Merge branch 'for-5.7/numa' into libnvdimm-for-next

- Promote numa_map_to_online_node() to a cross-kernel generic facility.

- Save x86 numa information to allow for node-id lookups for reserved
  memory ranges, deploy that capability for the e820-pmem driver.

- Introduce phys_to_target_node() to facilitate drivers that want to
  know resulting numa node if a given reserved address range was
  onlined.

arch/powerpc/platforms/pseries/papr_scm.c

@@ -285,25 +285,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	return 0;
 }
 
-static inline int papr_scm_node(int node)
-{
-	int min_dist = INT_MAX, dist;
-	int nid, min_node;
-
-	if ((node == NUMA_NO_NODE) || node_online(node))
-		return node;
-
-	min_node = first_online_node;
-	for_each_online_node(nid) {
-		dist = node_distance(node, nid);
-		if (dist < min_dist) {
-			min_dist = dist;
-			min_node = nid;
-		}
-	}
-	return min_node;
-}
-
 static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 {
 	struct device *dev = &p->pdev->dev;
@@ -349,7 +330,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 
 	memset(&ndr_desc, 0, sizeof(ndr_desc));
 	target_nid = dev_to_node(&p->pdev->dev);
-	online_nid = papr_scm_node(target_nid);
+	online_nid = numa_map_to_online_node(target_nid);
 	ndr_desc.numa_node = online_nid;
 	ndr_desc.target_node = target_nid;
 	ndr_desc.res = &p->res;

arch/x86/Kconfig

@@ -1664,6 +1664,7 @@ config X86_PMEM_LEGACY
 	depends on PHYS_ADDR_T_64BIT
 	depends on BLK_DEV
 	select X86_PMEM_LEGACY_DEVICE
+	select NUMA_KEEP_MEMINFO if NUMA
 	select LIBNVDIMM
 	help
 	  Treat memory marked using the non-standard e820 type of 12 as used

arch/x86/mm/numa.c

@@ -25,11 +25,8 @@ nodemask_t numa_nodes_parsed __initdata;
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
-static struct numa_meminfo numa_meminfo
-#ifndef CONFIG_MEMORY_HOTPLUG
-__initdata
-#endif
-;
+static struct numa_meminfo numa_meminfo __initdata_or_meminfo;
+static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo;
 
 static int numa_distance_cnt;
 static u8 *numa_distance;
@@ -168,6 +165,19 @@ void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
 		(mi->nr_blks - idx) * sizeof(mi->blk[0]));
 }
 
+/**
+ * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another
+ * @dst: numa_meminfo to append block to
+ * @idx: Index of memblk to remove
+ * @src: numa_meminfo to remove memblk from
+ */
+static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx,
+					 struct numa_meminfo *src)
+{
+	dst->blk[dst->nr_blks++] = src->blk[idx];
+	numa_remove_memblk_from(idx, src);
+}
+
 /**
  * numa_add_memblk - Add one numa_memblk to numa_meminfo
  * @nid: NUMA node ID of the new memblk
@@ -237,14 +247,19 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 	for (i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *bi = &mi->blk[i];
 
-		/* make sure all blocks are inside the limits */
+		/* move / save reserved memory ranges */
+		if (!memblock_overlaps_region(&memblock.memory,
+					bi->start, bi->end - bi->start)) {
+			numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi);
+			continue;
+		}
+
+		/* make sure all non-reserved blocks are inside the limits */
 		bi->start = max(bi->start, low);
 		bi->end = min(bi->end, high);
 
-		/* and there's no empty or non-exist block */
-		if (bi->start >= bi->end ||
-		    !memblock_overlaps_region(&memblock.memory,
-			bi->start, bi->end - bi->start))
+		/* and there's no empty block */
+		if (bi->start >= bi->end)
 			numa_remove_memblk_from(i--, mi);
 	}
 
@@ -881,16 +896,38 @@ EXPORT_SYMBOL(cpumask_of_node);
 
