arm64: untag user pointers passed to the kernel

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

copy_from_user (and a few other similar functions) are used to copy data from user memory into the kernel memory or vice versa. Since a user can provided a tagged pointer to one of the syscalls that use copy_from_user, we need to correctly handle such pointers.

Do this by untagging user pointers in access_ok and in __uaccess_mask_ptr, before performing access validity checks.

Note, that this patch only temporarily untags the pointers to perform the checks, but then passes them as is into the kernel internals.

Reviewed-by Kees Cook <[email protected]>

Reviewed-by Catalin Marinas <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 arch/arm64/include/asm/uaccess.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

arch/arm64/include/asm/uaccess.h +7 -3

index e5d5f31c6d36..df729afca0ba 100644
@@ -73,6 +73,8 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
+	addr = untagged_addr(addr);
+
 	__chk_user_ptr(addr);
 	asm volatile(
 	// A + B <= C + 1 for all A,B,C, in four easy steps:

@@ -226,7 +228,8 @@ static inline void uaccess_enable_not_uao(void)
 
 /*
  * Sanitise a uaccess pointer such that it becomes NULL if above the
- * current addr_limit.
+ * current addr_limit. In case the pointer is tagged (has the top byte set),
+ * untag the pointer before checking.
  */
 #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr)
 static inline void __user *__uaccess_mask_ptr(const void __user *ptr)

@@ -234,10 +237,11 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr)
 	void __user *safe_ptr;
 
 	asm volatile(
-	"	bics	xzr, %1, %2\n"
+	"	bics	xzr, %3, %2\n"
 	"	csel	%0, %1, xzr, eq\n"
 	: "=&r" (safe_ptr)
-	: "r" (ptr), "r" (current_thread_info()->addr_limit)
+	: "r" (ptr), "r" (current_thread_info()->addr_limit),
+	  "r" (untagged_addr(ptr))
 	: "cc");
 
 	csdb();

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

strncpy_from_user and strnlen_user accept user addresses as arguments, and do not go through the same path as copy_from_user and others, so here we need to handle the case of tagged user addresses separately.

Untag user pointers passed to these functions.

Note, that this patch only temporarily untags the pointers to perform validity checks, but then uses them as is to perform user memory accesses.

Reviewed-by Khalid Aziz <[email protected]>

Acked-by Kees Cook <[email protected]>

Reviewed-by Catalin Marinas <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 lib/strncpy_from_user.c | 3 ++-
 lib/strnlen_user.c      | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

lib/strncpy_from_user.c +2 -1

index 023ba9f3b99f..dccb95af6003 100644
@@ -6,6 +6,7 @@
 #include <linux/uaccess.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/mm.h>
 
 #include <asm/byteorder.h>
 #include <asm/word-at-a-time.h>

@@ -108,7 +109,7 @@ long strncpy_from_user(char *dst, const char __user *src, long count)
 		return 0;
 
 	max_addr = user_addr_max();
-	src_addr = (unsigned long)src;
+	src_addr = (unsigned long)untagged_addr(src);
 	if (likely(src_addr < max_addr)) {
 		unsigned long max = max_addr - src_addr;
 		long retval;

lib/strnlen_user.c +2 -1

index 7f2db3fe311f..28ff554a1be8 100644
@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/uaccess.h>
+#include <linux/mm.h>
 
 #include <asm/word-at-a-time.h>
 

@@ -109,7 +110,7 @@ long strnlen_user(const char __user *str, long count)
 		return 0;
 
 	max_addr = user_addr_max();
-	src_addr = (unsigned long)str;
+	src_addr = (unsigned long)untagged_addr(str);
 	if (likely(src_addr < max_addr)) {
 		unsigned long max = max_addr - src_addr;
 		long retval;

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

---
 arch/arm64/include/asm/processor.h   |  6 +++
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/include/asm/uaccess.h     |  3 +-
 arch/arm64/kernel/process.c          | 67 ++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h           |  5 +++
 kernel/sys.c                         | 16 +++++++
 6 files changed, 97 insertions(+), 1 deletion(-)

arch/arm64/include/asm/processor.h +6 -0

index fcd0e691b1ea..fee457456aa8 100644
@@ -307,6 +307,12 @@ extern void __init minsigstksz_setup(void);
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
 
+/* PR_TAGGED_ADDR prctl */
+long set_tagged_addr_ctrl(unsigned long arg);
+long get_tagged_addr_ctrl(void);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+
 /*
  * For CONFIG_GCC_PLUGIN_STACKLEAK
  *

arch/arm64/include/asm/thread_info.h +1 -0

index f1d032be628a..354a31d2b737 100644
@@ -99,6 +99,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_SVE			23	/* Scalable Vector Extension in use */
 #define TIF_SVE_VL_INHERIT	24	/* Inherit sve_vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
+#define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)

arch/arm64/include/asm/uaccess.h +2 -1

index df729afca0ba..995b9ea11a89 100644
@@ -73,7 +73,8 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
-	addr = untagged_addr(addr);
+	if (test_thread_flag(TIF_TAGGED_ADDR))
+		addr = untagged_addr(addr);
 
 	__chk_user_ptr(addr);
 	asm volatile(

arch/arm64/kernel/process.c +67 -0

index 3767fb21a5b8..69d0be1fc708 100644
@@ -30,6 +30,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>

@@ -323,6 +324,7 @@ void flush_thread(void)
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	clear_thread_flag(TIF_TAGGED_ADDR);
 }
 
 void release_thread(struct task_struct *dead_task)

@@ -552,3 +554,68 @@ void arch_setup_new_exec(void)
 
 	ptrauth_thread_init_user(current);
 }
+
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_prctl_allowed = 1;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;
+	if (is_compat_task())
+		return -EINVAL;
+	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+		return -EINVAL;
+
+	if (arg & PR_TAGGED_ADDR_ENABLE)
+		set_thread_flag(TIF_TAGGED_ADDR);
+	else
+		clear_thread_flag(TIF_TAGGED_ADDR);
+
+	return 0;
+}
+
+long get_tagged_addr_ctrl(void)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;
+	if (is_compat_task())
+		return -EINVAL;
+
+	if (test_thread_flag(TIF_TAGGED_ADDR))
+		return PR_TAGGED_ADDR_ENABLE;
+
+	return 0;
+}
+
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+static int zero;
+static int one = 1;
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr",
+		.mode		= 0644,
+		.data		= &tagged_addr_prctl_allowed,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{ }
+};
+
+static int __init tagged_addr_init(void)
+{
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+	return 0;
+}
+
+core_initcall(tagged_addr_init);

include/uapi/linux/prctl.h +5 -0

index 094bb03b9cc2..2e927b3e9d6c 100644
@@ -229,4 +229,9 @@ struct prctl_mm_map {
 # define PR_PAC_APDBKEY			(1UL << 3)
 # define PR_PAC_APGAKEY			(1UL << 4)
 
+/* Tagged user address controls for arm64 */
+#define PR_SET_TAGGED_ADDR_CTRL		55
+#define PR_GET_TAGGED_ADDR_CTRL		56
+# define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+
 #endif /* _LINUX_PRCTL_H */

kernel/sys.c +16 -0

index 2969304c29fe..ec48396b4943 100644
@@ -124,6 +124,12 @@
 #ifndef PAC_RESET_KEYS
 # define PAC_RESET_KEYS(a, b)	(-EINVAL)
 #endif
+#ifndef SET_TAGGED_ADDR_CTRL
+# define SET_TAGGED_ADDR_CTRL(a)	(-EINVAL)
+#endif
+#ifndef GET_TAGGED_ADDR_CTRL
+# define GET_TAGGED_ADDR_CTRL()		(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for

