3 files changed, 42 insertions, 11 deletions

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 07cdc2ed4965..c893c6a3d707 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -784,6 +784,7 @@ void __init mem_init(void)
 	free_all_bootmem();
 
 	after_bootmem = 1;
+	x86_init.hyper.init_after_bootmem();
 
 	mem_init_print_info(NULL);
 	printk(KERN_INFO "virtual kernel memory layout:\n"
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 6d1ff39c2438..0a400606dea0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1190,6 +1190,7 @@ void __init mem_init(void)
 	/* this will put all memory onto the freelists */
 	free_all_bootmem();
 	after_bootmem = 1;
+	x86_init.hyper.init_after_bootmem();
 
 	/*
 	 * Must be done after boot memory is put on freelist, because here we
@@ -1339,14 +1340,39 @@ 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 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 */
+	/* If this is UV system, always set 2G block size */
+	if (is_uv_system()) {
+		bz = MAX_BLOCK_SIZE;
+		goto done;
+	}
 
+	/* 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;
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 155ecbac9e28..48c591251600 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -90,9 +90,10 @@ unsigned long arch_mmap_rnd(void)
 	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
 }
 
-static unsigned long mmap_base(unsigned long rnd, unsigned long task_size)
+static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
+			       struct rlimit *rlim_stack)
 {
-	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
 	unsigned long gap_min, gap_max;
 
@@ -126,16 +127,17 @@ static unsigned long mmap_legacy_base(unsigned long rnd,
  * process VM image, sets up which VM layout function to use:
  */
 static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
-		unsigned long random_factor, unsigned long task_size)
+		unsigned long random_factor, unsigned long task_size,
+		struct rlimit *rlim_stack)
 {
 	*legacy_base = mmap_legacy_base(random_factor, task_size);
 	if (mmap_is_legacy())
 		*base = *legacy_base;
 	else
-		*base = mmap_base(random_factor, task_size);
+		*base = mmap_base(random_factor, task_size, rlim_stack);
 }
 
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	if (mmap_is_legacy())
 		mm->get_unmapped_area = arch_get_unmapped_area;
@@ -143,7 +145,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 
 	arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
-			arch_rnd(mmap64_rnd_bits), task_size_64bit(0));
+			arch_rnd(mmap64_rnd_bits), task_size_64bit(0),
+			rlim_stack);
 
 #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
 	/*
@@ -153,7 +156,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	 * mmap_base, the compat syscall uses mmap_compat_base.
 	 */
 	arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base,
-			arch_rnd(mmap32_rnd_bits), task_size_32bit());
+			arch_rnd(mmap32_rnd_bits), task_size_32bit(),
+			rlim_stack);
 #endif
 }