1 files changed, 134 insertions, 65 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a13ac524f6ff..d5cd52805149 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -25,6 +25,7 @@
 #include <linux/notifier.h>
 #include <linux/rbtree.h>
 #include <linux/xarray.h>
+#include <linux/io.h>
 #include <linux/rcupdate.h>
 #include <linux/pfn.h>
 #include <linux/kmemleak.h>
@@ -36,6 +37,7 @@
 #include <linux/overflow.h>
 #include <linux/pgtable.h>
 #include <linux/uaccess.h>
+#include <linux/hugetlb.h>
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
@@ -83,10 +85,11 @@ static void free_work(struct work_struct *w)
 /*** Page table manipulation functions ***/
 static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			phys_addr_t phys_addr, pgprot_t prot,
-			pgtbl_mod_mask *mask)
+			unsigned int max_page_shift, pgtbl_mod_mask *mask)
 {
 	pte_t *pte;
 	u64 pfn;
+	unsigned long size = PAGE_SIZE;
 
 	pfn = phys_addr >> PAGE_SHIFT;
 	pte = pte_alloc_kernel_track(pmd, addr, mask);
@@ -94,9 +97,22 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		return -ENOMEM;
 	do {
 		BUG_ON(!pte_none(*pte));
+
+#ifdef CONFIG_HUGETLB_PAGE
+		size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift);
+		if (size != PAGE_SIZE) {
+			pte_t entry = pfn_pte(pfn, prot);
+
+			entry = pte_mkhuge(entry);
+			entry = arch_make_huge_pte(entry, ilog2(size), 0);
+			set_huge_pte_at(&init_mm, addr, pte, entry);
+			pfn += PFN_DOWN(size);
+			continue;
+		}
+#endif
 		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
 		pfn++;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+	} while (pte += PFN_DOWN(size), addr += size, addr != end);
 	*mask |= PGTBL_PTE_MODIFIED;
 	return 0;
 }
@@ -145,7 +161,7 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 			continue;
 		}
 
-		if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
+		if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask))
 			return -ENOMEM;
 	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
 	return 0;
@@ -1592,6 +1608,7 @@ static DEFINE_MUTEX(vmap_purge_lock);
 /* for per-CPU blocks */
 static void purge_fragmented_blocks_allcpus(void);
 
+#ifdef CONFIG_X86_64
 /*
  * called before a call to iounmap() if the caller wants vm_area_struct's
  * immediately freed.
@@ -1600,6 +1617,7 @@ void set_iounmap_nonlazy(void)
 {
 	atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1);
 }
+#endif /* CONFIG_X86_64 */
 
 /*
  * Purges all lazily-freed vmap areas.
@@ -2344,15 +2362,16 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm)
 }
 
 static struct vm_struct *__get_vm_area_node(unsigned long size,
-		unsigned long align, unsigned long flags, unsigned long start,
-		unsigned long end, int node, gfp_t gfp_mask, const void *caller)
+		unsigned long align, unsigned long shift, unsigned long flags,
+		unsigned long start, unsigned long end, int node,
+		gfp_t gfp_mask, const void *caller)
 {
 	struct vmap_area *va;
 	struct vm_struct *area;
 	unsigned long requested_size = size;
 
 	BUG_ON(in_interrupt());
-	size = PAGE_ALIGN(size);
+	size = ALIGN(size, 1ul << shift);
 	if (unlikely(!size))
 		return NULL;
 
@@ -2384,8 +2403,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
 				       unsigned long start, unsigned long end,
 				       const void *caller)
 {
-	return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
-				  GFP_KERNEL, caller);
+	return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end,
+				  NUMA_NO_NODE, GFP_KERNEL, caller);
 }
 
 /**
@@ -2401,7 +2420,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
  */
 struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
 {
-	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
+	return __get_vm_area_node(size, 1, PAGE_SHIFT, flags,
+				  VMALLOC_START, VMALLOC_END,
 				  NUMA_NO_NODE, GFP_KERNEL,
 				  __builtin_return_address(0));
 }
@@ -2409,7 +2429,8 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
 struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
 				const void *caller)
 {
-	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
+	return __get_vm_area_node(size, 1, PAGE_SHIFT, flags,
+				  VMALLOC_START, VMALLOC_END,
 				  NUMA_NO_NODE, GFP_KERNEL, caller);
 }
 
