[PATCH 3.16 73/76] x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec

[PATCH 3.16 73/76] x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit b3bbfb3fb5d25776b8e3f361d2eedaabb0b496cd upstream.

For __get_user() paths, do not allow the kernel to speculate on the value
of a user controlled pointer. In addition to the 'stac' instruction for
Supervisor Mode Access Protection (SMAP), a barrier_nospec() causes the
access_ok() result to resolve in the pipeline before the CPU might take any
speculative action on the pointer value. Given the cost of 'stac' the
speculation barrier is placed after 'stac' to hopefully overlap the cost of
disabling SMAP with the cost of flushing the instruction pipeline.

Since __get_user is a major kernel interface that deals with user
controlled pointers, the __uaccess_begin_nospec() mechanism will prevent
speculative execution past an access_ok() permission check. While
speculative execution past access_ok() is not enough to lead to a kernel
memory leak, it is a necessary precondition.

To be clear, __uaccess_begin_nospec() is addressing a class of potential
problems near __get_user() usages.

Note, that while the barrier_nospec() in __uaccess_begin_nospec() is used
to protect __get_user(), pointer masking similar to array_index_nospec()
will be used for get_user() since it incorporates a bounds check near the
usage.

uaccess_try_nospec provides the same mechanism for get_user_try.

No functional changes.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Andi Kleen <ak@linux.intel.com>
Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727415922.33451.5796614273104346583.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16: use current_thread_info()]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/include/asm/uaccess.h | 9 +++++++++
 1 file changed, 9 insertions(+)

--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -145,6 +145,11 @@ extern int __get_user_bad(void);
 
 #define __uaccess_begin() stac()
 #define __uaccess_end()   clac()
+#define __uaccess_begin_nospec()	\
+({					\
+	stac();				\
+	barrier_nospec();		\
+})
 
 /*
  * This is a type: either unsigned long, if the argument fits into
@@ -470,6 +475,10 @@ struct __large_struct { unsigned long bu
 	__uaccess_begin();						\
 	barrier();
 
+#define uaccess_try_nospec do {						\
+	current_thread_info()->uaccess_err = 0;				\
+	__uaccess_begin_nospec();					\
+
 #define uaccess_catch(err)						\
 	__uaccess_end();						\
 	(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0);	\

[PATCH 3.16 73/76] x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit b3bbfb3fb5d25776b8e3f361d2eedaabb0b496cd upstream.

For __get_user() paths, do not allow the kernel to speculate on the value
of a user controlled pointer. In addition to the 'stac' instruction for
Supervisor Mode Access Protection (SMAP), a barrier_nospec() causes the
access_ok() result to resolve in the pipeline before the CPU might take any
speculative action on the pointer value. Given the cost of 'stac' the
speculation barrier is placed after 'stac' to hopefully overlap the cost of
disabling SMAP with the cost of flushing the instruction pipeline.

Since __get_user is a major kernel interface that deals with user
controlled pointers, the __uaccess_begin_nospec() mechanism will prevent
speculative execution past an access_ok() permission check. While
speculative execution past access_ok() is not enough to lead to a kernel
memory leak, it is a necessary precondition.

To be clear, __uaccess_begin_nospec() is addressing a class of potential
problems near __get_user() usages.

Note, that while the barrier_nospec() in __uaccess_begin_nospec() is used
to protect __get_user(), pointer masking similar to array_index_nospec()
will be used for get_user() since it incorporates a bounds check near the
usage.

uaccess_try_nospec provides the same mechanism for get_user_try.

No functional changes.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Andi Kleen <ak@linux.intel.com>
Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727415922.33451.5796614273104346583.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16: use current_thread_info()]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/include/asm/uaccess.h | 9 +++++++++
 1 file changed, 9 insertions(+)

--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -145,6 +145,11 @@ extern int __get_user_bad(void);
 
 #define __uaccess_begin() stac()
 #define __uaccess_end()   clac()
+#define __uaccess_begin_nospec()	\
+({					\
+	stac();				\
+	barrier_nospec();		\
+})
 
 /*
  * This is a type: either unsigned long, if the argument fits into
@@ -470,6 +475,10 @@ struct __large_struct { unsigned long bu
 	__uaccess_begin();						\
 	barrier();
 
+#define uaccess_try_nospec do {						\
+	current_thread_info()->uaccess_err = 0;				\
+	__uaccess_begin_nospec();					\
+
 #define uaccess_catch(err)						\
 	__uaccess_end();						\
 	(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0);	\

[PATCH 3.16 56/76] x86/syscall: Sanitize syscall table de-references under speculation

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Ben Hutchings <ben@decadent.org.uk>

commit 2fbd7af5af8665d18bcefae3e9700be07e22b681 upstream.

The upstream version of this, touching C code, was written by Dan Williams,
with the following description:

> The syscall table base is a user controlled function pointer in kernel
> space. Use array_index_nospec() to prevent any out of bounds speculation.
>
> While retpoline prevents speculating into a userspace directed target it
> does not stop the pointer de-reference, the concern is leaking memory
> relative to the syscall table base, by observing instruction cache
> behavior.

The x86_64 assembly version for 4.4 was written by Jiri Slaby, with
the following description:

> In 4.4.118, we have commit c8961332d6da (x86/syscall: Sanitize syscall
> table de-references under speculation), which is a backport of upstream
> commit 2fbd7af5af86. But it fixed only the C part of the upstream patch
> -- the IA32 sysentry. So it ommitted completely the assembly part -- the
> 64bit sysentry.
>
> Fix that in this patch by explicit array_index_mask_nospec written in
> assembly. The same was used in lib/getuser.S.
>
> However, to have "sbb" working properly, we have to switch from "cmp"
> against (NR_syscalls-1) to (NR_syscalls), otherwise the last syscall
> number would be "and"ed by 0. It is because the original "ja" relies on
> "CF" or "ZF", but we rely only on "CF" in "sbb". That means: switch to
> "jae" conditional jump too.
>
> Final note: use rcx for mask as this is exactly what is overwritten by
> the 4th syscall argument (r10) right after.

In 3.16 the x86_32 syscall table lookup is also written in assembly.
So I've taken Jiri's version and added similar masking in entry_32.S,
using edx as the temporary.  edx is clobbered by SAVE_REGS and seems
to be free at this point.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Andy Lutomirski <luto@kernel.org>
Cc: alan@linux.intel.com
Cc: Jinpu Wang <jinpu.wang@profitbricks.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -426,6 +426,8 @@ sysenter_past_esp:
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
 	jae sysenter_badsys
+	sbb %edx, %edx				/* array_index_mask_nospec() */
+	and %edx, %eax
 	call *sys_call_table(,%eax,4)
 sysenter_after_call:
 	movl %eax,PT_EAX(%esp)
@@ -503,6 +505,8 @@ ENTRY(system_call)
 	cmpl $(NR_syscalls), %eax
 	jae syscall_badsys
 syscall_call:
+	sbb %edx, %edx				/* array_index_mask_nospec() */
+	and %edx, %eax
 	call *sys_call_table(,%eax,4)
 syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -445,12 +445,14 @@ GLOBAL(system_call_after_swapgs)
 	jnz tracesys
 system_call_fastpath:
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$NR_syscalls, %rax
 #else
 	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	cmpl	$NR_syscalls, %eax
 #endif
-	ja badsys
+	jae	badsys
+	sbb	%rcx, %rcx			/* array_index_mask_nospec() */
+	and	%rcx, %rax
 	movq %r10,%rcx
 #ifdef CONFIG_RETPOLINE
 	movq	sys_call_table(, %rax, 8), %rax
@@ -577,12 +579,14 @@ tracesys:
 	LOAD_ARGS ARGOFFSET, 1
 	RESTORE_REST
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$NR_syscalls, %rax
 #else
 	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	cmpl	$NR_syscalls, %eax
 #endif
-	ja   int_ret_from_sys_call	/* RAX(%rsp) set to -ENOSYS above */
+	jae	int_ret_from_sys_call		/* RAX(%rsp) set to -ENOSYS above */
+	sbb	%rcx, %rcx			/* array_index_mask_nospec() */
+	and	%rcx, %rax
 	movq %r10,%rcx	/* fixup for C */
 #ifdef CONFIG_RETPOLINE
 	movq	sys_call_table(, %rax, 8), %rax

[PATCH 3.16 56/76] x86/syscall: Sanitize syscall table de-references under speculation

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Ben Hutchings <ben@decadent.org.uk>

commit 2fbd7af5af8665d18bcefae3e9700be07e22b681 upstream.

