From: Thomas Garnier <thgarnie@google.com>
To: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Andy Lutomirski" <luto@amacapital.net>,
"Ingo Molnar" <mingo@kernel.org>,
"Martin Schwidefsky" <schwidefsky@de.ibm.com>,
"Heiko Carstens" <heiko.carstens@de.ibm.com>,
"David Howells" <dhowells@redhat.com>,
"Arnd Bergmann" <arnd@arndb.de>,
"Al Viro" <viro@zeniv.linux.org.uk>,
"Dave Hansen" <dave.hansen@intel.com>,
"René Nyffenegger" <mail@renenyffenegger.ch>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Kees Cook" <keescook@chromium.org>,
"Paul E . McKenney" <paulmck@linux.vnet.ibm.com>,
"Andy Lutomirski" <luto@kernel.org>,
"Ard Biesheuvel" <ard.biesheuvel@linaro.org>,
"Nicolas Pitre" <nicolas.pitre@linaro.org>,
"Petr Mladek" <pmladek@suse.com>,
"Sebastian Andrzej Siewior" <bigeasy@linutronix.de>,
"Sergey Senozhatsky" <sergey.senozhatsky@gmail.com>,
"Helge Deller" <deller@gmx.de>, "Rik van Riel" <riel@redhat.com>,
"John Stultz" <john.stultz@linaro.org>,
"Thomas Gleixner" <tglx@linutronix>
Subject: Re: [PATCH v3 2/4] x86/syscalls: Specific usage of verify_pre_usermode_state
Date: Wed, 15 Mar 2017 10:43:10 -0700 [thread overview]
Message-ID: <CAJcbSZGrD2q7ymUSFNMtvwL+JUzbQ5WNA=MU6tpJ6XVnfJipcw@mail.gmail.com> (raw)
In-Reply-To: <8fa1a789-231f-dc2c-4a43-6406194259f9@zytor.com>
Thanks for the feedback. I will look into inlining by default (looking
at code size on different arch), the updated patch for x86 in the
meantime:
===========
Implement specific usage of verify_pre_usermode_state for user-mode
returns for x86.
---
Based on next-20170308
---
arch/x86/Kconfig | 1 +
arch/x86/entry/common.c | 3 +++
arch/x86/entry/entry_64.S | 8 ++++++++
arch/x86/include/asm/pgtable_64_types.h | 11 +++++++++++
arch/x86/include/asm/processor.h | 11 -----------
5 files changed, 23 insertions(+), 11 deletions(-)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 005df7c825f5..6d48e18e6f09 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,6 +63,7 @@ config X86
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
+ select ARCH_NO_SYSCALL_VERIFY_PRE_USERMODE_STATE
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 370c42c7f046..525edbb77f03 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -22,6 +22,7 @@
#include <linux/context_tracking.h>
#include <linux/user-return-notifier.h>
#include <linux/uprobes.h>
+#include <linux/syscalls.h>
#include <asm/desc.h>
#include <asm/traps.h>
@@ -180,6 +181,8 @@ __visible inline void
prepare_exit_to_usermode(struct pt_regs *regs)
struct thread_info *ti = current_thread_info();
u32 cached_flags;
+ verify_pre_usermode_state();
+
if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
local_irq_disable();
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d2b2a2948ffe..c079b010205c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -218,6 +218,14 @@ entry_SYSCALL_64_fastpath:
testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
jnz 1f
+ /*
+ * If address limit is not based on user-mode, jump to slow path for
+ * additional security checks.
+ */
+ movq $TASK_SIZE_MAX, %rcx
+ cmp %rcx, TASK_addr_limit(%r11)
+ jnz 1f
+
LOCKDEP_SYS_EXIT
TRACE_IRQS_ON /* user mode is traced as IRQs on */
movq RIP(%rsp), %rcx
diff --git a/arch/x86/include/asm/pgtable_64_types.h
b/arch/x86/include/asm/pgtable_64_types.h
index 3a264200c62f..0fbbb79d058c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -76,4 +76,15 @@ typedef struct { pteval_t pte; } pte_t;
#define EARLY_DYNAMIC_PAGE_TABLES 64
+/*
+ * User space process size. 47bits minus one guard page. The guard
+ * page is necessary on Intel CPUs: if a SYSCALL instruction is at
+ * the highest possible canonical userspace address, then that
+ * syscall will enter the kernel with a non-canonical return
+ * address, and SYSRET will explode dangerously. We avoid this
+ * particular problem by preventing anything from being mapped
+ * at the maximum canonical address.
