+ mm-introduce-numa_emulation.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: mm: introduce numa_emulation
has been added to the -mm mm-unstable branch.  Its filename is
     mm-introduce-numa_emulation.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-introduce-numa_emulation.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Subject: mm: introduce numa_emulation
Date: Wed, 7 Aug 2024 09:41:03 +0300

Move numa_emulation code from arch/x86 to mm/numa_emulation.c

This code will be later reused by arch_numa.

No functional changes.

Link: https://lkml.kernel.org/r/20240807064110.1003856-20-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Tested-by: Zi Yan <ziy@nvidia.com> # for x86_64 and arm64
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> [arm64 + CXL via QEMU]
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Rob Herring (Arm) <robh@kernel.org>
Cc: Samuel Holland <samuel.holland@sifive.com>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/x86/Kconfig             |    8 
 arch/x86/include/asm/numa.h  |   12 
 arch/x86/mm/Makefile         |    1 
 arch/x86/mm/numa_emulation.c |  573 ---------------------------------
 arch/x86/mm/numa_internal.h  |   11 
 include/linux/numa_memblks.h |   17 
 mm/Kconfig                   |    8 
 mm/Makefile                  |    1 
 mm/numa_emulation.c          |  571 ++++++++++++++++++++++++++++++++
 9 files changed, 597 insertions(+), 605 deletions(-)

--- a/arch/x86/include/asm/numa.h~mm-introduce-numa_emulation
+++ a/arch/x86/include/asm/numa.h
@@ -65,16 +65,4 @@ static inline void init_gi_nodes(void)
 void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable);
 #endif
 
-#ifdef CONFIG_NUMA_EMU
-int numa_emu_cmdline(char *str);
-void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
-					unsigned int nr_emu_nids);
-u64 __init numa_emu_dma_end(void);
-#else /* CONFIG_NUMA_EMU */
-static inline int numa_emu_cmdline(char *str)
-{
-	return -EINVAL;
-}
-#endif /* CONFIG_NUMA_EMU */
-
 #endif	/* _ASM_X86_NUMA_H */
--- a/arch/x86/Kconfig~mm-introduce-numa_emulation
+++ a/arch/x86/Kconfig
@@ -1600,14 +1600,6 @@ config X86_64_ACPI_NUMA
 	help
 	  Enable ACPI SRAT based node topology detection.
 
