6 files changed, 62 insertions, 9 deletions

diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 0596e8e0cc19..207d9aef662d 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -108,8 +108,8 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 
 static inline void get_head_page_multiple(struct page *page, int nr)
 {
-	VM_BUG_ON(page != compound_head(page));
-	VM_BUG_ON(page_count(page) == 0);
+	VM_BUG_ON_PAGE(page != compound_head(page), page);
+	VM_BUG_ON_PAGE(page_count(page) == 0, page);
 	atomic_add(nr, &page->_count);
 	SetPageReferenced(page);
 }
@@ -135,7 +135,7 @@ static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
 	head = pte_page(pte);
 	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 	do {
-		VM_BUG_ON(compound_head(page) != head);
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
 		if (PageTail(page))
 			get_huge_page_tail(page);
@@ -212,7 +212,7 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
 	head = pte_page(pte);
 	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 	do {
-		VM_BUG_ON(compound_head(page) != head);
+		VM_BUG_ON_PAGE(compound_head(page) != head, page);
 		pages[*nr] = page;
 		if (PageTail(page))
 			get_huge_page_tail(page);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 5bdc5430597c..e39504878aec 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -665,7 +665,7 @@ void __init initmem_init(void)
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
 #endif
 
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 	sparse_memory_present_with_active_regions(0);
 
 #ifdef CONFIG_FLATMEM
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 104d56a9245f..f35c66c5959a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -643,7 +643,7 @@ kernel_physical_mapping_init(unsigned long start,
 #ifndef CONFIG_NUMA
 void __init initmem_init(void)
 {
-	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
+	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
 }
 #endif
 
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 8dabbed409ee..1e9da795767a 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -74,7 +74,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end)
 	u64 i;
 	phys_addr_t this_start, this_end;
 
-	for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) {
+	for_each_free_mem_range(i, NUMA_NO_NODE, &this_start, &this_end, NULL) {
 		this_start = clamp_t(phys_addr_t, this_start, start, end);
 		this_end = clamp_t(phys_addr_t, this_end, start, end);
 		if (this_start < this_end) {
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c85da7bb6b60..81b2750f3666 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -491,7 +491,16 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 
 	for (i = 0; i < mi->nr_blks; i++) {
 		struct numa_memblk *mb = &mi->blk[i];
-		memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.memory, mb->nid);
+
+		/*
+		 * At this time, all memory regions reserved by memblock are
+		 * used by the kernel. Set the nid in memblock.reserved will
+		 * mark out all the nodes the kernel resides in.
+		 */
+		memblock_set_node(mb->start, mb->end - mb->start,
+				  &memblock.reserved, mb->nid);
 	}
 
 	/*
@@ -553,6 +562,30 @@ static void __init numa_init_array(void)
 	}
 }
 
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+	int i, nid;
+	nodemask_t numa_kernel_nodes;
+	unsigned long start, end;
+	struct memblock_type *type = &memblock.reserved;
+
+	/* Mark all kernel nodes. */
+	for (i = 0; i < type->cnt; i++)
+		node_set(type->regions[i].nid, numa_kernel_nodes);
+
+	/* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+	for (i = 0; i < numa_meminfo.nr_blks; i++) {
+		nid = numa_meminfo.blk[i].nid;
+		if (!node_isset(nid, numa_kernel_nodes))
+			continue;
+
+		start = numa_meminfo.blk[i].start;
+		end = numa_meminfo.blk[i].end;
+
+		memblock_clear_hotplug(start, end - start);
+	}
+}
+
 static int __init numa_init(int (*init_func)(void))
 {
 	int i;
@@ -565,7 +598,12 @@ static int __init numa_init(int (*init_func)(void))
 	nodes_clear(node_possible_map);
 	nodes_clear(node_online_map);
 	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
-	WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory,
+				  MAX_NUMNODES));
+	WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved,
+				  MAX_NUMNODES));
+	/* In case that parsing SRAT failed. */
+	WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX));
 	numa_reset_distance();
 
 	ret = init_func();
@@ -601,6 +639,16 @@ static int __init numa_init(int (*init_func)(void))
 			numa_clear_node(i);
 	}
 	numa_init_array();
+
+	/*
+	 * At very early time, the kernel have to use some memory such as
+	 * loading the kernel image. We cannot prevent this anyway. So any
+	 * node the kernel resides in should be un-hotpluggable.
+	 *
+	 * And when we come here, numa_init() won't fail.
+	 */
+	numa_clear_kernel_node_hotplug();
+
 	return 0;
 }
 
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 5ecf65117e6f..1953e9c9391a 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -191,6 +191,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		(unsigned long long) start, (unsigned long long) end - 1,
 		hotpluggable ? " hotplug" : "");
 
+	/* Mark hotplug range in memblock. */
+	if (hotpluggable && memblock_mark_hotplug(start, ma->length))
+		pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
+			(unsigned long long)start, (unsigned long long)end - 1);
+
 	return 0;
 out_err_bad_srat:
 	bad_srat();