lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240911143421.85612-2-faresx@amazon.de>
Date: Wed, 11 Sep 2024 14:34:00 +0000
From: Fares Mehanna <faresx@...zon.de>
To: 
CC: <nh-open-source@...zon.com>, Fares Mehanna <faresx@...zon.de>, Roman Kagan
	<rkagan@...zon.de>, Marc Zyngier <maz@...nel.org>, Oliver Upton
	<oliver.upton@...ux.dev>, James Morse <james.morse@....com>, Suzuki K Poulose
	<suzuki.poulose@....com>, Zenghui Yu <yuzenghui@...wei.com>, Catalin Marinas
	<catalin.marinas@....com>, Will Deacon <will@...nel.org>, Andrew Morton
	<akpm@...ux-foundation.org>, Kemeng Shi <shikemeng@...weicloud.com>,
	Pierre-Clément Tosi <ptosi@...gle.com>, Ard Biesheuvel
	<ardb@...nel.org>, Mark Rutland <mark.rutland@....com>, "Javier Martinez
 Canillas" <javierm@...hat.com>, Arnd Bergmann <arnd@...db.de>, Fuad Tabba
	<tabba@...gle.com>, Mark Brown <broonie@...nel.org>, Joey Gouly
	<joey.gouly@....com>, Kristina Martsenko <kristina.martsenko@....com>, "Randy
 Dunlap" <rdunlap@...radead.org>, Bjorn Helgaas <bhelgaas@...gle.com>,
	Jean-Philippe Brucker <jean-philippe@...aro.org>, "Mike Rapoport (IBM)"
	<rppt@...nel.org>, David Hildenbrand <david@...hat.com>, "moderated
 list:KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)"
	<linux-arm-kernel@...ts.infradead.org>, "open list:KERNEL VIRTUAL MACHINE FOR
 ARM64 (KVM/arm64)" <kvmarm@...ts.linux.dev>, open list
	<linux-kernel@...r.kernel.org>, "open list:MEMORY MANAGEMENT"
	<linux-mm@...ck.org>
Subject: [RFC PATCH 1/7] mseal: expose interface to seal / unseal user memory ranges

To make sure the kernel mm-local mapping is untouched by the user, we will seal
the VMA before changing the protection to be used by the kernel.

This will guarantee that userspace can't unmap or alter this VMA while it is
being used by the kernel.

After the kernel is done with the secret memory, it will unseal the VMA to be
able to unmap and free it.

Unseal operation is not exposed to userspace.

Signed-off-by: Fares Mehanna <faresx@...zon.de>
Signed-off-by: Roman Kagan <rkagan@...zon.de>
---
 mm/internal.h |  7 +++++
 mm/mseal.c    | 81 ++++++++++++++++++++++++++++++++-------------------
 2 files changed, 58 insertions(+), 30 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index b4d86436565b..cf7280d101e9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1501,6 +1501,8 @@ bool can_modify_mm(struct mm_struct *mm, unsigned long start,
 		unsigned long end);
 bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
 		unsigned long end, int behavior);
+/* mm's mmap write lock must be taken before seal/unseal operation */
+int do_mseal(unsigned long start, unsigned long end, bool seal);
 #else
 static inline int can_do_mseal(unsigned long flags)
 {
@@ -1518,6 +1520,11 @@ static inline bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start,
 {
 	return true;
 }
+
+static inline int do_mseal(unsigned long start, unsigned long end, bool seal)
+{
+	return -EINVAL;
+}
 #endif
 
 #ifdef CONFIG_SHRINKER_DEBUG
diff --git a/mm/mseal.c b/mm/mseal.c
index 15bba28acc00..aac9399ffd5d 100644
--- a/mm/mseal.c
+++ b/mm/mseal.c
@@ -26,6 +26,11 @@ static inline void set_vma_sealed(struct vm_area_struct *vma)
 	vm_flags_set(vma, VM_SEALED);
 }
 
+static inline void clear_vma_sealed(struct vm_area_struct *vma)
+{
+	vm_flags_clear(vma, VM_SEALED);
+}
+
 /*
  * check if a vma is sealed for modification.
  * return true, if modification is allowed.
@@ -117,7 +122,7 @@ bool can_modify_mm_madv(struct mm_struct *mm, unsigned long start, unsigned long
 
 static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		struct vm_area_struct **prev, unsigned long start,
-		unsigned long end, vm_flags_t newflags)
+		unsigned long end, vm_flags_t newflags, bool seal)
 {
 	int ret = 0;
 	vm_flags_t oldflags = vma->vm_flags;
@@ -131,7 +136,10 @@ static int mseal_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		goto out;
 	}
 
