Linux-RISC-V Archive on lore.kernel.org
 help / color / Atom feed
From: Mike Rapoport <rppt@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	linux-mm@kvack.org, "H. Peter Anvin" <hpa@zytor.com>,
	Christopher Lameter <cl@linux.com>,
	Idan Yaniv <idan.yaniv@ibm.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Elena Reshetova <elena.reshetova@intel.com>,
	linux-arch@vger.kernel.org, Tycho Andersen <tycho@tycho.ws>,
	linux-nvdimm@lists.01.org, Will Deacon <will@kernel.org>,
	x86@kernel.org, Matthew Wilcox <willy@infradead.org>,
	Mike Rapoport <rppt@linux.ibm.com>,
	Ingo Molnar <mingo@redhat.com>, Arnd Bergmann <arnd@arndb.de>,
	James Bottomley <jejb@linux.ibm.com>,
	Borislav Petkov <bp@alien8.de>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Andy Lutomirski <luto@kernel.org>,
	Paul Walmsley <paul.walmsley@sifive.com>,
	"Kirill A. Shutemov" <kirill@shutemov.name>,
	Thomas Gleixner <tglx@linutronix.de>,
	linux-arm-kernel@lists.infradead.org, linux-api@vger.kernel.org,
	linux-riscv@lists.infradead.org,
	Palmer Dabbelt <palmer@dabbelt.com>,
	linux-fsdevel@vger.kernel.org,
	Andrew Morton <akpm@linux-foundation.org>,
	Mike Rapoport <rppt@kernel.org>
Subject: [PATCH 3/6] mm: introduce secretmemfd system call to create "secret" memory areas
Date: Mon, 20 Jul 2020 12:24:32 +0300
Message-ID: <20200720092435.17469-4-rppt@kernel.org> (raw)
In-Reply-To: <20200720092435.17469-1-rppt@kernel.org>

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

Introduce "secretmemfd" system call with the ability to create memory areas
visible only in the context of the owning process and not mapped not only
to other processes but in the kernel page tables as well.

The user will create a file descriptor using the secretmemfd system call
where flags supplied as a parameter to this system call will define the
desired protection mode for the memory associated with that file
descriptor. Currently there are two protection modes:

* exclusive - the memory area is unmapped from the kernel direct map and it
              is present only in the page tables of the owning mm.
* uncached  - the memory area is present only in the page tables of the
              owning mm and it is mapped there as uncached.

For instance, the following example will create an uncached mapping (error
handling is omitted):

	fd = secretmemfd(SECRETMEM_UNCACHED);
	ftruncate(fd, MAP_SIZE);
	ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED,
		   fd, 0);

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
 include/uapi/linux/magic.h     |   1 +
 include/uapi/linux/secretmem.h |   9 ++
 mm/Kconfig                     |   4 +
 mm/Makefile                    |   1 +
 mm/secretmem.c                 | 263 +++++++++++++++++++++++++++++++++
 5 files changed, 278 insertions(+)
 create mode 100644 include/uapi/linux/secretmem.h
 create mode 100644 mm/secretmem.c

diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index f3956fc11de6..35687dcb1a42 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -97,5 +97,6 @@
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define Z3FOLD_MAGIC		0x33
 #define PPC_CMM_MAGIC		0xc7571590
+#define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/include/uapi/linux/secretmem.h b/include/uapi/linux/secretmem.h
new file mode 100644
index 000000000000..cef7a59f7492
--- /dev/null
+++ b/include/uapi/linux/secretmem.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SECRERTMEM_H
+#define _UAPI_LINUX_SECRERTMEM_H
+
+/* secretmem operation modes */
+#define SECRETMEM_EXCLUSIVE	0x1
+#define SECRETMEM_UNCACHED	0x2
+
+#endif /* _UAPI_LINUX_SECRERTMEM_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index f2104cc0d35c..c5aa948214f9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -872,4 +872,8 @@ config ARCH_HAS_HUGEPD
 config MAPPING_DIRTY_HELPERS
         bool
 
+config SECRETMEM
+        def_bool ARCH_HAS_SET_DIRECT_MAP
+	select GENERIC_ALLOCATOR
+
 endmenu
diff --git a/mm/Makefile b/mm/Makefile
index 6e9d46b2efc9..c2aa7a393b73 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -121,3 +121,4 @@ obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
 obj-$(CONFIG_PTDUMP_CORE) += ptdump.o
 obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
+obj-$(CONFIG_SECRETMEM) += secretmem.o
diff --git a/mm/secretmem.c b/mm/secretmem.c
new file mode 100644
index 000000000000..2f65219baf80
--- /dev/null
+++ b/mm/secretmem.c
@@ -0,0 +1,263 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/memfd.h>
+#include <linux/bitops.h>
+#include <linux/printk.h>
+#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/pseudo_fs.h>
+#include <linux/set_memory.h>
+#include <linux/sched/signal.h>
+
+#include <uapi/linux/secretmem.h>
+#include <uapi/linux/magic.h>
+
+#include <asm/tlbflush.h>
+
+#include "internal.h"
+
+#undef pr_fmt
+#define pr_fmt(fmt) "secretmem: " fmt
+
+#define SECRETMEM_MODE_MASK	(SECRETMEM_EXCLUSIVE | SECRETMEM_UNCACHED)
+#define SECRETMEM_FLAGS_MASK	SECRETMEM_MODE_MASK
+
+struct secretmem_ctx {
+	unsigned int mode;
+};
+
+static struct page *secretmem_alloc_page(gfp_t gfp)
+{
+	/*
+	 * FIXME: use a cache of large pages to reduce the direct map
+	 * fragmentation
+	 */
+	return alloc_page(gfp);
+}
+
+static vm_fault_t secretmem_fault(struct vm_fault *vmf)
+{
+	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;
+
+	if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
+		return vmf_error(-EINVAL);
+
+	page = find_get_entry(mapping, offset);
+	if (!page) {
+		page = secretmem_alloc_page(vmf->gfp_mask);
+		if (!page)
+			return vmf_error(-ENOMEM);
+
+		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);
+		if (ret)
+			goto err_del_page_cache;
+
+		addr = (unsigned long)page_address(page);
+		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+		__SetPageUptodate(page);
+
+		ret = VM_FAULT_LOCKED;
+	}
+
+	vmf->page = page;
+	return ret;
+
+err_del_page_cache:
+	delete_from_page_cache(page);
+err_put_page:
+	put_page(page);
+	return vmf_error(ret);
+}
+
+static const struct vm_operations_struct secretmem_vm_ops = {
+	.fault = secretmem_fault,
+};
+
+static int secretmem_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct secretmem_ctx *ctx = file->private_data;
+	unsigned long mode = ctx->mode;
+	unsigned long len = vma->vm_end - vma->vm_start;
+
+	if (!mode)
+		return -EINVAL;
+
+	if (mlock_future_check(vma->vm_mm, vma->vm_flags | VM_LOCKED, len))
+		return -EAGAIN;
+
+	switch (mode) {
+	case SECRETMEM_UNCACHED:
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+		fallthrough;
+	case SECRETMEM_EXCLUSIVE:
+		vma->vm_ops = &secretmem_vm_ops;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	vma->vm_flags |= VM_LOCKED;
+
+	return 0;
+}
+
+const struct file_operations secretmem_fops = {
+	.mmap		= secretmem_mmap,
+};
+
+static bool secretmem_isolate_page(struct page *page, isolate_mode_t mode)
+{
+	return false;
+}
+
+static int secretmem_migratepage(struct address_space *mapping,
+				 struct page *newpage, struct page *page,
+				 enum migrate_mode mode)
+{
+	return -EBUSY;
+}
+
+static void secretmem_freepage(struct page *page)
+{
+	set_direct_map_default_noflush(page);
+}
+
+static const struct address_space_operations secretmem_aops = {
+	.freepage	= secretmem_freepage,
+	.migratepage	= secretmem_migratepage,
+	.isolate_page	= secretmem_isolate_page,
+};
+
+static struct vfsmount *secretmem_mnt;
+
+static struct file *secretmem_file_create(unsigned long flags)
+{
+	struct file *file = ERR_PTR(-ENOMEM);
+	struct secretmem_ctx *ctx;
+	struct inode *inode;
+
+	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		goto err_free_inode;
+
+	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
+				 O_RDWR, &secretmem_fops);
+	if (IS_ERR(file))
+		goto err_free_ctx;
+
+	mapping_set_unevictable(inode->i_mapping);
+
+	inode->i_mapping->private_data = ctx;
+	inode->i_mapping->a_ops = &secretmem_aops;
+
+	/* pretend we are a normal file with zero size */
+	inode->i_mode |= S_IFREG;
+	inode->i_size = 0;
+
+	file->private_data = ctx;
+
+	ctx->mode = flags & SECRETMEM_MODE_MASK;
+
+	return file;
+
+err_free_ctx:
+	kfree(ctx);
+err_free_inode:
+	iput(inode);
+	return file;
+}
+
+SYSCALL_DEFINE1(secretmemfd, unsigned long, flags)
+{
+	struct file *file;
+	unsigned int mode;
+	int fd, err;
+
+	/* make sure local flags do not confict with global fcntl.h */
+	BUILD_BUG_ON(SECRETMEM_FLAGS_MASK & O_CLOEXEC);
+
+	if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC))
+		return -EINVAL;
+
+	/* modes are mutually exclusive, only one mode bit should be set */
+	mode = flags & SECRETMEM_FLAGS_MASK;
+	if (ffs(mode) != fls(mode))
+		return -EINVAL;
+
+	fd = get_unused_fd_flags(flags & O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	file = secretmem_file_create(flags);
+	if (IS_ERR(file)) {
+		err = PTR_ERR(file);
+		goto err_put_fd;
+	}
+
+	file->f_flags |= O_LARGEFILE;
+
+	fd_install(fd, file);
+	return fd;
+
+err_put_fd:
+	put_unused_fd(fd);
+	return err;
+}
+
+static void secretmem_evict_inode(struct inode *inode)
+{
+	struct secretmem_ctx *ctx = inode->i_private;
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+	kfree(ctx);
+}
+
+static const struct super_operations secretmem_super_ops = {
+	.evict_inode = secretmem_evict_inode,
+};
+
+static int secretmem_init_fs_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx = init_pseudo(fc, SECRETMEM_MAGIC);
+
+	if (!ctx)
+		return -ENOMEM;
+	ctx->ops = &secretmem_super_ops;
+
+	return 0;
+}
+
+static struct file_system_type secretmem_fs = {
+	.name		= "secretmem",
+	.init_fs_context = secretmem_init_fs_context,
+	.kill_sb	= kill_anon_super,
+};
+
+static int secretmem_init(void)
+{
+	int ret = 0;
+
+	secretmem_mnt = kern_mount(&secretmem_fs);
+	if (IS_ERR(secretmem_mnt))
+		ret = PTR_ERR(secretmem_mnt);
+
+	return ret;
+}
+fs_initcall(secretmem_init);
-- 
2.26.2


_______________________________________________
linux-riscv mailing list
linux-riscv@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-riscv

  parent reply index

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-20  9:24 [PATCH 0/6] " Mike Rapoport
2020-07-20  9:24 ` [PATCH 1/6] mm: add definition of PMD_PAGE_ORDER Mike Rapoport
2020-07-20  9:24 ` [PATCH 2/6] mmap: make mlock_future_check() global Mike Rapoport
2020-07-20  9:24 ` Mike Rapoport [this message]
2020-07-20 11:30   ` [PATCH 3/6] mm: introduce secretmemfd system call to create "secret" memory areas Arnd Bergmann
2020-07-20 14:20     ` Mike Rapoport
2020-07-20 14:34       ` Arnd Bergmann
2020-07-20 17:46         ` Mike Rapoport
2020-07-20 15:51     ` James Bottomley
2020-07-20 18:08       ` Arnd Bergmann
2020-07-20 19:16         ` James Bottomley
2020-07-20 20:05           ` Arnd Bergmann
2020-07-21 10:59   ` Michael Kerrisk (man-pages)
2020-07-20  9:24 ` [PATCH 4/6] arch, mm: wire up secretmemfd system call were relevant Mike Rapoport
2020-07-26 17:44   ` Palmer Dabbelt
2020-07-20  9:24 ` [PATCH 5/6] mm: secretmem: use PMD-size pages to amortize direct map fragmentation Mike Rapoport
2020-07-20  9:24 ` [PATCH 6/6] mm: secretmem: add ability to reserve memory at boot 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=20200720092435.17469-4-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=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-RISC-V Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-riscv/0 linux-riscv/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-riscv linux-riscv/ https://lore.kernel.org/linux-riscv \
		linux-riscv@lists.infradead.org
	public-inbox-index linux-riscv

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.infradead.lists.linux-riscv


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