@@ -2492,6 +2498,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = PAC_RESET_KEYS(me, arg2);
 		break;
+	case PR_SET_TAGGED_ADDR_CTRL:
+		if (arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = SET_TAGGED_ADDR_CTRL(arg2);
+		break;
+	case PR_GET_TAGGED_ADDR_CTRL:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = GET_TAGGED_ADDR_CTRL();
+		break;
 	default:
 		error = -EINVAL;
 		break;

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

---
 arch/arm64/include/asm/processor.h   |  6 +++
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/include/asm/uaccess.h     |  3 +-
 arch/arm64/kernel/process.c          | 67 ++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h           |  5 +++
 kernel/sys.c                         | 16 +++++++
 6 files changed, 97 insertions(+), 1 deletion(-)

arch/arm64/include/asm/processor.h +6 -0

index fcd0e691b1ea..fee457456aa8 100644
@@ -307,6 +307,12 @@ extern void __init minsigstksz_setup(void);
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
 
+/* PR_TAGGED_ADDR prctl */
+long set_tagged_addr_ctrl(unsigned long arg);
+long get_tagged_addr_ctrl(void);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+
 /*
  * For CONFIG_GCC_PLUGIN_STACKLEAK
  *

arch/arm64/include/asm/thread_info.h +1 -0

index f1d032be628a..354a31d2b737 100644
@@ -99,6 +99,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_SVE			23	/* Scalable Vector Extension in use */
 #define TIF_SVE_VL_INHERIT	24	/* Inherit sve_vl_onexec across exec */
 #define TIF_SSBD		25	/* Wants SSB mitigation */
+#define TIF_TAGGED_ADDR		26	/* Allow tagged user addresses */
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)

arch/arm64/include/asm/uaccess.h +2 -1

index df729afca0ba..995b9ea11a89 100644
@@ -73,7 +73,8 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
-	addr = untagged_addr(addr);
+	if (test_thread_flag(TIF_TAGGED_ADDR))
+		addr = untagged_addr(addr);
 
 	__chk_user_ptr(addr);
 	asm volatile(

arch/arm64/kernel/process.c +35 -0

index 3767fb21a5b8..69d0be1fc708 100644
@@ -30,6 +30,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>

@@ -323,6 +324,7 @@ void flush_thread(void)
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	clear_thread_flag(TIF_TAGGED_ADDR);
 }
 
 void release_thread(struct task_struct *dead_task)

@@ -552,3 +554,68 @@ void arch_setup_new_exec(void)
 
 	ptrauth_thread_init_user(current);
 }
+
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_prctl_allowed = 1;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;
+	if (is_compat_task())
+		return -EINVAL;
+	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+		return -EINVAL;
+
+	if (arg & PR_TAGGED_ADDR_ENABLE)
+		set_thread_flag(TIF_TAGGED_ADDR);
+	else
+		clear_thread_flag(TIF_TAGGED_ADDR);
+
+	return 0;
+}
+
+long get_tagged_addr_ctrl(void)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;
+	if (is_compat_task())
+		return -EINVAL;
+
+	if (test_thread_flag(TIF_TAGGED_ADDR))
+		return PR_TAGGED_ADDR_ENABLE;
+

arch/arm64/kernel/process.c +22 -0

+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr",
+		.mode		= 0644,
+		.data		= &tagged_addr_prctl_allowed,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{ }
+};
+
+static int __init tagged_addr_init(void)
+{
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+	return 0;
+}
+
+core_initcall(tagged_addr_init);

include/uapi/linux/prctl.h +0 -0

index 094bb03b9cc2..2e927b3e9d6c 100644

include/uapi/linux/prctl.h +0 -0

 #endif /* _LINUX_PRCTL_H */

kernel/sys.c +6 -0

index 2969304c29fe..ec48396b4943 100644
@@ -124,6 +124,12 @@
 #ifndef PAC_RESET_KEYS
 # define PAC_RESET_KEYS(a, b)	(-EINVAL)
 #endif
+#ifndef SET_TAGGED_ADDR_CTRL
+# define SET_TAGGED_ADDR_CTRL(a)	(-EINVAL)
+#endif
+#ifndef GET_TAGGED_ADDR_CTRL
+# define GET_TAGGED_ADDR_CTRL()		(-EINVAL)
+#endif
 
 /*
  * this is where the system-wide overflow UID and GID are defined, for

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 599

Quoted 7 lines · Andrey Konovalov

arch/arm64/kernel/process.c +7 -0

+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+static int zero;
+static int one = 1;

!!!

And these can't even be const without a cast. Yuk.

(Not your fault though, but it would be nice to have a proc_dobool() to avoid this.)

Quoted 6 lines

include/uapi/linux/prctl.h +0 -0

@@ -229,4 +229,9 @@ struct prctl_mm_map {
 # define PR_PAC_APDBKEY			(1UL << 3)
 # define PR_PAC_APGAKEY			(1UL << 4)
 

include/uapi/linux/prctl.h struct prctl_mm_map { · line 236

Quoted 5 lines

include/uapi/linux/prctl.h +5 -0

+/* Tagged user address controls for arm64 */
+#define PR_SET_TAGGED_ADDR_CTRL		55
+#define PR_GET_TAGGED_ADDR_CTRL		56
+# define PR_TAGGED_ADDR_ENABLE		(1UL << 0)
+

Do we expect this prctl to be applicable to other arches, or is it strictly arm64-specific?

include/uapi/linux/prctl.h SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, · line 2502

Quoted 6 lines

include/uapi/linux/prctl.h +2 -0

@@ -2492,6 +2498,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			return -EINVAL;
 		error = PAC_RESET_KEYS(me, arg2);
 		break;
+	case PR_SET_TAGGED_ADDR_CTRL:
+		if (arg3 || arg4 || arg5)

<bikeshed>

How do you anticipate these arguments being used in the future?

For the SVE prctls I took the view that "get" could only ever mean one thing, and "put" already had a flags argument with spare bits for future expansion anyway, so forcing the extra arguments to zero would be unnecessary.

Opinions seem to differ on whether requiring surplus arguments to be 0 is beneficial for hygiene, but the glibc prototype for prctl() is

	int prctl (int __option, ...);

so it seemed annoying to have to pass extra arguments to it just for the sake of it. IMHO this also makes the code at the call site less readable, since it's not immediately apparent that all those 0s are meaningless.

include/uapi/linux/prctl.h SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, · line 2509

Quoted 7 lines

include/uapi/linux/prctl.h +7 -0

+			return -EINVAL;
+		error = SET_TAGGED_ADDR_CTRL(arg2);
+		break;
+	case PR_GET_TAGGED_ADDR_CTRL:
+		if (arg2 || arg3 || arg4 || arg5)
+			return -EINVAL;
+		error = GET_TAGGED_ADDR_CTRL();

Having a "get" prctl is probably a good idea, but is there a clear usecase for it?

Quoted 6 lines · Dave P Martin

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 599

Quoted 2 lines · Andrey Konovalov

arch/arm64/kernel/process.c +2 -0

+static int zero;
+static int one = 1;

!!!

