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>
torvalds · Apr 6, 2023 · 23baf83 · 23baf83
1 parent 61883d3
commit 23baf83
Show file tree

Hide file tree

Showing 84 changed files with 223 additions and 253 deletions.
diff --git a/Documentation/admin-guide/kdump/vmcoreinfo.rst b/Documentation/admin-guide/kdump/vmcoreinfo.rst
@@ -172,7 +172,7 @@ variables.
 Offset of the free_list's member. This value is used to compute the number
 of free pages.
 
-Each zone has a free_area structure array called free_area[MAX_ORDER].
+Each zone has a free_area structure array called free_area[MAX_ORDER + 1].
 The free_list represents a linked list of free page blocks.
 
 (list_head, next|prev)
@@ -189,8 +189,8 @@ Offsets of the vmap_area's members. They carry vmalloc-specific
 information. Makedumpfile gets the start address of the vmalloc region
 from this.
 
-(zone.free_area, MAX_ORDER)
----------------------------
+(zone.free_area, MAX_ORDER + 1)
+-------------------------------
 
 Free areas descriptor. User-space tools use this value to iterate the
 free_area ranges. MAX_ORDER is used by the zone buddy allocator.

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
@@ -3969,7 +3969,7 @@
 			[KNL] Minimal page reporting order
 			Format: <integer>
 			Adjust the minimal page reporting order. The page
-			reporting is disabled when it exceeds (MAX_ORDER-1).
+			reporting is disabled when it exceeds MAX_ORDER.
 
 	panic=		[KNL] Kernel behaviour on panic: delay <timeout>
 			timeout > 0: seconds before rebooting

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
@@ -556,7 +556,7 @@ endmenu	 # "ARC Architecture Configuration"
 
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
-	default "12" if ARC_HUGEPAGE_16M
-	default "11"
+	default "11" if ARC_HUGEPAGE_16M
+	default "10"
 
 source "kernel/power/Kconfig"
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
@@ -1355,9 +1355,9 @@ config ARM_MODULE_PLTS
 
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
-	default "12" if SOC_AM33XX
-	default "9" if SA1111
-	default "11"
+	default "11" if SOC_AM33XX
+	default "8" if SA1111
+	default "10"
 	help
 	  The kernel memory allocator divides physically contiguous memory
 	  blocks into "zones", where each zone is a power of two number of
@@ -1366,9 +1366,6 @@ 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.
-
 config ALIGNMENT_TRAP
 	def_bool CPU_CP15_MMU
 	select HAVE_PROC_CPU if PROC_FS

diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
@@ -31,7 +31,7 @@ CONFIG_SOC_VF610=y
 CONFIG_SMP=y
 CONFIG_ARM_PSCI=y
 CONFIG_HIGHMEM=y
-CONFIG_ARCH_FORCE_MAX_ORDER=14
+CONFIG_ARCH_FORCE_MAX_ORDER=13
 CONFIG_CMDLINE="noinitrd console=ttymxc0,115200"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y

diff --git a/arch/arm/configs/milbeaut_m10v_defconfig b/arch/arm/configs/milbeaut_m10v_defconfig
@@ -26,7 +26,7 @@ CONFIG_THUMB2_KERNEL=y
 # CONFIG_THUMB2_AVOID_R_ARM_THM_JUMP11 is not set
 # CONFIG_ARM_PATCH_IDIV is not set
 CONFIG_HIGHMEM=y
-CONFIG_ARCH_FORCE_MAX_ORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=11
 CONFIG_SECCOMP=y
 CONFIG_KEXEC=y
 CONFIG_EFI=y

diff --git a/arch/arm/configs/oxnas_v6_defconfig b/arch/arm/configs/oxnas_v6_defconfig
@@ -12,7 +12,7 @@ CONFIG_ARCH_OXNAS=y
 CONFIG_MACH_OX820=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=16
-CONFIG_ARCH_FORCE_MAX_ORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=11
 CONFIG_SECCOMP=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y

diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
@@ -20,7 +20,7 @@ CONFIG_PXA_SHARPSL=y
 CONFIG_MACH_AKITA=y
 CONFIG_MACH_BORZOI=y
 CONFIG_AEABI=y
-CONFIG_ARCH_FORCE_MAX_ORDER=9
+CONFIG_ARCH_FORCE_MAX_ORDER=8
 CONFIG_CMDLINE="root=/dev/ram0 ro"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y

diff --git a/arch/arm/configs/sama7_defconfig b/arch/arm/configs/sama7_defconfig
@@ -19,7 +19,7 @@ CONFIG_ATMEL_CLOCKSOURCE_TCB=y
 # CONFIG_CACHE_L2X0 is not set
 # CONFIG_ARM_PATCH_IDIV is not set
 # CONFIG_CPU_SW_DOMAIN_PAN is not set
-CONFIG_ARCH_FORCE_MAX_ORDER=15
+CONFIG_ARCH_FORCE_MAX_ORDER=14
 CONFIG_UACCESS_WITH_MEMCPY=y
 # CONFIG_ATAGS is not set
 CONFIG_CMDLINE="console=ttyS0,115200 earlyprintk ignore_loglevel"

diff --git a/arch/arm/configs/sp7021_defconfig b/arch/arm/configs/sp7021_defconfig
@@ -17,7 +17,7 @@ CONFIG_ARCH_SUNPLUS=y
 # CONFIG_VDSO is not set
 CONFIG_SMP=y
 CONFIG_THUMB2_KERNEL=y
-CONFIG_ARCH_FORCE_MAX_ORDER=12
+CONFIG_ARCH_FORCE_MAX_ORDER=11
 CONFIG_VFP=y
 CONFIG_NEON=y
 CONFIG_MODULES=y

diff --git 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
@@ -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
@@ -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
@@ -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);

diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
@@ -334,7 +334,7 @@ config HIGHMEM
 