 #endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-int memory_add_physaddr_to_nid(u64 start)
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+static int meminfo_to_nid(struct numa_meminfo *mi, u64 start)
 {
-	struct numa_meminfo *mi = &numa_meminfo;
-	int nid = mi->blk[0].nid;
 	int i;
 
 	for (i = 0; i < mi->nr_blks; i++)
 		if (mi->blk[i].start <= start && mi->blk[i].end > start)
-			nid = mi->blk[i].nid;
+			return mi->blk[i].nid;
+	return NUMA_NO_NODE;
+}
+
+int phys_to_target_node(phys_addr_t start)
+{
+	int nid = meminfo_to_nid(&numa_meminfo, start);
+
+	/*
+	 * Prefer online nodes, but if reserved memory might be
+	 * hot-added continue the search with reserved ranges.
+	 */
+	if (nid != NUMA_NO_NODE)
+		return nid;
+
+	return meminfo_to_nid(&numa_reserved_meminfo, start);
+}
+EXPORT_SYMBOL_GPL(phys_to_target_node);
+
+int memory_add_physaddr_to_nid(u64 start)
+{
+	int nid = meminfo_to_nid(&numa_meminfo, start);
+
+	if (nid == NUMA_NO_NODE)
+		nid = numa_meminfo.blk[0].nid;
 	return nid;
 }
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);

drivers/acpi/numa/srat.c

@@ -72,47 +72,6 @@ int acpi_map_pxm_to_node(int pxm)
 }
 EXPORT_SYMBOL(acpi_map_pxm_to_node);
 
-/**
- * acpi_map_pxm_to_online_node - Map proximity ID to online node
- * @pxm: ACPI proximity ID
- *
- * This is similar to acpi_map_pxm_to_node(), but always returns an online
- * node.  When the mapped node from a given proximity ID is offline, it
- * looks up the node distance table and returns the nearest online node.
- *
- * ACPI device drivers, which are called after the NUMA initialization has
- * completed in the kernel, can call this interface to obtain their device
- * NUMA topology from ACPI tables.  Such drivers do not have to deal with
- * offline nodes.  A node may be offline when a device proximity ID is
- * unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
- * "numa=off" on x86.
- */
-int acpi_map_pxm_to_online_node(int pxm)
-{
-	int node, min_node;
-
-	node = acpi_map_pxm_to_node(pxm);
-
-	if (node == NUMA_NO_NODE)
-		node = 0;
-
-	min_node = node;
-	if (!node_online(node)) {
-		int min_dist = INT_MAX, dist, n;
-
-		for_each_online_node(n) {
-			dist = node_distance(node, n);
-			if (dist < min_dist) {
-				min_dist = dist;
-				min_node = n;
-			}
-		}
-	}
-
-	return min_node;
-}
-EXPORT_SYMBOL(acpi_map_pxm_to_online_node);
-
 static void __init
 acpi_table_print_srat_entry(struct acpi_subtable_header *header)
 {

drivers/nvdimm/e820.c

@@ -7,6 +7,7 @@
 #include <linux/memory_hotplug.h>
 #include <linux/libnvdimm.h>
 #include <linux/module.h>
+#include <linux/numa.h>
 
 static int e820_pmem_remove(struct platform_device *pdev)
 {
@@ -16,27 +17,16 @@ static int e820_pmem_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-static int e820_range_to_nid(resource_size_t addr)
-{
-	return memory_add_physaddr_to_nid(addr);
-}
-#else
-static int e820_range_to_nid(resource_size_t addr)
-{
-	return NUMA_NO_NODE;
-}
-#endif
-
 static int e820_register_one(struct resource *res, void *data)
 {
 	struct nd_region_desc ndr_desc;
 	struct nvdimm_bus *nvdimm_bus = data;
+	int nid = phys_to_target_node(res->start);
 
 	memset(&ndr_desc, 0, sizeof(ndr_desc));
 	ndr_desc.res = res;
-	ndr_desc.numa_node = e820_range_to_nid(res->start);
-	ndr_desc.target_node = ndr_desc.numa_node;
+	ndr_desc.numa_node = numa_map_to_online_node(nid);
+	ndr_desc.target_node = nid;
 	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
 	if (!nvdimm_pmem_region_create(nvdimm_bus, &ndr_desc))
 		return -ENXIO;

include/linux/acpi.h

@@ -416,9 +416,30 @@ extern void acpi_osi_setup(char *str);
 extern bool acpi_osi_is_win8(void);
 