Quoted 4 lines

And these can't even be const without a cast. Yuk.

(Not your fault though, but it would be nice to have a proc_dobool() to avoid this.)

I had the same reaction. Maybe for another patch sanitising this pattern across the kernel.

Quoted 7 lines · Catalin Marinas

Quoted 6 lines · Dave P Martin

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 599

Quoted 2 lines · Andrey Konovalov

arch/arm64/kernel/process.c +2 -0

+static int zero;
+static int one = 1;

!!!

Quoted 7 lines

Quoted 4 lines

And these can't even be const without a cast. Yuk.

(Not your fault though, but it would be nice to have a proc_dobool() to avoid this.)

I had the same reaction. Maybe for another patch sanitising this pattern across the kernel.

That's actually already happening (via -mm tree last I looked). tl;dr:
it ends up using a cast hidden in a macro. It's in linux-next already along with a checkpatch.pl addition to yell about doing what's being done here. ;)

https://lore.kernel.org/lkml/[email protected]/#r

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

---
 arch/arm64/include/asm/processor.h   |  6 +++
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/include/asm/uaccess.h     |  3 +-
 arch/arm64/kernel/process.c          | 67 ++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h           |  5 +++
 kernel/sys.c                         | 16 +++++++
 6 files changed, 97 insertions(+), 1 deletion(-)

arch/arm64/include/asm/processor.h +0 -0

index fcd0e691b1ea..fee457456aa8 100644

arch/arm64/include/asm/processor.h +5 -0

+long set_tagged_addr_ctrl(unsigned long arg);
+long get_tagged_addr_ctrl(void);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+

arch/arm64/kernel/process.c +2 -0

index 3767fb21a5b8..69d0be1fc708 100644
@@ -30,6 +30,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>

@@ -323,6 +324,7 @@ void flush_thread(void)
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	clear_thread_flag(TIF_TAGGED_ADDR);
 }
 
 void release_thread(struct task_struct *dead_task)

@@ -552,3 +554,68 @@ void arch_setup_new_exec(void)
 
 	ptrauth_thread_init_user(current);
 }

Quoted 31 lines · Andrey Konovalov

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

---
 arch/arm64/include/asm/processor.h   |  6 +++
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/include/asm/uaccess.h     |  3 +-
 arch/arm64/kernel/process.c          | 67 ++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h           |  5 +++
 kernel/sys.c                         | 16 +++++++
 6 files changed, 97 insertions(+), 1 deletion(-)

arch/arm64/include/asm/processor.h +0 -0

index fcd0e691b1ea..fee457456aa8 100644
@@ -307,6 +307,12 @@ extern void __init minsigstksz_setup(void);
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
 

arch/arm64/include/asm/processor.h extern void __init minsigstksz_setup(void); · line 310

Quoted 1 line

arch/arm64/include/asm/processor.h +1 -0

+/* PR_TAGGED_ADDR prctl */

(A couple of comments I missed in my last reply:)

Name mismatch?

Quoted 5 lines

arch/arm64/include/asm/processor.h +5 -0

+long set_tagged_addr_ctrl(unsigned long arg);
+long get_tagged_addr_ctrl(void);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+

[...]

Quoted 22 lines

arch/arm64/kernel/process.c +2 -0

index 3767fb21a5b8..69d0be1fc708 100644
@@ -30,6 +30,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>

@@ -323,6 +324,7 @@ void flush_thread(void)
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	clear_thread_flag(TIF_TAGGED_ADDR);
 }
 
 void release_thread(struct task_struct *dead_task)

@@ -552,3 +554,68 @@ void arch_setup_new_exec(void)
 

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 566

Quoted 12 lines

arch/arm64/kernel/process.c +10 -0

 	ptrauth_thread_init_user(current);
 }
+
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_prctl_allowed = 1;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;

So, tagging can actually be locked on by having a process enable it and then some possibly unrelated process clearing tagged_addr_prctl_allowed. That feels a bit weird.

Do we want to allow a process that has tagging on to be able to turn it off at all? Possibly things like CRIU might want to do that.

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 570

Quoted 4 lines

arch/arm64/kernel/process.c +4 -0

+	if (is_compat_task())
+		return -EINVAL;
+	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+		return -EINVAL;

How do we expect this argument to be extended in the future?

I'm wondering whether this is really a bitmask or an enum, or a mixture of the two. Maybe it doesn't matter.

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 575

Quoted 4 lines

arch/arm64/kernel/process.c +4 -0

+	if (arg & PR_TAGGED_ADDR_ENABLE)
+		set_thread_flag(TIF_TAGGED_ADDR);
+	else
+		clear_thread_flag(TIF_TAGGED_ADDR);

I think update_thread_flag() could be used here.

Quoted 32 lines · Dave P Martin

Quoted 31 lines · Andrey Konovalov

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

---
 arch/arm64/include/asm/processor.h   |  6 +++
 arch/arm64/include/asm/thread_info.h |  1 +
 arch/arm64/include/asm/uaccess.h     |  3 +-
 arch/arm64/kernel/process.c          | 67 ++++++++++++++++++++++++++++
 include/uapi/linux/prctl.h           |  5 +++
 kernel/sys.c                         | 16 +++++++
 6 files changed, 97 insertions(+), 1 deletion(-)

arch/arm64/include/asm/processor.h +0 -0

index fcd0e691b1ea..fee457456aa8 100644
@@ -307,6 +307,12 @@ extern void __init minsigstksz_setup(void);
 /* PR_PAC_RESET_KEYS prctl */
 #define PAC_RESET_KEYS(tsk, arg)	ptrauth_prctl_reset_keys(tsk, arg)
 

Quoted 5 lines

arch/arm64/include/asm/processor.h extern void __init minsigstksz_setup(void); · line 310

Quoted 1 line

arch/arm64/include/asm/processor.h +1 -0

+/* PR_TAGGED_ADDR prctl */

(A couple of comments I missed in my last reply:)

Name mismatch?

Yeah, it went through several names but it seems that I didn't update all places.

Quoted 30 lines

Quoted 5 lines

arch/arm64/include/asm/processor.h +5 -0

+long set_tagged_addr_ctrl(unsigned long arg);
+long get_tagged_addr_ctrl(void);
+#define SET_TAGGED_ADDR_CTRL(arg)	set_tagged_addr_ctrl(arg)
+#define GET_TAGGED_ADDR_CTRL()		get_tagged_addr_ctrl()
+

[...]

Quoted 22 lines

arch/arm64/kernel/process.c +2 -0

index 3767fb21a5b8..69d0be1fc708 100644
@@ -30,6 +30,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/stddef.h>
+#include <linux/sysctl.h>
 #include <linux/unistd.h>
 #include <linux/user.h>
 #include <linux/delay.h>

@@ -323,6 +324,7 @@ void flush_thread(void)
 	fpsimd_flush_thread();
 	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
+	clear_thread_flag(TIF_TAGGED_ADDR);
 }
 
 void release_thread(struct task_struct *dead_task)

@@ -552,3 +554,68 @@ void arch_setup_new_exec(void)
 

Quoted 16 lines

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 566

Quoted 12 lines

arch/arm64/kernel/process.c +10 -0

 	ptrauth_thread_init_user(current);
 }
+
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_prctl_allowed = 1;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;

So, tagging can actually be locked on by having a process enable it and then some possibly unrelated process clearing tagged_addr_prctl_allowed. That feels a bit weird.