-config NUMA_EMU
-	bool "NUMA emulation"
-	depends on NUMA
-	help
-	  Enable NUMA emulation. A flat machine will be split
-	  into virtual nodes when booted with "numa=fake=N", where N is the
-	  number of nodes. This is only useful for debugging.
-
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
 	range 1 10
--- a/arch/x86/mm/Makefile~mm-introduce-numa_emulation
+++ a/arch/x86/mm/Makefile
@@ -57,7 +57,6 @@ obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmio
 obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
-obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
 obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)	+= pkeys.o
 obj-$(CONFIG_RANDOMIZE_MEMORY)			+= kaslr.o
diff --git a/arch/x86/mm/numa_emulation.c a/arch/x86/mm/numa_emulation.c
deleted file mode 100644
--- a/arch/x86/mm/numa_emulation.c
+++ /dev/null
@@ -1,573 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * NUMA emulation
- */
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/topology.h>
-#include <linux/memblock.h>
-#include <linux/numa_memblks.h>
-#include <asm/dma.h>
-
-#include "numa_internal.h"
-
-#define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
-#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
-
-static int emu_nid_to_phys[MAX_NUMNODES];
-static char *emu_cmdline __initdata;
-
-int __init numa_emu_cmdline(char *str)
-{
-	emu_cmdline = str;
-	return 0;
-}
-
-static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
-{
-	int i;
-
-	for (i = 0; i < mi->nr_blks; i++)
-		if (mi->blk[i].nid == nid)
-			return i;
-	return -ENOENT;
-}
-
-static u64 __init mem_hole_size(u64 start, u64 end)
-{
-	unsigned long start_pfn = PFN_UP(start);
-	unsigned long end_pfn = PFN_DOWN(end);
-
-	if (start_pfn < end_pfn)
-		return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn));
-	return 0;
-}
-
-/*
- * Sets up nid to range from @start to @end.  The return value is -errno if
- * something went wrong, 0 otherwise.
- */
-static int __init emu_setup_memblk(struct numa_meminfo *ei,
-				   struct numa_meminfo *pi,
-				   int nid, int phys_blk, u64 size)
-{
-	struct numa_memblk *eb = &ei->blk[ei->nr_blks];
-	struct numa_memblk *pb = &pi->blk[phys_blk];
-
-	if (ei->nr_blks >= NR_NODE_MEMBLKS) {
-		pr_err("NUMA: Too many emulated memblks, failing emulation\n");
-		return -EINVAL;
-	}
-
-	ei->nr_blks++;
-	eb->start = pb->start;
-	eb->end = pb->start + size;
-	eb->nid = nid;
-
-	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
-		emu_nid_to_phys[nid] = pb->nid;
-
-	pb->start += size;
-	if (pb->start >= pb->end) {
-		WARN_ON_ONCE(pb->start > pb->end);
-		numa_remove_memblk_from(phys_blk, pi);
-	}
-
-	printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
-	       nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
-	return 0;
-}
-
-/*
- * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
- * to max_addr.
- *
- * Returns zero on success or negative on error.
- */
-static int __init split_nodes_interleave(struct numa_meminfo *ei,
-					 struct numa_meminfo *pi,
-					 u64 addr, u64 max_addr, int nr_nodes)
-{
-	nodemask_t physnode_mask = numa_nodes_parsed;
-	u64 size;
-	int big;
-	int nid = 0;
-	int i, ret;
-
-	if (nr_nodes <= 0)
-		return -1;
-	if (nr_nodes > MAX_NUMNODES) {
-		pr_info("numa=fake=%d too large, reducing to %d\n",
-			nr_nodes, MAX_NUMNODES);
-		nr_nodes = MAX_NUMNODES;
-	}
-
-	/*
-	 * Calculate target node size.  x86_32 freaks on __udivdi3() so do
-	 * the division in ulong number of pages and convert back.
-	 */
-	size = max_addr - addr - mem_hole_size(addr, max_addr);
-	size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes);
-
-	/*
-	 * Calculate the number of big nodes that can be allocated as a result
-	 * of consolidating the remainder.
-	 */
-	big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) /
-		FAKE_NODE_MIN_SIZE;
-
-	size &= FAKE_NODE_MIN_HASH_MASK;
-	if (!size) {
-		pr_err("Not enough memory for each node.  "
-			"NUMA emulation disabled.\n");
-		return -1;
-	}
-
-	/*
-	 * Continue to fill physical nodes with fake nodes until there is no
-	 * memory left on any of them.
-	 */
-	while (!nodes_empty(physnode_mask)) {
-		for_each_node_mask(i, physnode_mask) {
-			u64 dma32_end = numa_emu_dma_end();
-			u64 start, limit, end;
-			int phys_blk;
-
-			phys_blk = emu_find_memblk_by_nid(i, pi);
-			if (phys_blk < 0) {
-				node_clear(i, physnode_mask);
-				continue;
-			}
-			start = pi->blk[phys_blk].start;
-			limit = pi->blk[phys_blk].end;
-			end = start + size;
-
-			if (nid < big)
-				end += FAKE_NODE_MIN_SIZE;
-
-			/*
-			 * Continue to add memory to this fake node if its
-			 * non-reserved memory is less than the per-node size.
-			 */
-			while (end - start - mem_hole_size(start, end) < size) {
-				end += FAKE_NODE_MIN_SIZE;
-				if (end > limit) {
-					end = limit;
-					break;
-				}
-			}
-
-			/*
-			 * If there won't be at least FAKE_NODE_MIN_SIZE of
-			 * non-reserved memory in ZONE_DMA32 for the next node,
-			 * this one must extend to the boundary.
-			 */
-			if (end < dma32_end && dma32_end - end -
-			    mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
-				end = dma32_end;
-
-			/*
-			 * If there won't be enough non-reserved memory for the
-			 * next node, this one must extend to the end of the
-			 * physical node.
-			 */
-			if (limit - end - mem_hole_size(end, limit) < size)
-				end = limit;
-
-			ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes,
-					       phys_blk,
-					       min(end, limit) - start);
-			if (ret < 0)
