On 12/06/2019 12:43, Andrey Konovalov wrote:

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 keescook@chromium.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Andrey Konovalov andreyknvl@google.com

Reviewed-by: Vincenzo Frascino vincenzo.frascino@arm.com

---

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

diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index e5d5f31c6d36..df729afca0ba 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -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();

On 12/06/2019 12:43, Andrey Konovalov wrote:

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 khalid.aziz@oracle.com Acked-by: Kees Cook keescook@chromium.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Andrey Konovalov andreyknvl@google.com

Reviewed-by: Vincenzo Frascino vincenzo.frascino@arm.com

---

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

diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 023ba9f3b99f..dccb95af6003 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -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;

diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 7f2db3fe311f..28ff554a1be8 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -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;

On 12/06/2019 12:43, Andrey Konovalov wrote:

From: Catalin Marinas catalin.marinas@arm.com

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 catalin.marinas@arm.com

Reviewed-by: Vincenzo Frascino vincenzo.frascino@arm.com

---

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(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fcd0e691b1ea..fee457456aa8 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -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

diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index f1d032be628a..354a31d2b737 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -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) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index df729afca0ba..995b9ea11a89 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -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( diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 3767fb21a5b8..69d0be1fc708 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -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); diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 094bb03b9cc2..2e927b3e9d6c 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -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 */ diff --git a/kernel/sys.c b/kernel/sys.c index 2969304c29fe..ec48396b4943 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -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;

On Wed, Jun 12, 2019 at 01:43:20PM +0200, Andrey Konovalov wrote:

From: Catalin Marinas catalin.marinas@arm.com

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 catalin.marinas@arm.com

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(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fcd0e691b1ea..fee457456aa8 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -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

diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index f1d032be628a..354a31d2b737 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -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) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index df729afca0ba..995b9ea11a89 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -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( diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 3767fb21a5b8..69d0be1fc708 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -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;

!!!

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.)

+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); diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 094bb03b9cc2..2e927b3e9d6c 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -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)

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

#endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sys.c b/kernel/sys.c index 2969304c29fe..ec48396b4943 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -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)
  

<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.

</bikeshed>

(OTOH, the extra arguments are harmless and prctl is far from being a general-purpose syscall.)

• 	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?

(The usecase for PR_SVE_GET_VL was always a bit dubious, since the VL can also be read via an SVE insn or a compiler intrinsic, which is less portable but much cheaper. As for the PR_SVE_SET_VL_INHERIT flag that can be read via PR_SVE_GET_VL, I've never been sure how useful it is to be able to read that...)

[...]

Cheers ---Dave

On Wed, Jun 12, 2019 at 01:43:20PM +0200, Andrey Konovalov wrote:

From: Catalin Marinas catalin.marinas@arm.com

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 catalin.marinas@arm.com

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(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fcd0e691b1ea..fee457456aa8 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -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 */

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

Name mismatch?

+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()

[...]

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 3767fb21a5b8..69d0be1fc708 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -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;
  

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.

• 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.

• 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.

[...]

Cheers ---Dave

On 13/06/2019 16:35, Catalin Marinas wrote:

On Thu, Jun 13, 2019 at 12:16:59PM +0100, Dave P Martin wrote:

...

On Wed, Jun 12, 2019 at 01:43:20PM +0200, Andrey Konovalov wrote:

...

From: Catalin Marinas catalin.marinas@arm.com

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 catalin.marinas@arm.com

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(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fcd0e691b1ea..fee457456aa8 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -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 */

(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.

...

...

+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()

[...]

...

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 3767fb21a5b8..69d0be1fc708 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -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;
  

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).

Why you are not keen on a Kconfig option?

...

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.

...

...

• 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.

...

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.

...

...

• 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.