The problem is that if you disable the ABI globally, lots of applications would crash. This sysctl is meant as a way to disable the opt-in to the TBI ABI. Another option would be a kernel command line option (I'm not keen on a Kconfig option).

Quoted 2 lines

Do we want to allow a process that has tagging on to be able to turn it off at all? Possibly things like CRIU might want to do that.

I left it in for symmetry but I don't expect it to be used. A potential use-case is doing it per subsequent threads in an application.

Quoted 6 lines

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 570

Quoted 4 lines

arch/arm64/kernel/process.c +4 -0

+	if (is_compat_task())
+		return -EINVAL;
+	if (arg & ~PR_TAGGED_ADDR_ENABLE)
+		return -EINVAL;

How do we expect this argument to be extended in the future?

Yes, for MTE. That's why I wouldn't allow random bits here.

Quoted 2 lines

I'm wondering whether this is really a bitmask or an enum, or a mixture of the two. Maybe it doesn't matter.

User may want to set PR_TAGGED_ADDR_ENABLE | PR_MTE_PRECISE in a single call.

Quoted 6 lines

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 575

Quoted 4 lines

arch/arm64/kernel/process.c +4 -0

+	if (arg & PR_TAGGED_ADDR_ENABLE)
+		set_thread_flag(TIF_TAGGED_ADDR);
+	else
+		clear_thread_flag(TIF_TAGGED_ADDR);

I think update_thread_flag() could be used here.

Yes. I forgot you added this.

Quoted 17 lines · Catalin Marinas

Quoted 15 lines · Dave P Martin

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 566

Quoted 10 lines · Andrey Konovalov

arch/arm64/kernel/process.c +10 -0

+
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_prctl_allowed = 1;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;

So, tagging can actually be locked on by having a process enable it and then some possibly unrelated process clearing tagged_addr_prctl_allowed. That feels a bit weird.

Quoted 4 lines

The problem is that if you disable the ABI globally, lots of applications would crash. This sysctl is meant as a way to disable the opt-in to the TBI ABI. Another option would be a kernel command line option (I'm not keen on a Kconfig option).

Why you are not keen on a Kconfig option?

Quoted 23 lines · Vincenzo Frascino

Quoted 21 lines · Catalin Marinas

Quoted 15 lines · Dave P Martin

arch/arm64/kernel/process.c void arch_setup_new_exec(void) · line 566

Quoted 10 lines · Andrey Konovalov

arch/arm64/kernel/process.c +10 -0

+
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_prctl_allowed = 1;
+
+long set_tagged_addr_ctrl(unsigned long arg)
+{
+	if (!tagged_addr_prctl_allowed)
+		return -EINVAL;

So, tagging can actually be locked on by having a process enable it and then some possibly unrelated process clearing tagged_addr_prctl_allowed. That feels a bit weird.

The problem is that if you disable the ABI globally, lots of applications would crash. This sysctl is meant as a way to disable the opt-in to the TBI ABI. Another option would be a kernel command line option (I'm not keen on a Kconfig option).

Quoted 1 line

Why you are not keen on a Kconfig option?

Because I don't want to rebuild the kernel/reboot just to be able to test how user space handles the ABI opt-in. I'm ok with a Kconfig option to disable this globally in addition to a run-time option (if actually needed, I'm not sure).

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

Quoted 13 lines · Andrey Konovalov

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Quoted 1 line

Signed-off-by Catalin Marinas <[email protected]>

A question for the user-space folk: if an application opts in to this ABI, would you want the sigcontext.fault_address and/or siginfo.si_addr to contain the tag? We currently clear it early in the arm64 entry.S but we could find a way to pass it down if needed.

Quoted 13 lines · Andrey Konovalov

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Quoted 1 line

Signed-off-by Catalin Marinas <[email protected]>

A question for the user-space folk: if an application opts in to this ABI, would you want the sigcontext.fault_address and/or siginfo.si_addr to contain the tag? We currently clear it early in the arm64 entry.S but we could find a way to pass it down if needed.

Quoted 14 lines · Catalin Marinas

Quoted 13 lines · Andrey Konovalov

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Quoted 6 lines

Quoted 1 line

Signed-off-by Catalin Marinas <[email protected]>

A question for the user-space folk: if an application opts in to this ABI, would you want the sigcontext.fault_address and/or siginfo.si_addr to contain the tag? We currently clear it early in the arm64 entry.S but we could find a way to pass it down if needed.

For HWASan this would not be useful because we instrument memory accesses with explicit checks anyway. For MTE, on the other hand, it would be very convenient to know the fault address tag without disassembling the code.

Quoted 22 lines · Evgenii Stepanov

Quoted 20 lines · Catalin Marinas

Quoted 10 lines · Andrey Konovalov

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

Quoted 4 lines

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

A question for the user-space folk: if an application opts in to this ABI, would you want the sigcontext.fault_address and/or siginfo.si_addr to contain the tag? We currently clear it early in the arm64 entry.S but we could find a way to pass it down if needed.

Quoted 4 lines

For HWASan this would not be useful because we instrument memory accesses with explicit checks anyway. For MTE, on the other hand, it would be very convenient to know the fault address tag without disassembling the code.

I could as this differently: does anything break if, once the user opts in to TBI, fault_address and/or si_addr have non-zero top byte?

Alternatively, we could present the original FAR_EL1 register as a separate field as we do with ESR_EL1, independently of whether the user opted in to TBI or not.

--
Catalin

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

Quoted 10 lines · Andrey Konovalov

From: Catalin Marinas <[email protected]>

It is not desirable to relax the ABI to allow tagged user addresses into the kernel indiscriminately. This patch introduces a prctl() interface for enabling or disabling the tagged ABI with a global sysctl control for preventing applications from enabling the relaxed ABI (meant for testing user-space prctl() return error checking without reconfiguring the kernel). The ABI properties are inherited by threads of the same application and fork()'ed children but cleared on execve().

Quoted 4 lines

The PR_SET_TAGGED_ADDR_CTRL will be expanded in the future to handle MTE-specific settings like imprecise vs precise exceptions.

Signed-off-by Catalin Marinas <[email protected]>

Catalin, would you like to do the requested changes to this patch yourself and send it to me or should I do that?

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

This patch allows tagged pointers to be passed to the following memory
syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect, mremap, msync, munlock, move_pages.

The mmap and mremap syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.