+ */
+#define TASK_SIZE_MAX ((_AC(1, UL) << 47) - PAGE_SIZE)
+
#endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index f385eca5407a..9bc99d37133e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -829,17 +829,6 @@ static inline void spin_lock_prefetch(const void *x)
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#else
-/*
- * User space process size. 47bits minus one guard page. The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously. We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
- */
-#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE)
-
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
--
2.12.0.367.g23dc2f6d3c-goog
On Tue, Mar 14, 2017 at 10:53 AM, H. Peter Anvin <hpa@zytor.com> wrote:
> On 03/14/17 09:51, Thomas Garnier wrote:
>>>
>>> I wanted to comment on that thing: why on earth isn't
>>> verify_pre_usermode_state() an inline? Making it an out-of-line
>>> function adds pointless extra overhead to the C code when we are talking
>>> about a few instructions.
>>
>> Because outside of arch specific implementation it is called by each
>> syscall handler. it will increase the code size a lot.
>>
>
> Don't assume that. On a lot of architectures a function call can be
> more expensive than a simple compare and branch, because the compiler
> has to assume a whole bunch of registers are lost at that point.
>
> Either way, don't penalize the common architectures for it. Not okay.
>
> -hpa
>
--
Thomas
next prev parent reply other threads:[~2017-03-15 17:43 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-11 0:04 [PATCH v3 1/4] syscalls: Restore address limit after a syscall Thomas Garnier
2017-03-11 0:04 ` [PATCH v3 2/4] x86/syscalls: Specific usage of verify_pre_usermode_state Thomas Garnier
2017-03-11 9:42 ` Ingo Molnar
2017-03-13 15:53 ` Thomas Garnier
[not found] ` <20170311094200.GA27700-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2017-03-13 21:48 ` H. Peter Anvin
2017-03-14 0:04 ` H. Peter Anvin
2017-03-14 9:40 ` H. Peter Anvin
2017-03-14 15:17 ` Thomas Garnier
2017-03-14 15:39 ` Andy Lutomirski
2017-03-14 16:29 ` Thomas Garnier
2017-03-14 16:44 ` H. Peter Anvin
2017-03-14 16:51 ` Thomas Garnier
2017-03-14 17:53 ` H. Peter Anvin
2017-03-15 17:43 ` Thomas Garnier [this message]
2017-03-22 19:15 ` Thomas Garnier
2017-03-22 20:21 ` H. Peter Anvin
2017-03-22 20:41 ` Thomas Garnier
2017-03-22 20:49 ` H. Peter Anvin
2017-03-22 21:11 ` Thomas Garnier
[not found] ` <CAJcbSZEouZ2v+q_i-3Xiba2FNT18ipKwF09838vvfSCwEi7e4Q-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-03-23 19:14 ` H. Peter Anvin
2017-03-14 16:30 ` H. Peter Anvin
2017-03-11 0:05 ` [PATCH v3 3/4] arm/syscalls: " Thomas Garnier
2017-03-11 0:05 ` [PATCH v3 4/4] arm64/syscalls: " Thomas Garnier
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='CAJcbSZGrD2q7ymUSFNMtvwL+JUzbQ5WNA=MU6tpJ6XVnfJipcw@mail.gmail.com' \
--to=thgarnie@google.com \
--cc=akpm@linux-foundation.org \
--cc=ard.biesheuvel@linaro.org \
--cc=arnd@arndb.de \
--cc=bigeasy@linutronix.de \
--cc=dave.hansen@intel.com \
--cc=deller@gmx.de \
--cc=dhowells@redhat.com \
--cc=heiko.carstens@de.ibm.com \
--cc=hpa@zytor.com \
--cc=john.stultz@linaro.org \
--cc=keescook@chromium.org \
--cc=luto@amacapital.net \
--cc=luto@kernel.org \
--cc=mail@renenyffenegger.ch \
--cc=mingo@kernel.org \
--cc=nicolas.pitre@linaro.org \
--cc=paulmck@linux.vnet.ibm.com \
--cc=pmladek@suse.com \
--cc=riel@redhat.com \
--cc=schwidefsky@de.ibm.com \
--cc=sergey.senozhatsky@gmail.com \
--cc=tglx@linutronix \
--cc=viro@zeniv.linux.org.uk \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).