x86-64, NUMA: Move NUMA emulation into numa_emulation.c

Create numa_emulation.c and move all NUMA emulation code there.  The
definitions of struct numa_memblk and numa_meminfo are moved to
numa_64.h.  Also, numa_remove_memblk_from(), numa_cleanup_meminfo(),
numa_reset_distance() along with numa_emulation() are made global.

- v2: Internal declarations moved to numa_internal.h as suggested by
      Yinghai.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>

1 files changed, 452 insertions, 0 deletions

diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
new file mode 100644
index 000000000000..23fa2d00253a
--- /dev/null
+++ b/arch/x86/mm/numa_emulation.c
@@ -0,0 +1,452 @@
+/*
+ * NUMA emulation
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/topology.h>
+#include <linux/memblock.h>
+#include <asm/dma.h>
+
+#include "numa_internal.h"
+
+static int emu_nid_to_phys[MAX_NUMNODES] __cpuinitdata;
+static char *emu_cmdline __initdata;
+
+void __init numa_emu_cmdline(char *str)
+{
+	emu_cmdline = str;
+}
+
+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;
+}
+
+/*
+ * 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 %016Lx-%016Lx (%LuMB)\n", nid,
+	       eb->start, eb->end, (eb->end - eb->start) >> 20);
+	return 0;
+}
+
+/*
+ * Sets up nr_nodes fake nodes interleaved over physical nodes ranging from addr
+ * to max_addr.  The return value is the number of nodes allocated.
+ */
+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 = NODE_MASK_NONE;
+	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;
+	}
+
+	size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / 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;
+	}
+
+	for (i = 0; i < pi->nr_blks; i++)
+		node_set(pi->blk[i].nid, physnode_mask);
+
+	/*
+	 * Continue to fill physical nodes with fake nodes until there is no
+	 * memory left on any of them.
+	 */
+	while (nodes_weight(physnode_mask)) {
+		for_each_node_mask(i, physnode_mask) {
+			u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN);
+			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 -
+			       memblock_x86_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 -
+			    memblock_x86_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 -
+			    memblock_x86_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 - memblock_x86_hole_size(start, end) < size) {
+		end += FAKE_NODE_MIN_SIZE;
+		if (end > max_addr) {
+			end = max_addr;
+			break;
+		}
+	}
+	return end;
+}
+
+/*
+ * Sets up fake nodes of `size' interleaved over physical nodes ranging from
+ * `addr' to `max_addr'.  The return value is the number of nodes allocated.
+ */
+static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+					      struct numa_meminfo *pi,
+					      u64 addr, u64 max_addr, u64 size)
+{
+	nodemask_t physnode_mask = NODE_MASK_NONE;
+	u64 min_size;
+	int nid = 0;
+	int i, ret;
+
+	if (!size)
+		return -1;
+	/*
+	 * 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 = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) /
+						MAX_NUMNODES;
+	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
+	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
+		min_size = (min_size + FAKE_NODE_MIN_SIZE) &
+						FAKE_NODE_MIN_HASH_MASK;
+	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 &= FAKE_NODE_MIN_HASH_MASK;
+
+	for (i = 0; i < pi->nr_blks; i++)
+		node_set(pi->blk[i].nid, physnode_mask);
+
+	/*
+	 * Fill physical nodes with fake nodes of size until there is no memory
+	 * left on any of them.
+	 */
+	while (nodes_weight(physnode_mask)) {
+		for_each_node_mask(i, physnode_mask) {
+			u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT;
+			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 = 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 -
+			    memblock_x86_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 -
+			    memblock_x86_hole_size(end, limit) < size)
+				end = limit;
+
+			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
+					       phys_blk,
+					       min(end, limit) - start);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
+/*
+ * Sets up the system RAM area from start_pfn to last_pfn according to the
+ * numa=fake command-line option.
+ */
+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 = max_pfn << PAGE_SHIFT;
+	u8 *phys_dist = NULL;
+	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, '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, NULL, 0);
+		ret = split_nodes_interleave(&ei, &pi, 0, max_addr, n);
+	}
+
+	if (ret < 0)
+		goto no_emu;
+
+	if (numa_cleanup_meminfo(&ei) < 0) {
+		pr_warning("NUMA: Warning: constructed meminfo invalid, disabling emulation\n");
+		goto no_emu;
+	}
+
+	/*
+	 * Copy the original distance table.  It's temporary so no need to
+	 * reserve it.
+	 */
+	if (numa_dist_cnt) {
+		size_t size = numa_dist_cnt * sizeof(phys_dist[0]);
+		u64 phys;
+
+		phys = memblock_find_in_range(0,
+					      (u64)max_pfn_mapped << PAGE_SHIFT,
+					      size, PAGE_SIZE);
+		if (phys == MEMBLOCK_ERROR) {
+			pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
+			goto no_emu;
+		}
+		phys_dist = __va(phys);
+
+		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);
+	}
+
+	/* commit */
+	*numa_meminfo = ei;
+
+	/*
+	 * Transform __apicid_to_node table to use emulated nids by
+	 * reverse-mapping phys_nid.  The maps should always exist but fall
+	 * back to zero just in case.
+	 */
+	for (i = 0; i < ARRAY_SIZE(__apicid_to_node); i++) {
+		if (__apicid_to_node[i] == NUMA_NO_NODE)
+			continue;
+		for (j = 0; j < ARRAY_SIZE(emu_nid_to_phys); j++)
+			if (__apicid_to_node[i] == emu_nid_to_phys[j])
+				break;
+		__apicid_to_node[i] = j < ARRAY_SIZE(emu_nid_to_phys) ? j : 0;
+	}
+
+	/* 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] = 0;
+
+	/* transform distance table */
+	numa_reset_distance();
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		for (j = 0; j < MAX_NUMNODES; j++) {
+			int physi = emu_nid_to_phys[i];
+			int physj = emu_nid_to_phys[j];
+			int dist;
+
+			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);
+		}
+	}
+	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 __cpuinit numa_add_cpu(int cpu)
+{
+	int physnid, nid;
+
+	nid = numa_cpu_node(cpu);
+	if (nid == NUMA_NO_NODE)
+		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 __cpuinit numa_remove_cpu(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 __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+	struct cpumask *mask;
+	int nid, physnid, i;
+
+	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(i) {
+		if (emu_nid_to_phys[nid] != physnid)
+			continue;
+
+		mask = debug_cpumask_set_cpu(cpu, enable);
+		if (!mask)
+			return;
+
+		if (enable)
+			cpumask_set_cpu(cpu, mask);
+		else
+			cpumask_clear_cpu(cpu, mask);
+	}
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 1);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 0);
+}
+#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */