mm/vmalloc: Hugepage vmalloc mappings

ascend inclusion
category: feature
bugzilla: NA
CVE: NA

https://lwn.net/ml/linux-kernel/20200825145753.529284-12-npiggin@gmail.com/

Don't distinction between vmalloc and hugepage vmalloc, because there is no size
print in alloc_large_system_hash in v4.19.

And this patch add page_order in vm_struct, it will break kabi.
--------------

Support huge page vmalloc mappings. Config option HAVE_ARCH_HUGE_VMALLOC
enables support on architectures that define HAVE_ARCH_HUGE_VMAP and
supports PMD sized vmap mappings.

vmalloc will attempt to allocate PMD-sized pages if allocating PMD size or
larger, and fall back to small pages if that was unsuccessful.

Allocations that do not use PAGE_KERNEL prot are not permitted to use huge
pages, because not all callers expect this (e.g., module allocations vs
strict module rwx).

This reduces TLB misses by nearly 30x on a `git diff` workload on a 2-node
POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%.

This can result in more internal fragmentation and memory overhead for a
given allocation, an option nohugevmalloc is added to disable at boot.
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NRui Xiang <rui.xiang@huawei.com>
Reviewed-by: NDing Tianhong <dingtianhong@huawei.com>
Reviewed-by: NZefan Li <lizefan@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

arch/Kconfig

@@ -528,6 +528,10 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 config HAVE_ARCH_HUGE_VMAP
 	bool
 
+config HAVE_ARCH_HUGE_VMALLOC
+	depends on HAVE_ARCH_HUGE_VMAP
+	bool
+
 config HAVE_ARCH_SOFT_DIRTY
 	bool
 

include/linux/vmalloc.h

@@ -39,6 +39,7 @@ struct vm_struct {
 	unsigned long		size;
 	unsigned long		flags;
 	struct page		**pages;
+	unsigned int		page_order;
 	unsigned int		nr_pages;
 	phys_addr_t		phys_addr;
 	const void		*caller;

mm/vmalloc.c

@@ -41,6 +41,19 @@
 
 #include "internal.h"
 
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+static bool __ro_after_init vmap_allow_huge = true;
+
+static int __init set_nohugevmalloc(char *str)
+{
+	vmap_allow_huge = false;
+	return 0;
+}
+early_param("nohugevmalloc", set_nohugevmalloc);
+#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+static const bool vmap_allow_huge = false;
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+
 struct vfree_deferred {
 	struct llist_head list;
 	struct work_struct wq;
@@ -410,6 +423,61 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
 	return 0;
 }
 
+static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	int err = 0;
+	int nr = 0;
+
+	BUG_ON(addr >= end);
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr);
+		if (err)
+			return err;
+	} while (pgd++, addr = next, addr != end);
+
+	return 0;
+}
+
+static int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+	unsigned int i, nr = (end - addr) >> PAGE_SHIFT;
+
+	WARN_ON(page_shift < PAGE_SHIFT);
+
+	if (page_shift == PAGE_SHIFT)
+		return vmap_small_pages_range_noflush(addr, end, prot, pages);
+
+	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
+		int err;
+
+		err = vmap_range_noflush(addr, addr + (1UL << page_shift),
+					__pa(page_address(pages[i])), prot,
+					page_shift);
+		if (err)
+			return err;
+
+		addr += 1UL << page_shift;
+	}
+
+	return 0;
+}
+
+static int vmap_pages_range(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+	int err;
+
+	err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
+	flush_cache_vmap(addr, end);
+	return err;
+}
+
 /**
  * map_kernel_range_noflush - map kernel VM area with the specified pages
  * @addr: start of the VM area to map
@@ -431,22 +499,7 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
 int map_kernel_range_noflush(unsigned long addr, unsigned long size,
 			     pgprot_t prot, struct page **pages)
 {
-	unsigned long end = addr + size;
-	unsigned long next;
-	pgd_t *pgd;
-	int err = 0;
-	int nr = 0;
-
-	BUG_ON(addr >= end);
-	pgd = pgd_offset_k(addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr);
-		if (err)
-			return err;
-	} while (pgd++, addr = next, addr != end);
-
-	return 0;
+	return vmap_pages_range_noflush(addr, addr + size, prot, pages, PAGE_SHIFT);
 }
 
 int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
@@ -2270,11 +2323,11 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	if (deallocate_pages) {
 		int i;
 
