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>

19 files changed, 42 insertions, 42 deletions

diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 817eda2075aa..c491fabe3617 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -226,8 +226,8 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
-	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
-		count = PAGE_SIZE << (MAX_ORDER - 1);
+	if (count > (PAGE_SIZE << MAX_ORDER))
+		count = PAGE_SIZE << MAX_ORDER;
 
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
@@ -373,8 +373,8 @@ static ssize_t regmap_reg_ranges_read_file(struct file *file,
 	if (*ppos < 0 || !count)
 		return -EINVAL;
 
-	if (count > (PAGE_SIZE << (MAX_ORDER - 1)))
-		count = PAGE_SIZE << (MAX_ORDER - 1);
+	if (count > (PAGE_SIZE << MAX_ORDER))
+		count = PAGE_SIZE << MAX_ORDER;
 
 	buf = kmalloc(count, GFP_KERNEL);
 	if (!buf)
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 90d2dfb6448e..cec2c20f5e59 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3079,7 +3079,7 @@ static void raw_cmd_free(struct floppy_raw_cmd **ptr)
 	}
 }
 
-#define MAX_LEN (1UL << (MAX_ORDER - 1) << PAGE_SHIFT)
+#define MAX_LEN (1UL << MAX_ORDER << PAGE_SHIFT)
 
 static int raw_cmd_copyin(int cmd, void __user *param,
 				 struct floppy_raw_cmd **rcmd)
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index e2f25926eb51..bf095baca244 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -886,7 +886,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
 		/*
 		 * The length of the ID shouldn't be assumed by software since
 		 * it may change in the future.  The allocation size is limited
-		 * to 1 << (PAGE_SHIFT + MAX_ORDER - 1) by the page allocator.
+		 * to 1 << (PAGE_SHIFT + MAX_ORDER) by the page allocator.
 		 * If the allocation fails, simply return ENOMEM rather than
 		 * warning in the kernel log.
 		 */
diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c
index 09586a837b1e..3df7a256e919 100644
--- a/drivers/crypto/hisilicon/sgl.c
+++ b/drivers/crypto/hisilicon/sgl.c
@@ -70,11 +70,11 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
 			 HISI_ACC_SGL_ALIGN_SIZE);
 
 	/*
-	 * the pool may allocate a block of memory of size PAGE_SIZE * 2^(MAX_ORDER - 1),
+	 * the pool may allocate a block of memory of size PAGE_SIZE * 2^MAX_ORDER,
 	 * block size may exceed 2^31 on ia64, so the max of block size is 2^31
 	 */
-	block_size = 1 << (PAGE_SHIFT + MAX_ORDER <= 32 ?
-			   PAGE_SHIFT + MAX_ORDER - 1 : 31);
+	block_size = 1 << (PAGE_SHIFT + MAX_ORDER < 32 ?
+			   PAGE_SHIFT + MAX_ORDER : 31);
 	sgl_num_per_block = block_size / sgl_size;
 	block_num = count / sgl_num_per_block;
 	remain_sgl = count % sgl_num_per_block;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index eae9e9f6d3bf..6bc26b4b06b8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -36,7 +36,7 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 	struct sg_table *st;
 	struct scatterlist *sg;
 	unsigned int npages; /* restricted by sg_alloc_table */
-	int max_order = MAX_ORDER - 1;
+	int max_order = MAX_ORDER;
 	unsigned int max_segment;
 	gfp_t gfp;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index defece0bcb81..99f39a5feca1 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -115,7 +115,7 @@ static int get_huge_pages(struct drm_i915_gem_object *obj)
 		do {
 			struct page *page;
 
-			GEM_BUG_ON(order >= MAX_ORDER);
+			GEM_BUG_ON(order > MAX_ORDER);
 			page = alloc_pages(GFP | __GFP_ZERO, order);
 			if (!page)
 				goto err;
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index aa116a7bbae3..6c8585abe08d 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -65,11 +65,11 @@ module_param(page_pool_size, ulong, 0644);
 
 static atomic_long_t allocated_pages;
 
-static struct ttm_pool_type global_write_combined[MAX_ORDER];
-static struct ttm_pool_type global_uncached[MAX_ORDER];
+static struct ttm_pool_type global_write_combined[MAX_ORDER + 1];
+static struct ttm_pool_type global_uncached[MAX_ORDER + 1];
 
-static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
-static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
+static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER + 1];
+static struct ttm_pool_type global_dma32_uncached[MAX_ORDER + 1];
 
 static spinlock_t shrinker_lock;
 static struct list_head shrinker_list;
@@ -405,7 +405,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 	else
 		gfp_flags |= GFP_HIGHUSER;
 
