Linux-api Archive on lore.kernel.org
 help / color / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
	Andrew Morton <akpm@linux-foundation.org>,
	Andy Lutomirski <luto@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
	Borislav Petkov <bp@alien8.de>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Christopher Lameter <cl@linux.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Elena Reshetova <elena.reshetova@intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>, Idan Yaniv <idan.yaniv@ibm.com>,
	Ingo Molnar <mingo@redhat.com>,
	James Bottomley <jejb@linux.ibm.com>,
	"Kirill A. Shutemov" <kirill@shutemov.name>,
	Matthew Wilcox <willy@infradead.org>,
	Mike Rapoport <rppt@linux.ibm.com>,
	Mike Rapoport <rppt@kernel.org>,
	Michael Kerrisk <mtk.manpages@gmail.com>,
	Palmer Dabbelt <palmer@dabbelt.com>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Tycho Andersen <tycho@tycho.ws>, Will Deacon <will@kernel.org>,
	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-nvdimm@lists.01.org, linux-riscv@lists.infradead.org,
	x86@kernel.org
Subject: [PATCH v2 6/7] mm: secretmem: add ability to reserve memory at boot
Date: Mon, 27 Jul 2020 19:29:34 +0300
Message-ID: <20200727162935.31714-7-rppt@kernel.org> (raw)
In-Reply-To: <20200727162935.31714-1-rppt@kernel.org>

From: Mike Rapoport <rppt@linux.ibm.com>

Taking pages out from the direct map and bringing them back may create
undesired fragmentation and usage of the smaller pages in the direct
mapping of the physical memory.

This can be avoided if a significantly large area of the physical memory
would be reserved for secretmem purposes at boot time.

Add ability to reserve physical memory for secretmem at boot time using
"secretmem" kernel parameter and then use that reserved memory as a global
pool for secret memory needs.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
 mm/secretmem.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 126 insertions(+), 8 deletions(-)

diff --git a/mm/secretmem.c b/mm/secretmem.c
index da609701e10e..35616e3982a4 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -8,6 +8,7 @@
 #include <linux/pagemap.h>
 #include <linux/genalloc.h>
 #include <linux/syscalls.h>
+#include <linux/memblock.h>
 #include <linux/pseudo_fs.h>
 #include <linux/set_memory.h>
 #include <linux/sched/signal.h>
@@ -30,6 +31,39 @@ struct secretmem_ctx {
 	unsigned int mode;
 };
 
+struct secretmem_pool {
+	struct gen_pool *pool;
+	unsigned long reserved_size;
+	void *reserved;
+};
+
+static struct secretmem_pool secretmem_pool;
+
+static struct page *secretmem_alloc_huge_page(gfp_t gfp)
+{
+	struct gen_pool *pool = secretmem_pool.pool;
+	unsigned long addr = 0;
+	struct page *page = NULL;
+
+	if (pool) {
+		if (gen_pool_avail(pool) < PMD_SIZE)
+			return NULL;
+
+		addr = gen_pool_alloc(pool, PMD_SIZE);
+		if (!addr)
+			return NULL;
+
+		page = virt_to_page(addr);
+	} else {
+		page = alloc_pages(gfp, PMD_PAGE_ORDER);
+
+		if (page)
+			split_page(page, PMD_PAGE_ORDER);
+	}
+
+	return page;
+}
+
 static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
 {
 	unsigned long nr_pages = (1 << PMD_PAGE_ORDER);
@@ -38,12 +72,11 @@ static int secretmem_pool_increase(struct secretmem_ctx *ctx, gfp_t gfp)
 	struct page *page;
 	int err;
 
-	page = alloc_pages(gfp, PMD_PAGE_ORDER);
+	page = secretmem_alloc_huge_page(gfp);
 	if (!page)
 		return -ENOMEM;
 
 	addr = (unsigned long)page_address(page);
-	split_page(page, PMD_PAGE_ORDER);
 
 	err = gen_pool_add(pool, addr, PMD_SIZE, NUMA_NO_NODE);
 	if (err) {
@@ -269,11 +302,13 @@ 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)
+static void secretmem_recycle_range(unsigned long start, unsigned long end)
+{
+	gen_pool_free(secretmem_pool.pool, start, PMD_SIZE);
+}
+
+static void secretmem_release_range(unsigned long start, unsigned long end)
 {
-	unsigned long start = chunk->start_addr;
-	unsigned long end = chunk->end_addr;
 	unsigned long nr_pages, addr;
 
 	nr_pages = (end - start + 1) / PAGE_SIZE;
@@ -283,6 +318,18 @@ static void secretmem_cleanup_chunk(struct gen_pool *pool,
 		put_page(virt_to_page(addr));
 }
 
+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;
+
+	if (secretmem_pool.pool)
+		secretmem_recycle_range(start, end);
+	else
+		secretmem_release_range(start, end);
+}
+
 static void secretmem_cleanup_pool(struct secretmem_ctx *ctx)
 {
 	struct gen_pool *pool = ctx->pool;
@@ -322,14 +369,85 @@ static struct file_system_type secretmem_fs = {
 	.kill_sb	= kill_anon_super,
 };
 