-				return ret;
-		}
-	}
-	return 0;
-}
-
-/*
- * Returns the end address of a node so that there is at least `size' amount of
- * non-reserved memory or `max_addr' is reached.
- */
-static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
-{
-	u64 end = start + size;
-
-	while (end - start - mem_hole_size(start, end) < size) {
-		end += FAKE_NODE_MIN_SIZE;
-		if (end > max_addr) {
-			end = max_addr;
-			break;
-		}
-	}
-	return end;
-}
-
-static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes)
-{
-	unsigned long max_pfn = PHYS_PFN(max_addr);
-	unsigned long base_pfn = PHYS_PFN(base);
-	unsigned long hole_pfns = PHYS_PFN(hole);
-
-	return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes);
-}
-
-/*
- * Sets up fake nodes of `size' interleaved over physical nodes ranging from
- * `addr' to `max_addr'.
- *
- * Returns zero on success or negative on error.
- */
-static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
-					      struct numa_meminfo *pi,
-					      u64 addr, u64 max_addr, u64 size,
-					      int nr_nodes, struct numa_memblk *pblk,
-					      int nid)
-{
-	nodemask_t physnode_mask = numa_nodes_parsed;
-	int i, ret, uniform = 0;
-	u64 min_size;
-
-	if ((!size && !nr_nodes) || (nr_nodes && !pblk))
-		return -1;
-
-	/*
-	 * In the 'uniform' case split the passed in physical node by
-	 * nr_nodes, in the non-uniform case, ignore the passed in
-	 * physical block and try to create nodes of at least size
-	 * @size.
-	 *
-	 * In the uniform case, split the nodes strictly by physical
-	 * capacity, i.e. ignore holes. In the non-uniform case account
-	 * for holes and treat @size as a minimum floor.
-	 */
-	if (!nr_nodes)
-		nr_nodes = MAX_NUMNODES;
-	else {
-		nodes_clear(physnode_mask);
-		node_set(pblk->nid, physnode_mask);
-		uniform = 1;
-	}
-
-	if (uniform) {
-		min_size = uniform_size(max_addr, addr, 0, nr_nodes);
-		size = min_size;
-	} else {
-		/*
-		 * The limit on emulated nodes is MAX_NUMNODES, so the
-		 * size per node is increased accordingly if the
-		 * requested size is too small.  This creates a uniform
-		 * distribution of node sizes across the entire machine
-		 * (but not necessarily over physical nodes).
-		 */
-		min_size = uniform_size(max_addr, addr,
-				mem_hole_size(addr, max_addr), nr_nodes);
-	}
-	min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
-	if (size < min_size) {
-		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
-			size >> 20, min_size >> 20);
-		size = min_size;
-	}
-	size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
-
-	/*
-	 * Fill physical nodes with fake nodes of size until there is no memory
-	 * left on any of them.
-	 */
-	while (!nodes_empty(physnode_mask)) {
-		for_each_node_mask(i, physnode_mask) {
-			u64 dma32_end = numa_emu_dma_end();
-			u64 start, limit, end;
-			int phys_blk;
-
-			phys_blk = emu_find_memblk_by_nid(i, pi);
-			if (phys_blk < 0) {
-				node_clear(i, physnode_mask);
-				continue;
-			}
-
-			start = pi->blk[phys_blk].start;
-			limit = pi->blk[phys_blk].end;
-
-			if (uniform)
-				end = start + size;
-			else
-				end = find_end_of_node(start, limit, size);
-			/*
-			 * If there won't be at least FAKE_NODE_MIN_SIZE of
-			 * non-reserved memory in ZONE_DMA32 for the next node,
-			 * this one must extend to the boundary.
-			 */
-			if (end < dma32_end && dma32_end - end -
-			    mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
-				end = dma32_end;
-
-			/*
-			 * If there won't be enough non-reserved memory for the
-			 * next node, this one must extend to the end of the
-			 * physical node.
-			 */
-			if ((limit - end - mem_hole_size(end, limit) < size)
-					&& !uniform)
-				end = limit;
-
-			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
-					       phys_blk,
-					       min(end, limit) - start);
-			if (ret < 0)
-				return ret;
-		}
-	}
-	return nid;
-}
-
-static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
-					      struct numa_meminfo *pi,
-					      u64 addr, u64 max_addr, u64 size)
-{
-	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
-			0, NULL, 0);
-}
-
-static int __init setup_emu2phys_nid(int *dfl_phys_nid)
-{
-	int i, max_emu_nid = 0;
-
-	*dfl_phys_nid = NUMA_NO_NODE;
-	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) {
-		if (emu_nid_to_phys[i] != NUMA_NO_NODE) {
-			max_emu_nid = i;
-			if (*dfl_phys_nid == NUMA_NO_NODE)
-				*dfl_phys_nid = emu_nid_to_phys[i];
-		}
-	}
-
-	return max_emu_nid;
-}
-
-/**
- * numa_emulation - Emulate NUMA nodes
- * @numa_meminfo: NUMA configuration to massage
- * @numa_dist_cnt: The size of the physical NUMA distance table
- *
- * Emulate NUMA nodes according to the numa=fake kernel parameter.
- * @numa_meminfo contains the physical memory configuration and is modified
- * to reflect the emulated configuration on success.  @numa_dist_cnt is
- * used to determine the size of the physical distance table.
- *
- * On success, the following modifications are made.
- *
- * - @numa_meminfo is updated to reflect the emulated nodes.
- *
- * - __apicid_to_node[] is updated such that APIC IDs are mapped to the
- *   emulated nodes.
- *
- * - NUMA distance table is rebuilt to represent distances between emulated
- *   nodes.  The distances are determined considering how emulated nodes
- *   are mapped to physical nodes and match the actual distances.
- *
- * - emu_nid_to_phys[] reflects how emulated nodes are mapped to physical
- *   nodes.  This is used by numa_add_cpu() and numa_remove_cpu().
- *