The upstream version of this, touching C code, was written by Dan Williams,
with the following description:

> The syscall table base is a user controlled function pointer in kernel
> space. Use array_index_nospec() to prevent any out of bounds speculation.
>
> While retpoline prevents speculating into a userspace directed target it
> does not stop the pointer de-reference, the concern is leaking memory
> relative to the syscall table base, by observing instruction cache
> behavior.

The x86_64 assembly version for 4.4 was written by Jiri Slaby, with
the following description:

> In 4.4.118, we have commit c8961332d6da (x86/syscall: Sanitize syscall
> table de-references under speculation), which is a backport of upstream
> commit 2fbd7af5af86. But it fixed only the C part of the upstream patch
> -- the IA32 sysentry. So it ommitted completely the assembly part -- the
> 64bit sysentry.
>
> Fix that in this patch by explicit array_index_mask_nospec written in
> assembly. The same was used in lib/getuser.S.
>
> However, to have "sbb" working properly, we have to switch from "cmp"
> against (NR_syscalls-1) to (NR_syscalls), otherwise the last syscall
> number would be "and"ed by 0. It is because the original "ja" relies on
> "CF" or "ZF", but we rely only on "CF" in "sbb". That means: switch to
> "jae" conditional jump too.
>
> Final note: use rcx for mask as this is exactly what is overwritten by
> the 4th syscall argument (r10) right after.

In 3.16 the x86_32 syscall table lookup is also written in assembly.
So I've taken Jiri's version and added similar masking in entry_32.S,
using edx as the temporary.  edx is clobbered by SAVE_REGS and seems
to be free at this point.

Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Andy Lutomirski <luto@kernel.org>
Cc: alan@linux.intel.com
Cc: Jinpu Wang <jinpu.wang@profitbricks.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -426,6 +426,8 @@ sysenter_past_esp:
 sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
 	jae sysenter_badsys
+	sbb %edx, %edx				/* array_index_mask_nospec() */
+	and %edx, %eax
 	call *sys_call_table(,%eax,4)
 sysenter_after_call:
 	movl %eax,PT_EAX(%esp)
@@ -503,6 +505,8 @@ ENTRY(system_call)
 	cmpl $(NR_syscalls), %eax
 	jae syscall_badsys
 syscall_call:
+	sbb %edx, %edx				/* array_index_mask_nospec() */
+	and %edx, %eax
 	call *sys_call_table(,%eax,4)
 syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -445,12 +445,14 @@ GLOBAL(system_call_after_swapgs)
 	jnz tracesys
 system_call_fastpath:
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$NR_syscalls, %rax
 #else
 	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	cmpl	$NR_syscalls, %eax
 #endif
-	ja badsys
+	jae	badsys
+	sbb	%rcx, %rcx			/* array_index_mask_nospec() */
+	and	%rcx, %rax
 	movq %r10,%rcx
 #ifdef CONFIG_RETPOLINE
 	movq	sys_call_table(, %rax, 8), %rax
@@ -577,12 +579,14 @@ tracesys:
 	LOAD_ARGS ARGOFFSET, 1
 	RESTORE_REST
 #if __SYSCALL_MASK == ~0
-	cmpq $__NR_syscall_max,%rax
+	cmpq	$NR_syscalls, %rax
 #else
 	andl $__SYSCALL_MASK,%eax
-	cmpl $__NR_syscall_max,%eax
+	cmpl	$NR_syscalls, %eax
 #endif
-	ja   int_ret_from_sys_call	/* RAX(%rsp) set to -ENOSYS above */
+	jae	int_ret_from_sys_call		/* RAX(%rsp) set to -ENOSYS above */
+	sbb	%rcx, %rcx			/* array_index_mask_nospec() */
+	and	%rcx, %rax
 	movq %r10,%rcx	/* fixup for C */
 #ifdef CONFIG_RETPOLINE
 	movq	sys_call_table(, %rax, 8), %rax

Re: [PATCH 3.16 56/76] x86/syscall: Sanitize syscall table de-references under speculation

[Jiri Slaby]

On 03/12/2018, 04:06 AM, Ben Hutchings wrote:
> In 3.16 the x86_32 syscall table lookup is also written in assembly.
> So I've taken Jiri's version and added similar masking in entry_32.S,
> using edx as the temporary.  edx is clobbered by SAVE_REGS and seems
> to be free at this point.

I don't know the state in 3.16, but in 3.12, I had to fix the 32bit
entry on 64bit in arch/x86/ia32/ia32entry.S (ia32_sysenter_target &
others) too.

thanks,
-- 
js
suse labs

Re: [PATCH 3.16 56/76] x86/syscall: Sanitize syscall table de-references under speculation

[Jiri Slaby]

On 03/12/2018, 04:06 AM, Ben Hutchings wrote:
> In 3.16 the x86_32 syscall table lookup is also written in assembly.
> So I've taken Jiri's version and added similar masking in entry_32.S,
> using edx as the temporary.  edx is clobbered by SAVE_REGS and seems
> to be free at this point.

I don't know the state in 3.16, but in 3.12, I had to fix the 32bit
entry on 64bit in arch/x86/ia32/ia32entry.S (ia32_sysenter_target &
others) too.

thanks,
-- 
js
suse labs

Re: [PATCH 3.16 56/76] x86/syscall: Sanitize syscall table de-references under speculation

[Ben Hutchings]

[-- Attachment #1: Type: text/plain, Size: 713 bytes --]

On Mon, 2018-03-12 at 08:32 +0100, Jiri Slaby wrote:
> On 03/12/2018, 04:06 AM, Ben Hutchings wrote:
> > In 3.16 the x86_32 syscall table lookup is also written in assembly.
> > So I've taken Jiri's version and added similar masking in entry_32.S,
> > using edx as the temporary.  edx is clobbered by SAVE_REGS and seems
> > to be free at this point.
> 
> I don't know the state in 3.16, but in 3.12, I had to fix the 32bit
> entry on 64bit in arch/x86/ia32/ia32entry.S (ia32_sysenter_target &
> others) too.

Thank you, yes I need to fix them in 3.16 too.  I also failed to use
retpolines there.

Ben.

-- 
Ben Hutchings
The first rule of tautology club is the first rule of tautology club.


[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH 3.16 56/76] x86/syscall: Sanitize syscall table de-references under speculation

[Ben Hutchings]

[-- Attachment #1: Type: text/plain, Size: 713 bytes --]

On Mon, 2018-03-12 at 08:32 +0100, Jiri Slaby wrote:
> On 03/12/2018, 04:06 AM, Ben Hutchings wrote:
> > In 3.16 the x86_32 syscall table lookup is also written in assembly.
> > So I've taken Jiri's version and added similar masking in entry_32.S,
> > using edx as the temporary.  edx is clobbered by SAVE_REGS and seems
> > to be free at this point.
> 
> I don't know the state in 3.16, but in 3.12, I had to fix the 32bit
> entry on 64bit in arch/x86/ia32/ia32entry.S (ia32_sysenter_target &
> others) too.

Thank you, yes I need to fix them in 3.16 too.  I also failed to use
retpolines there.

Ben.

-- 
Ben Hutchings
The first rule of tautology club is the first rule of tautology club.


[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH 3.16 51/76] Documentation: Document array_index_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Mark Rutland <mark.rutland@arm.com>

commit f84a56f73dddaeac1dba8045b007f742f61cd2da upstream.

