// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 1993  Linus Torvalds
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
 *  Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002
 *  Numa awareness, Christoph Lameter, SGI, June 2005
 *  Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019
 */
/*
 * Linux v6.18, mm/vmalloc.c:3678-3789
 * Source: https://github.com/torvalds/linux/blob/v6.18/mm/vmalloc.c
 * Complete function: __vmalloc_area_node
 * Body unchanged. Kernel dependencies are not bundled.
 * License text: GPL-2.0.txt
 */

static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
				 pgprot_t prot, unsigned int page_shift,
				 int node)
{
	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
	bool nofail = gfp_mask & __GFP_NOFAIL;
	unsigned long addr = (unsigned long)area->addr;
	unsigned long size = get_vm_area_size(area);
	unsigned long array_size;
	unsigned int nr_small_pages = size >> PAGE_SHIFT;
	unsigned int page_order;
	unsigned int flags;
	int ret;

	array_size = (unsigned long)nr_small_pages * sizeof(struct page *);

	if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
		gfp_mask |= __GFP_HIGHMEM;

	/* Please note that the recursion is strictly bounded. */
	if (array_size > PAGE_SIZE) {
		area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node,
					area->caller);
	} else {
		area->pages = kmalloc_node_noprof(array_size, nested_gfp, node);
	}

	if (!area->pages) {
		warn_alloc(gfp_mask, NULL,
			"vmalloc error: size %lu, failed to allocated page array size %lu",
			nr_small_pages * PAGE_SIZE, array_size);
		free_vm_area(area);
		return NULL;
	}

	set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
	page_order = vm_area_page_order(area);

	/*
	 * High-order nofail allocations are really expensive and
	 * potentially dangerous (pre-mature OOM, disruptive reclaim
	 * and compaction etc.
	 *
	 * Please note, the __vmalloc_node_range_noprof() falls-back
	 * to order-0 pages if high-order attempt is unsuccessful.
	 */
	area->nr_pages = vm_area_alloc_pages((page_order ?
		gfp_mask & ~__GFP_NOFAIL : gfp_mask) | __GFP_NOWARN,
		node, page_order, nr_small_pages, area->pages);

	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
	/* All pages of vm should be charged to same memcg, so use first one. */
	if (gfp_mask & __GFP_ACCOUNT && area->nr_pages)
		mod_memcg_page_state(area->pages[0], MEMCG_VMALLOC,
				     area->nr_pages);

	/*
	 * If not enough pages were obtained to accomplish an
	 * allocation request, free them via vfree() if any.
	 */
	if (area->nr_pages != nr_small_pages) {
		/*
		 * vm_area_alloc_pages() can fail due to insufficient memory but
		 * also:-
		 *
		 * - a pending fatal signal
		 * - insufficient huge page-order pages
		 *
		 * Since we always retry allocations at order-0 in the huge page
		 * case a warning for either is spurious.
		 */
		if (!fatal_signal_pending(current) && page_order == 0)
			warn_alloc(gfp_mask, NULL,
				"vmalloc error: size %lu, failed to allocate pages",
				area->nr_pages * PAGE_SIZE);
		goto fail;
	}

	/*
	 * page tables allocations ignore external gfp mask, enforce it
	 * by the scope API
	 */
	if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
		flags = memalloc_nofs_save();
	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
		flags = memalloc_noio_save();

	do {
		ret = vmap_pages_range(addr, addr + size, prot, area->pages,
			page_shift);
		if (nofail && (ret < 0))
			schedule_timeout_uninterruptible(1);
	} while (nofail && (ret < 0));

	if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
		memalloc_nofs_restore(flags);
	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
		memalloc_noio_restore(flags);

	if (ret < 0) {
		warn_alloc(gfp_mask, NULL,
			"vmalloc error: size %lu, failed to map pages",
			area->nr_pages * PAGE_SIZE);
		goto fail;
	}

	return area->addr;

fail:
	vfree(area->addr);
	return NULL;
}