All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ingo Molnar <mingo@kernel.org>
To: Thomas Garnier <thgarnie@google.com>
Cc: "Martin Schwidefsky" <schwidefsky@de.ibm.com>,
	"Heiko Carstens" <heiko.carstens@de.ibm.com>,
	"Dave Hansen" <dave.hansen@intel.com>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Al Viro" <viro@zeniv.linux.org.uk>,
	"David Howells" <dhowells@redhat.com>,
	"René Nyffenegger" <mail@renenyffenegger.ch>,
	"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Eric W . Biederman" <ebiederm@xmission.com>,
	"Oleg Nesterov" <oleg@redhat.com>,
	"Pavel Tikhomirov" <ptikhomirov@virtuozzo.com>,
	"Ingo Molnar" <mingo@redhat.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Rik van Riel" <riel@redhat.com>,
	"Kees Cook" <keescook@chromium.org>,
	"Josh Poimboeuf" <jpoimboe@redhat.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Brian Gerst" <brgerst@gmail.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	"Christian Borntraeger" <borntraeger@de.ibm.com>,
	"Russell King" <linux@armlinux.org.uk>,
	"Will Deacon" <will.deacon@arm.com>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Mark Rutland" <mark.rutland@arm.com>,
	"James Morse" <james.morse@arm.com>,
	linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-api@vger.kernel.org, x86@kernel.org,
	linux-arm-kernel@lists.infradead.org,
	kernel-hardening@lists.openwall.com
Subject: [kernel-hardening] Re: [PATCH v8 1/4] syscalls: Verify address limit before returning to user-mode
Date: Fri, 28 Apr 2017 08:35:25 +0200	[thread overview]
Message-ID: <20170428063525.zmkthmhipczfnbgr@gmail.com> (raw)
In-Reply-To: <20170427144227.113630-1-thgarnie@google.com>


* Thomas Garnier <thgarnie@google.com> wrote:

> Ensure that a syscall does not return to user-mode with a kernel address
> limit. If that happens, a process can corrupt kernel-mode memory and
> elevate privileges [1].
> 
> The CONFIG_ADDR_LIMIT_CHECK option disables the generic check so each
> architecture can create optimized versions.
> 
> [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990
> 
> Signed-off-by: Thomas Garnier <thgarnie@google.com>
> Tested-by: Kees Cook <keescook@chromium.org>
> ---
> Based on next-20170426
> ---
>  arch/s390/Kconfig        |  1 +
>  include/linux/syscalls.h | 27 ++++++++++++++++++++++++++-
>  init/Kconfig             |  6 ++++++
>  kernel/sys.c             | 13 +++++++++++++
>  4 files changed, 46 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
> index d25435d94b6e..164de1d24e92 100644
> --- a/arch/s390/Kconfig
> +++ b/arch/s390/Kconfig
> @@ -103,6 +103,7 @@ config S390
>  	select ARCH_INLINE_WRITE_UNLOCK_BH
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQ
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
> +	select ADDR_LIMIT_CHECK
>  	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
>  	select ARCH_SUPPORTS_ATOMIC_RMW
>  	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index 980c3c9b06f8..ebde64f1622c 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -191,6 +191,28 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
>  	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
>  
> +
> +/*
> + * Called before coming back to user-mode. Returning to user-mode with an
> + * address limit different than USER_DS can allow to overwrite kernel memory.
> + */
> +static inline void addr_limit_check_syscall(void)
> +{
> +	BUG_ON(!segment_eq(get_fs(), USER_DS));
> +}
> +
> +#ifndef CONFIG_ADDR_LIMIT_CHECK
> +#define ADDR_LIMIT_CHECK_PRE() \
> +	bool user_caller = segment_eq(get_fs(), USER_DS)
> +#define ADDR_LIMIT_CHECK_POST() \
> +	if (user_caller) addr_limit_check_syscall()
> +#else
> +#define ADDR_LIMIT_CHECK_PRE()
> +#define ADDR_LIMIT_CHECK_POST()
> +asmlinkage void addr_limit_check_failed(void) __noreturn;
> +#endif
> +
> +
>  #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
>  #define __SYSCALL_DEFINEx(x, name, ...)					\
>  	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
> @@ -199,7 +221,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
>  	{								\
> -		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		long ret;						\
> +		ADDR_LIMIT_CHECK_PRE();					\
> +		ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		ADDR_LIMIT_CHECK_POST();				\
>  		__MAP(x,__SC_TEST,__VA_ARGS__);				\
>  		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
>  		return ret;						\
> diff --git a/init/Kconfig b/init/Kconfig
> index 42a346b0df43..599d9fe30703 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1961,6 +1961,12 @@ config PROFILING
>  config TRACEPOINTS
>  	bool
>  
> +config ADDR_LIMIT_CHECK
> +	bool
> +	help
> +	  Disable the generic address limit check. Allow each architecture to
> +	  optimize how and when the verification is done.
> +
>  source "arch/Kconfig"
>  
>  endmenu		# General setup
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 8a94b4eabcaa..a1cbcd715d62 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -2458,3 +2458,16 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
>  	return 0;
>  }
>  #endif /* CONFIG_COMPAT */
> +
> +#ifdef CONFIG_ADDR_LIMIT_CHECK
> +/*
> + * Used when an architecture specific implementation detects an invalid address
> + * limit. This function does not return.
> + */
> +asmlinkage void addr_limit_check_failed(void)
> +{
> +	/* Try to fail on the generic address limit check */
> +	addr_limit_check_syscall();
> +	panic("Invalid address limit before returning to user-mode");
> +}
> +#endif