On 6/12/19 5:43 AM, Andrey Konovalov wrote:

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 catalin.marinas@arm.com Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Andrey Konovalov andreyknvl@google.com

---

Reviewed-by: Khalid Aziz khalid.aziz@oracle.com

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(-)

diff --git a/mm/madvise.c b/mm/madvise.c index 628022e674a7..39b82f8a698f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -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;

diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 01600d80ae01..78e0a88b2680 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -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;

diff --git a/mm/migrate.c b/mm/migrate.c index f2ecc2855a12..d22c45cf36b2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -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) diff --git a/mm/mincore.c b/mm/mincore.c index c3f058bd0faf..64c322ed845c 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -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;

diff --git a/mm/mlock.c b/mm/mlock.c index 080f3b36415b..e82609eaa428 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -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;

diff --git a/mm/mprotect.c b/mm/mprotect.c index bf38dfbbb4b4..19f981b733bc 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -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;

diff --git a/mm/mremap.c b/mm/mremap.c index fc241d23cd97..64c9a3b8be0a 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -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;

diff --git a/mm/msync.c b/mm/msync.c index ef30a429623a..c3bd3e75f687 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -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))

On Wed, Jun 19, 2019 at 6:46 PM Khalid Aziz khalid.aziz@oracle.com wrote:

On 6/19/19 9:55 AM, Khalid Aziz wrote:

...

On 6/12/19 5:43 AM, Andrey Konovalov wrote:

...

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 catalin.marinas@arm.com Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Andrey Konovalov andreyknvl@google.com

---

Reviewed-by: Khalid Aziz khalid.aziz@oracle.com

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......."

Sure, will do in v18, thanks!

-- Khalid

...

...

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(-)

diff --git a/mm/madvise.c b/mm/madvise.c index 628022e674a7..39b82f8a698f 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -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;

diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 01600d80ae01..78e0a88b2680 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -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;

diff --git a/mm/migrate.c b/mm/migrate.c index f2ecc2855a12..d22c45cf36b2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -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)
  

diff --git a/mm/mincore.c b/mm/mincore.c index c3f058bd0faf..64c322ed845c 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -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

diff --git a/mm/mlock.c b/mm/mlock.c index 080f3b36415b..e82609eaa428 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -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;

diff --git a/mm/mprotect.c b/mm/mprotect.c index bf38dfbbb4b4..19f981b733bc 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -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;

diff --git a/mm/mremap.c b/mm/mremap.c index fc241d23cd97..64c9a3b8be0a 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -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;

diff --git a/mm/msync.c b/mm/msync.c index ef30a429623a..c3bd3e75f687 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -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))

On 12/06/2019 12:43, Andrey Konovalov wrote:

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 keescook@chromium.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Andrey Konovalov andreyknvl@google.com

Reviewed-by: Vincenzo Frascino vincenzo.frascino@arm.com

---

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

diff --git a/mm/gup.c b/mm/gup.c index ddde097cf9e4..c37df3d455a2 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -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;

On 6/12/19 5:43 AM, Andrey Konovalov wrote:

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 catalin.marinas@arm.com Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Andrey Konovalov andreyknvl@google.com

---

With the suggested change to commit log in my previous email:

Reviewed-by: Khalid Aziz khalid.aziz@oracle.com

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

diff --git a/mm/frame_vector.c b/mm/frame_vector.c index c64dca6e27c2..c431ca81dad5 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -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);

On 12/06/2019 12:43, Andrey Konovalov wrote:

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 keescook@chromium.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Andrey Konovalov andreyknvl@google.com

Reviewed-by: Vincenzo Frascino vincenzo.frascino@arm.com

---

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

diff --git a/fs/namespace.c b/fs/namespace.c index b26778bdc236..2e85712a19ed 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -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;

On 6/12/19 5:43 AM, Andrey Konovalov wrote:

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 keescook@chromium.org Acked-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Andrey Konovalov andreyknvl@google.com

---

Patch looks good, but commit log should be updated to not be specific to arm64.

