From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id A1668C433DB for ; Thu, 21 Jan 2021 12:28:52 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 1B673239D1 for ; Thu, 21 Jan 2021 12:28:52 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 1B673239D1 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 8E3706B0005; Thu, 21 Jan 2021 07:28:51 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 86CA16B0010; Thu, 21 Jan 2021 07:28:51 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 6BFB06B0012; Thu, 21 Jan 2021 07:28:51 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0197.hostedemail.com [216.40.44.197]) by kanga.kvack.org (Postfix) with ESMTP id 4F55A6B0005 for ; Thu, 21 Jan 2021 07:28:51 -0500 (EST) Received: from smtpin14.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay01.hostedemail.com (Postfix) with ESMTP id 11CDB180AD80F for ; Thu, 21 Jan 2021 12:28:51 +0000 (UTC) X-FDA: 77729711262.14.burn52_53093a727563 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin14.hostedemail.com (Postfix) with ESMTP id E80E318229835 for ; Thu, 21 Jan 2021 12:28:50 +0000 (UTC) X-HE-Tag: burn52_53093a727563 X-Filterd-Recvd-Size: 12910 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by imf47.hostedemail.com (Postfix) with ESMTP for ; Thu, 21 Jan 2021 12:28:50 +0000 (UTC) Received: by mail.kernel.org (Postfix) with ESMTPSA id 9461D23A00; Thu, 21 Jan 2021 12:28:39 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1611232129; bh=9kaVLl7ns6FDXpeBythPZbgRKr2kk8KbnqpQJU19OBs=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=HnqgRuO0LOTHyk6g9Xvq1dFVel9zw9hTm8TQQVORwQic36aIup+MTwSMASfaZvf1o IEVGsxlFFfJ65h/VpDsDNUHorY/gwoZOvTmr7B36D636ZdGudu7wXdmB3XNRwCa0w1 yWknpajjb73468E9zw++w3gkPg1xIeyETOKKeBNAPQ/iW/LpD27xTsgv7XdF0grw6r SZy1m6Uc8YAsXF0lpWvbcgmVHRd+k5NH3LaiggM4EEbBfKral7IAsyFX9dzOsF9xuN Y+oCaINMAuMtRU4hpKXeGa3Vjc+OoGxWaIa434FZ0xh8Anc0Or/4E8XXyIF7/dkAaz klUi9VNgb9kWQ== From: Mike Rapoport To: Andrew Morton Cc: Alexander Viro , Andy Lutomirski , Arnd Bergmann , Borislav Petkov , Catalin Marinas , Christopher Lameter , Dan Williams , Dave Hansen , David Hildenbrand , Elena Reshetova , "H. Peter Anvin" , Ingo Molnar , James Bottomley , "Kirill A. Shutemov" , Matthew Wilcox , Mark Rutland , Mike Rapoport , Mike Rapoport , Michael Kerrisk , Palmer Dabbelt , Paul Walmsley , Peter Zijlstra , Rick Edgecombe , Roman Gushchin , Shakeel Butt , Shuah Khan , Thomas Gleixner , Tycho Andersen , Will Deacon , linux-api@vger.kernel.org, linux-arch@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-kselftest@vger.kernel.org, linux-nvdimm@lists.01.org, linux-riscv@lists.infradead.org, x86@kernel.org, Hagen Paul Pfeifer , Palmer Dabbelt Subject: [PATCH v16 07/11] secretmem: use PMD-size pages to amortize direct map fragmentation Date: Thu, 21 Jan 2021 14:27:19 +0200 Message-Id: <20210121122723.3446-8-rppt@kernel.org> X-Mailer: git-send-email 2.28.0 In-Reply-To: <20210121122723.3446-1-rppt@kernel.org> References: <20210121122723.3446-1-rppt@kernel.org> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: Mike Rapoport 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. As pages allocated by secretmem become unmovable, use CMA to back large page caches so that page allocator won't be surprised by failing attempt = to migrate these pages. The CMA area used by secretmem is controlled by the "secretmem=3D" kernel parameter. This allows explicit control over the memory available for secretmem and provides upper hard limit for secretmem consumption. Signed-off-by: Mike Rapoport Cc: Alexander Viro Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christopher Lameter Cc: Dan Williams Cc: Dave Hansen Cc: David Hildenbrand Cc: Elena Reshetova Cc: Hagen Paul Pfeifer Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Bottomley