-		for (i = 0; i < area->nr_pages; i++) {
+		for (i = 0; i < area->nr_pages; i += 1U << area->page_order) {
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
-			__free_pages(page, 0);
+			__free_pages(page, area->page_order);
 		}
 
 		kvfree(area->pages);
@@ -2403,9 +2456,12 @@ static void *__vmalloc_node(unsigned long size, unsigned long align,
 			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, const void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
-				 pgprot_t prot, int node)
+				 pgprot_t prot, unsigned int page_shift, int node)
 {
 	struct page **pages;
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long size = get_vm_area_size(area);
+	unsigned int page_order = page_shift - PAGE_SHIFT;
 	unsigned int nr_pages, array_size, i;
 	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
 	const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
@@ -2413,7 +2469,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 					0 :
 					__GFP_HIGHMEM;
 
-	nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
+	nr_pages = size >> PAGE_SHIFT;
 	array_size = (nr_pages * sizeof(struct page *));
 
 	/* Please note that the recursion is strictly bounded. */
@@ -2432,27 +2488,27 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 	area->pages = pages;
 	area->nr_pages = nr_pages;
+	area->page_order = page_order;
 
-	for (i = 0; i < area->nr_pages; i++) {
+	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
 		struct page *page;
+		int p;
 
-		if (node == NUMA_NO_NODE)
-			page = alloc_page(alloc_mask|highmem_mask);
-		else
-			page = alloc_pages_node(node, alloc_mask|highmem_mask, 0);
-
+		page = alloc_pages_node(node, alloc_mask|highmem_mask, page_order);
 		if (unlikely(!page)) {
 			/* Successfully allocated i pages, free them in __vunmap() */
 			area->nr_pages = i;
 			goto fail;
 		}
-		area->pages[i] = page;
+
+		for (p = 0; p < (1U << page_order); p++)
+			area->pages[i + p] = page + p;
+
 		if (gfpflags_allow_blocking(gfp_mask|highmem_mask))
 			cond_resched();
 	}
 
-	if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area),
-			prot, pages) < 0)
+	if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0)
 		goto fail;
 
 	return area->addr;
@@ -2460,7 +2516,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 fail:
 	warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure, allocated %ld of %ld bytes",
-			  (area->nr_pages*PAGE_SIZE), area->size);
+			  (area->nr_pages*PAGE_SIZE), size);
 	vfree(area->addr);
 	return NULL;
 }
@@ -2489,19 +2545,42 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	struct vm_struct *area;
 	void *addr;
 	unsigned long real_size = size;
+	unsigned long real_align = align;
+	unsigned int shift = PAGE_SHIFT;
 
-	size = PAGE_ALIGN(size);
 	if (!size || (size >> PAGE_SHIFT) > totalram_pages)
 		goto fail;
 
+	if (vmap_allow_huge && (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))) {
+		unsigned long size_per_node;
+
+		/*
+		 * Try huge pages. Only try for PAGE_KERNEL allocations,
+		 * others like modules don't yet expect huge pages in
+		 * their allocations due to apply_to_page_range not
+		 * supporting them.
+		 */
+
+		size_per_node = size;
+		if (node == NUMA_NO_NODE)
+			size_per_node /= num_online_nodes();
+		if (size_per_node >= PMD_SIZE) {
+			shift = PMD_SHIFT;
+			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);
 	if (!area)
 		goto fail;
 
-	addr = __vmalloc_area_node(area, gfp_mask, prot, node);
+	addr = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
 	if (!addr)
-		return NULL;
+		goto fail;
 
 	/*
 	 * First make sure the mappings are removed from all page-tables
@@ -2521,8 +2600,19 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	return addr;
 
 fail:
-	warn_alloc(gfp_mask, NULL,
+	if (shift > PAGE_SHIFT) {
+		free_vm_area(area);
+		shift = PAGE_SHIFT;
+		align = real_align;
+		size = real_size;
+		goto again;
+	}
+
+	if (!area) {
+		/* Warn for area allocation, page allocations already warn */
+		warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure: %lu bytes", real_size);
+	}
 	return NULL;
 }
 
@@ -3501,7 +3591,7 @@ static int s_show(struct seq_file *m, void *p)
 		seq_printf(m, " %pS", v->caller);
 
 	if (v->nr_pages)
-		seq_printf(m, " pages=%d", v->nr_pages);
+		seq_printf(m, " pages=%d order=%d", v->nr_pages, v->page_order);
 
 	if (v->phys_addr)
 		seq_printf(m, " phys=%pa", &v->phys_addr);