+static int secretmem_reserved_mem_init(void)
+{
+	struct gen_pool *pool;
+	struct page *page;
+	void *addr;
+	int err;
+
+	if (!secretmem_pool.reserved)
+		return 0;
+
+	pool = gen_pool_create(PMD_SHIFT, NUMA_NO_NODE);
+	if (!pool)
+		return -ENOMEM;
+
+	err = gen_pool_add(pool, (unsigned long)secretmem_pool.reserved,
+			   secretmem_pool.reserved_size, NUMA_NO_NODE);
+	if (err)
+		goto err_destroy_pool;
+
+	for (addr = secretmem_pool.reserved;
+	     addr < secretmem_pool.reserved + secretmem_pool.reserved_size;
+	     addr += PAGE_SIZE) {
+		page = virt_to_page(addr);
+		__ClearPageReserved(page);
+		set_page_count(page, 1);
+	}
+
+	secretmem_pool.pool = pool;
+	page = virt_to_page(secretmem_pool.reserved);
+	__kernel_map_pages(page, secretmem_pool.reserved_size / PAGE_SIZE, 0);
+	return 0;
+
+err_destroy_pool:
+	gen_pool_destroy(pool);
+	return err;
+}
+
 static int secretmem_init(void)
 {
-	int ret = 0;
+	int ret;
+
+	ret = secretmem_reserved_mem_init();
+	if (ret)
+		return ret;
 
 	secretmem_mnt = kern_mount(&secretmem_fs);
-	if (IS_ERR(secretmem_mnt))
+	if (IS_ERR(secretmem_mnt)) {
+		gen_pool_destroy(secretmem_pool.pool);
 		ret = PTR_ERR(secretmem_mnt);
+	}
 
 	return ret;
 }
 fs_initcall(secretmem_init);
+
+static int __init secretmem_setup(char *str)
+{
+	phys_addr_t align = PMD_SIZE;
+	unsigned long reserved_size;
+	void *reserved;
+
+	reserved_size = memparse(str, NULL);
+	if (!reserved_size)
+		return 0;
+
+	if (reserved_size * 2 > PUD_SIZE)
+		align = PUD_SIZE;
+
+	reserved = memblock_alloc(reserved_size, align);
+	if (!reserved) {
+		pr_err("failed to reserve %lu bytes\n", secretmem_pool.reserved_size);
+		return 0;
+	}
+
+	secretmem_pool.reserved_size = reserved_size;
+	secretmem_pool.reserved = reserved;
+
+	pr_info("reserved %luM\n", reserved_size >> 20);
+
+	return 1;
+}
+__setup("secretmem=", secretmem_setup);
-- 
2.26.2


  parent reply index

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-27 16:29 [PATCH v2 0/7] mm: introduce memfd_secret system call to create "secret" memory areas Mike Rapoport
2020-07-27 16:29 ` [PATCH v2 1/7] mm: add definition of PMD_PAGE_ORDER Mike Rapoport
2020-07-27 16:29 ` [PATCH v2 2/7] mmap: make mlock_future_check() global Mike Rapoport
2020-07-27 16:29 ` [PATCH v2 3/7] mm: introduce memfd_secret system call to create "secret" memory areas Mike Rapoport
2020-07-30 16:22   ` Catalin Marinas
2020-07-30 20:44     ` Mike Rapoport
2020-07-31 14:10       ` Catalin Marinas
2020-07-31 14:29     ` Mark Rutland
2020-07-31 16:22       ` Catalin Marinas
2020-07-27 16:29 ` [PATCH v2 4/7] arch, mm: wire up memfd_secret system call were relevant Mike Rapoport
2020-07-27 17:25   ` Arnd Bergmann
2020-07-27 16:29 ` [PATCH v2 5/7] mm: secretmem: use PMD-size pages to amortize direct map fragmentation Mike Rapoport
2020-07-27 16:29 ` Mike Rapoport [this message]
2020-07-27 16:29 ` [PATCH v2 7/7] mm: secretmem: add ability to reserve memory at boot Mike Rapoport
2020-07-27 17:11   ` Mike Rapoport

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200727162935.31714-7-rppt@kernel.org \
    --to=rppt@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=catalin.marinas@arm.com \
    --cc=cl@linux.com \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=elena.reshetova@intel.com \
    --cc=hpa@zytor.com \
    --cc=idan.yaniv@ibm.com \
    --cc=jejb@linux.ibm.com \
    --cc=kirill@shutemov.name \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-riscv@lists.infradead.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=mtk.manpages@gmail.com \
    --cc=palmer@dabbelt.com \
    --cc=paul.walmsley@sifive.com \
    --cc=peterz@infradead.org \
    --cc=rppt@linux.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=tycho@tycho.ws \
    --cc=viro@zeniv.linux.org.uk \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-api Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-api/0 linux-api/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-api linux-api/ https://lore.kernel.org/linux-api \
		linux-api@vger.kernel.org
	public-inbox-index linux-api

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-api


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git