- * If emulation is not enabled or fails, emu_nid_to_phys[] is filled with
- * identity mapping and no other modification is made.
- */
-void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
-{
-	static struct numa_meminfo ei __initdata;
-	static struct numa_meminfo pi __initdata;
-	const u64 max_addr = PFN_PHYS(max_pfn);
-	u8 *phys_dist = NULL;
-	size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
-	int max_emu_nid, dfl_phys_nid;
-	int i, j, ret;
-
-	if (!emu_cmdline)
-		goto no_emu;
-
-	memset(&ei, 0, sizeof(ei));
-	pi = *numa_meminfo;
-
-	for (i = 0; i < MAX_NUMNODES; i++)
-		emu_nid_to_phys[i] = NUMA_NO_NODE;
-
-	/*
-	 * If the numa=fake command-line contains a 'M' or 'G', it represents
-	 * the fixed node size.  Otherwise, if it is just a single number N,
-	 * split the system RAM into N fake nodes.
-	 */
-	if (strchr(emu_cmdline, 'U')) {
-		nodemask_t physnode_mask = numa_nodes_parsed;
-		unsigned long n;
-		int nid = 0;
-
-		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
-		ret = -1;
-		for_each_node_mask(i, physnode_mask) {
-			/*
-			 * The reason we pass in blk[0] is due to
-			 * numa_remove_memblk_from() called by
-			 * emu_setup_memblk() will delete entry 0
-			 * and then move everything else up in the pi.blk
-			 * array. Therefore we should always be looking
-			 * at blk[0].
-			 */
-			ret = split_nodes_size_interleave_uniform(&ei, &pi,
-					pi.blk[0].start, pi.blk[0].end, 0,
-					n, &pi.blk[0], nid);
-			if (ret < 0)
-				break;
-			if (ret < n) {
-				pr_info("%s: phys: %d only got %d of %ld nodes, failing\n",
-						__func__, i, ret, n);
-				ret = -1;
-				break;
-			}
-			nid = ret;
-		}
-	} else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
-		u64 size;
-
-		size = memparse(emu_cmdline, &emu_cmdline);
-		ret = split_nodes_size_interleave(&ei, &pi, 0, max_addr, size);
-	} else {
-		unsigned long n;
-
-		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
-		ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
-	}
-	if (*emu_cmdline == ':')
-		emu_cmdline++;
-
-	if (ret < 0)
-		goto no_emu;
-
-	if (numa_cleanup_meminfo(&ei) < 0) {
-		pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
-		goto no_emu;
-	}
-
-	/* copy the physical distance table */
-	if (numa_dist_cnt) {
-		phys_dist = memblock_alloc(phys_size, PAGE_SIZE);
-		if (!phys_dist) {
-			pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
-			goto no_emu;
-		}
-
-		for (i = 0; i < numa_dist_cnt; i++)
-			for (j = 0; j < numa_dist_cnt; j++)
-				phys_dist[i * numa_dist_cnt + j] =
-					node_distance(i, j);
-	}
-
-	/*
-	 * Determine the max emulated nid and the default phys nid to use
-	 * for unmapped nodes.
-	 */
-	max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid);
-
-	/* commit */
-	*numa_meminfo = ei;
-
-	/* Make sure numa_nodes_parsed only contains emulated nodes */
-	nodes_clear(numa_nodes_parsed);
-	for (i = 0; i < ARRAY_SIZE(ei.blk); i++)
-		if (ei.blk[i].start != ei.blk[i].end &&
-		    ei.blk[i].nid != NUMA_NO_NODE)
-			node_set(ei.blk[i].nid, numa_nodes_parsed);
-
-	numa_emu_update_cpu_to_node(emu_nid_to_phys, ARRAY_SIZE(emu_nid_to_phys));
-
-	/* make sure all emulated nodes are mapped to a physical node */
-	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
-		if (emu_nid_to_phys[i] == NUMA_NO_NODE)
-			emu_nid_to_phys[i] = dfl_phys_nid;
-
-	/* transform distance table */
-	numa_reset_distance();
-	for (i = 0; i < max_emu_nid + 1; i++) {
-		for (j = 0; j < max_emu_nid + 1; j++) {
-			int physi = emu_nid_to_phys[i];
-			int physj = emu_nid_to_phys[j];
-			int dist;
-
-			if (get_option(&emu_cmdline, &dist) == 2)
-				;
-			else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
-				dist = physi == physj ?
-					LOCAL_DISTANCE : REMOTE_DISTANCE;
-			else
-				dist = phys_dist[physi * numa_dist_cnt + physj];
-
-			numa_set_distance(i, j, dist);
-		}
-	}
-
-	/* free the copied physical distance table */
-	memblock_free(phys_dist, phys_size);
-	return;
-
-no_emu:
-	/* No emulation.  Build identity emu_nid_to_phys[] for numa_add_cpu() */
-	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
-		emu_nid_to_phys[i] = i;
-}
-
-#ifndef CONFIG_DEBUG_PER_CPU_MAPS
-void numa_add_cpu(unsigned int cpu)
-{
-	int physnid, nid;
-
-	nid = early_cpu_to_node(cpu);
-	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
-
-	physnid = emu_nid_to_phys[nid];
-
-	/*
-	 * Map the cpu to each emulated node that is allocated on the physical
-	 * node of the cpu's apic id.
-	 */
-	for_each_online_node(nid)
-		if (emu_nid_to_phys[nid] == physnid)
-			cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
-}
-
-void numa_remove_cpu(unsigned int cpu)
-{
-	int i;
-
-	for_each_online_node(i)
-		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
-}
-#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
-static void numa_set_cpumask(unsigned int cpu, bool enable)
-{
-	int nid, physnid;
-
-	nid = early_cpu_to_node(cpu);
-	if (nid == NUMA_NO_NODE) {
-		/* early_cpu_to_node() already emits a warning and trace */
-		return;
-	}
-
-	physnid = emu_nid_to_phys[nid];
-
-	for_each_online_node(nid) {
-		if (emu_nid_to_phys[nid] != physnid)
-			continue;
-
-		debug_cpumask_set_cpu(cpu, nid, enable);
-	}
-}
-
-void numa_add_cpu(unsigned int cpu)
-{
-	numa_set_cpumask(cpu, true);
-}
-
-void numa_remove_cpu(unsigned int cpu)
-{
-	numa_set_cpumask(cpu, false);
-}
-#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
--- a/arch/x86/mm/numa_internal.h~mm-introduce-numa_emulation
+++ a/arch/x86/mm/numa_internal.h
@@ -7,15 +7,4 @@
 