Ok, this version looks pretty good to me. Could you (re-)send a full series?

I assume some of these changes need to be propagated into the followup patches but 
even if not it's better to pick up a clean series.

Thanks,

	Ingo

WARNING: multiple messages have this Message-ID (diff)
From: Ingo Molnar <mingo-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
To: Thomas Garnier <thgarnie-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: "Martin Schwidefsky"
	<schwidefsky-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>,
	"Heiko Carstens"
	<heiko.carstens-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org>,
	"Dave Hansen"
	<dave.hansen-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>,
	"Arnd Bergmann" <arnd-r2nGTMty4D4@public.gmane.org>,
	"Andrew Morton"
	<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>,
	"Al Viro"
	<viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn@public.gmane.org>,
	"David Howells"
	<dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"René Nyffenegger"
	<mail-gLCNRsNSrVdVZEhyV+6z5nIPMjoJpjVV@public.gmane.org>,
	"Paul E . McKenney"
	<paulmck-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>,
	"Thomas Gleixner" <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>,
	"Eric W . Biederman"
	<ebiederm-aS9lmoZGLiVWk0Htik3J/w@public.gmane.org>,
	"Oleg Nesterov" <oleg-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"Pavel Tikhomirov"
	<ptikhomirov-5HdwGun5lf+gSpxsJD1C4w@public.gmane.org>,
	"Ingo Molnar" <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"H . Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>,
	"Andy Lutomirski" <luto-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
	"Paolo Bonzini"
	<pbonzini-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"Rik van Riel" <riel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"Kees Cook" <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
Subject: Re: [PATCH v8 1/4] syscalls: Verify address limit before returning to user-mode
Date: Fri, 28 Apr 2017 08:35:25 +0200	[thread overview]
Message-ID: <20170428063525.zmkthmhipczfnbgr@gmail.com> (raw)
In-Reply-To: <20170427144227.113630-1-thgarnie-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>


* Thomas Garnier <thgarnie-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org> wrote:

