid);
 
 	/* This covers non-smp usecase mandated by "nosmp" option */
 	if (max_cpus == 0)
 		return;
 
 	for_each_possible_cpu(cpuid) {
-		if (cpuid == smp_processor_id())
+		if (cpuid == curr_cpuid)
 			continue;
 		if (cpu_ops[cpuid]->cpu_prepare) {
 			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
@@ -59,6 +65,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 				continue;
 		}
 		set_cpu_present(cpuid, true);
+		numa_store_cpu_info(cpuid);
 	}
 }
 
@@ -79,6 +86,7 @@ void __init setup_smp(void)
 		if (hart == cpuid_to_hartid_map(0)) {
 			BUG_ON(found_boot_cpu);
 			found_boot_cpu = 1;
+			early_map_cpu_to_node(0, of_node_to_nid(dn));
 			continue;
 		}
 		if (cpuid >= NR_CPUS) {
@@ -88,6 +96,7 @@ void __init setup_smp(void)
 		}
 
 		cpuid_to_hartid_map(cpuid) = hart;
+		early_map_cpu_to_node(cpuid, of_node_to_nid(dn));
 		cpuid++;
 	}
 
@@ -153,6 +162,7 @@ asmlinkage __visible void smp_callin(void)
 	current->active_mm = mm;
 
 	notify_cpu_starting(curr_cpuid);
+	numa_add_cpu(curr_cpuid);
 	update_siblings_masks(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
 
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 62716b43660b..30b61f2c6b87 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -21,6 +21,7 @@
 #include <asm/soc.h>
 #include <asm/io.h>
 #include <asm/ptdump.h>
+#include <asm/numa.h>
 
 #include "../kernel/head.h"
 
@@ -199,7 +200,6 @@ void __init setup_bootmem(void)
 	early_init_fdt_scan_reserved_mem();
 	dma_contiguous_reserve(dma32_phys_limit);
 	memblock_allow_resize();
-	memblock_dump_all();
 }
 
 #ifdef CONFIG_MMU
@@ -654,8 +654,10 @@ void __init paging_init(void)
 
 void __init misc_mem_init(void)
 {
+	arch_numa_init();
 	sparse_init();
 	zone_sizes_init();
+	memblock_dump_all();
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP