Linux-arch Archive on lore.kernel.org
 help / color / Atom feed
From: Yu-cheng Yu <yu-cheng.yu@intel.com>
To: x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>,
	linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
	linux-mm@kvack.org, linux-arch@vger.kernel.org,
	linux-api@vger.kernel.org, Arnd Bergmann <arnd@arndb.de>,
	Andy Lutomirski <luto@kernel.org>,
	Balbir Singh <bsingharora@gmail.com>,
	Borislav Petkov <bp@alien8.de>,
	Cyrill Gorcunov <gorcunov@gmail.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Eugene Syromiatnikov <esyr@redhat.com>,
	Florian Weimer <fweimer@redhat.com>,
	"H.J. Lu" <hjl.tools@gmail.com>, Jann Horn <jannh@google.com>,
	Jonathan Corbet <corbet@lwn.net>,
	Kees Cook <keescook@chromium.org>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Nadav Amit <nadav.amit@gmail.com>,
	Oleg Nesterov <oleg@redhat.com>, Pavel Machek <pavel@ucw.cz>,
	Peter Zijlstra <peterz@infradead.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
	Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com>,
	Dave Martin <Dave.Martin@arm.com>,
	Weijiang Yang <weijiang.yang@intel.com>,
	Pengfei Xu <pengfei.xu@intel.com>
Cc: Yu-cheng Yu <yu-cheng.yu@intel.com>
Subject: [PATCH v14 26/26] mm: Introduce PROT_SHSTK for shadow stack
Date: Mon, 12 Oct 2020 08:38:50 -0700
Message-ID: <20201012153850.26996-27-yu-cheng.yu@intel.com> (raw)
In-Reply-To: <20201012153850.26996-1-yu-cheng.yu@intel.com>

There are three possible options to create a shadow stack allocation API:
an arch_prctl, a new syscall, or adding PROT_SHSTK to mmap()/mprotect().
Each has its advantages and compromises.

An arch_prctl() is the least intrusive.  However, the existing x86
arch_prctl() takes only two parameters.  Multiple parameters must be
passed in a memory buffer.  There is a proposal to pass more parameters in
registers [1], but no active discussion on that.

A new syscall minimizes compatibility issues and offers an extensible frame
work to other architectures, but this will likely result in some overlap of
mmap()/mprotect().

The introduction of PROT_SHSTK to mmap()/mprotect() takes advantage of
existing APIs.  The x86-specific PROT_SHSTK is translated to VM_SHSTK and
a shadow stack mapping is created without reinventing the wheel.  There are
potential pitfalls though.  The most obvious one would be using this as a
bypass to shadow stack protection.  However, the attacker would have to get
to the syscall first.

Since arch_calc_vm_prot_bits() is modified, I have moved arch_vm_get_page
_prot() and arch_calc_vm_prot_bits() to x86/include/asm/mman.h.
This will be more consistent with other architectures.

[1] https://lore.kernel.org/lkml/20200828121624.108243-1-hjl.tools@gmail.com/

Signed-off-by: Yu-cheng Yu <yu-cheng.yu@intel.com>
---
 arch/x86/include/asm/mman.h      | 83 ++++++++++++++++++++++++++++++++
 arch/x86/include/uapi/asm/mman.h | 28 ++---------
 include/linux/mm.h               |  1 +
 mm/mmap.c                        |  8 ++-
 4 files changed, 95 insertions(+), 25 deletions(-)
 create mode 100644 arch/x86/include/asm/mman.h

diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
new file mode 100644
index 000000000000..0dcaef6f889a
--- /dev/null
+++ b/arch/x86/include/asm/mman.h
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_MMAN_H
+#define _ASM_X86_MMAN_H
+
+#include <linux/mm.h>
+#include <uapi/asm/mman.h>
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+/*
+ * Take the 4 protection key bits out of the vma->vm_flags
+ * value and turn them in to the bits that we can put in
+ * to a pte.
+ *
+ * Only override these if Protection Keys are available
+ * (which is only on 64-bit).
+ */
+#define arch_vm_get_page_prot(vm_flags)	__pgprot(	\
+		((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) |	\
+		((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) |	\
+		((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) |	\
+		((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0))
+
+#define pkey_vm_prot_bits(prot, key) (			\
+		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
+		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
+		((key) & 0x4 ? VM_PKEY_BIT2 : 0) |      \
+		((key) & 0x8 ? VM_PKEY_BIT3 : 0))
+#else
+#define pkey_vm_prot_bits(prot, key) (0)
+#endif
+
+static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
+	unsigned long pkey)
+{
+	unsigned long vm_prot_bits = pkey_vm_prot_bits(prot, pkey);
+
+	if (!(prot & PROT_WRITE) && (prot & PROT_SHSTK))
+		vm_prot_bits |= VM_SHSTK;
+
+	return vm_prot_bits;
+}
+#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
+
+#ifdef CONFIG_X86_SHADOW_STACK_USER
+static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
+{
+	unsigned long valid = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM;
+
+	if (prot & ~(valid | PROT_SHSTK))
+		return false;
+
+	if (prot & PROT_SHSTK) {
+		struct vm_area_struct *vma;
+
+		if (!current->thread.cet.shstk_size)
+			return false;
+
+		/*
+		 * A shadow stack mapping is indirectly writable by only
+		 * the CALL and WRUSS instructions, but not other write
+		 * instructions).  PROT_SHSTK and PROT_WRITE are mutually
+		 * exclusive.
+		 */
+		if (prot & PROT_WRITE)
+			return false;
+
+		vma = find_vma(current->mm, addr);
+		if (!vma)
+			return false;
+
+		/*
+		 * Shadow stack cannot be backed by a file or shared.
+		 */
+		if (vma->vm_file || (vma->vm_flags & VM_SHARED))
+			return false;
+	}
+
+	return true;
+}
+#define arch_validate_prot arch_validate_prot
+#endif
+
+#endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/include/uapi/asm/mman.h b/arch/x86/include/uapi/asm/mman.h
index d4a8d0424bfb..39bb7db344a6 100644
--- a/arch/x86/include/uapi/asm/mman.h
+++ b/arch/x86/include/uapi/asm/mman.h
@@ -1,31 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_X86_MMAN_H
-#define _ASM_X86_MMAN_H
+#ifndef _UAPI_ASM_X86_MMAN_H
+#define _UAPI_ASM_X86_MMAN_H
 
 #define MAP_32BIT	0x40		/* only give out 32bit addresses */
 
-#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
-/*
- * Take the 4 protection key bits out of the vma->vm_flags
- * value and turn them in to the bits that we can put in
- * to a pte.
- *
- * Only override these if Protection Keys are available
- * (which is only on 64-bit).
- */
-#define arch_vm_get_page_prot(vm_flags)	__pgprot(	\
-		((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) |	\
-		((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) |	\
-		((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) |	\
-		((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0))
-
-#define arch_calc_vm_prot_bits(prot, key) (		\
-		((key) & 0x1 ? VM_PKEY_BIT0 : 0) |      \
-		((key) & 0x2 ? VM_PKEY_BIT1 : 0) |      \
-		((key) & 0x4 ? VM_PKEY_BIT2 : 0) |      \
-		((key) & 0x8 ? VM_PKEY_BIT3 : 0))
-#endif
+#define PROT_SHSTK	0x10		/* shadow stack pages */
 
 #include <asm-generic/mman.h>
 
-#endif /* _ASM_X86_MMAN_H */
+#endif /* _UAPI_ASM_X86_MMAN_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 71677d498300..203b0ff02e7c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -334,6 +334,7 @@ extern unsigned int kobjsize(const void *objp);
 
 #if defined(CONFIG_X86)
 # define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
+# define VM_ARCH_CLEAR	VM_SHSTK
 #elif defined(CONFIG_PPC)
 # define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)
diff --git a/mm/mmap.c b/mm/mmap.c
index fc04184d2eae..f7a62f1bf92b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1445,6 +1445,12 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 		struct inode *inode = file_inode(file);
 		unsigned long flags_mask;
 
+		/*
+		 * Call stack cannot be backed by a file.
+		 */
+		if (vm_flags & VM_SHSTK)
+			return -EINVAL;
+
 		if (!file_mmap_ok(file, inode, pgoff, len))
 			return -EOVERFLOW;
 
@@ -1509,7 +1515,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 	} else {
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
-			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
+			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP|VM_SHSTK))
 				return -EINVAL;
 			/*
 			 * Ignore pgoff.
-- 
2.21.0


      parent reply index

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-12 15:38 [PATCH v14 00/26] Control-flow Enforcement: Shadow Stack Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 01/26] Documentation/x86: Add CET description Yu-cheng Yu
2020-11-06 17:34   ` Borislav Petkov
2020-11-06 18:16     ` Yu, Yu-cheng
2020-11-06 18:28       ` Borislav Petkov
2020-11-06 18:32         ` Yu, Yu-cheng
2020-10-12 15:38 ` [PATCH v14 02/26] x86/cpufeatures: Add CET CPU feature flags for Control-flow Enforcement Technology (CET) Yu-cheng Yu
2020-11-06 18:49   ` Borislav Petkov
2020-11-06 19:48     ` Yu, Yu-cheng
2020-11-06 20:11       ` Borislav Petkov
2020-11-06 20:14         ` Yu, Yu-cheng
2020-10-12 15:38 ` [PATCH v14 03/26] x86/fpu/xstate: Introduce CET MSR XSAVES supervisor states Yu-cheng Yu
2020-10-12 19:58   ` Cyrill Gorcunov
2020-10-12 20:48     ` Yu, Yu-cheng
2020-10-12 15:38 ` [PATCH v14 04/26] x86/cet: Add control-protection fault handler Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 05/26] x86/cet/shstk: Add Kconfig option for user-mode Shadow Stack Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 06/26] x86/mm: Change _PAGE_DIRTY to _PAGE_DIRTY_HW Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 07/26] x86/mm: Remove _PAGE_DIRTY_HW from kernel RO pages Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 08/26] x86/mm: Introduce _PAGE_COW Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 09/26] drm/i915/gvt: Change _PAGE_DIRTY to _PAGE_DIRTY_BITS Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 10/26] x86/mm: Update pte_modify for _PAGE_COW Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 11/26] x86/mm: Update ptep_set_wrprotect() and pmdp_set_wrprotect() for transition from _PAGE_DIRTY_HW to _PAGE_COW Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 12/26] mm: Introduce VM_SHSTK for shadow stack memory Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 13/26] x86/mm: Shadow Stack page fault error checking Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 14/26] x86/mm: Update maybe_mkwrite() for shadow stack Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 15/26] mm: Fixup places that call pte_mkwrite() directly Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 16/26] mm: Add guard pages around a shadow stack Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 17/26] mm/mmap: Add shadow stack pages to memory accounting Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 18/26] mm: Update can_follow_write_pte() for shadow stack Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 19/26] mm: Re-introduce vm_flags to do_mmap() Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 20/26] x86/cet/shstk: User-mode shadow stack support Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 21/26] x86/cet/shstk: Handle signals for shadow stack Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 22/26] binfmt_elf: Define GNU_PROPERTY_X86_FEATURE_1_AND properties Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 23/26] ELF: Introduce arch_setup_elf_property() Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 24/26] x86/cet/shstk: Handle thread shadow stack Yu-cheng Yu
2020-10-12 15:38 ` [PATCH v14 25/26] x86/cet/shstk: Add arch_prctl functions for " Yu-cheng Yu
2020-10-12 15:38 ` Yu-cheng Yu [this message]

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=20201012153850.26996-27-yu-cheng.yu@intel.com \
    --to=yu-cheng.yu@intel.com \
    --cc=Dave.Martin@arm.com \
    --cc=arnd@arndb.de \
    --cc=bp@alien8.de \
    --cc=bsingharora@gmail.com \
    --cc=corbet@lwn.net \
    --cc=dave.hansen@linux.intel.com \
    --cc=esyr@redhat.com \
    --cc=fweimer@redhat.com \
    --cc=gorcunov@gmail.com \
    --cc=hjl.tools@gmail.com \
    --cc=hpa@zytor.com \
    --cc=jannh@google.com \
    --cc=keescook@chromium.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mike.kravetz@oracle.com \
    --cc=mingo@redhat.com \
    --cc=nadav.amit@gmail.com \
    --cc=oleg@redhat.com \
    --cc=pavel@ucw.cz \
    --cc=pengfei.xu@intel.com \
    --cc=peterz@infradead.org \
    --cc=ravi.v.shankar@intel.com \
    --cc=rdunlap@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=vedvyas.shanbhogue@intel.com \
    --cc=weijiang.yang@intel.com \
    --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-arch Archive on lore.kernel.org

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

Example config snippet for mirrors

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


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