> Ensure that a syscall does not return to user-mode with a kernel address
> limit. If that happens, a process can corrupt kernel-mode memory and
> elevate privileges [1].
> 
> The CONFIG_ADDR_LIMIT_CHECK option disables the generic check so each
> architecture can create optimized versions.
> 
> [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990
> 
> Signed-off-by: Thomas Garnier <thgarnie-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
> Tested-by: Kees Cook <keescook-F7+t8E8rja9g9hUCZPvPmw@public.gmane.org>
> ---
> Based on next-20170426
> ---
>  arch/s390/Kconfig        |  1 +
>  include/linux/syscalls.h | 27 ++++++++++++++++++++++++++-
>  init/Kconfig             |  6 ++++++
>  kernel/sys.c             | 13 +++++++++++++
>  4 files changed, 46 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
> index d25435d94b6e..164de1d24e92 100644
> --- a/arch/s390/Kconfig
> +++ b/arch/s390/Kconfig
> @@ -103,6 +103,7 @@ config S390
>  	select ARCH_INLINE_WRITE_UNLOCK_BH
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQ
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
> +	select ADDR_LIMIT_CHECK
>  	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
>  	select ARCH_SUPPORTS_ATOMIC_RMW
>  	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index 980c3c9b06f8..ebde64f1622c 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -191,6 +191,28 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
>  	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
>  
> +
> +/*
> + * Called before coming back to user-mode. Returning to user-mode with an
> + * address limit different than USER_DS can allow to overwrite kernel memory.
> + */
> +static inline void addr_limit_check_syscall(void)
> +{
> +	BUG_ON(!segment_eq(get_fs(), USER_DS));
> +}
> +
> +#ifndef CONFIG_ADDR_LIMIT_CHECK
> +#define ADDR_LIMIT_CHECK_PRE() \
> +	bool user_caller = segment_eq(get_fs(), USER_DS)
> +#define ADDR_LIMIT_CHECK_POST() \
> +	if (user_caller) addr_limit_check_syscall()
> +#else
> +#define ADDR_LIMIT_CHECK_PRE()
> +#define ADDR_LIMIT_CHECK_POST()
> +asmlinkage void addr_limit_check_failed(void) __noreturn;
> +#endif
> +
> +
>  #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
>  #define __SYSCALL_DEFINEx(x, name, ...)					\
>  	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
> @@ -199,7 +221,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
>  	{								\
> -		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		long ret;						\
> +		ADDR_LIMIT_CHECK_PRE();					\
> +		ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		ADDR_LIMIT_CHECK_POST();				\
>  		__MAP(x,__SC_TEST,__VA_ARGS__);				\
>  		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
>  		return ret;						\
> diff --git a/init/Kconfig b/init/Kconfig
> index 42a346b0df43..599d9fe30703 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1961,6 +1961,12 @@ config PROFILING
>  config TRACEPOINTS
>  	bool
>  
> +config ADDR_LIMIT_CHECK
> +	bool
> +	help
> +	  Disable the generic address limit check. Allow each architecture to
> +	  optimize how and when the verification is done.
> +
>  source "arch/Kconfig"
>  
>  endmenu		# General setup
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 8a94b4eabcaa..a1cbcd715d62 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -2458,3 +2458,16 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
>  	return 0;
>  }
>  #endif /* CONFIG_COMPAT */
> +
> +#ifdef CONFIG_ADDR_LIMIT_CHECK
> +/*
> + * Used when an architecture specific implementation detects an invalid address
> + * limit. This function does not return.
> + */
> +asmlinkage void addr_limit_check_failed(void)
> +{
> +	/* Try to fail on the generic address limit check */
> +	addr_limit_check_syscall();
> +	panic("Invalid address limit before returning to user-mode");
> +}
> +#endif

Ok, this version looks pretty good to me. Could you (re-)send a full series?

I assume some of these changes need to be propagated into the followup patches but 
even if not it's better to pick up a clean series.

Thanks,

	Ingo

WARNING: multiple messages have this Message-ID (diff)
From: mingo@kernel.org (Ingo Molnar)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v8 1/4] syscalls: Verify address limit before returning to user-mode
Date: Fri, 28 Apr 2017 08:35:25 +0200	[thread overview]
Message-ID: <20170428063525.zmkthmhipczfnbgr@gmail.com> (raw)
In-Reply-To: <20170427144227.113630-1-thgarnie@google.com>


* Thomas Garnier <thgarnie@google.com> wrote:

