[PATCH v7 6/7] mm: secretmem: use PMD-size pages to amortize direct map fragmentation

[Mike Rapoport]

From: Mike Rapoport <rppt@xxxxxxxxxxxxx>

Removing a PAGE_SIZE page from the direct map every time such page is
allocated for a secret memory mapping will cause severe fragmentation of
the direct map. This fragmentation can be reduced by using PMD-size pages
as a pool for small pages for secret memory mappings.

Add a gen_pool per secretmem inode and lazily populate this pool with
PMD-size pages.

Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxx>
---
 mm/secretmem.c | 124 ++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 107 insertions(+), 17 deletions(-)

diff --git a/mm/secretmem.c b/mm/secretmem.c
index 2a63db2ed132..4f9e07d212be 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -12,8 +12,10 @@
 #include <linux/bitops.h>
 #include <linux/printk.h>
 #include <linux/pagemap.h>
+#include <linux/genalloc.h>
 #include <linux/syscalls.h>
 #include <linux/pseudo_fs.h>
+#include <linux/memcontrol.h>
 #include <linux/set_memory.h>
 #include <linux/sched/signal.h>
 
@@ -40,24 +42,80 @@
 #define SECRETMEM_FLAGS_MASK	SECRETMEM_MODE_MASK
 
 struct secretmem_ctx {
+	struct gen_pool *pool;
 	unsigned int mode;
 };
 
-static struct page *secretmem_alloc_page(gfp_t gfp)
+static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
 {
+	unsigned long nr_pages = (1 << PMD_PAGE_ORDER);
+	struct gen_pool *pool = ctx->pool;
+	unsigned long addr;
+	struct page *page;
+	int err;
+
+	page = alloc_pages(gfp | __GFP_ACCOUNT, PMD_PAGE_ORDER);
+	if (!page)
+		return -ENOMEM;
+
+	addr = (unsigned long)page_address(page);
+
+	err = set_direct_map_invalid_noflush(page, nr_pages);
+	if (err)
+		goto err_free_pages;
+
+	err = gen_pool_add(pool, addr, PMD_SIZE, NUMA_NO_NODE);
+	if (err)
+		goto err_set_direct_map;
+
+	split_page(page, PMD_PAGE_ORDER);
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+
+	return 0;
+
+err_set_direct_map:
 	/*
-	 * FIXME: use a cache of large pages to reduce the direct map
-	 * fragmentation
+	 * If a split of PUD-size page was required, it already happened
+	 * when we made the pages invalid which guarantees that this call
+	 * won't fail
 	 */
-	return alloc_page(gfp);
+	set_direct_map_default_noflush(page, nr_pages);
+
+err_free_pages:
+	__free_pages(page, PMD_PAGE_ORDER);
+	return err;
+}
+
+static struct page *secretmem_alloc_page(struct secretmem_ctx *ctx,
+					 gfp_t gfp)
+{
+	struct gen_pool *pool = ctx->pool;
+	unsigned long addr;
+	struct page *page;
+	int err;
+
+	if (gen_pool_avail(pool) < PAGE_SIZE) {
+		err = secretmem_pool_increase(ctx, gfp);
+		if (err)
+			return NULL;
+	}
+
+	addr = gen_pool_alloc(pool, PAGE_SIZE);
+	if (!addr)
+		return NULL;
+
+	page = virt_to_page(addr);
+	get_page(page);
+
+	return page;
 }
 
 static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 {
+	struct secretmem_ctx *ctx = vmf->vma->vm_file->private_data;
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	pgoff_t offset = vmf->pgoff;
-	unsigned long addr;
 	struct page *page;
 	int ret = 0;
 
@@ -66,22 +124,22 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 
 	page = find_get_entry(mapping, offset);
 	if (!page) {
-		page = secretmem_alloc_page(vmf->gfp_mask);
+		page = secretmem_alloc_page(ctx, vmf->gfp_mask);
 		if (!page)
 			return vmf_error(-ENOMEM);
 