 #ifdef CONFIG_ACPI_NUMA
-int acpi_map_pxm_to_online_node(int pxm);
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
+
+/**
+ * acpi_map_pxm_to_online_node - Map proximity ID to online node
+ * @pxm: ACPI proximity ID
+ *
+ * This is similar to acpi_map_pxm_to_node(), but always returns an online
+ * node.  When the mapped node from a given proximity ID is offline, it
+ * looks up the node distance table and returns the nearest online node.
+ *
+ * ACPI device drivers, which are called after the NUMA initialization has
+ * completed in the kernel, can call this interface to obtain their device
+ * NUMA topology from ACPI tables.  Such drivers do not have to deal with
+ * offline nodes.  A node may be offline when a device proximity ID is
+ * unique, SRAT memory entry does not exist, or NUMA is disabled, ex.
+ * "numa=off" on x86.
+ */
+static inline int acpi_map_pxm_to_online_node(int pxm)
+{
+	int node = acpi_map_pxm_to_node(pxm);
+
+	return numa_map_to_online_node(node);
+}
 #else
 static inline int acpi_map_pxm_to_online_node(int pxm)
 {

include/linux/numa.h

@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_NUMA_H
 #define _LINUX_NUMA_H
-
+#include <linux/types.h>
 
 #ifdef CONFIG_NODES_SHIFT
 #define NODES_SHIFT     CONFIG_NODES_SHIFT
@@ -13,4 +13,32 @@
 
 #define	NUMA_NO_NODE	(-1)
 
+/* optionally keep NUMA memory info available post init */
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+#define __initdata_or_meminfo
+#else
+#define __initdata_or_meminfo __initdata
+#endif
+
+#ifdef CONFIG_NUMA
+/* Generic implementation available */
+int numa_map_to_online_node(int node);
+
+/*
+ * Optional architecture specific implementation, users need a "depends
+ * on $ARCH"
+ */
+int phys_to_target_node(phys_addr_t addr);
+#else
+static inline int numa_map_to_online_node(int node)
+{
+	return NUMA_NO_NODE;
+}
+
+static inline int phys_to_target_node(phys_addr_t addr)
+{
+	return NUMA_NO_NODE;
+}
+#endif
+
 #endif /* _LINUX_NUMA_H */

mm/Kconfig

@@ -139,6 +139,10 @@ config HAVE_FAST_GUP
 config ARCH_KEEP_MEMBLOCK
 	bool
 
+# Keep arch NUMA mapping infrastructure post-init.
+config NUMA_KEEP_MEMINFO
+	bool
+
 config MEMORY_ISOLATION
 	bool
 
@@ -154,6 +158,7 @@ config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
+	select NUMA_KEEP_MEMINFO if NUMA
 
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y

mm/mempolicy.c

@@ -127,6 +127,32 @@ static struct mempolicy default_policy = {
 
 static struct mempolicy preferred_node_policy[MAX_NUMNODES];
 
+/**
+ * numa_map_to_online_node - Find closest online node
+ * @nid: Node id to start the search
+ *
+ * Lookup the next closest node by distance if @nid is not online.
+ */
+int numa_map_to_online_node(int node)
+{
+	int min_dist = INT_MAX, dist, n, min_node;
+
+	if (node == NUMA_NO_NODE || node_online(node))
+		return node;
+
+	min_node = node;
+	for_each_online_node(n) {
+		dist = node_distance(node, n);
+		if (dist < min_dist) {
+			min_dist = dist;
+			min_node = n;
+		}
+	}
+
+	return min_node;
+}
+EXPORT_SYMBOL_GPL(numa_map_to_online_node);
+
 struct mempolicy *get_task_policy(struct task_struct *p)
 {
 	struct mempolicy *pol = p->mempolicy;