 void __init x86_numa_init(void);
 
-struct numa_meminfo;
-
-#ifdef CONFIG_NUMA_EMU
-void __init numa_emulation(struct numa_meminfo *numa_meminfo,
-			   int numa_dist_cnt);
-#else
-static inline void numa_emulation(struct numa_meminfo *numa_meminfo,
-				  int numa_dist_cnt)
-{ }
-#endif
-
 #endif	/* __X86_MM_NUMA_INTERNAL_H */
--- a/include/linux/numa_memblks.h~mm-introduce-numa_emulation
+++ a/include/linux/numa_memblks.h
@@ -34,6 +34,23 @@ int __init numa_register_meminfo(struct
 void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
 				       const struct numa_meminfo *mi);
 
+#ifdef CONFIG_NUMA_EMU
+int numa_emu_cmdline(char *str);
+void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
+					unsigned int nr_emu_nids);
+u64 __init numa_emu_dma_end(void);
+void __init numa_emulation(struct numa_meminfo *numa_meminfo,
+			   int numa_dist_cnt);
+#else
+static inline void numa_emulation(struct numa_meminfo *numa_meminfo,
+				  int numa_dist_cnt)
+{ }
+static inline int numa_emu_cmdline(char *str)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_NUMA_EMU */
+
 #endif /* CONFIG_NUMA_MEMBLKS */
 
 #endif	/* __NUMA_MEMBLKS_H */
--- a/mm/Kconfig~mm-introduce-numa_emulation
+++ a/mm/Kconfig
@@ -1270,6 +1270,14 @@ config EXECMEM
 config NUMA_MEMBLKS
 	bool
 
+config NUMA_EMU
+	bool "NUMA emulation"
+	depends on NUMA_MEMBLKS
+	help
+	  Enable NUMA emulation. A flat machine will be split
+	  into virtual nodes when booted with "numa=fake=N", where N is the
+	  number of nodes. This is only useful for debugging.
+
 source "mm/damon/Kconfig"
 