Document the rationale and usage of the new array_index_nospec() helper.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: linux-arch@vger.kernel.org
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: gregkh@linuxfoundation.org
Cc: kernel-hardening@lists.openwall.com
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727413645.33451.15878817161436755393.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 Documentation/speculation.txt | 90 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)
 create mode 100644 Documentation/speculation.txt

--- /dev/null
+++ b/Documentation/speculation.txt
@@ -0,0 +1,90 @@
+This document explains potential effects of speculation, and how undesirable
+effects can be mitigated portably using common APIs.
+
+===========
+Speculation
+===========
+
+To improve performance and minimize average latencies, many contemporary CPUs
+employ speculative execution techniques such as branch prediction, performing
+work which may be discarded at a later stage.
+
+Typically speculative execution cannot be observed from architectural state,
+such as the contents of registers. However, in some cases it is possible to
+observe its impact on microarchitectural state, such as the presence or
+absence of data in caches. Such state may form side-channels which can be
+observed to extract secret information.
+
+For example, in the presence of branch prediction, it is possible for bounds
+checks to be ignored by code which is speculatively executed. Consider the
+following code:
+
+	int load_array(int *array, unsigned int index)
+	{
+		if (index >= MAX_ARRAY_ELEMS)
+			return 0;
+		else
+			return array[index];
+	}
+
+Which, on arm64, may be compiled to an assembly sequence such as:
+
+	CMP	<index>, #MAX_ARRAY_ELEMS
+	B.LT	less
+	MOV	<returnval>, #0
+	RET
+  less:
+	LDR	<returnval>, [<array>, <index>]
+	RET
+
+It is possible that a CPU mis-predicts the conditional branch, and
+speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This
+value will subsequently be discarded, but the speculated load may affect
+microarchitectural state which can be subsequently measured.
+
+More complex sequences involving multiple dependent memory accesses may
+result in sensitive information being leaked. Consider the following
+code, building on the prior example:
+
+	int load_dependent_arrays(int *arr1, int *arr2, int index)
+	{
+		int val1, val2,
+
+		val1 = load_array(arr1, index);
+		val2 = load_array(arr2, val1);
+
+		return val2;
+	}
+
+Under speculation, the first call to load_array() may return the value
+of an out-of-bounds address, while the second call will influence
+microarchitectural state dependent on this value. This may provide an
+arbitrary read primitive.
+
+====================================
+Mitigating speculation side-channels
+====================================
+
+The kernel provides a generic API to ensure that bounds checks are
+respected even under speculation. Architectures which are affected by
+speculation-based side-channels are expected to implement these
+primitives.
+
+The array_index_nospec() helper in <linux/nospec.h> can be used to
+prevent information from being leaked via side-channels.
+
+A call to array_index_nospec(index, size) returns a sanitized index
+value that is bounded to [0, size) even under cpu speculation
+conditions.
+
+This can be used to protect the earlier load_array() example:
+
+	int load_array(int *array, unsigned int index)
+	{
+		if (index >= MAX_ARRAY_ELEMS)
+			return 0;
+		else {
+			index = array_index_nospec(index, MAX_ARRAY_ELEMS);
+			return array[index];
+		}
+	}

[PATCH 3.16 51/76] Documentation: Document array_index_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Mark Rutland <mark.rutland@arm.com>

commit f84a56f73dddaeac1dba8045b007f742f61cd2da upstream.

Document the rationale and usage of the new array_index_nospec() helper.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: linux-arch@vger.kernel.org
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: gregkh@linuxfoundation.org
Cc: kernel-hardening@lists.openwall.com
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727413645.33451.15878817161436755393.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 Documentation/speculation.txt | 90 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)
 create mode 100644 Documentation/speculation.txt

--- /dev/null
+++ b/Documentation/speculation.txt
@@ -0,0 +1,90 @@
+This document explains potential effects of speculation, and how undesirable
+effects can be mitigated portably using common APIs.
+
+===========
+Speculation
+===========
+
+To improve performance and minimize average latencies, many contemporary CPUs
+employ speculative execution techniques such as branch prediction, performing
+work which may be discarded at a later stage.
+
+Typically speculative execution cannot be observed from architectural state,
+such as the contents of registers. However, in some cases it is possible to
+observe its impact on microarchitectural state, such as the presence or
+absence of data in caches. Such state may form side-channels which can be
+observed to extract secret information.
+
+For example, in the presence of branch prediction, it is possible for bounds
+checks to be ignored by code which is speculatively executed. Consider the
+following code:
+
+	int load_array(int *array, unsigned int index)
+	{
+		if (index >= MAX_ARRAY_ELEMS)
+			return 0;
+		else
+			return array[index];
+	}
+
+Which, on arm64, may be compiled to an assembly sequence such as:
+
+	CMP	<index>, #MAX_ARRAY_ELEMS
+	B.LT	less
+	MOV	<returnval>, #0
+	RET
+  less:
+	LDR	<returnval>, [<array>, <index>]
+	RET
+
+It is possible that a CPU mis-predicts the conditional branch, and
+speculatively loads array[index], even if index >= MAX_ARRAY_ELEMS. This
+value will subsequently be discarded, but the speculated load may affect
+microarchitectural state which can be subsequently measured.
+
+More complex sequences involving multiple dependent memory accesses may
+result in sensitive information being leaked. Consider the following
+code, building on the prior example:
+
+	int load_dependent_arrays(int *arr1, int *arr2, int index)
+	{
+		int val1, val2,
+
+		val1 = load_array(arr1, index);
+		val2 = load_array(arr2, val1);
+
+		return val2;
+	}
+
+Under speculation, the first call to load_array() may return the value
+of an out-of-bounds address, while the second call will influence
+microarchitectural state dependent on this value. This may provide an
+arbitrary read primitive.
+
+====================================
+Mitigating speculation side-channels
+====================================
+
+The kernel provides a generic API to ensure that bounds checks are
+respected even under speculation. Architectures which are affected by
+speculation-based side-channels are expected to implement these
+primitives.
+
+The array_index_nospec() helper in <linux/nospec.h> can be used to
+prevent information from being leaked via side-channels.
+
+A call to array_index_nospec(index, size) returns a sanitized index
+value that is bounded to [0, size) even under cpu speculation
+conditions.
+
+This can be used to protect the earlier load_array() example:
+
+	int load_array(int *array, unsigned int index)
+	{
+		if (index >= MAX_ARRAY_ELEMS)
+			return 0;
+		else {
+			index = array_index_nospec(index, MAX_ARRAY_ELEMS);
+			return array[index];
+		}
+	}

[PATCH 3.16 69/76] nospec: Kill array_index_nospec_mask_check()

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 1d91c1d2c80cb70e2e553845e278b87a960c04da upstream.

There are multiple problems with the dynamic sanity checking in
array_index_nospec_mask_check():

* It causes unnecessary overhead in the 32-bit case since integer sized
  @index values will no longer cause the check to be compiled away like
  in the 64-bit case.

* In the 32-bit case it may trigger with user controllable input when
  the expectation is that should only trigger during development of new
  kernel enabling.

* The macro reuses the input parameter in multiple locations which is
  broken if someone passes an expression like 'index++' to
  array_index_nospec().

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/151881604278.17395.6605847763178076520.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/nospec.h | 22 +---------------------
 1 file changed, 1 insertion(+), 21 deletions(-)

--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -30,26 +30,6 @@ static inline unsigned long array_index_
 #endif
 
 /*
- * Warn developers about inappropriate array_index_nospec() usage.
- *
- * Even if the CPU speculates past the WARN_ONCE branch, the
- * sign bit of @index is taken into account when generating the
- * mask.
- *
- * This warning is compiled out when the compiler can infer that
- * @index and @size are less than LONG_MAX.
- */
-#define array_index_mask_nospec_check(index, size)				\
-({										\
-	if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX,			\
-	    "array_index_nospec() limited to range of [0, LONG_MAX]\n"))	\
-		_mask = 0;							\
-	else									\
-		_mask = array_index_mask_nospec(index, size);			\
-	_mask;									\
-})
-
-/*
  * array_index_nospec - sanitize an array index after a bounds check
  *
  * For a code sequence like:
@@ -67,7 +47,7 @@ static inline unsigned long array_index_
 ({									\
 	typeof(index) _i = (index);					\
 	typeof(size) _s = (size);					\
-	unsigned long _mask = array_index_mask_nospec_check(_i, _s);	\
+	unsigned long _mask = array_index_mask_nospec(_i, _s);		\
 									\
 	BUILD_BUG_ON(sizeof(_i) > sizeof(long));			\
 	BUILD_BUG_ON(sizeof(_s) > sizeof(long));			\

[PATCH 3.16 69/76] nospec: Kill array_index_nospec_mask_check()

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 1d91c1d2c80cb70e2e553845e278b87a960c04da upstream.