Cc: "Kirill A. Shutemov" Cc: Mark Rutland Cc: Matthew Wilcox Cc: Michael Kerrisk Cc: Palmer Dabbelt Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Rick Edgecombe Cc: Roman Gushchin Cc: Shakeel Butt Cc: Shuah Khan Cc: Thomas Gleixner Cc: Tycho Andersen Cc: Will Deacon --- mm/Kconfig | 2 + mm/secretmem.c | 175 +++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 150 insertions(+), 27 deletions(-) diff --git a/mm/Kconfig b/mm/Kconfig index 5f8243442f66..ec35bf406439 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -874,5 +874,7 @@ config KMAP_LOCAL =20 config SECRETMEM def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED + select GENERIC_ALLOCATOR + select CMA =20 endmenu diff --git a/mm/secretmem.c b/mm/secretmem.c index 904351d12c33..469211c7cc3a 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -7,12 +7,15 @@ =20 #include #include +#include #include #include #include #include #include +#include #include +#include #include #include #include @@ -35,24 +38,94 @@ #define SECRETMEM_FLAGS_MASK SECRETMEM_MODE_MASK =20 struct secretmem_ctx { + struct gen_pool *pool; unsigned int mode; }; =20 -static struct page *secretmem_alloc_page(gfp_t gfp) +static struct cma *secretmem_cma; + +static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp) { + unsigned long nr_pages =3D (1 << PMD_PAGE_ORDER); + struct gen_pool *pool =3D ctx->pool; + unsigned long addr; + struct page *page; + int i, err; + + page =3D cma_alloc(secretmem_cma, nr_pages, PMD_SIZE, gfp & __GFP_NOWAR= N); + if (!page) + return -ENOMEM; + /* - * FIXME: use a cache of large pages to reduce the direct map - * fragmentation + * clear the data left from the prevoius user before dropping the + * pages from the direct map */ - return alloc_page(gfp | __GFP_ZERO); + for (i =3D 0; i < nr_pages; i++) + clear_highpage(page + i); + + err =3D set_direct_map_invalid_noflush(page, nr_pages); + if (err) + goto err_cma_release; + + addr =3D (unsigned long)page_address(page); + err =3D gen_pool_add(pool, addr, PMD_SIZE, NUMA_NO_NODE); + if (err) + goto err_set_direct_map; + + flush_tlb_kernel_range(addr, addr + PMD_SIZE); + + return 0; + +err_set_direct_map: + /* + * If a split of PUD-size page was required, it already happened + * when we marked the pages invalid which guarantees that this call + * won't fail + */ + set_direct_map_default_noflush(page, nr_pages); +err_cma_release: + cma_release(secretmem_cma, page, nr_pages); + return err; +} + +static void secretmem_free_page(struct secretmem_ctx *ctx, struct page *= page) +{ + unsigned long addr =3D (unsigned long)page_address(page); + struct gen_pool *pool =3D ctx->pool; + + gen_pool_free(pool, addr, PAGE_SIZE); +} + +static struct page *secretmem_alloc_page(struct secretmem_ctx *ctx, + gfp_t gfp) +{ + struct gen_pool *pool =3D ctx->pool; + unsigned long addr; + struct page *page; + int err; + + if (gen_pool_avail(pool) < PAGE_SIZE) { + err =3D secretmem_pool_increase(ctx, gfp); + if (err) + return NULL; + } + + addr =3D gen_pool_alloc(pool, PAGE_SIZE); + if (!addr) + return NULL; + + page =3D virt_to_page(addr); + get_page(page); + + return page; } =20 static vm_fault_t secretmem_fault(struct vm_fault *vmf) { + struct secretmem_ctx *ctx =3D vmf->vma->vm_file->private_data; struct address_space *mapping =3D vmf->vma->vm_file->f_mapping; struct inode *inode =3D file_inode(vmf->vma->vm_file); pgoff_t offset =3D vmf->pgoff; - unsigned long addr; struct page *page; int err; =20 @@ -62,40 +135,25 @@ static vm_fault_t secretmem_fault(struct vm_fault *v= mf) retry: page =3D find_lock_page(mapping, offset); if (!page) { - page =3D secretmem_alloc_page(vmf->gfp_mask); + page =3D secretmem_alloc_page(ctx, vmf->gfp_mask); if (!page) return VM_FAULT_OOM; =20 - err =3D