 endmenu
--- a/mm/Makefile~mm-introduce-numa_emulation
+++ a/mm/Makefile
@@ -119,6 +119,7 @@ obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += e
 obj-$(CONFIG_CMA)	+= cma.o
 obj-$(CONFIG_NUMA) += numa.o
 obj-$(CONFIG_NUMA_MEMBLKS) += numa_memblks.o
+obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
 obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
 obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
 obj-$(CONFIG_PAGE_TABLE_CHECK) += page_table_check.o
diff --git a/mm/numa_emulation.c a/mm/numa_emulation.c
new file mode 100644
--- /dev/null
+++ a/mm/numa_emulation.c
@@ -0,0 +1,571 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NUMA emulation
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/topology.h>
+#include <linux/memblock.h>
+#include <linux/numa_memblks.h>
+#include <asm/numa.h>
+
+#define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
+#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
+
+static int emu_nid_to_phys[MAX_NUMNODES];
+static char *emu_cmdline __initdata;
+
+int __init numa_emu_cmdline(char *str)
+{
+	emu_cmdline = str;
+	return 0;
+}
+
+static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
+{
+	int i;
+
+	for (i = 0; i < mi->nr_blks; i++)
+		if (mi->blk[i].nid == nid)
+			return i;
+	return -ENOENT;
+}
+
+static u64 __init mem_hole_size(u64 start, u64 end)
+{
+	unsigned long start_pfn = PFN_UP(start);
+	unsigned long end_pfn = PFN_DOWN(end);
+
+	if (start_pfn < end_pfn)
+		return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn));
+	return 0;
+}
+
+/*
+ * Sets up nid to range from @start to @end.  The return value is -errno if
+ * something went wrong, 0 otherwise.
+ */
+static int __init emu_setup_memblk(struct numa_meminfo *ei,
+				   struct numa_meminfo *pi,
+				   int nid, int phys_blk, u64 size)
+{
+	struct numa_memblk *eb = &ei->blk[ei->nr_blks];
+	struct numa_memblk *pb = &pi->blk[phys_blk];
+
+	if (ei->nr_blks >= NR_NODE_MEMBLKS) {
+		pr_err("NUMA: Too many emulated memblks, failing emulation\n");
+		return -EINVAL;
+	}
+
+	ei->nr_blks++;
+	eb->start = pb->start;
+	eb->end = pb->start + size;
+	eb->nid = nid;
+
+	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
+		emu_nid_to_phys[nid] = pb->nid;
+
+	pb->start += size;
+	if (pb->start >= pb->end) {
+		WARN_ON_ONCE(pb->start > pb->end);
+		numa_remove_memblk_from(phys_blk, pi);
+	}
+
+	printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
+	       nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
+	return 0;
+}
+
+/*
+ * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
+ * to max_addr.
+ *
+ * Returns zero on success or negative on error.
+ */
+static int __init split_nodes_interleave(struct numa_meminfo *ei,
+					 struct numa_meminfo *pi,
+					 u64 addr, u64 max_addr, int nr_nodes)
+{
+	nodemask_t physnode_mask = numa_nodes_parsed;
+	u64 size;
+	int big;
+	int nid = 0;
+	int i, ret;
+
+	if (nr_nodes <= 0)
+		return -1;
+	if (nr_nodes > MAX_NUMNODES) {
+		pr_info("numa=fake=%d too large, reducing to %d\n",
+			nr_nodes, MAX_NUMNODES);
+		nr_nodes = MAX_NUMNODES;
+	}
+
+	/*
+	 * Calculate target node size.  x86_32 freaks on __udivdi3() so do
+	 * the division in ulong number of pages and convert back.
+	 */
+	size = max_addr - addr - mem_hole_size(addr, max_addr);
+	size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes);
+
+	/*
+	 * Calculate the number of big nodes that can be allocated as a result
+	 * of consolidating the remainder.
+	 */
+	big = ((size & ~FAKE_NODE_MIN_HASH_MASK) * nr_nodes) /
+		FAKE_NODE_MIN_SIZE;
+
+	size &= FAKE_NODE_MIN_HASH_MASK;
+	if (!size) {
+		pr_err("Not enough memory for each node.  "
+			"NUMA emulation disabled.\n");
+		return -1;
+	}
+
+	/*
+	 * Continue to fill physical nodes with fake nodes until there is no
+	 * memory left on any of them.
+	 */
+	while (!nodes_empty(physnode_mask)) {
+		for_each_node_mask(i, physnode_mask) {
+			u64 dma32_end = numa_emu_dma_end();
+			u64 start, limit, end;
+			int phys_blk;
+
+			phys_blk = emu_find_memblk_by_nid(i, pi);
+			if (phys_blk < 0) {
+				node_clear(i, physnode_mask);
+				continue;
+			}
+			start = pi->blk[phys_blk].start;
+			limit = pi->blk[phys_blk].end;
+			end = start + size;
+
+			if (nid < big)
+				end += FAKE_NODE_MIN_SIZE;
+
+			/*
+			 * Continue to add memory to this fake node if its
+			 * non-reserved memory is less than the per-node size.
+			 */
+			while (end - start - mem_hole_size(start, end) < size) {
+				end += FAKE_NODE_MIN_SIZE;
+				if (end > limit) {
+					end = limit;
+					break;
+				}
+			}
+
+			/*
+			 * If there won't be at least FAKE_NODE_MIN_SIZE of
+			 * non-reserved memory in ZONE_DMA32 for the next node,
+			 * this one must extend to the boundary.
+			 */
+			if (end < dma32_end && dma32_end - end -
+			    mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+				end = dma32_end;
+
+			/*
+			 * If there won't be enough non-reserved memory for the
+			 * next node, this one must extend to the end of the
+			 * physical node.
+			 */
+			if (limit - end - mem_hole_size(end, limit) < size)
+				end = limit;
+
+			ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes,
+					       phys_blk,
+					       min(end, limit) - start);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Returns the end address of a node so that there is at least `size' amount of
+ * non-reserved memory or `max_addr' is reached.
+ */
+static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
+{
+	u64 end = start + size;
+
+	while (end - start - mem_hole_size(start, end) < size) {
+		end += FAKE_NODE_MIN_SIZE;
+		if (end > max_addr) {
+			end = max_addr;
+			break;
+		}
+	}
+	return end;
+}
+
+static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes)
+{
+	unsigned long max_pfn = PHYS_PFN(max_addr);
+	unsigned long base_pfn = PHYS_PFN(base);
+	unsigned long hole_pfns = PHYS_PFN(hole);
+
+	return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes);
+}
+
+/*
+ * Sets up fake nodes of `size' interleaved over physical nodes ranging from
+ * `addr' to `max_addr'.
+ *
+ * Returns zero on success or negative on error.
+ */
+static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
+					      struct numa_meminfo *pi,
+					      u64 addr, u64 max_addr, u64 size,
+					      int nr_nodes, struct numa_memblk *pblk,
+					      int nid)
+{
+	nodemask_t physnode_mask = numa_nodes_parsed;
+	int i, ret, uniform = 0;
+	u64 min_size;
+
+	if ((!size && !nr_nodes) || (nr_nodes && !pblk))
+		return -1;
+
+	/*
+	 * In the 'uniform' case split the passed in physical node by
+	 * nr_nodes, in the non-uniform case, ignore the passed in
+	 * physical block and try to create nodes of at least size
+	 * @size.
+	 *
+	 * In the uniform case, split the nodes strictly by physical
+	 * capacity, i.e. ignore holes. In the non-uniform case account
+	 * for holes and treat @size as a minimum floor.
+	 */
+	if (!nr_nodes)
+		nr_nodes = MAX_NUMNODES;
+	else {
+		nodes_clear(physnode_mask);
+		node_set(pblk->nid, physnode_mask);
+		uniform = 1;
+	}
+
+	if (uniform) {
+		min_size = uniform_size(max_addr, addr, 0, nr_nodes);
+		size = min_size;
+	} else {
+		/*
+		 * The limit on emulated nodes is MAX_NUMNODES, so the
+		 * size per node is increased accordingly if the
+		 * requested size is too small.  This creates a uniform
+		 * distribution of node sizes across the entire machine
+		 * (but not necessarily over physical nodes).
+		 */
+		min_size = uniform_size(max_addr, addr,
+				mem_hole_size(addr, max_addr), nr_nodes);
+	}
+	min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
+	if (size < min_size) {
+		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
+			size >> 20, min_size >> 20);
+		size = min_size;
+	}
+	size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
+
+	/*
+	 * Fill physical nodes with fake nodes of size until there is no memory
+	 * left on any of them.
+	 */
+	while (!nodes_empty(physnode_mask)) {
+		for_each_node_mask(i, physnode_mask) {
+			u64 dma32_end = numa_emu_dma_end();
+			u64 start, limit, end;
+			int phys_blk;
+
+			phys_blk = emu_find_memblk_by_nid(i, pi);