Reviewed-by: Khalid Aziz khalid.aziz@oracle.com

drivers/media/v4l2-core/videobuf-dma-contig.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) exact_copy_from_user diff --git a/drivers/media/v4l2-core/videobuf-dma-contig.c b/drivers/media/v4l2-core/videobuf-dma-contig.c index e1bf50df4c70..8a1ddd146b17 100644 --- a/drivers/media/v4l2-core/videobuf-dma-contig.c +++ b/drivers/media/v4l2-core/videobuf-dma-contig.c @@ -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);

Hi Andrey,

On 6/12/19 1:43 PM, Andrey Konovalov wrote:

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 catalin.marinas@arm.com Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Andrey Konovalov andreyknvl@google.com

Reviewed-by: Eric Auger eric.auger@redhat.com

Thanks

Eric

---

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

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 3ddc375e7063..528e39a1c2dd 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -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) {

On 12/06/2019 12:43, Andrey Konovalov wrote:

--- /dev/null +++ b/tools/testing/selftests/arm64/tags_lib.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0

+#include <stdlib.h> +#include <sys/prctl.h>

+#define TAG_SHIFT (56) +#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.

+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));

+}

...

On arm64 the TCR_EL1.TBI0 bit has been always enabled hence the userspace (EL0) is allowed to set a non-zero value in the top byte but the resulting pointers are not allowed at the user-kernel syscall ABI boundary.

With the relaxed ABI proposed through this document, it is now possible to pass tagged pointers to the syscalls, when these pointers are in memory ranges obtained by an anonymous (MAP_ANONYMOUS) mmap().

This change in the ABI requires a mechanism to requires the userspace to opt-in to such an option.

Specify and document the way in which sysctl and prctl() can be used in combination to allow the userspace to opt-in this feature.

Cc: Catalin Marinas catalin.marinas@arm.com Cc: Will Deacon will.deacon@arm.com CC: Andrey Konovalov andreyknvl@google.com Signed-off-by: Vincenzo Frascino vincenzo.frascino@arm.com --- Documentation/arm64/tagged-address-abi.txt | 111 +++++++++++++++++++++ 1 file changed, 111 insertions(+) create mode 100644 Documentation/arm64/tagged-address-abi.txt

diff --git a/Documentation/arm64/tagged-address-abi.txt b/Documentation/arm64/tagged-address-abi.txt new file mode 100644 index 000000000000..96e149e2c55c --- /dev/null +++ b/Documentation/arm64/tagged-address-abi.txt @@ -0,0 +1,111 @@ +ARM64 TAGGED ADDRESS ABI +======================== + +This document describes the usage and semantics of the Tagged Address +ABI on arm64. + +1. Introduction +--------------- + +On arm64 the TCR_EL1.TBI0 bit has been always enabled on the arm64 kernel, +hence the userspace (EL0) is allowed to set a non-zero value in the top +byte but the resulting pointers are not allowed at the user-kernel syscall +ABI boundary. + +This document describes a relaxation of the ABI with which it is possible +to pass tagged tagged pointers to the syscalls, when these pointers are in +memory ranges obtained as described in paragraph 2. + +Since it is not desirable to relax the ABI to allow tagged user addresses +into the kernel indiscriminately, arm64 provides a new sysctl interface +(/proc/sys/abi/tagged_addr) that is used to prevent the applications from +enabling the relaxed ABI and a new prctl() interface that can be used to +enable or disable the relaxed ABI. + +The sysctl is meant also for testing purposes in order to provide a simple +way for the userspace to verify the return error checking of the prctl() +command without having to reconfigure the kernel. + +The ABI properties are inherited by threads of the same application and +fork()'ed children but cleared when a new process is spawn (execve()). + +2. ARM64 Tagged Address ABI +--------------------------- + +From the kernel syscall interface prospective, we define, for the purposes +of this document, a "valid tagged pointer" as a pointer that either it has +a zero value set in the top byte or it has a non-zero value, it is in memory +ranges privately owned by a userspace process and it is obtained in one of +the following ways: + - mmap() done by the process itself, where either: + * flags = MAP_PRIVATE | MAP_ANONYMOUS + * flags = MAP_PRIVATE and the file descriptor refers to a regular + file or "/dev/zero" + - a mapping below sbrk(0) done by the process itself + - any memory mapped by the kernel in the process's address space during + creation and following the restrictions presented above (i.e. data, bss, + stack). + +The ARM64 Tagged Address ABI is an opt-in feature, and an application can +control it using the following prctl()s: + - PR_SET_TAGGED_ADDR_CTRL: can be used to enable the Tagged Address ABI. + - PR_GET_TAGGED_ADDR_CTRL: can be used to check the status of the Tagged + Address ABI. + +As a consequence of invoking PR_SET_TAGGED_ADDR_CTRL prctl() by an applications, +the ABI guarantees the following behaviours: + + - Every current or newly introduced syscall can accept any valid tagged + pointers. + + - If a non valid tagged pointer is passed to a syscall then the behaviour + is undefined. + + - Every valid tagged pointer is expected to work as an untagged one. + + - The kernel preserves any valid tagged pointers and returns them to the + userspace unchanged in all the cases except the ones documented in the + "Preserving tags" paragraph of tagged-pointers.txt. + +A definition of the meaning of tagged pointers on arm64 can be found in: +Documentation/arm64/tagged-pointers.txt. + +3. ARM64 Tagged Address ABI Exceptions +-------------------------------------- + +The behaviours described in paragraph 2, with particular reference to the +acceptance by the syscalls of any valid tagged pointer are not applicable +to the following cases: + - mmap() addr parameter. + - mremap() new_address parameter. + - prctl_set_mm() struct prctl_map fields. + - prctl_set_mm_map() struct prctl_map fields. + +4. Example of correct usage +--------------------------- + +void main(void) +{ + static int tbi_enabled = 0; + unsigned long tag = 0; + + char *ptr = mmap(NULL, PAGE_SIZE, PROT_READ | PROT_WRITE, + MAP_ANONYMOUS, -1, 0); + + if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, + 0, 0, 0) == 0) + tbi_enabled = 1; + + if (!ptr) + return -1; + + if (tbi_enabled) + tag = rand() & 0xff; + + ptr = (char *)((unsigned long)ptr | (tag << TAG_SHIFT)); + + *ptr = 'a'; + + ... +} +