> Ensure that a syscall does not return to user-mode with a kernel address
> limit. If that happens, a process can corrupt kernel-mode memory and
> elevate privileges [1].
> 
> The CONFIG_ADDR_LIMIT_CHECK option disables the generic check so each
> architecture can create optimized versions.
> 
> [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990
> 
> Signed-off-by: Thomas Garnier <thgarnie@google.com>
> Tested-by: Kees Cook <keescook@chromium.org>
> ---
> Based on next-20170426
> ---
>  arch/s390/Kconfig        |  1 +
>  include/linux/syscalls.h | 27 ++++++++++++++++++++++++++-
>  init/Kconfig             |  6 ++++++
>  kernel/sys.c             | 13 +++++++++++++
>  4 files changed, 46 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
> index d25435d94b6e..164de1d24e92 100644
> --- a/arch/s390/Kconfig
> +++ b/arch/s390/Kconfig
> @@ -103,6 +103,7 @@ config S390
>  	select ARCH_INLINE_WRITE_UNLOCK_BH
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQ
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
> +	select ADDR_LIMIT_CHECK
>  	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
>  	select ARCH_SUPPORTS_ATOMIC_RMW
>  	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index 980c3c9b06f8..ebde64f1622c 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -191,6 +191,28 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
>  	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
>  
> +
> +/*
> + * Called before coming back to user-mode. Returning to user-mode with an
> + * address limit different than USER_DS can allow to overwrite kernel memory.
> + */
> +static inline void addr_limit_check_syscall(void)
> +{
> +	BUG_ON(!segment_eq(get_fs(), USER_DS));
> +}
> +
> +#ifndef CONFIG_ADDR_LIMIT_CHECK
> +#define ADDR_LIMIT_CHECK_PRE() \
> +	bool user_caller = segment_eq(get_fs(), USER_DS)
> +#define ADDR_LIMIT_CHECK_POST() \
> +	if (user_caller) addr_limit_check_syscall()
> +#else
> +#define ADDR_LIMIT_CHECK_PRE()
> +#define ADDR_LIMIT_CHECK_POST()
> +asmlinkage void addr_limit_check_failed(void) __noreturn;
> +#endif
> +
> +
>  #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
>  #define __SYSCALL_DEFINEx(x, name, ...)					\
>  	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
> @@ -199,7 +221,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
>  	{								\
> -		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		long ret;						\
> +		ADDR_LIMIT_CHECK_PRE();					\
> +		ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		ADDR_LIMIT_CHECK_POST();				\
>  		__MAP(x,__SC_TEST,__VA_ARGS__);				\
>  		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
>  		return ret;						\
> diff --git a/init/Kconfig b/init/Kconfig
> index 42a346b0df43..599d9fe30703 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1961,6 +1961,12 @@ config PROFILING
>  config TRACEPOINTS
>  	bool
>  
> +config ADDR_LIMIT_CHECK
> +	bool
> +	help
> +	  Disable the generic address limit check. Allow each architecture to
> +	  optimize how and when the verification is done.
> +
>  source "arch/Kconfig"
>  
>  endmenu		# General setup
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 8a94b4eabcaa..a1cbcd715d62 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -2458,3 +2458,16 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
>  	return 0;
>  }
>  #endif /* CONFIG_COMPAT */
> +
> +#ifdef CONFIG_ADDR_LIMIT_CHECK
> +/*
> + * Used when an architecture specific implementation detects an invalid address
> + * limit. This function does not return.
> + */
> +asmlinkage void addr_limit_check_failed(void)
> +{
> +	/* Try to fail on the generic address limit check */
> +	addr_limit_check_syscall();
> +	panic("Invalid address limit before returning to user-mode");
> +}
> +#endif

Ok, this version looks pretty good to me. Could you (re-)send a full series?

I assume some of these changes need to be propagated into the followup patches but 
even if not it's better to pick up a clean series.

Thanks,

	Ingo

WARNING: multiple messages have this Message-ID (diff)
From: Ingo Molnar <mingo@kernel.org>
To: Thomas Garnier <thgarnie@google.com>
Cc: "Martin Schwidefsky" <schwidefsky@de.ibm.com>,
	"Heiko Carstens" <heiko.carstens@de.ibm.com>,
	"Dave Hansen" <dave.hansen@intel.com>,
	"Arnd Bergmann" <arnd@arndb.de>,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Al Viro" <viro@zeniv.linux.org.uk>,
	"David Howells" <dhowells@redhat.com>,
	"René Nyffenegger" <mail@renenyffenegger.ch>,
	"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
	"Thomas Gleixner" <tglx@linutronix.de>,
	"Eric W . Biederman" <ebiederm@xmission.com>,
	"Oleg Nesterov" <oleg@redhat.com>,
	"Pavel Tikhomirov" <ptikhomirov@virtuozzo.com>,
	"Ingo Molnar" <mingo@redhat.com>,
	"H . Peter Anvin" <hpa@zytor.com>,
	"Andy Lutomirski" <luto@kernel.org>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Rik van Riel" <riel@redhat.com>,
	"Kees Cook" <keescook@chromium.org>,
	"Josh Poimboeuf" <jpoimboe@redhat.com>,
	"Borislav Petkov" <bp@alien8.de>,
	"Brian Gerst" <brgerst@gmail.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
	"Christian Borntraeger" <borntraeger@de.ibm.com>,
	"Russell King" <linux@armlinux.org.uk>,
	"Will Deacon" <will.deacon@arm.com>,
	"Catalin Marinas" <catalin.marinas@arm.com>,
	"Mark Rutland" <mark.rutland@arm.com>,
	"James Morse" <james.morse@arm.com>,
	linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-api@vger.kernel.org, x86@kernel.org,
	linux-arm-kernel@lists.infradead.org,
	kernel-hardening@lists.openwall.com
Subject: Re: [PATCH v8 1/4] syscalls: Verify address limit before returning to user-mode
Date: Fri, 28 Apr 2017 08:35:25 +0200	[thread overview]
Message-ID: <20170428063525.zmkthmhipczfnbgr@gmail.com> (raw)
In-Reply-To: <20170427144227.113630-1-thgarnie@google.com>