-	for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages));
+	for (order = min_t(unsigned int, MAX_ORDER, __fls(num_pages));
 	     num_pages;
 	     order = min_t(unsigned int, order, __fls(num_pages))) {
 		struct ttm_pool_type *pt;
@@ -542,7 +542,7 @@ void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
 
 	if (use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < MAX_ORDER; ++j)
+			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_init(&pool->caching[i].orders[j],
 						   pool, i, j);
 	}
@@ -562,7 +562,7 @@ void ttm_pool_fini(struct ttm_pool *pool)
 
 	if (pool->use_dma_alloc) {
 		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
-			for (j = 0; j < MAX_ORDER; ++j)
+			for (j = 0; j <= MAX_ORDER; ++j)
 				ttm_pool_type_fini(&pool->caching[i].orders[j]);
 	}
 
@@ -616,7 +616,7 @@ static void ttm_pool_debugfs_header(struct seq_file *m)
 	unsigned int i;
 
 	seq_puts(m, "\t ");
-	for (i = 0; i < MAX_ORDER; ++i)
+	for (i = 0; i <= MAX_ORDER; ++i)
 		seq_printf(m, " ---%2u---", i);
 	seq_puts(m, "\n");
 }
@@ -627,7 +627,7 @@ static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
 {
 	unsigned int i;
 
-	for (i = 0; i < MAX_ORDER; ++i)
+	for (i = 0; i <= MAX_ORDER; ++i)
 		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
 	seq_puts(m, "\n");
 }
@@ -736,7 +736,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
 	spin_lock_init(&shrinker_lock);
 	INIT_LIST_HEAD(&shrinker_list);
 
-	for (i = 0; i < MAX_ORDER; ++i) {
+	for (i = 0; i <= MAX_ORDER; ++i) {
 		ttm_pool_type_init(&global_write_combined[i], NULL,
 				   ttm_write_combined, i);
 		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
@@ -769,7 +769,7 @@ void ttm_pool_mgr_fini(void)
 {
 	unsigned int i;
 
-	for (i = 0; i < MAX_ORDER; ++i) {
+	for (i = 0; i <= MAX_ORDER; ++i) {
 		ttm_pool_type_fini(&global_write_combined[i]);
 		ttm_pool_type_fini(&global_uncached[i]);
 
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 8d772ea8a583..b574c58a3487 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -182,7 +182,7 @@
 #ifdef CONFIG_CMA_ALIGNMENT
 #define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + CONFIG_CMA_ALIGNMENT)
 #else
-#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER - 1)
+#define Q_MAX_SZ_SHIFT			(PAGE_SHIFT + MAX_ORDER)
 #endif
 
 /*
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index ac996fd6bd9c..7a9f0b0bddbd 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -736,7 +736,7 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	struct page **pages;
 	unsigned int i = 0, nid = dev_to_node(dev);
 
-	order_mask &= GENMASK(MAX_ORDER - 1, 0);
+	order_mask &= GENMASK(MAX_ORDER, 0);
 	if (!order_mask)
 		return NULL;
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 586271b8aa39..85790b870877 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2440,8 +2440,8 @@ static bool its_parse_indirect_baser(struct its_node *its,
 	 * feature is not supported by hardware.
 	 */
 	new_order = max_t(u32, get_order(esz << ids), new_order);
-	if (new_order >= MAX_ORDER) {
-		new_order = MAX_ORDER - 1;
+	if (new_order > MAX_ORDER) {
+		new_order = MAX_ORDER;
 		ids = ilog2(PAGE_ORDER_TO_SIZE(new_order) / (int)esz);
 		pr_warn("ITS@%pa: %s Table too large, reduce ids %llu->%u\n",
 			&its->phys_base, its_base_type_string[type],
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index cf077f9b30c3..733053c2eaa0 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -408,7 +408,7 @@ static void __cache_size_refresh(void)
  * If the allocation may fail we use __get_free_pages. Memory fragmentation
  * won't have a fatal effect here, but it just causes flushes of some other
  * buffers and more I/O will be performed. Don't use __get_free_pages if it
- * always fails (i.e. order >= MAX_ORDER).
+ * always fails (i.e. order > MAX_ORDER).
  *
  * If the allocation shouldn't fail we use __vmalloc. This is only for the
  * initial reserve allocation, so there's no risk of wasting all vmalloc
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index d0e27438a73c..55fc5b80e649 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -443,7 +443,7 @@ static int genwqe_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (vsize == 0)
 		return -EINVAL;
 
-	if (get_order(vsize) >= MAX_ORDER)
+	if (get_order(vsize) > MAX_ORDER)
 		return -ENOMEM;
 
 	dma_map = kzalloc(sizeof(struct dma_mapping), GFP_KERNEL);
diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
index ac29698d085a..1c798d6b2dfb 100644
--- a/drivers/misc/genwqe/card_utils.c
+++ b/drivers/misc/genwqe/card_utils.c
@@ -210,7 +210,7 @@ u32 genwqe_crc32(u8 *buff, size_t len, u32 init)
 void *__genwqe_alloc_consistent(struct genwqe_dev *cd, size_t size,
 			       dma_addr_t *dma_handle)
 {
-	if (get_order(size) >= MAX_ORDER)
+	if (get_order(size) > MAX_ORDER)
 		return NULL;
 
 	return dma_alloc_coherent(&cd->pci_dev->dev, size, dma_handle,
@@ -308,7 +308,7 @@ int genwqe_alloc_sync_sgl(struct genwqe_dev *cd, struct genwqe_sgl *sgl,
 	sgl->write = write;
 	sgl->sgl_size = genwqe_sgl_size(sgl->nr_pages);
 