+			if (phys_blk < 0) {
+				node_clear(i, physnode_mask);
+				continue;
+			}
+
+			start = pi->blk[phys_blk].start;
+			limit = pi->blk[phys_blk].end;
+
+			if (uniform)
+				end = start + size;
+			else
+				end = find_end_of_node(start, limit, size);
+			/*
+			 * If there won't be at least FAKE_NODE_MIN_SIZE of
+			 * non-reserved memory in ZONE_DMA32 for the next node,
+			 * this one must extend to the boundary.
+			 */
+			if (end < dma32_end && dma32_end - end -
+			    mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE)
+				end = dma32_end;
+
+			/*
+			 * If there won't be enough non-reserved memory for the
+			 * next node, this one must extend to the end of the
+			 * physical node.
+			 */
+			if ((limit - end - mem_hole_size(end, limit) < size)
+					&& !uniform)
+				end = limit;
+
+			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
+					       phys_blk,
+					       min(end, limit) - start);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return nid;
+}
+
+static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+					      struct numa_meminfo *pi,
+					      u64 addr, u64 max_addr, u64 size)
+{
+	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
+			0, NULL, 0);
+}
+
+static int __init setup_emu2phys_nid(int *dfl_phys_nid)
+{
+	int i, max_emu_nid = 0;
+
+	*dfl_phys_nid = NUMA_NO_NODE;
+	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++) {
+		if (emu_nid_to_phys[i] != NUMA_NO_NODE) {
+			max_emu_nid = i;
+			if (*dfl_phys_nid == NUMA_NO_NODE)
+				*dfl_phys_nid = emu_nid_to_phys[i];
+		}
+	}
+
+	return max_emu_nid;
+}
+
+/**
+ * numa_emulation - Emulate NUMA nodes
+ * @numa_meminfo: NUMA configuration to massage
+ * @numa_dist_cnt: The size of the physical NUMA distance table
+ *
+ * Emulate NUMA nodes according to the numa=fake kernel parameter.
+ * @numa_meminfo contains the physical memory configuration and is modified
+ * to reflect the emulated configuration on success.  @numa_dist_cnt is
+ * used to determine the size of the physical distance table.
+ *
+ * On success, the following modifications are made.
+ *
+ * - @numa_meminfo is updated to reflect the emulated nodes.
+ *
+ * - __apicid_to_node[] is updated such that APIC IDs are mapped to the
+ *   emulated nodes.
+ *
+ * - NUMA distance table is rebuilt to represent distances between emulated
+ *   nodes.  The distances are determined considering how emulated nodes
+ *   are mapped to physical nodes and match the actual distances.
+ *
+ * - emu_nid_to_phys[] reflects how emulated nodes are mapped to physical
+ *   nodes.  This is used by numa_add_cpu() and numa_remove_cpu().
+ *
+ * If emulation is not enabled or fails, emu_nid_to_phys[] is filled with
+ * identity mapping and no other modification is made.
+ */
+void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
+{
+	static struct numa_meminfo ei __initdata;
+	static struct numa_meminfo pi __initdata;
+	const u64 max_addr = PFN_PHYS(max_pfn);
+	u8 *phys_dist = NULL;
+	size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
+	int max_emu_nid, dfl_phys_nid;
+	int i, j, ret;
+
+	if (!emu_cmdline)
+		goto no_emu;
+
+	memset(&ei, 0, sizeof(ei));
+	pi = *numa_meminfo;
+
+	for (i = 0; i < MAX_NUMNODES; i++)
+		emu_nid_to_phys[i] = NUMA_NO_NODE;
+
+	/*
+	 * If the numa=fake command-line contains a 'M' or 'G', it represents
+	 * the fixed node size.  Otherwise, if it is just a single number N,
+	 * split the system RAM into N fake nodes.
+	 */
+	if (strchr(emu_cmdline, 'U')) {
+		nodemask_t physnode_mask = numa_nodes_parsed;
+		unsigned long n;
+		int nid = 0;
+
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
+		ret = -1;
+		for_each_node_mask(i, physnode_mask) {
+			/*
+			 * The reason we pass in blk[0] is due to
+			 * numa_remove_memblk_from() called by
+			 * emu_setup_memblk() will delete entry 0
+			 * and then move everything else up in the pi.blk
+			 * array. Therefore we should always be looking
+			 * at blk[0].
+			 */
+			ret = split_nodes_size_interleave_uniform(&ei, &pi,
+					pi.blk[0].start, pi.blk[0].end, 0,
+					n, &pi.blk[0], nid);
+			if (ret < 0)
+				break;
+			if (ret < n) {
+				pr_info("%s: phys: %d only got %d of %ld nodes, failing\n",
+						__func__, i, ret, n);
+				ret = -1;
+				break;
+			}
+			nid = ret;
+		}
+	} else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
+		u64 size;
+
+		size = memparse(emu_cmdline, &emu_cmdline);
+		ret = split_nodes_size_interleave(&ei, &pi, 0, max_addr, size);
+	} else {
+		unsigned long n;
+
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
+		ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
+	}
+	if (*emu_cmdline == ':')
+		emu_cmdline++;
+
+	if (ret < 0)
+		goto no_emu;
+
+	if (numa_cleanup_meminfo(&ei) < 0) {
+		pr_warn("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
+		goto no_emu;
+	}
+
+	/* copy the physical distance table */
+	if (numa_dist_cnt) {
+		phys_dist = memblock_alloc(phys_size, PAGE_SIZE);
+		if (!phys_dist) {
+			pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
+			goto no_emu;
+		}
+
+		for (i = 0; i < numa_dist_cnt; i++)
+			for (j = 0; j < numa_dist_cnt; j++)
+				phys_dist[i * numa_dist_cnt + j] =
+					node_distance(i, j);
+	}
+
+	/*
+	 * Determine the max emulated nid and the default phys nid to use
+	 * for unmapped nodes.
+	 */
+	max_emu_nid = setup_emu2phys_nid(&dfl_phys_nid);
+
+	/* commit */
+	*numa_meminfo = ei;
+
+	/* Make sure numa_nodes_parsed only contains emulated nodes */
+	nodes_clear(numa_nodes_parsed);
+	for (i = 0; i < ARRAY_SIZE(ei.blk); i++)
+		if (ei.blk[i].start != ei.blk[i].end &&
+		    ei.blk[i].nid != NUMA_NO_NODE)
+			node_set(ei.blk[i].nid, numa_nodes_parsed);
+
+	numa_emu_update_cpu_to_node(emu_nid_to_phys, ARRAY_SIZE(emu_nid_to_phys));
+
+	/* make sure all emulated nodes are mapped to a physical node */
+	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
+		if (emu_nid_to_phys[i] == NUMA_NO_NODE)
+			emu_nid_to_phys[i] = dfl_phys_nid;
+
+	/* transform distance table */
+	numa_reset_distance();
+	for (i = 0; i < max_emu_nid + 1; i++) {
+		for (j = 0; j < max_emu_nid + 1; j++) {
+			int physi = emu_nid_to_phys[i];
+			int physj = emu_nid_to_phys[j];
+			int dist;
+
+			if (get_option(&emu_cmdline, &dist) == 2)
+				;
+			else if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
+				dist = physi == physj ?
+					LOCAL_DISTANCE : REMOTE_DISTANCE;
+			else
+				dist = phys_dist[physi * numa_dist_cnt + physj];
+
+			numa_set_distance(i, j, dist);
+		}
+	}
+
+	/* free the copied physical distance table */
+	memblock_free(phys_dist, phys_size);
+	return;
+
+no_emu:
+	/* No emulation.  Build identity emu_nid_to_phys[] for numa_add_cpu() */
+	for (i = 0; i < ARRAY_SIZE(emu_nid_to_phys); i++)
+		emu_nid_to_phys[i] = i;
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+void numa_add_cpu(unsigned int cpu)
+{
+	int physnid, nid;
+
+	nid = early_cpu_to_node(cpu);
+	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
+
+	physnid = emu_nid_to_phys[nid];
+
+	/*
+	 * Map the cpu to each emulated node that is allocated on the physical
+	 * node of the cpu's apic id.
+	 */
+	for_each_online_node(nid)
+		if (emu_nid_to_phys[nid] == physnid)
+			cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
+}
+
+void numa_remove_cpu(unsigned int cpu)
+{
+	int i;
+
+	for_each_online_node(i)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[i]);
+}
+#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+static void numa_set_cpumask(unsigned int cpu, bool enable)
+{
+	int nid, physnid;
+
+	nid = early_cpu_to_node(cpu);
+	if (nid == NUMA_NO_NODE) {
+		/* early_cpu_to_node() already emits a warning and trace */
+		return;
+	}
+
+	physnid = emu_nid_to_phys[nid];
+
+	for_each_online_node(nid) {
+		if (emu_nid_to_phys[nid] != physnid)
+			continue;
+
+		debug_cpumask_set_cpu(cpu, nid, enable);
+	}
+}
+
+void numa_add_cpu(unsigned int cpu)
+{
+	numa_set_cpumask(cpu, true);
+}
+
+void numa_remove_cpu(unsigned int cpu)
+{
+	numa_set_cpumask(cpu, false);
+}
+#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
_