Hi Catalin,

On 12/06/2019 16:35, Catalin Marinas wrote:

Hi Vincenzo,

Some minor comments below but it looks fine to me overall. Cc'ing Szabolcs as well since I'd like a view from the libc people.

Thanks for this, I saw Szabolcs comments.

On Wed, Jun 12, 2019 at 03:21:10PM +0100, Vincenzo Frascino wrote:

...

diff --git a/Documentation/arm64/tagged-address-abi.txt b/Documentation/arm64/tagged-address-abi.txt new file mode 100644 index 000000000000..96e149e2c55c --- /dev/null +++ b/Documentation/arm64/tagged-address-abi.txt @@ -0,0 +1,111 @@ +ARM64 TAGGED ADDRESS ABI +========================

+This document describes the usage and semantics of the Tagged Address +ABI on arm64.

+1. Introduction +---------------

+On arm64 the TCR_EL1.TBI0 bit has been always enabled on the arm64 kernel, +hence the userspace (EL0) is allowed to set a non-zero value in the top

I'd be clearer here: "userspace (EL0) is allowed to perform a user memory access through a 64-bit pointer with a non-zero top byte" (or something along the lines). Otherwise setting a non-zero top byte is allowed on any architecture, dereferencing it is a problem.

Ok.

...

+byte but the resulting pointers are not allowed at the user-kernel syscall +ABI boundary.

+This document describes a relaxation of the ABI with which it is possible

"relaxation of the ABI that makes it possible to..."

...

+to pass tagged tagged pointers to the syscalls, when these pointers are in +memory ranges obtained as described in paragraph 2.

"section 2" is better. There are a lot more paragraphs.

Agree.

...

+Since it is not desirable to relax the ABI to allow tagged user addresses +into the kernel indiscriminately, arm64 provides a new sysctl interface +(/proc/sys/abi/tagged_addr) that is used to prevent the applications from +enabling the relaxed ABI and a new prctl() interface that can be used to +enable or disable the relaxed ABI.

+The sysctl is meant also for testing purposes in order to provide a simple +way for the userspace to verify the return error checking of the prctl() +command without having to reconfigure the kernel.

+The ABI properties are inherited by threads of the same application and +fork()'ed children but cleared when a new process is spawn (execve()).

"spawned".

I guess you could drop these three paragraphs here and mention the inheritance properties when introducing the prctl() below. You can also mention the global sysctl switch after the prctl() was introduced.