set_direct_map_invalid_noflush(page, 1); - if (err) { - put_page(page); - return vmf_error(err); - } - __SetPageUptodate(page); err =3D add_to_page_cache(page, mapping, offset, vmf->gfp_mask); if (unlikely(err)) { + secretmem_free_page(ctx, page); put_page(page); if (err =3D=3D -EEXIST) goto retry; - goto err_restore_direct_map; + return vmf_error(err); } =20 - addr =3D (unsigned long)page_address(page); - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + set_page_private(page, (unsigned long)ctx); } =20 vmf->page =3D page; return VM_FAULT_LOCKED; - -err_restore_direct_map: - /* - * If a split of large page was required, it already happened - * when we marked the page invalid which guarantees that this call - * won't fail - */ - set_direct_map_default_noflush(page, 1); - return vmf_error(err); } =20 static const struct vm_operations_struct secretmem_vm_ops =3D { @@ -141,8 +199,9 @@ static int secretmem_migratepage(struct address_space= *mapping, =20 static void secretmem_freepage(struct page *page) { - set_direct_map_default_noflush(page, 1); - clear_highpage(page); + struct secretmem_ctx *ctx =3D (struct secretmem_ctx *)page_private(page= ); + + secretmem_free_page(ctx, page); } =20 static const struct address_space_operations secretmem_aops =3D { @@ -177,13 +236,18 @@ static struct file *secretmem_file_create(unsigned = long flags) if (!ctx) goto err_free_inode; =20 + ctx->pool =3D gen_pool_create(PAGE_SHIFT, NUMA_NO_NODE); + if (!ctx->pool) + goto err_free_ctx; + file =3D alloc_file_pseudo(inode, secretmem_mnt, "secretmem", O_RDWR, &secretmem_fops); if (IS_ERR(file)) - goto err_free_ctx; + goto err_free_pool; =20 mapping_set_unevictable(inode->i_mapping); =20 + inode->i_private =3D ctx; inode->i_mapping->private_data =3D ctx; inode->i_mapping->a_ops =3D &secretmem_aops; =20 @@ -197,6 +261,8 @@ static struct file *secretmem_file_create(unsigned lo= ng flags) =20 return file; =20 +err_free_pool: + gen_pool_destroy(ctx->pool); err_free_ctx: kfree(ctx); err_free_inode: @@ -215,6 +281,9 @@ SYSCALL_DEFINE1(memfd_secret, unsigned long, flags) if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC)) return -EINVAL; =20 + if (!secretmem_cma) + return -ENOMEM; + fd =3D get_unused_fd_flags(flags & O_CLOEXEC); if (fd < 0) return fd; @@ -235,11 +304,37 @@ SYSCALL_DEFINE1(memfd_secret, unsigned long, flags) return err; } =20 +static void secretmem_cleanup_chunk(struct gen_pool *pool, + struct gen_pool_chunk *chunk, void *data) +{ + unsigned long start =3D chunk->start_addr; + unsigned long end =3D chunk->end_addr; + struct page *page =3D virt_to_page(start); + unsigned long nr_pages =3D (end - start + 1) / PAGE_SIZE; + int i; + + set_direct_map_default_noflush(page, nr_pages); + + for (i =3D 0; i < nr_pages; i++) + clear_highpage(page + i); + + cma_release(secretmem_cma, page, nr_pages); +} + +static void secretmem_cleanup_pool(struct secretmem_ctx *ctx) +{ + struct gen_pool *pool =3D 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 =3D inode->i_private; =20 truncate_inode_pages_final(&inode->i_data); + secretmem_cleanup_pool(ctx); clear_inode(inode); kfree(ctx); } @@ -276,3 +371,29 @@ static int secretmem_init(void) return ret; } fs_initcall(secretmem_init); + +static int __init secretmem_setup(char *str) +{ + phys_addr_t align =3D PMD_SIZE; + unsigned long reserved_size; + int err; + + reserved_size =3D memparse(str, NULL); + if (!reserved_size) + return 0; + + if (reserved_size * 2 > PUD_SIZE) + align =3D PUD_SIZE; + + err =3D cma_declare_contiguous(0, reserved_size, 0, align, 0, false, + "secretmem", &secretmem_cma); + if (err) { + pr_err("failed to create CMA: %d\n", err); + return err; + } + + pr_info("reserved %luM\n", reserved_size >> 20); + + return 0; +} +__setup("secretmem=3D", secretmem_setup); --=20 2.28.0