-	if (get_order(sgl->sgl_size) >= MAX_ORDER) {
+	if (get_order(sgl->sgl_size) > MAX_ORDER) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: too much memory requested!\n", __func__);
 		return ret;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 25be7f8ac7cd..3973ca6adf4c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1041,7 +1041,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 		return;
 
 	order = get_order(alloc_size);
-	if (order >= MAX_ORDER) {
+	if (order > MAX_ORDER) {
 		if (net_ratelimit())
 			dev_warn(ring_to_dev(ring), "failed to allocate tx spare buffer, exceed to max order\n");
 		return;
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index b35c9b6f913b..4e18b4cefa97 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -75,7 +75,7 @@
  * pool for the 4MB. Thus the 16 Rx and Tx queues require 32 * 5 = 160
  * plus 16 for the TSO pools for a total of 176 LTB mappings per VNIC.
  */
-#define IBMVNIC_ONE_LTB_MAX	((u32)((1 << (MAX_ORDER - 1)) * PAGE_SIZE))
+#define IBMVNIC_ONE_LTB_MAX	((u32)((1 << MAX_ORDER) * PAGE_SIZE))
 #define IBMVNIC_ONE_LTB_SIZE	min((u32)(8 << 20), IBMVNIC_ONE_LTB_MAX)
 #define IBMVNIC_LTB_SET_SIZE	(38 << 20)
 
diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index ec3f6cf05f8c..34781dec3856 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -946,7 +946,7 @@ static phys_addr_t hvfb_get_phymem(struct hv_device *hdev,
 	if (request_size == 0)
 		return -1;
 
-	if (order < MAX_ORDER) {
+	if (order <= MAX_ORDER) {
 		/* Call alloc_pages if the size is less than 2^MAX_ORDER */
 		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (!page)
@@ -977,7 +977,7 @@ static void hvfb_release_phymem(struct hv_device *hdev,
 {
 	unsigned int order = get_order(size);
 
-	if (order < MAX_ORDER)
+	if (order <= MAX_ORDER)
 		__free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order);
 	else
 		dma_free_coherent(&hdev->device,
diff --git a/drivers/video/fbdev/vermilion/vermilion.c b/drivers/video/fbdev/vermilion/vermilion.c
index 0374ee6b6d03..32e74e02a02f 100644
--- a/drivers/video/fbdev/vermilion/vermilion.c
+++ b/drivers/video/fbdev/vermilion/vermilion.c
@@ -197,7 +197,7 @@ static int vmlfb_alloc_vram(struct vml_info *vinfo,
 		va = &vinfo->vram[i];
 		order = 0;
 
-		while (requested > (PAGE_SIZE << order) && order < MAX_ORDER)
+		while (requested > (PAGE_SIZE << order) && order <= MAX_ORDER)
 			order++;
 
 		err = vmlfb_alloc_vram_area(va, order, 0);
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 3f78a3a1eb75..5b15936a5214 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -33,7 +33,7 @@
 #define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \
 					     __GFP_NOMEMALLOC)
 /* The order of free page blocks to report to host */
-#define VIRTIO_BALLOON_HINT_BLOCK_ORDER (MAX_ORDER - 1)
+#define VIRTIO_BALLOON_HINT_BLOCK_ORDER MAX_ORDER
 /* The size of a free page block in bytes */
 #define VIRTIO_BALLOON_HINT_BLOCK_BYTES \
 	(1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT))
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 0c2892ec6817..835f6cc2fb66 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -1120,13 +1120,13 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn,
  */
 static void virtio_mem_fake_online(unsigned long pfn, unsigned long nr_pages)
 {
-	unsigned long order = MAX_ORDER - 1;
+	unsigned long order = MAX_ORDER;
 	unsigned long i;
 
 	/*
 	 * We might get called for ranges that don't cover properly aligned
-	 * MAX_ORDER - 1 pages; however, we can only online properly aligned
-	 * pages with an order of MAX_ORDER - 1 at maximum.
+	 * MAX_ORDER pages; however, we can only online properly aligned
+	 * pages with an order of MAX_ORDER at maximum.
 	 */
 	while (!IS_ALIGNED(pfn | nr_pages, 1 << order))
 		order--;
@@ -1237,9 +1237,9 @@ static void virtio_mem_online_page(struct virtio_mem *vm,
 	bool do_online;
 
 	/*
-	 * We can get called with any order up to MAX_ORDER - 1. If our
-	 * subblock size is smaller than that and we have a mixture of plugged
-	 * and unplugged subblocks within such a page, we have to process in
+	 * We can get called with any order up to MAX_ORDER. If our subblock
+	 * size is smaller than that and we have a mixture of plugged and
+	 * unplugged subblocks within such a page, we have to process in
 	 * smaller granularity. In that case we'll adjust the order exactly once
 	 * within the loop.
 	 */