I will move the last two (rewording them) to the _section_ 2, but I would still prefer the Introduction to give an overview of the solution as well.

...

+2. ARM64 Tagged Address ABI +---------------------------

+From the kernel syscall interface prospective, we define, for the purposes +of this document, a "valid tagged pointer" as a pointer that either it has

"either has" (no 'it') sounds slightly better but I'm not a native English speaker either.

...

+a zero value set in the top byte or it has a non-zero value, it is in memory +ranges privately owned by a userspace process and it is obtained in one of +the following ways:

• • mmap() done by the process itself, where either:
• • flags = MAP_PRIVATE | MAP_ANONYMOUS
• • flags = MAP_PRIVATE and the file descriptor refers to a regular

•  file or "/dev/zero"
  

• • a mapping below sbrk(0) done by the process itself
• • any memory mapped by the kernel in the process's address space during
• creation and following the restrictions presented above (i.e. data, bss,
• stack).

+The ARM64 Tagged Address ABI is an opt-in feature, and an application can +control it using the following prctl()s:

• • PR_SET_TAGGED_ADDR_CTRL: can be used to enable the Tagged Address ABI.

enable or disable (not sure we need the latter but it doesn't heart).

I'd add the arg2 description here as well.

Good point I missed this.

...

• • PR_GET_TAGGED_ADDR_CTRL: can be used to check the status of the Tagged

•                         Address ABI.
  

+As a consequence of invoking PR_SET_TAGGED_ADDR_CTRL prctl() by an applications, +the ABI guarantees the following behaviours:

• • Every current or newly introduced syscall can accept any valid tagged
• pointers.
• • If a non valid tagged pointer is passed to a syscall then the behaviour
• is undefined.
• • Every valid tagged pointer is expected to work as an untagged one.
• • The kernel preserves any valid tagged pointers and returns them to the
• userspace unchanged in all the cases except the ones documented in the
• "Preserving tags" paragraph of tagged-pointers.txt.

I'd think we need to qualify the context here in which the kernel preserves the tagged pointers. Did you mean on the syscall return?

What this means is that on syscall return the tags are preserved, but if for example you have tagged pointers inside siginfo_t, they will not because according to tagged-pointers.txt non-zero tags are not preserved when delivering signals.

...

+A definition of the meaning of tagged pointers on arm64 can be found in: +Documentation/arm64/tagged-pointers.txt.

+3. ARM64 Tagged Address ABI Exceptions +--------------------------------------

+The behaviours described in paragraph 2, with particular reference to the

"section 2"

...

+acceptance by the syscalls of any valid tagged pointer are not applicable +to the following cases:

• • mmap() addr parameter.
• • mremap() new_address parameter.
• • prctl_set_mm() struct prctl_map fields.
• • prctl_set_mm_map() struct prctl_map fields.

+4. Example of correct usage +---------------------------

+void main(void) +{

• static int tbi_enabled = 0;
• unsigned long tag = 0;
• char *ptr = mmap(NULL, PAGE_SIZE, PROT_READ | PROT_WRITE,

• 	 MAP_ANONYMOUS, -1, 0);
  

• if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE,

•   0, 0, 0) == 0)
  

• tbi_enabled = 1;
  

• if (!ptr)

• return -1;
  

• if (tbi_enabled)

• tag = rand() & 0xff;
  

• ptr = (char *)((unsigned long)ptr | (tag << TAG_SHIFT));
• *ptr = 'a';
• ...

+}

-- 2.21.0

A couple of minor nits below.

On Wed, Jun 12, 2019 at 03:21:11PM +0100, Vincenzo Frascino wrote:

--- a/Documentation/arm64/tagged-pointers.txt +++ b/Documentation/arm64/tagged-pointers.txt @@ -18,7 +18,8 @@ Passing tagged addresses to the kernel

---

All interpretation of userspace memory addresses by the kernel assumes -an address tag of 0x00. +an address tag of 0x00, unless the userspace opts-in the ARM64 Tagged +Address ABI via the PR_SET_TAGGED_ADDR_CTRL prctl(). This includes, but is not limited to, addresses found in: @@ -31,18 +32,23 @@ This includes, but is not limited to, addresses found in:

• the frame pointer (x29) and frame records, e.g. when interpreting them to generate a backtrace or call graph.