* Thomas Garnier <thgarnie@google.com> wrote:

> Ensure that a syscall does not return to user-mode with a kernel address
> limit. If that happens, a process can corrupt kernel-mode memory and
> elevate privileges [1].
> 
> The CONFIG_ADDR_LIMIT_CHECK option disables the generic check so each
> architecture can create optimized versions.
> 
> [1] https://bugs.chromium.org/p/project-zero/issues/detail?id=990
> 
> Signed-off-by: Thomas Garnier <thgarnie@google.com>
> Tested-by: Kees Cook <keescook@chromium.org>
> ---
> Based on next-20170426
> ---
>  arch/s390/Kconfig        |  1 +
>  include/linux/syscalls.h | 27 ++++++++++++++++++++++++++-
>  init/Kconfig             |  6 ++++++
>  kernel/sys.c             | 13 +++++++++++++
>  4 files changed, 46 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
> index d25435d94b6e..164de1d24e92 100644
> --- a/arch/s390/Kconfig
> +++ b/arch/s390/Kconfig
> @@ -103,6 +103,7 @@ config S390
>  	select ARCH_INLINE_WRITE_UNLOCK_BH
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQ
>  	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
> +	select ADDR_LIMIT_CHECK
>  	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
>  	select ARCH_SUPPORTS_ATOMIC_RMW
>  	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
> diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
> index 980c3c9b06f8..ebde64f1622c 100644
> --- a/include/linux/syscalls.h
> +++ b/include/linux/syscalls.h
> @@ -191,6 +191,28 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	SYSCALL_METADATA(sname, x, __VA_ARGS__)			\
>  	__SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
>  
> +
> +/*
> + * Called before coming back to user-mode. Returning to user-mode with an
> + * address limit different than USER_DS can allow to overwrite kernel memory.
> + */
> +static inline void addr_limit_check_syscall(void)
> +{
> +	BUG_ON(!segment_eq(get_fs(), USER_DS));
> +}
> +
> +#ifndef CONFIG_ADDR_LIMIT_CHECK
> +#define ADDR_LIMIT_CHECK_PRE() \
> +	bool user_caller = segment_eq(get_fs(), USER_DS)
> +#define ADDR_LIMIT_CHECK_POST() \
> +	if (user_caller) addr_limit_check_syscall()
> +#else
> +#define ADDR_LIMIT_CHECK_PRE()
> +#define ADDR_LIMIT_CHECK_POST()
> +asmlinkage void addr_limit_check_failed(void) __noreturn;
> +#endif
> +
> +
>  #define __PROTECT(...) asmlinkage_protect(__VA_ARGS__)
>  #define __SYSCALL_DEFINEx(x, name, ...)					\
>  	asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
> @@ -199,7 +221,10 @@ extern struct trace_event_functions exit_syscall_print_funcs;
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
>  	asmlinkage long SyS##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
>  	{								\
> -		long ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		long ret;						\
> +		ADDR_LIMIT_CHECK_PRE();					\
> +		ret = SYSC##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
> +		ADDR_LIMIT_CHECK_POST();				\
>  		__MAP(x,__SC_TEST,__VA_ARGS__);				\
>  		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
>  		return ret;						\
> diff --git a/init/Kconfig b/init/Kconfig
> index 42a346b0df43..599d9fe30703 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1961,6 +1961,12 @@ config PROFILING
>  config TRACEPOINTS
>  	bool
>  
> +config ADDR_LIMIT_CHECK
> +	bool
> +	help
> +	  Disable the generic address limit check. Allow each architecture to
> +	  optimize how and when the verification is done.
> +
>  source "arch/Kconfig"
>  
>  endmenu		# General setup
> diff --git a/kernel/sys.c b/kernel/sys.c
> index 8a94b4eabcaa..a1cbcd715d62 100644
> --- a/kernel/sys.c
> +++ b/kernel/sys.c
> @@ -2458,3 +2458,16 @@ COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info)
>  	return 0;
>  }
>  #endif /* CONFIG_COMPAT */
> +
> +#ifdef CONFIG_ADDR_LIMIT_CHECK
> +/*
> + * Used when an architecture specific implementation detects an invalid address
> + * limit. This function does not return.
> + */
> +asmlinkage void addr_limit_check_failed(void)
> +{
> +	/* Try to fail on the generic address limit check */
> +	addr_limit_check_syscall();
> +	panic("Invalid address limit before returning to user-mode");
> +}
> +#endif

