mm/cma: refuse handing out non-contiguous page ranges

Let's disallow handing out PFN ranges with non-contiguous pages, so we can
remove the nth-page usage in __cma_alloc(), and so any callers don't have
to worry about that either when wanting to blindly iterate pages.

This is really only a problem in configs with SPARSEMEM but without
SPARSEMEM_VMEMMAP, and only when we would cross memory sections in some
cases.

Will this cause harm? Probably not, because it's mostly 32bit that does
not support SPARSEMEM_VMEMMAP. If this ever becomes a problem we could
look into allocating the memmap for the memory sections spanned by a
single CMA region in one go from memblock.

[[e-mail]: we can have NUMMU configs with SPARSEMEM enabled]
Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: David Hildenbrand <[e-mail]>
Reviewed-by: Alexandru Elisei <[e-mail]>
Reviewed-by: Lorenzo Stoakes <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

include/linux/mm.h

···
 extern unsigned long sysctl_admin_reserve_kbytes;
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+bool page_range_contiguous(const struct page *page, unsigned long nr_pages);
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 #else
 #define nth_page(page,n) ((page) + (n))
+static inline bool page_range_contiguous(const struct page *page,
+		unsigned long nr_pages)
+{
+	return true;
+}
 #endif
 
 /* to align the pointer to the (next) page boundary */

mm/cma.c

···
 				unsigned long count, unsigned int align,
 				struct page **pagep, gfp_t gfp)
 {
-	unsigned long mask, offset;
-	unsigned long pfn = -1;
-	unsigned long start = 0;
 	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
+	unsigned long start, pfn, mask, offset;
 	int ret = -EBUSY;
 	struct page *page = NULL;
 
···
 	if (bitmap_count > bitmap_maxno)
 		goto out;
 
-	for (;;) {
+	for (start = 0; ; start = bitmap_no + mask + 1) {
 		spin_lock_irq(&cma->lock);
 		/*
 		 * If the request is larger than the available number
···
 			spin_unlock_irq(&cma->lock);
 			break;
 		}
+
+		pfn = cmr->base_pfn + (bitmap_no << cma->order_per_bit);
+		page = pfn_to_page(pfn);
+
+		/*
+		 * Do not hand out page ranges that are not contiguous, so
+		 * callers can just iterate the pages without having to worry
+		 * about these corner cases.
+		 */
+		if (!page_range_contiguous(page, count)) {
+			spin_unlock_irq(&cma->lock);
+			pr_warn_ratelimited("%s: %s: skipping incompatible area [0x%lx-0x%lx]",
+					    __func__, cma->name, pfn, pfn + count - 1);
+			continue;
+		}
+
 		bitmap_set(cmr->bitmap, bitmap_no, bitmap_count);
 		cma->available_count -= count;
 		/*
···
 		 */
 		spin_unlock_irq(&cma->lock);
 
-		pfn = cmr->base_pfn + (bitmap_no << cma->order_per_bit);
 		mutex_lock(&cma->alloc_mutex);
 		ret = alloc_contig_range(pfn, pfn + count, ACR_FLAGS_CMA, gfp);
 		mutex_unlock(&cma->alloc_mutex);
-		if (ret == 0) {
-			page = pfn_to_page(pfn);
+		if (!ret)
 			break;
-		}
 
 		cma_clear_bitmap(cma, cmr, pfn, count);
 		if (ret != -EBUSY)
 			break;
 
 		pr_debug("%s(): memory range at pfn 0x%lx %p is busy, retrying\n",
-			 __func__, pfn, pfn_to_page(pfn));
+			 __func__, pfn, page);
 
-		trace_cma_alloc_busy_retry(cma->name, pfn, pfn_to_page(pfn),
-					   count, align);
-		/* try again with a bit different memory target */
-		start = bitmap_no + mask + 1;
+		trace_cma_alloc_busy_retry(cma->name, pfn, page, count, align);
 	}
 out:
-	*pagep = page;
+	if (!ret)
+		*pagep = page;
 	return ret;
 }
 
···
 	 */
 	if (page) {
 		for (i = 0; i < count; i++)
-			page_kasan_tag_reset(nth_page(page, i));
+			page_kasan_tag_reset(page + i);
 	}
 
 	if (ret && !(gfp & __GFP_NOWARN)) {

mm/util.c

···
 	return folio_pte_batch_flags(folio, NULL, ptep, &pte, max_nr, 0);
 }
 #endif /* CONFIG_MMU */
+
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+/**
+ * page_range_contiguous - test whether the page range is contiguous
+ * @page: the start of the page range.
+ * @nr_pages: the number of pages in the range.
+ *
+ * Test whether the page range is contiguous, such that they can be iterated
+ * naively, corresponding to iterating a contiguous PFN range.
+ *
+ * This function should primarily only be used for debug checks, or when
+ * working with page ranges that are not naturally contiguous (e.g., pages
+ * within a folio are).
+ *
+ * Returns true if contiguous, otherwise false.
+ */
+bool page_range_contiguous(const struct page *page, unsigned long nr_pages)
+{
+	const unsigned long start_pfn = page_to_pfn(page);
+	const unsigned long end_pfn = start_pfn + nr_pages;
+	unsigned long pfn;
+
+	/*
+	 * The memmap is allocated per memory section, so no need to check
+	 * within the first section. However, we need to check each other
+	 * spanned memory section once, making sure the first page in a
+	 * section could similarly be reached by just iterating pages.
+	 */
+	for (pfn = ALIGN(start_pfn, PAGES_PER_SECTION);
+	     pfn < end_pfn; pfn += PAGES_PER_SECTION)
+		if (unlikely(page + (pfn - start_pfn) != pfn_to_page(pfn)))
+			return false;
+	return true;
+}
+#endif