Patches currently in -mm which might be from rppt@kernel.org are

mm-move-kernel-numac-to-mm.patch
mips-sgi-ip27-make-node_data-the-same-as-on-all-other-architectures.patch
mips-sgi-ip27-ensure-node_possible_map-only-contains-valid-nodes.patch
mips-sgi-ip27-drop-have_arch_nodedata_extension.patch
mips-loongson64-rename-__node_data-to-node_data.patch
mips-loongson64-drop-have_arch_nodedata_extension.patch
arch-mm-move-definition-of-node_data-to-generic-code.patch
mm-drop-config_have_arch_nodedata_extension.patch
arch-mm-pull-out-allocation-of-node_data-to-generic-code.patch
x86-numa-simplify-numa_distance-allocation.patch
x86-numa-use-get_pfn_range_for_nid-to-verify-that-node-spans-memory.patch
x86-numa-move-fake_node_-defines-to-numa_emu.patch
x86-numa_emu-simplify-allocation-of-phys_dist.patch
x86-numa_emu-split-__apicid_to_node-update-to-a-helper-function.patch
x86-numa_emu-use-a-helper-function-to-get-max_dma32_pfn.patch
x86-numa-numa_addremove_cpu-make-cpu-parameter-unsigned.patch
mm-introduce-numa_memblks.patch
mm-move-numa_distance-and-related-code-from-x86-to-numa_memblks.patch
mm-introduce-numa_emulation.patch
mm-numa_memblks-introduce-numa_memblks_init.patch
mm-numa_memblks-make-several-functions-and-variables-static.patch
mm-numa_memblks-use-memblock_startend_of_dram-when-sanitizing-meminfo.patch
of-numa-return-einval-when-no-numa-node-id-is-found.patch
arch_numa-switch-over-to-numa_memblks.patch
arch_numa-switch-over-to-numa_memblks-fix.patch
mm-make-range-to-target_node-lookup-facility-a-part-of-numa_memblks.patch
docs-move-numa=fake-description-to-kernel-parameterstxt.patch