mm, treewide: redefine MAX_ORDER sanely

MAX_ORDER currently defined as number of orders page allocator supports:
user can ask buddy allocator for page order between 0 and MAX_ORDER-1.

This definition is counter-intuitive and lead to number of bugs all over
the kernel.

Change the definition of MAX_ORDER to be inclusive: the range of orders
user can ask from buddy allocator is 0..MAX_ORDER now.

[kirill@shutemov.name: fix min() warning]
  Link: https://lkml.kernel.org/r/20230315153800.32wib3n5rickolvh@box
[akpm@linux-foundation.org: fix another min_t warning]
[kirill@shutemov.name: fixups per Zi Yan]
  Link: https://lkml.kernel.org/r/20230316232144.b7ic4cif4kjiabws@box.shutemov.name
[akpm@linux-foundation.org: fix underlining in docs]
  Link: https://lore.kernel.org/oe-kbuild-all/202303191025.VRCTk6mP-lkp@intel.com/
Link: https://lkml.kernel.org/r/20230315113133.11326-11-kirill.shutemov@linux.intel.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Michael Ellerman <mpe@ellerman.id.au>	[powerpc]
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

4 files changed, 19 insertions, 22 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1023e896d46b..cb5c6aa3254e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1476,22 +1476,22 @@ config XEN
 
 # include/linux/mmzone.h requires the following to be true:
 #
-#   MAX_ORDER - 1 + PAGE_SHIFT <= SECTION_SIZE_BITS
+#   MAX_ORDER + PAGE_SHIFT <= SECTION_SIZE_BITS
 #
-# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS + 1 - PAGE_SHIFT:
+# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS - PAGE_SHIFT:
 #
 #     | SECTION_SIZE_BITS |  PAGE_SHIFT  |  max MAX_ORDER  |  default MAX_ORDER |
 # ----+-------------------+--------------+-----------------+--------------------+
-# 4K  |       27          |      12      |       16        |         11         |
-# 16K |       27          |      14      |       14        |         12         |
-# 64K |       29          |      16      |       14        |         14         |
+# 4K  |       27          |      12      |       15        |         10         |
+# 16K |       27          |      14      |       13        |         11         |
+# 64K |       29          |      16      |       13        |         13         |
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order" if ARM64_4K_PAGES || ARM64_16K_PAGES
-	default "14" if ARM64_64K_PAGES
-	range 12 14 if ARM64_16K_PAGES
-	default "12" if ARM64_16K_PAGES
-	range 11 16 if ARM64_4K_PAGES
-	default "11"
+	default "13" if ARM64_64K_PAGES
+	range 11 13 if ARM64_16K_PAGES
+	default "11" if ARM64_16K_PAGES
+	range 10 15 if ARM64_4K_PAGES
+	default "10"
 	help
 	  The kernel memory allocator divides physically contiguous memory
 	  blocks into "zones", where each zone is a power of two number of
@@ -1500,14 +1500,11 @@ config ARCH_FORCE_MAX_ORDER
 	  blocks of physically contiguous memory, then you may need to
 	  increase this value.
 
-	  This config option is actually maximum order plus one. For example,
-	  a value of 11 means that the largest free memory block is 2^10 pages.
-
 	  We make sure that we can allocate up to a HugePage size for each configuration.
 	  Hence we have :
-		MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2
+		MAX_ORDER = PMD_SHIFT - PAGE_SHIFT  => PAGE_SHIFT - 3
 
-	  However for 4K, we choose a higher default value, 11 as opposed to 10, giving us
+	  However for 4K, we choose a higher default value, 10 as opposed to 9, giving us
 	  4M allocations matching the default size used by generic code.
 
 config UNMAP_KERNEL_AT_EL0
diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h
index 4b73463423c3..5f5437621029 100644
--- a/arch/arm64/include/asm/sparsemem.h
+++ b/arch/arm64/include/asm/sparsemem.h
@@ -10,7 +10,7 @@
 /*
  * Section size must be at least 512MB for 64K base
  * page size config. Otherwise it will be less than
- * (MAX_ORDER - 1) and the build process will fail.
+ * MAX_ORDER and the build process will fail.
  */
 #ifdef CONFIG_ARM64_64K_PAGES
 #define SECTION_SIZE_BITS 29
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index 0a048dc06a7d..fe5472a184a3 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -16,7 +16,7 @@ struct hyp_pool {
 	 * API at EL2.
 	 */
 	hyp_spinlock_t lock;
-	struct list_head free_area[MAX_ORDER];
+	struct list_head free_area[MAX_ORDER + 1];
 	phys_addr_t range_start;
 	phys_addr_t range_end;
 	unsigned short max_order;
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index 803ba3222e75..b1e392186a0f 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -110,7 +110,7 @@ static void __hyp_attach_page(struct hyp_pool *pool,
 	 * after coalescing, so make sure to mark it HYP_NO_ORDER proactively.
 	 */
 	p->order = HYP_NO_ORDER;
-	for (; (order + 1) < pool->max_order; order++) {
+	for (; (order + 1) <= pool->max_order; order++) {
 		buddy = __find_buddy_avail(pool, p, order);
 		if (!buddy)
 			break;
@@ -203,9 +203,9 @@ void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
 	hyp_spin_lock(&pool->lock);
 
 	/* Look for a high-enough-order page */
-	while (i < pool->max_order && list_empty(&pool->free_area[i]))
+	while (i <= pool->max_order && list_empty(&pool->free_area[i]))
 		i++;
-	if (i >= pool->max_order) {
+	if (i > pool->max_order) {
 		hyp_spin_unlock(&pool->lock);
 		return NULL;
 	}
@@ -228,8 +228,8 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,
 	int i;
 
 	hyp_spin_lock_init(&pool->lock);
-	pool->max_order = min(MAX_ORDER, get_order((nr_pages + 1) << PAGE_SHIFT));
-	for (i = 0; i < pool->max_order; i++)
+	pool->max_order = min(MAX_ORDER, get_order(nr_pages << PAGE_SHIFT));
+	for (i = 0; i <= pool->max_order; i++)
 		INIT_LIST_HEAD(&pool->free_area[i]);
 	pool->range_start = phys;
 	pool->range_end = phys + (nr_pages << PAGE_SHIFT);