@@ -2564,6 +2585,7 @@ static void __vunmap(const void *addr, int deallocate_pages)
 
 			BUG_ON(!page);
 			__free_pages(page, page_order);
+			cond_resched();
 		}
 		atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
 
@@ -2755,6 +2777,54 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
 EXPORT_SYMBOL_GPL(vmap_pfn);
 #endif /* CONFIG_VMAP_PFN */
 
+static inline unsigned int
+vm_area_alloc_pages(gfp_t gfp, int nid,
+		unsigned int order, unsigned long nr_pages, struct page **pages)
+{
+	unsigned int nr_allocated = 0;
+
+	/*
+	 * For order-0 pages we make use of bulk allocator, if
+	 * the page array is partly or not at all populated due
+	 * to fails, fallback to a single page allocator that is
+	 * more permissive.
+	 */
+	if (!order)
+		nr_allocated = alloc_pages_bulk_array_node(
+			gfp, nid, nr_pages, pages);
+	else
+		/*
+		 * Compound pages required for remap_vmalloc_page if
+		 * high-order pages.
+		 */
+		gfp |= __GFP_COMP;
+
+	/* High-order pages or fallback path if "bulk" fails. */
+	while (nr_allocated < nr_pages) {
+		struct page *page;
+		int i;
+
+		page = alloc_pages_node(nid, gfp, order);
+		if (unlikely(!page))
+			break;
+
+		/*
+		 * Careful, we allocate and map page-order pages, but
+		 * tracking is done per PAGE_SIZE page so as to keep the
+		 * vm_struct APIs independent of the physical/mapped size.
+		 */
+		for (i = 0; i < (1U << order); i++)
+			pages[nr_allocated + i] = page + i;
+
+		if (gfpflags_allow_blocking(gfp))
+			cond_resched();
+
+		nr_allocated += 1U << order;
+	}
+
+	return nr_allocated;
+}
+
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, unsigned int page_shift,
 				 int node)
@@ -2765,8 +2835,6 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	unsigned long array_size;
 	unsigned int nr_small_pages = size >> PAGE_SHIFT;
 	unsigned int page_order;
-	struct page **pages;
-	unsigned int i;
 
 	array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
 	gfp_mask |= __GFP_NOWARN;
@@ -2775,62 +2843,44 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 	/* Please note that the recursion is strictly bounded. */
 	if (array_size > PAGE_SIZE) {
-		pages = __vmalloc_node(array_size, 1, nested_gfp, node,
+		area->pages = __vmalloc_node(array_size, 1, nested_gfp, node,
 					area->caller);
 	} else {
-		pages = kmalloc_node(array_size, nested_gfp, node);
+		area->pages = kmalloc_node(array_size, nested_gfp, node);
 	}
 
-	if (!pages) {
-		free_vm_area(area);
+	if (!area->pages) {
 		warn_alloc(gfp_mask, NULL,
-			   "vmalloc size %lu allocation failure: "
-			   "page array size %lu allocation failed",
-			   nr_small_pages * PAGE_SIZE, array_size);
+			"vmalloc error: size %lu, failed to allocated page array size %lu",
+			nr_small_pages * PAGE_SIZE, array_size);
+		free_vm_area(area);
 		return NULL;
 	}
 
-	area->pages = pages;
-	area->nr_pages = nr_small_pages;
 	set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
-
 	page_order = vm_area_page_order(area);
 
-	/*
-	 * Careful, we allocate and map page_order pages, but tracking is done
-	 * per PAGE_SIZE page so as to keep the vm_struct APIs independent of
-	 * the physical/mapped size.
-	 */
-	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
-		struct page *page;
-		int p;
-
-		/* Compound pages required for remap_vmalloc_page */
-		page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order);
-		if (unlikely(!page)) {
-			/* Successfully allocated i pages, free them in __vfree() */
-			area->nr_pages = i;
-			atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
-			warn_alloc(gfp_mask, NULL,
-				   "vmalloc size %lu allocation failure: "
-				   "page order %u allocation failed",
-				   area->nr_pages * PAGE_SIZE, page_order);
-			goto fail;
-		}
+	area->nr_pages = vm_area_alloc_pages(gfp_mask, node,
+		page_order, nr_small_pages, area->pages);
 