Reviewed-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 mm/madvise.c   | 2 ++
 mm/mempolicy.c | 3 +++
 mm/migrate.c   | 2 +-
 mm/mincore.c   | 2 ++
 mm/mlock.c     | 4 ++++
 mm/mprotect.c  | 2 ++
 mm/mremap.c    | 7 +++++++
 mm/msync.c     | 2 ++
 8 files changed, 23 insertions(+), 1 deletion(-)

mm/madvise.c +2 -0

index 628022e674a7..39b82f8a698f 100644
@@ -810,6 +810,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	size_t len;
 	struct blk_plug plug;
 
+	start = untagged_addr(start);
+
 	if (!madvise_behavior_valid(behavior))
 		return error;
 

mm/mempolicy.c +3 -0

index 01600d80ae01..78e0a88b2680 100644
@@ -1360,6 +1360,7 @@ static long kernel_mbind(unsigned long start, unsigned long len,
 	int err;
 	unsigned short mode_flags;
 
+	start = untagged_addr(start);
 	mode_flags = mode & MPOL_MODE_FLAGS;
 	mode &= ~MPOL_MODE_FLAGS;
 	if (mode >= MPOL_MAX)

@@ -1517,6 +1518,8 @@ static int kernel_get_mempolicy(int __user *policy,
 	int uninitialized_var(pval);
 	nodemask_t nodes;
 
+	addr = untagged_addr(addr);
+
 	if (nmask != NULL && maxnode < nr_node_ids)
 		return -EINVAL;
 

mm/migrate.c +1 -1

index f2ecc2855a12..d22c45cf36b2 100644
@@ -1616,7 +1616,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			goto out_flush;
 		if (get_user(node, nodes + i))
 			goto out_flush;
-		addr = (unsigned long)p;
+		addr = (unsigned long)untagged_addr(p);
 
 		err = -ENODEV;
 		if (node < 0 || node >= MAX_NUMNODES)

mm/mincore.c +2 -0

index c3f058bd0faf..64c322ed845c 100644
@@ -249,6 +249,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
 	unsigned long pages;
 	unsigned char *tmp;
 
+	start = untagged_addr(start);
+
 	/* Check the start address: needs to be page-aligned.. */
 	if (start & ~PAGE_MASK)
 		return -EINVAL;

mm/mlock.c +4 -0

index 080f3b36415b..e82609eaa428 100644
@@ -674,6 +674,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla
 	unsigned long lock_limit;
 	int error = -ENOMEM;
 
+	start = untagged_addr(start);
+
 	if (!can_do_mlock())
 		return -EPERM;
 

@@ -735,6 +737,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
+	start = untagged_addr(start);
+
 	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 

mm/mprotect.c +2 -0

index bf38dfbbb4b4..19f981b733bc 100644
@@ -465,6 +465,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
 
+	start = untagged_addr(start);
+
 	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
 	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
 		return -EINVAL;

mm/mremap.c +7 -0

index fc241d23cd97..64c9a3b8be0a 100644
@@ -606,6 +606,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
+	/*
+	 * Architectures may interpret the tag passed to mmap as a background
+	 * colour for the corresponding vma. For mremap we don't allow tagged
+	 * new_addr to preserve similar behaviour to mmap.
+	 */
+	addr = untagged_addr(addr);
+
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
 

mm/msync.c +2 -0

index ef30a429623a..c3bd3e75f687 100644
@@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 	int unmapped_error = 0;
 	int error = -EINVAL;
 
+	start = untagged_addr(start);
+
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;
 	if (offset_in_page(start))

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

This patch allows tagged pointers to be passed to the following memory
syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect, mremap, msync, munlock, move_pages.

The mmap and mremap syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.

Reviewed-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---

 mm/madvise.c   | 2 ++
 mm/mempolicy.c | 3 +++
 mm/migrate.c   | 2 +-
 mm/mincore.c   | 2 ++
 mm/mlock.c     | 4 ++++
 mm/mprotect.c  | 2 ++
 mm/mremap.c    | 7 +++++++
 mm/msync.c     | 2 ++
 8 files changed, 23 insertions(+), 1 deletion(-)

mm/madvise.c +2 -0

index 628022e674a7..39b82f8a698f 100644
@@ -810,6 +810,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	size_t len;
 	struct blk_plug plug;
 
+	start = untagged_addr(start);
+
 	if (!madvise_behavior_valid(behavior))
 		return error;
 

mm/mempolicy.c +3 -0

index 01600d80ae01..78e0a88b2680 100644
@@ -1360,6 +1360,7 @@ static long kernel_mbind(unsigned long start, unsigned long len,
 	int err;
 	unsigned short mode_flags;
 
+	start = untagged_addr(start);
 	mode_flags = mode & MPOL_MODE_FLAGS;
 	mode &= ~MPOL_MODE_FLAGS;
 	if (mode >= MPOL_MAX)

@@ -1517,6 +1518,8 @@ static int kernel_get_mempolicy(int __user *policy,
 	int uninitialized_var(pval);
 	nodemask_t nodes;
 
+	addr = untagged_addr(addr);
+
 	if (nmask != NULL && maxnode < nr_node_ids)
 		return -EINVAL;
 

mm/migrate.c +1 -1

index f2ecc2855a12..d22c45cf36b2 100644
@@ -1616,7 +1616,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			goto out_flush;
 		if (get_user(node, nodes + i))
 			goto out_flush;
-		addr = (unsigned long)p;
+		addr = (unsigned long)untagged_addr(p);
 
 		err = -ENODEV;
 		if (node < 0 || node >= MAX_NUMNODES)

mm/mincore.c +2 -0

index c3f058bd0faf..64c322ed845c 100644
@@ -249,6 +249,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
 	unsigned long pages;
 	unsigned char *tmp;
 
+	start = untagged_addr(start);
+
 	/* Check the start address: needs to be page-aligned.. */
 	if (start & ~PAGE_MASK)
 		return -EINVAL;

mm/mlock.c +4 -0

index 080f3b36415b..e82609eaa428 100644
@@ -674,6 +674,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla
 	unsigned long lock_limit;
 	int error = -ENOMEM;
 
+	start = untagged_addr(start);
+
 	if (!can_do_mlock())
 		return -EPERM;
 

@@ -735,6 +737,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
+	start = untagged_addr(start);
+
 	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 

mm/mprotect.c +2 -0

index bf38dfbbb4b4..19f981b733bc 100644
@@ -465,6 +465,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
 
+	start = untagged_addr(start);
+
 	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
 	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
 		return -EINVAL;

mm/mremap.c +7 -0

index fc241d23cd97..64c9a3b8be0a 100644
@@ -606,6 +606,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
+	/*
+	 * Architectures may interpret the tag passed to mmap as a background
+	 * colour for the corresponding vma. For mremap we don't allow tagged
+	 * new_addr to preserve similar behaviour to mmap.
+	 */
+	addr = untagged_addr(addr);
+
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
 

mm/msync.c +2 -0

index ef30a429623a..c3bd3e75f687 100644
@@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 	int unmapped_error = 0;
 	int error = -EINVAL;
 
+	start = untagged_addr(start);
+
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;
 	if (offset_in_page(start))

Quoted 12 lines · Andrey Konovalov

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

This patch allows tagged pointers to be passed to the following memory
syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect, mremap, msync, munlock, move_pages.

The mmap and mremap syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.