There are multiple problems with the dynamic sanity checking in
array_index_nospec_mask_check():

* It causes unnecessary overhead in the 32-bit case since integer sized
  @index values will no longer cause the check to be compiled away like
  in the 64-bit case.

* In the 32-bit case it may trigger with user controllable input when
  the expectation is that should only trigger during development of new
  kernel enabling.

* The macro reuses the input parameter in multiple locations which is
  broken if someone passes an expression like 'index++' to
  array_index_nospec().

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/151881604278.17395.6605847763178076520.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/nospec.h | 22 +---------------------
 1 file changed, 1 insertion(+), 21 deletions(-)

--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -30,26 +30,6 @@ static inline unsigned long array_index_
 #endif
 
 /*
- * Warn developers about inappropriate array_index_nospec() usage.
- *
- * Even if the CPU speculates past the WARN_ONCE branch, the
- * sign bit of @index is taken into account when generating the
- * mask.
- *
- * This warning is compiled out when the compiler can infer that
- * @index and @size are less than LONG_MAX.
- */
-#define array_index_mask_nospec_check(index, size)				\
-({										\
-	if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX,			\
-	    "array_index_nospec() limited to range of [0, LONG_MAX]\n"))	\
-		_mask = 0;							\
-	else									\
-		_mask = array_index_mask_nospec(index, size);			\
-	_mask;									\
-})
-
-/*
  * array_index_nospec - sanitize an array index after a bounds check
  *
  * For a code sequence like:
@@ -67,7 +47,7 @@ static inline unsigned long array_index_
 ({									\
 	typeof(index) _i = (index);					\
 	typeof(size) _s = (size);					\
-	unsigned long _mask = array_index_mask_nospec_check(_i, _s);	\
+	unsigned long _mask = array_index_mask_nospec(_i, _s);		\
 									\
 	BUILD_BUG_ON(sizeof(_i) > sizeof(long));			\
 	BUILD_BUG_ON(sizeof(_s) > sizeof(long));			\

[PATCH 3.16 57/76] vfs, fdtable: Prevent bounds-check bypass via speculative execution

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 56c30ba7b348b90484969054d561f711ba196507 upstream.

'fd' is a user controlled value that is used as a data dependency to
read from the 'fdt->fd' array.  In order to avoid potential leaks of
kernel memory values, block speculative execution of the instruction
stream that could issue reads based on an invalid 'file *' returned from
__fcheck_files.

Co-developed-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727418500.33451.17392199002892248656.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/fdtable.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/nospec.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/fs.h>
@@ -76,8 +77,10 @@ static inline struct file *__fcheck_file
 {
 	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
 
-	if (fd < fdt->max_fds)
+	if (fd < fdt->max_fds) {
+		fd = array_index_nospec(fd, fdt->max_fds);
 		return rcu_dereference_raw(fdt->fd[fd]);
+	}
 	return NULL;
 }
 

[PATCH 3.16 57/76] vfs, fdtable: Prevent bounds-check bypass via speculative execution

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 56c30ba7b348b90484969054d561f711ba196507 upstream.

'fd' is a user controlled value that is used as a data dependency to
read from the 'fdt->fd' array.  In order to avoid potential leaks of
kernel memory values, block speculative execution of the instruction
stream that could issue reads based on an invalid 'file *' returned from
__fcheck_files.

Co-developed-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727418500.33451.17392199002892248656.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/fdtable.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/nospec.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/fs.h>
@@ -76,8 +77,10 @@ static inline struct file *__fcheck_file
 {
 	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
 
-	if (fd < fdt->max_fds)
+	if (fd < fdt->max_fds) {
+		fd = array_index_nospec(fd, fdt->max_fds);
 		return rcu_dereference_raw(fdt->fd[fd]);
+	}
 	return NULL;
 }
 

[PATCH 3.16 58/76] nl80211: Sanitize array index in parse_txq_params

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 259d8c1e984318497c84eef547bbb6b1d9f4eb05 upstream.

Wireless drivers rely on parse_txq_params to validate that txq_params->ac
is less than NL80211_NUM_ACS by the time the low-level driver's ->conf_tx()
handler is called. Use a new helper, array_index_nospec(), to sanitize
txq_params->ac with respect to speculation. I.e. ensure that any
speculation into ->conf_tx() handlers is done with a value of
txq_params->ac that is within the bounds of [0, NL80211_NUM_ACS).

Reported-by: Christian Lamparter <chunkeey@gmail.com>
Reported-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: linux-wireless@vger.kernel.org
Cc: torvalds@linux-foundation.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727419584.33451.7700736761686184303.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 net/wireless/nl80211.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -14,6 +14,7 @@
 #include <linux/nl80211.h>
 #include <linux/rtnetlink.h>
 #include <linux/netlink.h>
+#include <linux/nospec.h>
 #include <linux/etherdevice.h>
 #include <net/net_namespace.h>
 #include <net/genetlink.h>
@@ -1829,20 +1830,22 @@ static const struct nla_policy txq_param
 static int parse_txq_params(struct nlattr *tb[],
 			    struct ieee80211_txq_params *txq_params)
 {
+	u8 ac;
+
 	if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] ||
 	    !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] ||
 	    !tb[NL80211_TXQ_ATTR_AIFS])
 		return -EINVAL;
 
-	txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]);
+	ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]);
 	txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]);
 	txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]);
 	txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]);
 	txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]);
 
-	if (txq_params->ac >= NL80211_NUM_ACS)
+	if (ac >= NL80211_NUM_ACS)
 		return -EINVAL;
-
+	txq_params->ac = array_index_nospec(ac, NL80211_NUM_ACS);
 	return 0;
 }
 

[PATCH 3.16 58/76] nl80211: Sanitize array index in parse_txq_params

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 259d8c1e984318497c84eef547bbb6b1d9f4eb05 upstream.

Wireless drivers rely on parse_txq_params to validate that txq_params->ac
is less than NL80211_NUM_ACS by the time the low-level driver's ->conf_tx()
handler is called. Use a new helper, array_index_nospec(), to sanitize
txq_params->ac with respect to speculation. I.e. ensure that any
speculation into ->conf_tx() handlers is done with a value of
txq_params->ac that is within the bounds of [0, NL80211_NUM_ACS).

Reported-by: Christian Lamparter <chunkeey@gmail.com>
Reported-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: linux-wireless@vger.kernel.org
Cc: torvalds@linux-foundation.org
Cc: "David S. Miller" <davem@davemloft.net>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727419584.33451.7700736761686184303.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 net/wireless/nl80211.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -14,6 +14,7 @@
 #include <linux/nl80211.h>
 #include <linux/rtnetlink.h>
 #include <linux/netlink.h>
+#include <linux/nospec.h>
 #include <linux/etherdevice.h>
 #include <net/net_namespace.h>
 #include <net/genetlink.h>
@@ -1829,20 +1830,22 @@ static const struct nla_policy txq_param
 static int parse_txq_params(struct nlattr *tb[],
 			    struct ieee80211_txq_params *txq_params)
 {
+	u8 ac;
+
 	if (!tb[NL80211_TXQ_ATTR_AC] || !tb[NL80211_TXQ_ATTR_TXOP] ||
 	    !tb[NL80211_TXQ_ATTR_CWMIN] || !tb[NL80211_TXQ_ATTR_CWMAX] ||
 	    !tb[NL80211_TXQ_ATTR_AIFS])
 		return -EINVAL;
 
-	txq_params->ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]);
+	ac = nla_get_u8(tb[NL80211_TXQ_ATTR_AC]);
 	txq_params->txop = nla_get_u16(tb[NL80211_TXQ_ATTR_TXOP]);
 	txq_params->cwmin = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMIN]);
 	txq_params->cwmax = nla_get_u16(tb[NL80211_TXQ_ATTR_CWMAX]);
 	txq_params->aifs = nla_get_u8(tb[NL80211_TXQ_ATTR_AIFS]);
 
-	if (txq_params->ac >= NL80211_NUM_ACS)
+	if (ac >= NL80211_NUM_ACS)
 		return -EINVAL;
-
+	txq_params->ac = array_index_nospec(ac, NL80211_NUM_ACS);
 	return 0;
 }
 

[PATCH 3.16 53/76] x86: Implement array_index_mask_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit babdde2698d482b6c0de1eab4f697cf5856c5859 upstream.

array_index_nospec() uses a mask to sanitize user controllable array
indexes, i.e. generate a 0 mask if 'index' >= 'size', and a ~0 mask
otherwise. While the default array_index_mask_nospec() handles the
carry-bit from the (index - size) result in software.

