1 files changed, 48 insertions, 17 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index af11a2890235..dca9abf2b85c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -88,12 +88,7 @@ static int __init nonx32_setup(char *str)
 }
 __setup("noexec32=", nonx32_setup);
 
-/*
- * When memory was added make sure all the processes MM have
- * suitable PGD entries in the local PGD level page.
- */
-#ifdef CONFIG_X86_5LEVEL
-void sync_global_pgds(unsigned long start, unsigned long end)
+static void sync_global_pgds_l5(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
 
@@ -129,8 +124,8 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		spin_unlock(&pgd_lock);
 	}
 }
-#else
-void sync_global_pgds(unsigned long start, unsigned long end)
+
+static void sync_global_pgds_l4(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
 
@@ -143,7 +138,7 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		 * With folded p4d, pgd_none() is always false, we need to
 		 * handle synchonization on p4d level.
 		 */
-		BUILD_BUG_ON(pgd_none(*pgd_ref));
+		MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref));
 		p4d_ref = p4d_offset(pgd_ref, addr);
 
 		if (p4d_none(*p4d_ref))
@@ -173,7 +168,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		spin_unlock(&pgd_lock);
 	}
 }
-#endif
+
+/*
+ * When memory was added make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+	if (pgtable_l5_enabled)
+		sync_global_pgds_l5(start, end);
+	else
+		sync_global_pgds_l4(start, end);
+}
 
 /*
  * NOTE: This function is marked __ref because it calls __init function
@@ -632,7 +638,7 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 	unsigned long vaddr = (unsigned long)__va(paddr);
 	int i = p4d_index(vaddr);
 
-	if (!IS_ENABLED(CONFIG_X86_5LEVEL))
+	if (!pgtable_l5_enabled)
 		return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask);
 
 	for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) {
@@ -712,7 +718,7 @@ kernel_physical_mapping_init(unsigned long paddr_start,
 					   page_size_mask);
 
 		spin_lock(&init_mm.page_table_lock);
-		if (IS_ENABLED(CONFIG_X86_5LEVEL))
+		if (pgtable_l5_enabled)
 			pgd_populate(&init_mm, pgd, p4d);
 		else
 			p4d_populate(&init_mm, p4d_offset(pgd, vaddr), (pud_t *) p4d);
@@ -1089,7 +1095,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
 		 * 5-level case we should free them. This code will have to change
 		 * to adapt for boot-time switching between 4 and 5 level page tables.
 		 */
-		if (CONFIG_PGTABLE_LEVELS == 5)
+		if (pgtable_l5_enabled)
 			free_pud_table(pud_base, p4d);
 	}
 
@@ -1322,14 +1328,39 @@ int kern_addr_valid(unsigned long addr)
 	return pfn_valid(pte_pfn(*pte));
 }
 
+/*
+ * Block size is the minimum amount of memory which can be hotplugged or
+ * hotremoved. It must be power of two and must be equal or larger than
+ * MIN_MEMORY_BLOCK_SIZE.
+ */
+#define MAX_BLOCK_SIZE (2UL << 30)
+
+/* Amount of ram needed to start using large blocks */
+#define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)
+
 static unsigned long probe_memory_block_size(void)
 {
-	unsigned long bz = MIN_MEMORY_BLOCK_SIZE;
+	unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
+	unsigned long bz;
+
+	/* If this is UV system, always set 2G block size */
+	if (is_uv_system()) {
+		bz = MAX_BLOCK_SIZE;
+		goto done;
+	}
 
-	/* if system is UV or has 64GB of RAM or more, use large blocks */
-	if (is_uv_system() || ((max_pfn << PAGE_SHIFT) >= (64UL << 30)))
-		bz = 2UL << 30; /* 2GB */
+	/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
+	if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {
+		bz = MIN_MEMORY_BLOCK_SIZE;
+		goto done;
+	}
 
+	/* Find the largest allowed block size that aligns to memory end */
+	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
+		if (IS_ALIGNED(boot_mem_end, bz))
+			break;
+	}
+done:
 	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);
 
 	return bz;