Ok, this version looks pretty good to me. Could you (re-)send a full series?

I assume some of these changes need to be propagated into the followup patches but 
even if not it's better to pick up a clean series.

Thanks,

	Ingo

  reply	other threads:[~2017-04-28  6:35 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-04-26 18:34 [kernel-hardening] [PATCH v8 1/4] syscalls: Verify address limit before returning to user-mode Thomas Garnier
2017-04-26 18:34 ` Thomas Garnier
2017-04-26 18:34 ` Thomas Garnier
2017-04-26 18:34 ` Thomas Garnier
2017-04-26 18:34 ` [kernel-hardening] [PATCH v8 2/4] x86/syscalls: Optimize address limit check Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34 ` [kernel-hardening] [PATCH v8 3/4] arm/syscalls: " Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34 ` [kernel-hardening] [PATCH v8 4/4] arm64/syscalls: " Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-26 18:34   ` Thomas Garnier
2017-04-27  6:49 ` [kernel-hardening] Re: [PATCH v8 1/4] syscalls: Verify address limit before returning to user-mode Ingo Molnar
2017-04-27  6:49   ` Ingo Molnar
2017-04-27  6:49   ` Ingo Molnar
2017-04-27  6:49   ` Ingo Molnar
2017-04-27 14:16   ` [kernel-hardening] " Thomas Garnier
2017-04-27 14:16     ` Thomas Garnier
2017-04-27 14:16     ` Thomas Garnier
2017-04-27 14:16     ` Thomas Garnier
2017-04-27 14:42     ` [kernel-hardening] " Thomas Garnier
2017-04-27 14:42       ` Thomas Garnier
2017-04-27 14:42       ` Thomas Garnier
2017-04-27 14:42       ` Thomas Garnier
2017-04-28  6:35       ` Ingo Molnar [this message]
2017-04-28  6:35         ` Ingo Molnar
2017-04-28  6:35         ` Ingo Molnar
2017-04-28  6:35         ` Ingo Molnar
2017-04-28  6:33     ` [kernel-hardening] " Ingo Molnar
2017-04-28  6:33       ` Ingo Molnar
2017-04-28  6:33       ` Ingo Molnar
2017-04-28  6:33       ` Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170428063525.zmkthmhipczfnbgr@gmail.com \
    --to=mingo@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=arnd@arndb.de \
    --cc=borntraeger@de.ibm.com \
    --cc=bp@alien8.de \
    --cc=brgerst@gmail.com \
    --cc=catalin.marinas@arm.com \
    --cc=dave.hansen@intel.com \
    --cc=dhowells@redhat.com \
    --cc=ebiederm@xmission.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=jpoimboe@redhat.com \
    --cc=keescook@chromium.org \
    --cc=kernel-hardening@lists.openwall.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=luto@kernel.org \
    --cc=mail@renenyffenegger.ch \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=oleg@redhat.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=pbonzini@redhat.com \
    --cc=ptikhomirov@virtuozzo.com \
    --cc=riel@redhat.com \
    --cc=schwidefsky@de.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=thgarnie@google.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=will.deacon@arm.com \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.