The x86 array_index_mask_nospec() does the same, but the carry-bit is
handled in the processor CF flag without conditional instructions in the
control flow.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727414808.33451.1873237130672785331.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/include/asm/barrier.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -25,6 +25,30 @@
 #endif
 
 /**
+ * array_index_mask_nospec() - generate a mask that is ~0UL when the
+ * 	bounds check succeeds and 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ *
+ * Returns:
+ *     0 - (index < size)
+ */
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+		unsigned long size)
+{
+	unsigned long mask;
+
+	asm ("cmp %1,%2; sbb %0,%0;"
+			:"=r" (mask)
+			:"r"(size),"r" (index)
+			:"cc");
+	return mask;
+}
+
+/* Override the default implementation from linux/nospec.h. */
+#define array_index_mask_nospec array_index_mask_nospec
+
+/**
  * read_barrier_depends - Flush all pending reads that subsequents reads
  * depend on.
  *

[PATCH 3.16 53/76] x86: Implement array_index_mask_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit babdde2698d482b6c0de1eab4f697cf5856c5859 upstream.

array_index_nospec() uses a mask to sanitize user controllable array
indexes, i.e. generate a 0 mask if 'index' >= 'size', and a ~0 mask
otherwise. While the default array_index_mask_nospec() handles the
carry-bit from the (index - size) result in software.

The x86 array_index_mask_nospec() does the same, but the carry-bit is
handled in the processor CF flag without conditional instructions in the
control flow.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727414808.33451.1873237130672785331.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/include/asm/barrier.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -25,6 +25,30 @@
 #endif
 
 /**
+ * array_index_mask_nospec() - generate a mask that is ~0UL when the
+ * 	bounds check succeeds and 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ *
+ * Returns:
+ *     0 - (index < size)
+ */
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+		unsigned long size)
+{
+	unsigned long mask;
+
+	asm ("cmp %1,%2; sbb %0,%0;"
+			:"=r" (mask)
+			:"r"(size),"r" (index)
+			:"cc");
+	return mask;
+}
+
+/* Override the default implementation from linux/nospec.h. */
+#define array_index_mask_nospec array_index_mask_nospec
+
+/**
  * read_barrier_depends - Flush all pending reads that subsequents reads
  * depend on.
  *

[PATCH 3.16 55/76] x86/get_user: Use pointer masking to limit speculation

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit c7f631cb07e7da06ac1d231ca178452339e32a94 upstream.

Quoting Linus:

    I do think that it would be a good idea to very expressly document
    the fact that it's not that the user access itself is unsafe. I do
    agree that things like "get_user()" want to be protected, but not
    because of any direct bugs or problems with get_user() and friends,
    but simply because get_user() is an excellent source of a pointer
    that is obviously controlled from a potentially attacking user
    space. So it's a prime candidate for then finding _subsequent_
    accesses that can then be used to perturb the cache.

Unlike the __get_user() case get_user() includes the address limit check
near the pointer de-reference. With that locality the speculation can be
mitigated with pointer narrowing rather than a barrier, i.e.
array_index_nospec(). Where the narrowing is performed by:

	cmp %limit, %ptr
	sbb %mask, %mask
	and %mask, %ptr

With respect to speculation the value of %ptr is either less than %limit
or NULL.

Co-developed-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727417469.33451.11804043010080838495.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/lib/getuser.S | 10 ++++++++++
 1 file changed, 10 insertions(+)

--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -40,6 +40,8 @@ ENTRY(__get_user_1)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 1:	movzbl (%_ASM_AX),%edx
 	xor %eax,%eax
@@ -55,6 +57,8 @@ ENTRY(__get_user_2)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 2:	movzwl -1(%_ASM_AX),%edx
 	xor %eax,%eax
@@ -70,6 +74,8 @@ ENTRY(__get_user_4)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 3:	movl -3(%_ASM_AX),%edx
 	xor %eax,%eax
@@ -86,6 +92,8 @@ ENTRY(__get_user_8)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 4:	movq -7(%_ASM_AX),%rdx
 	xor %eax,%eax
@@ -97,6 +105,8 @@ ENTRY(__get_user_8)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user_8
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 4:	movl -7(%_ASM_AX),%edx
 5:	movl -3(%_ASM_AX),%ecx

[PATCH 3.16 55/76] x86/get_user: Use pointer masking to limit speculation

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit c7f631cb07e7da06ac1d231ca178452339e32a94 upstream.

Quoting Linus:

    I do think that it would be a good idea to very expressly document
    the fact that it's not that the user access itself is unsafe. I do
    agree that things like "get_user()" want to be protected, but not
    because of any direct bugs or problems with get_user() and friends,
    but simply because get_user() is an excellent source of a pointer
    that is obviously controlled from a potentially attacking user
    space. So it's a prime candidate for then finding _subsequent_
    accesses that can then be used to perturb the cache.

Unlike the __get_user() case get_user() includes the address limit check
near the pointer de-reference. With that locality the speculation can be
mitigated with pointer narrowing rather than a barrier, i.e.
array_index_nospec(). Where the narrowing is performed by:

	cmp %limit, %ptr
	sbb %mask, %mask
	and %mask, %ptr

With respect to speculation the value of %ptr is either less than %limit
or NULL.

Co-developed-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727417469.33451.11804043010080838495.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/lib/getuser.S | 10 ++++++++++
 1 file changed, 10 insertions(+)

--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -40,6 +40,8 @@ ENTRY(__get_user_1)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 1:	movzbl (%_ASM_AX),%edx
 	xor %eax,%eax
@@ -55,6 +57,8 @@ ENTRY(__get_user_2)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 2:	movzwl -1(%_ASM_AX),%edx
 	xor %eax,%eax
@@ -70,6 +74,8 @@ ENTRY(__get_user_4)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 3:	movl -3(%_ASM_AX),%edx
 	xor %eax,%eax
@@ -86,6 +92,8 @@ ENTRY(__get_user_8)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 4:	movq -7(%_ASM_AX),%rdx
 	xor %eax,%eax
@@ -97,6 +105,8 @@ ENTRY(__get_user_8)
 	GET_THREAD_INFO(%_ASM_DX)
 	cmp TI_addr_limit(%_ASM_DX),%_ASM_AX
 	jae bad_get_user_8
+	sbb %_ASM_DX, %_ASM_DX		/* array_index_mask_nospec() */
+	and %_ASM_DX, %_ASM_AX
 	ASM_STAC
 4:	movl -7(%_ASM_AX),%edx
 5:	movl -3(%_ASM_AX),%ecx

[PATCH 3.16 52/76] array_index_nospec: Sanitize speculative array de-references

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit f3804203306e098dae9ca51540fcd5eb700d7f40 upstream.

array_index_nospec() is proposed as a generic mechanism to mitigate
against Spectre-variant-1 attacks, i.e. an attack that bypasses boundary
checks via speculative execution. The array_index_nospec()
implementation is expected to be safe for current generation CPUs across
multiple architectures (ARM, x86).