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
-	default "11"
+	default "10"
 
 config DRAM_BASE
 	hex "DRAM start addr (the same with memory-section in dts)"

diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
@@ -202,10 +202,10 @@ config IA64_CYCLONE
 	  If you're unsure, answer N.
 
 config ARCH_FORCE_MAX_ORDER
-	int "MAX_ORDER (11 - 17)"  if !HUGETLB_PAGE
-	range 11 17  if !HUGETLB_PAGE
-	default "17" if HUGETLB_PAGE
-	default "11"
+	int "MAX_ORDER (10 - 16)"  if !HUGETLB_PAGE
+	range 10 16  if !HUGETLB_PAGE
+	default "16" if HUGETLB_PAGE
+	default "10"
 
 config SMP
 	bool "Symmetric multi-processing support"

diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h
@@ -12,9 +12,9 @@
 #define SECTION_SIZE_BITS	(30)
 #define MAX_PHYSMEM_BITS	(50)
 #ifdef CONFIG_ARCH_FORCE_MAX_ORDER
-#if ((CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS)
+#if (CONFIG_ARCH_FORCE_MAX_ORDER + PAGE_SHIFT > SECTION_SIZE_BITS)
 #undef SECTION_SIZE_BITS
-#define SECTION_SIZE_BITS (CONFIG_ARCH_FORCE_MAX_ORDER - 1 + PAGE_SHIFT)
+#define SECTION_SIZE_BITS (CONFIG_ARCH_FORCE_MAX_ORDER + PAGE_SHIFT)
 #endif
 #endif
 

diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
@@ -170,7 +170,7 @@ static int __init hugetlb_setup_sz(char *str)
 	size = memparse(str, &str);
 	if (*str || !is_power_of_2(size) || !(tr_pages & size) ||
 		size <= PAGE_SIZE ||
-		size >= (1UL << PAGE_SHIFT << MAX_ORDER)) {
+		size > (1UL << PAGE_SHIFT << MAX_ORDER)) {
 		printk(KERN_WARNING "Invalid huge page size specified\n");
 		return 1;
 	}

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
@@ -420,12 +420,12 @@ config NODES_SHIFT
 
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
-	range 14 64 if PAGE_SIZE_64KB
-	default "14" if PAGE_SIZE_64KB
-	range 12 64 if PAGE_SIZE_16KB
-	default "12" if PAGE_SIZE_16KB
-	range 11 64
-	default "11"
+	range 13 63 if PAGE_SIZE_64KB
+	default "13" if PAGE_SIZE_64KB
+	range 11 63 if PAGE_SIZE_16KB
+	default "11" if PAGE_SIZE_16KB
+	range 10 63
+	default "10"
 	help
 	  The kernel memory allocator divides physically contiguous memory
 	  blocks into "zones", where each zone is a power of two number of
@@ -434,9 +434,6 @@ 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.
-
 	  The page size is not necessarily 4KB.  Keep this in mind
 	  when choosing a value for this option.
 

diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
@@ -400,7 +400,7 @@ config SINGLE_MEMORY_CHUNK
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order" if ADVANCED
 	depends on !SINGLE_MEMORY_CHUNK
-	default "11"
+	default "10"
 	help
 	  The kernel memory allocator divides physically contiguous memory
 	  blocks into "zones", where each zone is a power of two number of
@@ -413,9 +413,6 @@ config ARCH_FORCE_MAX_ORDER
 	  value also defines the minimal size of the hole that allows
 	  freeing unused memory map.
 
-	  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.
-
 config 060_WRITETHROUGH
 	bool "Use write-through caching for 68060 supervisor accesses"
 	depends on ADVANCED && M68060

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
@@ -2137,14 +2137,14 @@ endchoice
 
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
-	range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
-	default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
-	range 13 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
-	default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
-	range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
-	default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
-	range 0 64
-	default "11"
+	range 13 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+	default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+	range 12 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+	default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+	range 11 63 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
+	default "11" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
+	range 0 63
+	default "10"
 	help
 	  The kernel memory allocator divides physically contiguous memory
 	  blocks into "zones", where each zone is a power of two number of
@@ -2153,9 +2153,6 @@ 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.
-
 	  The page size is not necessarily 4KB.  Keep this in mind
 	  when choosing a value for this option.
 

diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
@@ -46,8 +46,8 @@ source "kernel/Kconfig.hz"
 
 config ARCH_FORCE_MAX_ORDER
 	int "Maximum zone order"
-	range 9 20
-	default "11"
+	range 8 19
+	default "10"
 	help
 	  The kernel memory allocator divides physically contiguous memory
 	  blocks into "zones", where each zone is a power of two number of
@@ -56,9 +56,6 @@ 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.
-
 endmenu
 
 source "arch/nios2/platform/Kconfig.platform"