Quoted 4 lines

Reviewed-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---

Reviewed-by Khalid Aziz <[email protected]>

Quoted 137 lines

 mm/madvise.c   | 2 ++
 mm/mempolicy.c | 3 +++
 mm/migrate.c   | 2 +-
 mm/mincore.c   | 2 ++
 mm/mlock.c     | 4 ++++
 mm/mprotect.c  | 2 ++
 mm/mremap.c    | 7 +++++++
 mm/msync.c     | 2 ++
 8 files changed, 23 insertions(+), 1 deletion(-)

mm/madvise.c +2 -0

index 628022e674a7..39b82f8a698f 100644
@@ -810,6 +810,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	size_t len;
 	struct blk_plug plug;
 
+	start = untagged_addr(start);
+
 	if (!madvise_behavior_valid(behavior))
 		return error;
 

mm/mempolicy.c +3 -0

index 01600d80ae01..78e0a88b2680 100644
@@ -1360,6 +1360,7 @@ static long kernel_mbind(unsigned long start, unsigned long len,
 	int err;
 	unsigned short mode_flags;
 
+	start = untagged_addr(start);
 	mode_flags = mode & MPOL_MODE_FLAGS;
 	mode &= ~MPOL_MODE_FLAGS;
 	if (mode >= MPOL_MAX)

@@ -1517,6 +1518,8 @@ static int kernel_get_mempolicy(int __user *policy,
 	int uninitialized_var(pval);
 	nodemask_t nodes;
 
+	addr = untagged_addr(addr);
+
 	if (nmask != NULL && maxnode < nr_node_ids)
 		return -EINVAL;
 

mm/migrate.c +1 -1

index f2ecc2855a12..d22c45cf36b2 100644
@@ -1616,7 +1616,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			goto out_flush;
 		if (get_user(node, nodes + i))
 			goto out_flush;
-		addr = (unsigned long)p;
+		addr = (unsigned long)untagged_addr(p);
 
 		err = -ENODEV;
 		if (node < 0 || node >= MAX_NUMNODES)

mm/mincore.c +2 -0

index c3f058bd0faf..64c322ed845c 100644
@@ -249,6 +249,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
 	unsigned long pages;
 	unsigned char *tmp;
 
+	start = untagged_addr(start);
+
 	/* Check the start address: needs to be page-aligned.. */
 	if (start & ~PAGE_MASK)
 		return -EINVAL;fixup_user_fault

mm/mlock.c +4 -0

index 080f3b36415b..e82609eaa428 100644
@@ -674,6 +674,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla
 	unsigned long lock_limit;
 	int error = -ENOMEM;
 
+	start = untagged_addr(start);
+
 	if (!can_do_mlock())
 		return -EPERM;
 

@@ -735,6 +737,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
+	start = untagged_addr(start);
+
 	len = PAGE_ALIGN(len + (offset_in_page(start)));
 	start &= PAGE_MASK;
 

mm/mprotect.c +2 -0

index bf38dfbbb4b4..19f981b733bc 100644
@@ -465,6 +465,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
 				(prot & PROT_READ);
 
+	start = untagged_addr(start);
+
 	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
 	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
 		return -EINVAL;

mm/mremap.c +7 -0

index fc241d23cd97..64c9a3b8be0a 100644
@@ -606,6 +606,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	LIST_HEAD(uf_unmap_early);
 	LIST_HEAD(uf_unmap);
 
+	/*
+	 * Architectures may interpret the tag passed to mmap as a background
+	 * colour for the corresponding vma. For mremap we don't allow tagged
+	 * new_addr to preserve similar behaviour to mmap.
+	 */
+	addr = untagged_addr(addr);
+
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
 

mm/msync.c +2 -0

index ef30a429623a..c3bd3e75f687 100644
@@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 	int unmapped_error = 0;
 	int error = -EINVAL;
 
+	start = untagged_addr(start);
+
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;
 	if (offset_in_page(start))

Quoted 13 lines · Khalid Aziz

Quoted 12 lines · Andrey Konovalov

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

This patch allows tagged pointers to be passed to the following memory
syscalls: get_mempolicy, madvise, mbind, mincore, mlock, mlock2, mprotect, mremap, msync, munlock, move_pages.

The mmap and mremap syscalls do not currently accept tagged addresses. Architectures may interpret the tag as a background colour for the corresponding vma.

Quoted 8 lines

Quoted 4 lines

Reviewed-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---

Reviewed-by Khalid Aziz <[email protected]>

I would also recommend updating commit log for all the patches in this series that are changing files under mm/ as opposed to arch/arm64 to not reference arm64 kernel ABI since the change applies to every architecture. So something along the lines of "This patch is part of a series that extends kernel ABI to allow......."

--
Khalid

Quoted 139 lines

Quoted 137 lines

 mm/madvise.c   | 2 ++
 mm/mempolicy.c | 3 +++
 mm/migrate.c   | 2 +-
 mm/mincore.c   | 2 ++
 mm/mlock.c     | 4 ++++
 mm/mprotect.c  | 2 ++
 mm/mremap.c    | 7 +++++++
 mm/msync.c     | 2 ++
 8 files changed, 23 insertions(+), 1 deletion(-)

mm/madvise.c +2 -0

index 628022e674a7..39b82f8a698f 100644
@@ -810,6 +810,8 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
     size_t len;
     struct blk_plug plug;
 
+    start = untagged_addr(start);
+
     if (!madvise_behavior_valid(behavior))
             return error;
 

mm/mempolicy.c +3 -0

index 01600d80ae01..78e0a88b2680 100644
@@ -1360,6 +1360,7 @@ static long kernel_mbind(unsigned long start, unsigned long len,
     int err;
     unsigned short mode_flags;
 
+    start = untagged_addr(start);
     mode_flags = mode & MPOL_MODE_FLAGS;
     mode &= ~MPOL_MODE_FLAGS;
     if (mode >= MPOL_MAX)

@@ -1517,6 +1518,8 @@ static int kernel_get_mempolicy(int __user *policy,
     int uninitialized_var(pval);
     nodemask_t nodes;
 
+    addr = untagged_addr(addr);
+
     if (nmask != NULL && maxnode < nr_node_ids)
             return -EINVAL;
 

mm/migrate.c +1 -1

index f2ecc2855a12..d22c45cf36b2 100644
@@ -1616,7 +1616,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
                     goto out_flush;
             if (get_user(node, nodes + i))
                     goto out_flush;
-            addr = (unsigned long)p;
+            addr = (unsigned long)untagged_addr(p);
 
             err = -ENODEV;
             if (node < 0 || node >= MAX_NUMNODES)

mm/mincore.c +2 -0

index c3f058bd0faf..64c322ed845c 100644
@@ -249,6 +249,8 @@ SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
     unsigned long pages;
     unsigned char *tmp;
 
+    start = untagged_addr(start);
+
     /* Check the start address: needs to be page-aligned.. */
     if (start & ~PAGE_MASK)
             return -EINVAL;fixup_user_fault

mm/mlock.c +4 -0

index 080f3b36415b..e82609eaa428 100644
@@ -674,6 +674,8 @@ static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t fla
     unsigned long lock_limit;
     int error = -ENOMEM;
 
+    start = untagged_addr(start);
+
     if (!can_do_mlock())
             return -EPERM;
 

@@ -735,6 +737,8 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
     int ret;
 
+    start = untagged_addr(start);
+
     len = PAGE_ALIGN(len + (offset_in_page(start)));
     start &= PAGE_MASK;
 

mm/mprotect.c +2 -0

index bf38dfbbb4b4..19f981b733bc 100644
@@ -465,6 +465,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
     const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
                             (prot & PROT_READ);
 
+    start = untagged_addr(start);
+
     prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
     if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
             return -EINVAL;

mm/mremap.c +7 -0

index fc241d23cd97..64c9a3b8be0a 100644
@@ -606,6 +606,13 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
     LIST_HEAD(uf_unmap_early);
     LIST_HEAD(uf_unmap);
 
+    /*
+     * Architectures may interpret the tag passed to mmap as a background
+     * colour for the corresponding vma. For mremap we don't allow tagged
+     * new_addr to preserve similar behaviour to mmap.
+     */
+    addr = untagged_addr(addr);
+
     if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
             return ret;
 

mm/msync.c +2 -0

index ef30a429623a..c3bd3e75f687 100644
@@ -37,6 +37,8 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
     int unmapped_error = 0;
     int error = -EINVAL;
 
+    start = untagged_addr(start);
+
     if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
             goto out;
     if (offset_in_page(start))

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

mm/gup.c provides a kernel interface that accepts user addresses and manipulates user pages directly (for example get_user_pages, that is used by the futex syscall). Since a user can provided tagged addresses, we need to handle this case.