-		for (p = 0; p < (1U << page_order); p++)
-			area->pages[i + p] = page + p;
+	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 
-		if (gfpflags_allow_blocking(gfp_mask))
-			cond_resched();
+	/*
+	 * If not enough pages were obtained to accomplish an
+	 * allocation request, free them via __vfree() if any.
+	 */
+	if (area->nr_pages != nr_small_pages) {
+		warn_alloc(gfp_mask, NULL,
+			"vmalloc error: size %lu, page order %u, failed to allocate pages",
+			area->nr_pages * PAGE_SIZE, page_order);
+		goto fail;
 	}
-	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 
-	if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0) {
+	if (vmap_pages_range(addr, addr + size, prot, area->pages,
+			page_shift) < 0) {
 		warn_alloc(gfp_mask, NULL,
-			   "vmalloc size %lu allocation failure: "
-			   "failed to map pages",
-			   area->nr_pages * PAGE_SIZE);
+			"vmalloc error: size %lu, failed to map pages",
+			area->nr_pages * PAGE_SIZE);
 		goto fail;
 	}
 
@@ -2875,13 +2925,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 
 	if ((size >> PAGE_SHIFT) > totalram_pages()) {
 		warn_alloc(gfp_mask, NULL,
-			   "vmalloc size %lu allocation failure: "
-			   "exceeds total pages", real_size);
+			"vmalloc error: size %lu, exceeds total pages",
+			real_size);
 		return NULL;
 	}
 
-	if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) &&
-			arch_vmap_pmd_supported(prot)) {
+	if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP)) {
 		unsigned long size_per_node;
 
 		/*
@@ -2894,21 +2943,23 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 		size_per_node = size;
 		if (node == NUMA_NO_NODE)
 			size_per_node /= num_online_nodes();
-		if (size_per_node >= PMD_SIZE) {
+		if (arch_vmap_pmd_supported(prot) && size_per_node >= PMD_SIZE)
 			shift = PMD_SHIFT;
-			align = max(real_align, 1UL << shift);
-			size = ALIGN(real_size, 1UL << shift);
-		}
+		else
+			shift = arch_vmap_pte_supported_shift(size_per_node);
+
+		align = max(real_align, 1UL << shift);
+		size = ALIGN(real_size, 1UL << shift);
 	}
 
 again:
-	size = PAGE_ALIGN(size);
-	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
-				vm_flags, start, end, node, gfp_mask, caller);
+	area = __get_vm_area_node(real_size, align, shift, VM_ALLOC |
+				  VM_UNINITIALIZED | vm_flags, start, end, node,
+				  gfp_mask, caller);
 	if (!area) {
 		warn_alloc(gfp_mask, NULL,
-			   "vmalloc size %lu allocation failure: "
-			   "vm_struct allocation failed", real_size);
+			"vmalloc error: size %lu, vm_struct allocation failed",
+			real_size);
 		goto fail;
 	}
 
@@ -2923,6 +2974,7 @@ again:
 	 */
 	clear_vm_uninitialized_flag(area);
 
+	size = PAGE_ALIGN(size);
 	kmemleak_vmalloc(area, size, gfp_mask);
 
 	return addr;
@@ -2999,6 +3051,23 @@ void *vmalloc(unsigned long size)
 EXPORT_SYMBOL(vmalloc);
 
 /**
+ * vmalloc_no_huge - allocate virtually contiguous memory using small pages
+ * @size:    allocation size
+ *
+ * Allocate enough non-huge pages to cover @size from the page level
+ * allocator and map them into contiguous kernel virtual space.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+void *vmalloc_no_huge(unsigned long size)
+{
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+				    GFP_KERNEL, PAGE_KERNEL, VM_NO_HUGE_VMAP,
+				    NUMA_NO_NODE, __builtin_return_address(0));
+}
+EXPORT_SYMBOL(vmalloc_no_huge);
+
+/**
  * vzalloc - allocate virtually contiguous memory with zero fill
  * @size:    allocation size
  *