-	set_vma_sealed(vma);
+	if (seal)
+		set_vma_sealed(vma);
+	else
+		clear_vma_sealed(vma);
 out:
 	*prev = vma;
 	return ret;
@@ -167,9 +175,9 @@ static int check_mm_seal(unsigned long start, unsigned long end)
 }
 
 /*
- * Apply sealing.
+ * Apply sealing / unsealing.
  */
-static int apply_mm_seal(unsigned long start, unsigned long end)
+static int apply_mm_seal(unsigned long start, unsigned long end, bool seal)
 {
 	unsigned long nstart;
 	struct vm_area_struct *vma, *prev;
@@ -191,11 +199,14 @@ static int apply_mm_seal(unsigned long start, unsigned long end)
 		unsigned long tmp;
 		vm_flags_t newflags;
 
-		newflags = vma->vm_flags | VM_SEALED;
+		if (seal)
+			newflags = vma->vm_flags | VM_SEALED;
+		else
+			newflags = vma->vm_flags & ~(VM_SEALED);
 		tmp = vma->vm_end;
 		if (tmp > end)
 			tmp = end;
-		error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags);
+		error = mseal_fixup(&vmi, vma, &prev, nstart, tmp, newflags, seal);
 		if (error)
 			return error;
 		nstart = vma_iter_end(&vmi);
@@ -204,6 +215,37 @@ static int apply_mm_seal(unsigned long start, unsigned long end)
 	return 0;
 }
 
+int do_mseal(unsigned long start, unsigned long end, bool seal)
+{
+	int ret;
+
+	if (end < start)
+		return -EINVAL;
+
+	if (end == start)
+		return 0;
+
+	/*
+	 * First pass, this helps to avoid
+	 * partial sealing in case of error in input address range,
+	 * e.g. ENOMEM error.
+	 */
+	ret = check_mm_seal(start, end);
+	if (ret)
+		goto out;
+
+	/*
+	 * Second pass, this should success, unless there are errors
+	 * from vma_modify_flags, e.g. merge/split error, or process
+	 * reaching the max supported VMAs, however, those cases shall
+	 * be rare.
+	 */
+	ret = apply_mm_seal(start, end, seal);
+
+out:
+	return ret;
+}
+
 /*
  * mseal(2) seals the VM's meta data from
  * selected syscalls.
@@ -256,7 +298,7 @@ static int apply_mm_seal(unsigned long start, unsigned long end)
  *
  *  unseal() is not supported.
  */
-static int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
+static int __do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 {
 	size_t len;
 	int ret = 0;
@@ -277,33 +319,12 @@ static int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 		return -EINVAL;
 
 	end = start + len;
-	if (end < start)
-		return -EINVAL;
-
-	if (end == start)
-		return 0;
 
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
-	/*
-	 * First pass, this helps to avoid
-	 * partial sealing in case of error in input address range,
-	 * e.g. ENOMEM error.
-	 */
-	ret = check_mm_seal(start, end);
-	if (ret)
-		goto out;
-
-	/*
-	 * Second pass, this should success, unless there are errors
-	 * from vma_modify_flags, e.g. merge/split error, or process
-	 * reaching the max supported VMAs, however, those cases shall
-	 * be rare.
-	 */
-	ret = apply_mm_seal(start, end);
+	ret = do_mseal(start, end, true);
 
-out:
 	mmap_write_unlock(current->mm);
 	return ret;
 }
@@ -311,5 +332,5 @@ static int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
 SYSCALL_DEFINE3(mseal, unsigned long, start, size_t, len, unsigned long,
 		flags)
 {
-	return do_mseal(start, len, flags);
+	return __do_mseal(start, len, flags);
 }
-- 
2.40.1




Amazon Web Services Development Center Germany GmbH
Krausenstr. 38
10117 Berlin
Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
Eingetragen am Amtsgericht Charlottenburg unter HRB 257764 B
Sitz: Berlin
Ust-ID: DE 365 538 597


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