Based on an original implementation by Linus Torvalds, tweaked to remove
speculative flows by Alexei Starovoitov, and tweaked again by Linus to
introduce an x86 assembly implementation for the mask generation.

Co-developed-by: Linus Torvalds <torvalds@linux-foundation.org>
Co-developed-by: Alexei Starovoitov <ast@kernel.org>
Suggested-by: Cyril Novikov <cnovikov@lynx.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: gregkh@linuxfoundation.org
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727414229.33451.18411580953862676575.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/nospec.h | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 72 insertions(+)
 create mode 100644 include/linux/nospec.h

--- /dev/null
+++ b/include/linux/nospec.h
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright(c) 2018 Linus Torvalds. All rights reserved.
+// Copyright(c) 2018 Alexei Starovoitov. All rights reserved.
+// Copyright(c) 2018 Intel Corporation. All rights reserved.
+
+#ifndef _LINUX_NOSPEC_H
+#define _LINUX_NOSPEC_H
+
+/**
+ * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ *
+ * When @index is out of bounds (@index >= @size), the sign bit will be
+ * set.  Extend the sign bit to all bits and invert, giving a result of
+ * zero for an out of bounds index, or ~0 if within bounds [0, @size).
+ */
+#ifndef array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+						    unsigned long size)
+{
+	/*
+	 * Warn developers about inappropriate array_index_nospec() usage.
+	 *
+	 * Even if the CPU speculates past the WARN_ONCE branch, the
+	 * sign bit of @index is taken into account when generating the
+	 * mask.
+	 *
+	 * This warning is compiled out when the compiler can infer that
+	 * @index and @size are less than LONG_MAX.
+	 */
+	if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX,
+			"array_index_nospec() limited to range of [0, LONG_MAX]\n"))
+		return 0;
+
+	/*
+	 * Always calculate and emit the mask even if the compiler
+	 * thinks the mask is not needed. The compiler does not take
+	 * into account the value of @index under speculation.
+	 */
+	OPTIMIZER_HIDE_VAR(index);
+	return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1);
+}
+#endif
+
+/*
+ * array_index_nospec - sanitize an array index after a bounds check
+ *
+ * For a code sequence like:
+ *
+ *     if (index < size) {
+ *         index = array_index_nospec(index, size);
+ *         val = array[index];
+ *     }
+ *
+ * ...if the CPU speculates past the bounds check then
+ * array_index_nospec() will clamp the index within the range of [0,
+ * size).
+ */
+#define array_index_nospec(index, size)					\
+({									\
+	typeof(index) _i = (index);					\
+	typeof(size) _s = (size);					\
+	unsigned long _mask = array_index_mask_nospec(_i, _s);		\
+									\
+	BUILD_BUG_ON(sizeof(_i) > sizeof(long));			\
+	BUILD_BUG_ON(sizeof(_s) > sizeof(long));			\
+									\
+	_i &= _mask;							\
+	_i;								\
+})
+#endif /* _LINUX_NOSPEC_H */

[PATCH 3.16 52/76] array_index_nospec: Sanitize speculative array de-references

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit f3804203306e098dae9ca51540fcd5eb700d7f40 upstream.

array_index_nospec() is proposed as a generic mechanism to mitigate
against Spectre-variant-1 attacks, i.e. an attack that bypasses boundary
checks via speculative execution. The array_index_nospec()
implementation is expected to be safe for current generation CPUs across
multiple architectures (ARM, x86).

Based on an original implementation by Linus Torvalds, tweaked to remove
speculative flows by Alexei Starovoitov, and tweaked again by Linus to
introduce an x86 assembly implementation for the mask generation.

Co-developed-by: Linus Torvalds <torvalds@linux-foundation.org>
Co-developed-by: Alexei Starovoitov <ast@kernel.org>
Suggested-by: Cyril Novikov <cnovikov@lynx.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: gregkh@linuxfoundation.org
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727414229.33451.18411580953862676575.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/nospec.h | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 72 insertions(+)
 create mode 100644 include/linux/nospec.h

--- /dev/null
+++ b/include/linux/nospec.h
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright(c) 2018 Linus Torvalds. All rights reserved.
+// Copyright(c) 2018 Alexei Starovoitov. All rights reserved.
+// Copyright(c) 2018 Intel Corporation. All rights reserved.
+
+#ifndef _LINUX_NOSPEC_H
+#define _LINUX_NOSPEC_H
+
+/**
+ * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ *
+ * When @index is out of bounds (@index >= @size), the sign bit will be
+ * set.  Extend the sign bit to all bits and invert, giving a result of
+ * zero for an out of bounds index, or ~0 if within bounds [0, @size).
+ */
+#ifndef array_index_mask_nospec
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+						    unsigned long size)
+{
+	/*
+	 * Warn developers about inappropriate array_index_nospec() usage.
+	 *
+	 * Even if the CPU speculates past the WARN_ONCE branch, the
+	 * sign bit of @index is taken into account when generating the
+	 * mask.
+	 *
+	 * This warning is compiled out when the compiler can infer that
+	 * @index and @size are less than LONG_MAX.
+	 */
+	if (WARN_ONCE(index > LONG_MAX || size > LONG_MAX,
+			"array_index_nospec() limited to range of [0, LONG_MAX]\n"))
+		return 0;
+
+	/*
+	 * Always calculate and emit the mask even if the compiler
+	 * thinks the mask is not needed. The compiler does not take
+	 * into account the value of @index under speculation.
+	 */
+	OPTIMIZER_HIDE_VAR(index);
+	return ~(long)(index | (size - 1UL - index)) >> (BITS_PER_LONG - 1);
+}
+#endif
+
+/*
+ * array_index_nospec - sanitize an array index after a bounds check
+ *
+ * For a code sequence like:
+ *
+ *     if (index < size) {
+ *         index = array_index_nospec(index, size);
+ *         val = array[index];
+ *     }
+ *
+ * ...if the CPU speculates past the bounds check then
+ * array_index_nospec() will clamp the index within the range of [0,
+ * size).
+ */
+#define array_index_nospec(index, size)					\
+({									\
+	typeof(index) _i = (index);					\
+	typeof(size) _s = (size);					\
+	unsigned long _mask = array_index_mask_nospec(_i, _s);		\
+									\
+	BUILD_BUG_ON(sizeof(_i) > sizeof(long));			\
+	BUILD_BUG_ON(sizeof(_s) > sizeof(long));			\
+									\
+	_i &= _mask;							\
+	_i;								\
+})
+#endif /* _LINUX_NOSPEC_H */

[PATCH 3.16 70/76] nospec: Include <asm/barrier.h> dependency

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit eb6174f6d1be16b19cfa43dac296bfed003ce1a6 upstream.

The nospec.h header expects the per-architecture header file
<asm/barrier.h> to optionally define array_index_mask_nospec(). Include
that dependency to prevent inadvertent fallback to the default
array_index_mask_nospec() implementation.

The default implementation may not provide a full mitigation
on architectures that perform data value speculation.

Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/151881605404.17395.1341935530792574707.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/nospec.h | 1 +
 1 file changed, 1 insertion(+)

--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -5,6 +5,7 @@
 
 #ifndef _LINUX_NOSPEC_H
 #define _LINUX_NOSPEC_H
+#include <asm/barrier.h>
 
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise

[PATCH 3.16 70/76] nospec: Include <asm/barrier.h> dependency

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit eb6174f6d1be16b19cfa43dac296bfed003ce1a6 upstream.

The nospec.h header expects the per-architecture header file
<asm/barrier.h> to optionally define array_index_mask_nospec(). Include
that dependency to prevent inadvertent fallback to the default
array_index_mask_nospec() implementation.

The default implementation may not provide a full mitigation
on architectures that perform data value speculation.

Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/151881605404.17395.1341935530792574707.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 include/linux/nospec.h | 1 +
 1 file changed, 1 insertion(+)

--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -5,6 +5,7 @@
 
 #ifndef _LINUX_NOSPEC_H
 #define _LINUX_NOSPEC_H
+#include <asm/barrier.h>
 
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise

[PATCH 3.16 75/76] x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 304ec1b050310548db33063e567123fae8fd0301 upstream.