-Using non-zero address tags in any of these locations may result in an -error code being returned, a (fatal) signal being raised, or other modes -of failure. +Using non-zero address tags in any of these locations when the +userspace application did not opt-in to the ARM64 Tagged Address ABI,

Nitpick: drop the comma after "ABI," since a predicate follows.

+may result in an error code being returned, a (fatal) signal being raised, +or other modes of failure. -For these reasons, passing non-zero address tags to the kernel via -system calls is forbidden, and using a non-zero address tag for sp is -strongly discouraged. +For these reasons, when the userspace application did not opt-in, passing +non-zero address tags to the kernel via system calls is forbidden, and using +a non-zero address tag for sp is strongly discouraged. Programs maintaining a frame pointer and frame records that use non-zero address tags may suffer impaired or inaccurate debug and profiling visibility. +A definition of the meaning of ARM64 Tagged Address ABI and of the +guarantees that the ABI provides when the userspace opts-in via prctl() +can be found in: Documentation/arm64/tagged-address-abi.txt.

Preserving tags

---

@@ -57,6 +63,9 @@ be preserved. The architecture prevents the use of a tagged PC, so the upper byte will be set to a sign-extension of bit 55 on exception return. +This behaviours are preserved even when the the userspace opts-in the ARM64

"These" ... "opts in to"

+Tagged Address ABI via the PR_SET_TAGGED_ADDR_CTRL prctl().

Other considerations

---

-- 2.21.0

On 13/06/2019 16:51, Vincenzo Frascino wrote:

On arm64 the TCR_EL1.TBI0 bit has been always enabled hence the userspace (EL0) is allowed to set a non-zero value in the top byte but the resulting pointers are not allowed at the user-kernel syscall ABI boundary.

With the relaxed ABI proposed through this document, it is now possible to pass tagged pointers to the syscalls, when these pointers are in memory ranges obtained by an anonymous (MAP_ANONYMOUS) mmap().

This change in the ABI requires a mechanism to requires the userspace to opt-in to such an option.

Specify and document the way in which sysctl and prctl() can be used in combination to allow the userspace to opt-in this feature.

Cc: Catalin Marinas catalin.marinas@arm.com Cc: Will Deacon will.deacon@arm.com CC: Andrey Konovalov andreyknvl@google.com Signed-off-by: Vincenzo Frascino vincenzo.frascino@arm.com

Acked-by: Szabolcs Nagy szabolcs.nagy@arm.com

---

Documentation/arm64/tagged-address-abi.txt | 134 +++++++++++++++++++++ 1 file changed, 134 insertions(+) create mode 100644 Documentation/arm64/tagged-address-abi.txt

diff --git a/Documentation/arm64/tagged-address-abi.txt b/Documentation/arm64/tagged-address-abi.txt new file mode 100644 index 000000000000..0ae900d4bb2d --- /dev/null +++ b/Documentation/arm64/tagged-address-abi.txt @@ -0,0 +1,134 @@ +ARM64 TAGGED ADDRESS ABI +========================

+This document describes the usage and semantics of the Tagged Address +ABI on arm64.

+1. Introduction +---------------

+On arm64 the TCR_EL1.TBI0 bit has been always enabled on the kernel, hence +the userspace (EL0) is entitled to perform a user memory access through a +64-bit pointer with a non-zero top byte but the resulting pointers are not +allowed at the user-kernel syscall ABI boundary.

+This document describes a relaxation of the ABI that makes it possible to +to pass tagged pointers to the syscalls, when these pointers are in memory +ranges obtained as described in section 2.

+Since it is not desirable to relax the ABI to allow tagged user addresses +into the kernel indiscriminately, arm64 provides a new sysctl interface +(/proc/sys/abi/tagged_addr) that is used to prevent the applications from +enabling the relaxed ABI and a new prctl() interface that can be used to +enable or disable the relaxed ABI. +A detailed description of the newly introduced mechanisms will be provided +in section 2.