+		/*
+		 * add_to_page_cache() calls mem_cgroup_charge(), so we
+		 * need to uncharge here to avoid double accounting
+		 */
+		memcg_kmem_uncharge_page(page, 0);
+
 		ret = add_to_page_cache(page, mapping, offset, vmf->gfp_mask);
 		if (unlikely(ret))
 			goto err_put_page;
 
-		ret = set_direct_map_invalid_noflush(page, 1);
-		if (ret)
-			goto err_del_page_cache;
-
-		addr = (unsigned long)page_address(page);
-		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
-
 		__SetPageUptodate(page);
+		set_page_private(page, (unsigned long)ctx);
 
 		ret = VM_FAULT_LOCKED;
 	}
@@ -89,8 +147,6 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
 	vmf->page = page;
 	return ret;
 
-err_del_page_cache:
-	delete_from_page_cache(page);
 err_put_page:
 	put_page(page);
 	return vmf_error(ret);
@@ -143,7 +199,11 @@ static int secretmem_migratepage(struct address_space *mapping,
 
 static void secretmem_freepage(struct page *page)
 {
-	set_direct_map_default_noflush(page, 1);
+	unsigned long addr = (unsigned long)page_address(page);
+	struct secretmem_ctx *ctx = (struct secretmem_ctx *)page_private(page);
+	struct gen_pool *pool = ctx->pool;
+
+	gen_pool_free(pool, addr, PAGE_SIZE);
 }
 
 static const struct address_space_operations secretmem_aops = {
@@ -178,13 +238,18 @@ static struct file *secretmem_file_create(unsigned long flags)
 	if (!ctx)
 		goto err_free_inode;
 
+	ctx->pool = gen_pool_create(PAGE_SHIFT, NUMA_NO_NODE);
+	if (!ctx->pool)
+		goto err_free_ctx;
+
 	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
 				 O_RDWR, &secretmem_fops);
 	if (IS_ERR(file))
-		goto err_free_ctx;
+		goto err_free_pool;
 
 	mapping_set_unevictable(inode->i_mapping);
 
+	inode->i_private = ctx;
 	inode->i_mapping->private_data = ctx;
 	inode->i_mapping->a_ops = &secretmem_aops;
 
@@ -198,6 +263,8 @@ static struct file *secretmem_file_create(unsigned long flags)
 
 	return file;
 
+err_free_pool:
+	gen_pool_destroy(ctx->pool);
 err_free_ctx:
 	kfree(ctx);
 err_free_inode:
@@ -236,11 +303,34 @@ SYSCALL_DEFINE1(memfd_secret, unsigned long, flags)
 	return err;
 }
 
+static void secretmem_cleanup_chunk(struct gen_pool *pool,
+				    struct gen_pool_chunk *chunk, void *data)
+{
+	unsigned long start = chunk->start_addr;
+	unsigned long end = chunk->end_addr;
+	unsigned long nr_pages, addr;
+
+	nr_pages = (end - start + 1) / PAGE_SIZE;
+	__kernel_map_pages(virt_to_page(start), nr_pages, 1);
+
+	for (addr = start; addr < end; addr += PAGE_SIZE)
+		put_page(virt_to_page(addr));
+}
+
+static void secretmem_cleanup_pool(struct secretmem_ctx *ctx)
+{
+	struct gen_pool *pool = ctx->pool;
+
+	gen_pool_for_each_chunk(pool, secretmem_cleanup_chunk, ctx);
+	gen_pool_destroy(pool);
+}
+
 static void secretmem_evict_inode(struct inode *inode)
 {
 	struct secretmem_ctx *ctx = inode->i_private;
 
 	truncate_inode_pages_final(&inode->i_data);
+	secretmem_cleanup_pool(ctx);
 	clear_inode(inode);
 	kfree(ctx);
 }
-- 
2.28.0