Add untagging to gup.c functions that use user addresses for vma lookups.

Reviewed-by Kees Cook <[email protected]>

Reviewed-by Catalin Marinas <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 mm/gup.c | 4 ++++
 1 file changed, 4 insertions(+)

mm/gup.c +4 -0

index ddde097cf9e4..c37df3d455a2 100644
@@ -802,6 +802,8 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (!nr_pages)
 		return 0;
 
+	start = untagged_addr(start);
+
 	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
 
 	/*

@@ -964,6 +966,8 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	struct vm_area_struct *vma;
 	vm_fault_t ret, major = 0;
 
+	address = untagged_addr(address);
+
 	if (unlocked)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

mm/gup.c provides a kernel interface that accepts user addresses and manipulates user pages directly (for example get_user_pages, that is used by the futex syscall). Since a user can provided tagged addresses, we need to handle this case.

Add untagging to gup.c functions that use user addresses for vma lookups.

Reviewed-by Kees Cook <[email protected]>

Reviewed-by Catalin Marinas <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---

 mm/gup.c | 4 ++++
 1 file changed, 4 insertions(+)

mm/gup.c +4 -0

index ddde097cf9e4..c37df3d455a2 100644
@@ -802,6 +802,8 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (!nr_pages)
 		return 0;
 
+	start = untagged_addr(start);
+
 	VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
 
 	/*

@@ -964,6 +966,8 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
 	struct vm_area_struct *vma;
 	vm_fault_t ret, major = 0;
 
+	address = untagged_addr(address);
+
 	if (unlocked)
 		fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

get_vaddr_frames uses provided user pointers for vma lookups, which can only by done with untagged pointers. Instead of locating and changing all callers of this function, perform untagging in it.

Acked-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 mm/frame_vector.c | 2 ++
 1 file changed, 2 insertions(+)

mm/frame_vector.c +2 -0

index c64dca6e27c2..c431ca81dad5 100644
@@ -46,6 +46,8 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 	if (WARN_ON_ONCE(nr_frames > vec->nr_allocated))
 		nr_frames = vec->nr_allocated;
 
+	start = untagged_addr(start);
+
 	down_read(&mm->mmap_sem);
 	locked = 1;
 	vma = find_vma_intersection(mm, start, start + 1);

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

get_vaddr_frames uses provided user pointers for vma lookups, which can only by done with untagged pointers. Instead of locating and changing all callers of this function, perform untagging in it.

Acked-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---

 mm/frame_vector.c | 2 ++
 1 file changed, 2 insertions(+)

mm/frame_vector.c +2 -0

index c64dca6e27c2..c431ca81dad5 100644
@@ -46,6 +46,8 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames,
 	if (WARN_ON_ONCE(nr_frames > vec->nr_allocated))
 		nr_frames = vec->nr_allocated;
 
+	start = untagged_addr(start);
+
 	down_read(&mm->mmap_sem);
 	locked = 1;
 	vma = find_vma_intersection(mm, start, start + 1);

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

In copy_mount_options a user address is being subtracted from TASK_SIZE. If the address is lower than TASK_SIZE, the size is calculated to not allow the exact_copy_from_user() call to cross TASK_SIZE boundary. However if the address is tagged, then the size will be calculated incorrectly.

Untag the address before subtracting.

Reviewed-by Kees Cook <[email protected]>

Reviewed-by Catalin Marinas <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 fs/namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/namespace.c +1 -1

index b26778bdc236..2e85712a19ed 100644
@@ -2993,7 +2993,7 @@ void *copy_mount_options(const void __user * data)
 	 * the remainder of the page.
 	 */
 	/* copy_from_user cannot cross TASK_SIZE ! */
-	size = TASK_SIZE - (unsigned long)data;
+	size = TASK_SIZE - (unsigned long)untagged_addr(data);
 	if (size > PAGE_SIZE)
 		size = PAGE_SIZE;
 

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

In copy_mount_options a user address is being subtracted from TASK_SIZE. If the address is lower than TASK_SIZE, the size is calculated to not allow the exact_copy_from_user() call to cross TASK_SIZE boundary. However if the address is tagged, then the size will be calculated incorrectly.

Untag the address before subtracting.

Reviewed-by Kees Cook <[email protected]>

Reviewed-by Catalin Marinas <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---

 fs/namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/namespace.c +1 -1

index b26778bdc236..2e85712a19ed 100644
@@ -2993,7 +2993,7 @@ void *copy_mount_options(const void __user * data)
 	 * the remainder of the page.
 	 */
 	/* copy_from_user cannot cross TASK_SIZE ! */
-	size = TASK_SIZE - (unsigned long)data;
+	size = TASK_SIZE - (unsigned long)untagged_addr(data);
 	if (size > PAGE_SIZE)
 		size = PAGE_SIZE;
 

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

userfaultfd code use provided user pointers for vma lookups, which can only by done with untagged pointers.

Untag user pointers in validate_range().

Reviewed-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 fs/userfaultfd.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

fs/userfaultfd.c +12 -10

index 3b30301c90ec..24d68c3b5ee2 100644
@@ -1263,21 +1263,23 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 }
 
 static __always_inline int validate_range(struct mm_struct *mm,
-					  __u64 start, __u64 len)
+					  __u64 *start, __u64 len)
 {
 	__u64 task_size = mm->task_size;
 
-	if (start & ~PAGE_MASK)
+	*start = untagged_addr(*start);
+
+	if (*start & ~PAGE_MASK)
 		return -EINVAL;
 	if (len & ~PAGE_MASK)
 		return -EINVAL;
 	if (!len)
 		return -EINVAL;
-	if (start < mmap_min_addr)
+	if (*start < mmap_min_addr)
 		return -EINVAL;
-	if (start >= task_size)
+	if (*start >= task_size)
 		return -EINVAL;
-	if (len > task_size - start)
+	if (len > task_size - *start)
 		return -EINVAL;
 	return 0;
 }

@@ -1327,7 +1329,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		goto out;
 	}
 
-	ret = validate_range(mm, uffdio_register.range.start,
+	ret = validate_range(mm, &uffdio_register.range.start,
 			     uffdio_register.range.len);
 	if (ret)
 		goto out;

@@ -1516,7 +1518,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
 		goto out;
 
-	ret = validate_range(mm, uffdio_unregister.start,
+	ret = validate_range(mm, &uffdio_unregister.start,
 			     uffdio_unregister.len);
 	if (ret)
 		goto out;

@@ -1667,7 +1669,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
 	if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
 		goto out;
 
-	ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
+	ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len);
 	if (ret)
 		goto out;
 

@@ -1707,7 +1709,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 			   sizeof(uffdio_copy)-sizeof(__s64)))
 		goto out;
 
-	ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
+	ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len);
 	if (ret)
 		goto out;
 	/*

@@ -1763,7 +1765,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
 			   sizeof(uffdio_zeropage)-sizeof(__s64)))
 		goto out;
 
-	ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
+	ret = validate_range(ctx->mm, &uffdio_zeropage.range.start,
 			     uffdio_zeropage.range.len);
 	if (ret)
 		goto out;

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

videobuf_dma_contig_user_get() uses provided user pointers for vma lookups, which can only by done with untagged pointers.