+2. ARM64 Tagged Address ABI +---------------------------

+From the kernel syscall interface perspective, we define, for the purposes +of this document, a "valid tagged pointer" as a pointer that either has a +zero value set in the top byte or has a non-zero value, it is in memory +ranges privately owned by a userspace process and it is obtained in one of +the following ways:

• • mmap() done by the process itself, where either:
• • flags have MAP_PRIVATE and MAP_ANONYMOUS
• • flags have MAP_PRIVATE and the file descriptor refers to a regular

•  file or "/dev/zero"
  

• • brk() system call done by the process itself (i.e. the heap area between
• the initial location of the program break at process creation and its
• current location).
• • any memory mapped by the kernel in the process's address space during
• creation and following the restrictions presented above (i.e. data, bss,
• stack).

+The ARM64 Tagged Address ABI is an opt-in feature, and an application can +control it using the following:

• • /proc/sys/abi/tagged_addr: a new sysctl interface that can be used to

•    prevent the applications from enabling the relaxed ABI.
  

•    The sysctl is meant also for testing purposes in order to provide a
  

•    simple way for the userspace to verify the return error checking of
  

•    the prctl() commands without having to reconfigure the kernel.
  

•    The sysctl supports the following configuration options:
  

•     - 0: Disable ARM64 Tagged Address ABI for all the applications.
  

•     - 1 (Default): Enable ARM64 Tagged Address ABI for all the
  

•                    applications.
  

•    If the ARM64 Tagged Address ABI is disabled at a certain point in
  

•    time, all the applications that were using tagging before this event
  

•    occurs, will continue to use tagging.
  

• • prctl()s:
• • PR_SET_TAGGED_ADDR_CTRL: can be used to enable or disable the Tagged

•    Address ABI.
  

•    The (unsigned int) arg2 argument is a bit mask describing the
  

•    control mode used:
  

•      - PR_TAGGED_ADDR_ENABLE: Enable ARM64 Tagged Address ABI.
  

•    The arguments arg3, arg4, and arg5 are ignored.
  

• • PR_GET_TAGGED_ADDR_CTRL: can be used to check the status of the Tagged

•    Address ABI.
  

•    The arguments arg2, arg3, arg4, and arg5 are ignored.
  

+The ABI properties set by the mechanisms described above are inherited by threads +of the same application and fork()'ed children but cleared by execve().

+As a consequence of invoking PR_SET_TAGGED_ADDR_CTRL prctl() by an applications, +the ABI guarantees the following behaviours:

• • Every current or newly introduced syscall can accept any valid tagged
• pointers.
• • If a non valid tagged pointer is passed to a syscall then the behaviour
• is undefined.
• • Every valid tagged pointer is expected to work as an untagged one.
• • The kernel preserves any valid tagged pointers and returns them to the
• userspace unchanged (i.e. on syscall return) in all the cases except the
• ones documented in the "Preserving tags" section of tagged-pointers.txt.

+A definition of the meaning of tagged pointers on arm64 can be found in: +Documentation/arm64/tagged-pointers.txt.

+3. ARM64 Tagged Address ABI Exceptions +--------------------------------------

+The behaviours described in section 2, with particular reference to the +acceptance by the syscalls of any valid tagged pointer are not applicable +to the following cases:

• • mmap() addr parameter.
• • mremap() new_address parameter.
• • prctl_set_mm() struct prctl_map fields.
• • prctl_set_mm_map() struct prctl_map fields.

+Any attempt to use non-zero tagged pointers will lead to undefined behaviour.

+4. Example of correct usage +---------------------------

+void main(void) +{

• static int tbi_enabled = 0;
• unsigned long tag = 0;
• char *ptr = mmap(NULL, PAGE_SIZE, PROT_READ | PROT_WRITE,

• 	 MAP_ANONYMOUS, -1, 0);
  

• if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE,

•   0, 0, 0) == 0)
  

• tbi_enabled = 1;
  

• if (ptr == (void *)-1) /* MAP_FAILED */

• return -1;
  

• if (tbi_enabled)

• tag = rand() & 0xff;
  

• ptr = (char *)((unsigned long)ptr | (tag << TAG_SHIFT));
• *ptr = 'a';
• ...

+}