Quoting Linus:

    I do think that it would be a good idea to very expressly document
    the fact that it's not that the user access itself is unsafe. I do
    agree that things like "get_user()" want to be protected, but not
    because of any direct bugs or problems with get_user() and friends,
    but simply because get_user() is an excellent source of a pointer
    that is obviously controlled from a potentially attacking user
    space. So it's a prime candidate for then finding _subsequent_
    accesses that can then be used to perturb the cache.

__uaccess_begin_nospec() covers __get_user() and copy_from_iter() where the
limit check is far away from the user pointer de-reference. In those cases
a barrier_nospec() prevents speculation with a potential pointer to
privileged memory. uaccess_try_nospec covers get_user_try.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727416953.33451.10508284228526170604.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16:
 - Convert several more functions to use __uaccess_begin_nospec(), that
   are just wrappers in mainline
 - There's no 'case 8' in __copy_to_user_inatomic()
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -433,7 +433,7 @@ do {									\
 ({									\
 	int __gu_err;							\
 	unsigned long __gu_val;						\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	__uaccess_end();						\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
@@ -541,7 +541,7 @@ struct __large_struct { unsigned long bu
  *	get_user_ex(...);
  * } get_user_catch(err)
  */
-#define get_user_try		uaccess_try
+#define get_user_try		uaccess_try_nospec
 #define get_user_catch(err)	uaccess_catch(err)
 
 #define get_user_ex(x, ptr)	do {					\
@@ -576,7 +576,7 @@ extern void __cmpxchg_wrong_size(void)
 	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	switch (size) {							\
 	case 1:								\
 	{								\
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -48,19 +48,19 @@ __copy_to_user_inatomic(void __user *to,
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__put_user_size(*(u8 *)from, (u8 __user *)to,
 					1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__put_user_size(*(u16 *)from, (u16 __user *)to,
 					2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__put_user_size(*(u32 *)from, (u32 __user *)to,
 					4, ret, 4);
 			__uaccess_end();
@@ -104,17 +104,17 @@ __copy_from_user_inatomic(void *to, cons
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
@@ -154,17 +154,17 @@ __copy_from_user(void *to, const void __
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
@@ -182,17 +182,17 @@ static __always_inline unsigned long __c
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -57,31 +57,31 @@ int __copy_from_user_nocheck(void *dst,
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
 	case 1:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u8 *)dst, (u8 __user *)src,
 			      ret, "b", "b", "=q", 1);
 		__uaccess_end();
 		return ret;
 	case 2:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u16 *)dst, (u16 __user *)src,
 			      ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
 	case 4:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u32 *)dst, (u32 __user *)src,
 			      ret, "l", "k", "=r", 4);
 		__uaccess_end();
 		return ret;
 	case 8:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			      ret, "q", "", "=r", 8);
 		__uaccess_end();
 		return ret;
 	case 10:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 10);
 		if (likely(!ret))
@@ -91,7 +91,7 @@ int __copy_from_user_nocheck(void *dst,
 		__uaccess_end();
 		return ret;
 	case 16:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 16);
 		if (likely(!ret))
@@ -190,7 +190,7 @@ int __copy_in_user(void __user *dst, con
 	switch (size) {
 	case 1: {
 		u8 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u8 __user *)src,
 			       ret, "b", "b", "=q", 1);
 		if (likely(!ret))
@@ -201,7 +201,7 @@ int __copy_in_user(void __user *dst, con
 	}
 	case 2: {
 		u16 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u16 __user *)src,
 			       ret, "w", "w", "=r", 2);
 		if (likely(!ret))
@@ -213,7 +213,7 @@ int __copy_in_user(void __user *dst, con
 
 	case 4: {
 		u32 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u32 __user *)src,
 			       ret, "l", "k", "=r", 4);
 		if (likely(!ret))
@@ -224,7 +224,7 @@ int __copy_in_user(void __user *dst, con
 	}
 	case 8: {
 		u64 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u64 __user *)src,
 			       ret, "q", "", "=r", 8);
 		if (likely(!ret))
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,7 +570,7 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
@@ -583,7 +583,7 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
 					unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user_zeroing(to, from, n);
 	else
@@ -596,7 +596,7 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
 					 unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
@@ -610,7 +610,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_intel_nocache(to, from, n);

[PATCH 3.16 75/76] x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit 304ec1b050310548db33063e567123fae8fd0301 upstream.

Quoting Linus:

    I do think that it would be a good idea to very expressly document
    the fact that it's not that the user access itself is unsafe. I do
    agree that things like "get_user()" want to be protected, but not
    because of any direct bugs or problems with get_user() and friends,
    but simply because get_user() is an excellent source of a pointer
    that is obviously controlled from a potentially attacking user
    space. So it's a prime candidate for then finding _subsequent_
    accesses that can then be used to perturb the cache.

__uaccess_begin_nospec() covers __get_user() and copy_from_iter() where the
limit check is far away from the user pointer de-reference. In those cases
a barrier_nospec() prevents speculation with a potential pointer to
privileged memory. uaccess_try_nospec covers get_user_try.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727416953.33451.10508284228526170604.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16:
 - Convert several more functions to use __uaccess_begin_nospec(), that
   are just wrappers in mainline
 - There's no 'case 8' in __copy_to_user_inatomic()
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -433,7 +433,7 @@ do {									\
 ({									\
 	int __gu_err;							\
 	unsigned long __gu_val;						\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	__uaccess_end();						\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
@@ -541,7 +541,7 @@ struct __large_struct { unsigned long bu
  *	get_user_ex(...);
  * } get_user_catch(err)
  */
-#define get_user_try		uaccess_try
+#define get_user_try		uaccess_try_nospec
 #define get_user_catch(err)	uaccess_catch(err)
 
 #define get_user_ex(x, ptr)	do {					\
@@ -576,7 +576,7 @@ extern void __cmpxchg_wrong_size(void)
 	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	switch (size) {							\
 	case 1:								\
 	{								\
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -48,19 +48,19 @@ __copy_to_user_inatomic(void __user *to,
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__put_user_size(*(u8 *)from, (u8 __user *)to,
 					1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__put_user_size(*(u16 *)from, (u16 __user *)to,
 					2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__put_user_size(*(u32 *)from, (u32 __user *)to,
 					4, ret, 4);
 			__uaccess_end();
@@ -104,17 +104,17 @@ __copy_from_user_inatomic(void *to, cons
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
@@ -154,17 +154,17 @@ __copy_from_user(void *to, const void __
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
@@ -182,17 +182,17 @@ static __always_inline unsigned long __c
 
 		switch (n) {
 		case 1:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u8 *)to, from, 1, ret, 1);
 			__uaccess_end();
 			return ret;
 		case 2:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u16 *)to, from, 2, ret, 2);
 			__uaccess_end();
 			return ret;
 		case 4:
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_size(*(u32 *)to, from, 4, ret, 4);
 			__uaccess_end();
 			return ret;
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -57,31 +57,31 @@ int __copy_from_user_nocheck(void *dst,
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
 	case 1:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u8 *)dst, (u8 __user *)src,
 			      ret, "b", "b", "=q", 1);
 		__uaccess_end();
 		return ret;
 	case 2:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u16 *)dst, (u16 __user *)src,
 			      ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
 	case 4:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u32 *)dst, (u32 __user *)src,
 			      ret, "l", "k", "=r", 4);
 		__uaccess_end();
 		return ret;
 	case 8:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			      ret, "q", "", "=r", 8);
 		__uaccess_end();
 		return ret;
 	case 10:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 10);
 		if (likely(!ret))
@@ -91,7 +91,7 @@ int __copy_from_user_nocheck(void *dst,
 		__uaccess_end();
 		return ret;
 	case 16:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 16);
 		if (likely(!ret))
@@ -190,7 +190,7 @@ int __copy_in_user(void __user *dst, con
 	switch (size) {
 	case 1: {
 		u8 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u8 __user *)src,
 			       ret, "b", "b", "=q", 1);
 		if (likely(!ret))
@@ -201,7 +201,7 @@ int __copy_in_user(void __user *dst, con
 	}
 	case 2: {
 		u16 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u16 __user *)src,
 			       ret, "w", "w", "=r", 2);
 		if (likely(!ret))
@@ -213,7 +213,7 @@ int __copy_in_user(void __user *dst, con
 
 	case 4: {
 		u32 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u32 __user *)src,
 			       ret, "l", "k", "=r", 4);
 		if (likely(!ret))
@@ -224,7 +224,7 @@ int __copy_in_user(void __user *dst, con
 	}
 	case 8: {
 		u64 tmp;
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm(tmp, (u64 __user *)src,
 			       ret, "q", "", "=r", 8);
 		if (likely(!ret))
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,7 +570,7 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
@@ -583,7 +583,7 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
 					unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user_zeroing(to, from, n);
 	else
@@ -596,7 +596,7 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
 					 unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
@@ -610,7 +610,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
 {
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_intel_nocache(to, from, n);