Untag the pointers in this function.

Reviewed-by Kees Cook <[email protected]>

Acked-by Mauro Carvalho Chehab <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---

 drivers/media/v4l2-core/videobuf-dma-contig.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

exact_copy_from_user

drivers/media/v4l2-core/videobuf-dma-contig.c +5 -4

index e1bf50df4c70..8a1ddd146b17 100644
@@ -160,6 +160,7 @@ static void videobuf_dma_contig_user_put(struct videobuf_dma_contig_memory *mem)
 static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem,
 					struct videobuf_buffer *vb)
 {
+	unsigned long untagged_baddr = untagged_addr(vb->baddr);
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long prev_pfn, this_pfn;

@@ -167,22 +168,22 @@ static int videobuf_dma_contig_user_get(struct videobuf_dma_contig_memory *mem,
 	unsigned int offset;
 	int ret;
 
-	offset = vb->baddr & ~PAGE_MASK;
+	offset = untagged_baddr & ~PAGE_MASK;
 	mem->size = PAGE_ALIGN(vb->size + offset);
 	ret = -EINVAL;
 
 	down_read(&mm->mmap_sem);
 
-	vma = find_vma(mm, vb->baddr);
+	vma = find_vma(mm, untagged_baddr);
 	if (!vma)
 		goto out_up;
 
-	if ((vb->baddr + mem->size) > vma->vm_end)
+	if ((untagged_baddr + mem->size) > vma->vm_end)
 		goto out_up;
 
 	pages_done = 0;
 	prev_pfn = 0; /* kill warning */
-	user_address = vb->baddr;
+	user_address = untagged_baddr;
 
 	while (pages_done < (mem->size >> PAGE_SHIFT)) {
 		ret = follow_pfn(vma, user_address, &this_pfn);

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

vaddr_get_pfn() uses provided user pointers for vma lookups, which can only by done with untagged pointers.

Untag user pointers in this function.

Reviewed-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 drivers/vfio/vfio_iommu_type1.c | 2 ++
 1 file changed, 2 insertions(+)

drivers/vfio/vfio_iommu_type1.c +2 -0

index 3ddc375e7063..528e39a1c2dd 100644
@@ -384,6 +384,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 
 	down_read(&mm->mmap_sem);
 
+	vaddr = untagged_addr(vaddr);
+
 	vma = find_vma_intersection(mm, vaddr, vaddr + 1);
 
 	if (vma && vma->vm_flags & VM_PFNMAP) {

This patch is a part of a series that extends arm64 kernel ABI to allow to pass tagged user pointers (with the top byte set to something else other than 0x00) as syscall arguments.

vaddr_get_pfn() uses provided user pointers for vma lookups, which can only by done with untagged pointers.

Untag user pointers in this function.

Reviewed-by Catalin Marinas <[email protected]>

Reviewed-by Kees Cook <[email protected]>

Signed-off-by Andrey Konovalov <[email protected]>

---
 drivers/vfio/vfio_iommu_type1.c | 2 ++
 1 file changed, 2 insertions(+)

drivers/vfio/vfio_iommu_type1.c +0 -0

index 3ddc375e7063..528e39a1c2dd 100644

tools/testing/selftests/arm64/tags_lib.c new file +6 -0

@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdlib.h>
+#include <sys/prctl.h>
+
+#define TAG_SHIFT	(56)

tools/testing/selftests/arm64/tags_lib.c new file +31 -0

+
+static void *tag_ptr(void *ptr)
+{
+	static int tagged_addr_err = 1;
+	unsigned long tag = 0;
+
+	/*
+	 * Note that this code is racy. We only use it as a part of a single
+	 * threaded test application. Beware of using in multithreaded ones.
+	 */
+	if (tagged_addr_err == 1)
+		tagged_addr_err = prctl(PR_SET_TAGGED_ADDR_CTRL,
+				PR_TAGGED_ADDR_ENABLE, 0, 0, 0);
+
+	if (!ptr)
+		return ptr;
+	if (!tagged_addr_err)
+		tag = rand() & 0xff;
+
+	return (void *)((unsigned long)ptr | (tag << TAG_SHIFT));
+}
+
+static void *untag_ptr(void *ptr)
+{
+	return (void *)((unsigned long)ptr & ~TAG_MASK);
+}
+
+void *malloc(size_t size)
+{
+	return tag_ptr(__libc_malloc(size));
+}

Quoted 9 lines · Andrey Konovalov

tools/testing/selftests/arm64/tags_lib.c new file +6 -0

@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdlib.h>
+#include <sys/prctl.h>
+
+#define TAG_SHIFT	(56)

tools/testing/selftests/arm64/tags_lib.c line 16

Quoted 10 lines

tools/testing/selftests/arm64/tags_lib.c new file +10 -0

+#define TAG_MASK	(0xffUL << TAG_SHIFT)
+
+#define PR_SET_TAGGED_ADDR_CTRL	55
+#define PR_GET_TAGGED_ADDR_CTRL	56
+#define PR_TAGGED_ADDR_ENABLE	(1UL << 0)
+
+void *__libc_malloc(size_t size);
+void __libc_free(void *ptr);
+void *__libc_realloc(void *ptr, size_t size);
+void *__libc_calloc(size_t nmemb, size_t size);

this does not work on at least musl.

the most robust solution would be to implement the malloc apis with mmap/munmap/mremap, if that's too cumbersome then use dlsym RTLD_NEXT (although that has the slight wart that in glibc it may call calloc so wrapping calloc that way is tricky).

in simple linux tests i'd just use static or stack allocations or mmap.

if a generic preloadable lib solution is needed then do it properly with pthread_once to avoid races etc.

Quoted 32 lines · Szabolcs Nagy

Quoted 9 lines · Andrey Konovalov

tools/testing/selftests/arm64/tags_lib.c new file +6 -0

@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdlib.h>
+#include <sys/prctl.h>
+
+#define TAG_SHIFT  (56)

tools/testing/selftests/arm64/tags_lib.c line 16

Quoted 10 lines

tools/testing/selftests/arm64/tags_lib.c new file +10 -0

+#define TAG_MASK   (0xffUL << TAG_SHIFT)
+
+#define PR_SET_TAGGED_ADDR_CTRL    55
+#define PR_GET_TAGGED_ADDR_CTRL    56
+#define PR_TAGGED_ADDR_ENABLE      (1UL << 0)
+
+void *__libc_malloc(size_t size);
+void __libc_free(void *ptr);
+void *__libc_realloc(void *ptr, size_t size);
+void *__libc_calloc(size_t nmemb, size_t size);

this does not work on at least musl.

the most robust solution would be to implement the malloc apis with mmap/munmap/mremap, if that's too cumbersome then use dlsym RTLD_NEXT (although that has the slight wart that in glibc it may call calloc so wrapping calloc that way is tricky).

in simple linux tests i'd just use static or stack allocations or mmap.

Quoted 3 lines

if a generic preloadable lib solution is needed then do it properly with pthread_once to avoid races etc.

Thanks for the feedback Szabolcs. I guess we can go back to the initial simple test that Andrey had and drop the whole LD_PRELOAD hack (I'll just use it for my internal testing).

BTW, when you get some time, please review Vincenzo's ABI documentation patches from a user/libc perspective. Once agreed, they should become part of this series.

--
Catalin