LoongArch: Add Non-Uniform Memory Access (NUMA) support

Add Non-Uniform Memory Access (NUMA) support for LoongArch. LoongArch
has 48-bit physical address, but the HyperTransport I/O bus only support
40-bit address, so we need a custom phys_to_dma() and dma_to_phys() to
extract the 4-bit node id (bit 44~47) from Loongson-3's 48-bit physical
address space and embed it into 40-bit. In the 40-bit dma address, node
id offset can be read from the LS7A_DMA_CFG register.

Reviewed-by: WANG Xuerui <git@xen0n.name>
Reviewed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

6 files changed, 131 insertions, 0 deletions

diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h
index 7b60f202faaf..9b8d49d9e61b 100644
--- a/arch/loongarch/include/asm/bootinfo.h
+++ b/arch/loongarch/include/asm/bootinfo.h
@@ -13,6 +13,8 @@ const char *get_system_type(void);
 extern void init_environ(void);
 extern void memblock_init(void);
 extern void platform_init(void);
+extern void plat_swiotlb_setup(void);
+extern int __init init_numa_memory(void);
 
 struct loongson_board_info {
 	int bios_size;
diff --git a/arch/loongarch/include/asm/dma-direct.h b/arch/loongarch/include/asm/dma-direct.h
new file mode 100644
index 000000000000..75ccd808a2af
--- /dev/null
+++ b/arch/loongarch/include/asm/dma-direct.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _LOONGARCH_DMA_DIRECT_H
+#define _LOONGARCH_DMA_DIRECT_H
+
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
+
+#endif /* _LOONGARCH_DMA_DIRECT_H */
diff --git a/arch/loongarch/include/asm/mmzone.h b/arch/loongarch/include/asm/mmzone.h
new file mode 100644
index 000000000000..fe67d0b4b33d
--- /dev/null
+++ b/arch/loongarch/include/asm/mmzone.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Huacai Chen (chenhuacai@loongson.cn)
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_MMZONE_H_
+#define _ASM_MMZONE_H_
+
+#include <asm/page.h>
+#include <asm/numa.h>
+
+extern struct pglist_data *node_data[];
+
+#define NODE_DATA(nid)	(node_data[(nid)])
+
+extern void setup_zero_pages(void);
+
+#endif /* _ASM_MMZONE_H_ */
diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h
new file mode 100644
index 000000000000..27f319b49862
--- /dev/null
+++ b/arch/loongarch/include/asm/numa.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Jianmin Lv <lvjianmin@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ *
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_LOONGARCH_NUMA_H
+#define _ASM_LOONGARCH_NUMA_H
+
+#include <linux/nodemask.h>
+
+#define NODE_ADDRSPACE_SHIFT 44
+
+#define pa_to_nid(addr)		(((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT)
+#define nid_to_addrbase(nid)	(_ULCAST_(nid) << NODE_ADDRSPACE_SHIFT)
+
+#ifdef CONFIG_NUMA
+
+extern int numa_off;
+extern s16 __cpuid_to_node[CONFIG_NR_CPUS];
+extern nodemask_t numa_nodes_parsed __initdata;
+
+struct numa_memblk {
+	u64			start;
+	u64			end;
+	int			nid;
+};
+
+#define NR_NODE_MEMBLKS		(MAX_NUMNODES*2)
+struct numa_meminfo {
+	int			nr_blks;
+	struct numa_memblk	blk[NR_NODE_MEMBLKS];
+};
+
+extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+
+extern void __init early_numa_add_cpu(int cpuid, s16 node);
+extern void numa_add_cpu(unsigned int cpu);
+extern void numa_remove_cpu(unsigned int cpu);
+
+static inline void numa_clear_node(int cpu)
+{
+}
+
+static inline void set_cpuid_to_node(int cpuid, s16 node)
+{
+	__cpuid_to_node[cpuid] = node;
+}
+
+extern int early_cpu_to_node(int cpu);
+
+#else
+
+static inline void early_numa_add_cpu(int cpuid, s16 node)	{ }
+static inline void numa_add_cpu(unsigned int cpu)		{ }
+static inline void numa_remove_cpu(unsigned int cpu)		{ }
+
+static inline int early_cpu_to_node(int cpu)
+{
+	return 0;
+}
+
+#endif	/* CONFIG_NUMA */
+
+#endif	/* _ASM_LOONGARCH_NUMA_H */
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 5e33987d0a13..5dc84d8f18d6 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -541,6 +541,18 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline long pte_protnone(pte_t pte)
+{
+	return (pte_val(pte) & _PAGE_PROTNONE);
+}
+
+static inline long pmd_protnone(pmd_t pmd)
+{
+	return (pmd_val(pmd) & _PAGE_PROTNONE);
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 /*
  * We provide our own get_unmapped area to cope with the virtual aliasing
  * constraints placed on us by the cache architecture.
diff --git a/arch/loongarch/include/asm/topology.h b/arch/loongarch/include/asm/topology.h
index da135841e5b1..66128dec0bf6 100644
--- a/arch/loongarch/include/asm/topology.h
+++ b/arch/loongarch/include/asm/topology.h
@@ -7,6 +7,27 @@
 
 #include <linux/smp.h>
 
+#ifdef CONFIG_NUMA
+
+extern cpumask_t cpus_on_node[];
+
+#define cpumask_of_node(node)  (&cpus_on_node[node])
+
+struct pci_bus;
+extern int pcibus_to_node(struct pci_bus *);
+
+#define cpumask_of_pcibus(bus)	(cpu_online_mask)
+
+extern unsigned char node_distances[MAX_NUMNODES][MAX_NUMNODES];
+
+void numa_set_distance(int from, int to, int distance);
+
+#define node_distance(from, to)	(node_distances[(from)][(to)])
+
+#else
+#define pcibus_to_node(bus)	0
+#endif
+
 #ifdef CONFIG_SMP
 #define topology_physical_package_id(cpu)	(cpu_data[cpu].package)
 #define topology_core_id(cpu)			(cpu_data[cpu].core)