[PATCH 3.16 54/76] x86: Introduce barrier_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit b3d7ad85b80bbc404635dca80f5b129f6242bc7a upstream.

Rename the open coded form of this instruction sequence from
rdtsc_ordered() into a generic barrier primitive, barrier_nospec().

One of the mitigations for Spectre variant1 vulnerabilities is to fence
speculative execution after successfully validating a bounds check. I.e.
force the result of a bounds check to resolve in the instruction pipeline
to ensure speculative execution honors that result before potentially
operating on out-of-bounds data.

No functional changes.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Andi Kleen <ak@linux.intel.com>
Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727415361.33451.9049453007262764675.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16: update rdtsc_barrier() instead of rdtsc_ordered()]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -48,6 +48,10 @@ static inline unsigned long array_index_
 /* Override the default implementation from linux/nospec.h. */
 #define array_index_mask_nospec array_index_mask_nospec
 
+/* Prevent speculative execution past this barrier. */
+#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
+					   "lfence", X86_FEATURE_LFENCE_RDTSC)
+
 /**
  * read_barrier_depends - Flush all pending reads that subsequents reads
  * depend on.
@@ -174,8 +178,7 @@ do {									\
  */
 static __always_inline void rdtsc_barrier(void)
 {
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+	barrier_nospec();
 }
 
 #endif /* _ASM_X86_BARRIER_H */

[PATCH 3.16 54/76] x86: Introduce barrier_nospec

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit b3d7ad85b80bbc404635dca80f5b129f6242bc7a upstream.

Rename the open coded form of this instruction sequence from
rdtsc_ordered() into a generic barrier primitive, barrier_nospec().

One of the mitigations for Spectre variant1 vulnerabilities is to fence
speculative execution after successfully validating a bounds check. I.e.
force the result of a bounds check to resolve in the instruction pipeline
to ensure speculative execution honors that result before potentially
operating on out-of-bounds data.

No functional changes.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Suggested-by: Andi Kleen <ak@linux.intel.com>
Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727415361.33451.9049453007262764675.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16: update rdtsc_barrier() instead of rdtsc_ordered()]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -48,6 +48,10 @@ static inline unsigned long array_index_
 /* Override the default implementation from linux/nospec.h. */
 #define array_index_mask_nospec array_index_mask_nospec
 
+/* Prevent speculative execution past this barrier. */
+#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
+					   "lfence", X86_FEATURE_LFENCE_RDTSC)
+
 /**
  * read_barrier_depends - Flush all pending reads that subsequents reads
  * depend on.
@@ -174,8 +178,7 @@ do {									\
  */
 static __always_inline void rdtsc_barrier(void)
 {
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+	barrier_nospec();
 }
 
 #endif /* _ASM_X86_BARRIER_H */

[PATCH 3.16 59/76] x86/spectre: Report get_user mitigation for spectre_v1

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit edfbae53dab8348fca778531be9f4855d2ca0360 upstream.

Reflect the presence of get_user(), __get_user(), and 'syscall' protections
in sysfs. The expectation is that new and better tooling will allow the
kernel to grow more usages of array_index_nospec(), for now, only claim
mitigation for __user pointer de-references.

Reported-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727420158.33451.11658324346540434635.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/kernel/cpu/bugs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -353,7 +353,7 @@ ssize_t cpu_show_spectre_v1(struct devic
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
 		return sprintf(buf, "Not affected\n");
-	return sprintf(buf, "Vulnerable\n");
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 }
 
 ssize_t cpu_show_spectre_v2(struct device *dev,

[PATCH 3.16 59/76] x86/spectre: Report get_user mitigation for spectre_v1

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit edfbae53dab8348fca778531be9f4855d2ca0360 upstream.

Reflect the presence of get_user(), __get_user(), and 'syscall' protections
in sysfs. The expectation is that new and better tooling will allow the
kernel to grow more usages of array_index_nospec(), for now, only claim
mitigation for __user pointer de-references.

Reported-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727420158.33451.11658324346540434635.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/kernel/cpu/bugs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -353,7 +353,7 @@ ssize_t cpu_show_spectre_v1(struct devic
 {
 	if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
 		return sprintf(buf, "Not affected\n");
-	return sprintf(buf, "Vulnerable\n");
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
 }
 
 ssize_t cpu_show_spectre_v2(struct device *dev,

[PATCH 3.16 74/76] x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end}

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit b5c4ae4f35325d520b230bab6eb3310613b72ac1 upstream.

In preparation for converting some __uaccess_begin() instances to
__uacess_begin_nospec(), make sure all 'from user' uaccess paths are
using the _begin(), _end() helpers rather than open-coded stac() and
clac().

No functional changes.

Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727416438.33451.17309465232057176966.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16:
 - Convert several more functions to use __uaccess_begin_nospec(), that
   are just wrappers in mainline
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/lib/usercopy_32.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,12 +570,12 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_to_user_ll);
@@ -583,12 +583,12 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 	if (movsl_is_ok(to, from, n))
 		__copy_user_zeroing(to, from, n);
 	else
 		n = __copy_user_zeroing_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll);
@@ -596,13 +596,13 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
 					 unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel((void __user *)to,
 				      (const void *)from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nozero);
@@ -610,7 +610,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -619,7 +619,7 @@ unsigned long __copy_from_user_ll_nocach
 #else
 	__copy_user_zeroing(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache);
@@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_intel_nocache(to, from, n);
@@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocach
 #else
 	__copy_user(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);

[PATCH 3.16 74/76] x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end}

[Ben Hutchings]

3.16.56-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Dan Williams <dan.j.williams@intel.com>

commit b5c4ae4f35325d520b230bab6eb3310613b72ac1 upstream.

In preparation for converting some __uaccess_begin() instances to
__uacess_begin_nospec(), make sure all 'from user' uaccess paths are
using the _begin(), _end() helpers rather than open-coded stac() and
clac().

No functional changes.

Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: kernel-hardening@lists.openwall.com
Cc: gregkh@linuxfoundation.org
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: torvalds@linux-foundation.org
Cc: alan@linux.intel.com
Link: https://lkml.kernel.org/r/151727416438.33451.17309465232057176966.stgit@dwillia2-desk3.amr.corp.intel.com
[bwh: Backported to 3.16:
 - Convert several more functions to use __uaccess_begin_nospec(), that
   are just wrappers in mainline
 - Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 arch/x86/lib/usercopy_32.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -570,12 +570,12 @@ do {									\
 unsigned long __copy_to_user_ll(void __user *to, const void *from,
 				unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_to_user_ll);
@@ -583,12 +583,12 @@ EXPORT_SYMBOL(__copy_to_user_ll);
 unsigned long __copy_from_user_ll(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 	if (movsl_is_ok(to, from, n))
 		__copy_user_zeroing(to, from, n);
 	else
 		n = __copy_user_zeroing_intel(to, from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll);
@@ -596,13 +596,13 @@ EXPORT_SYMBOL(__copy_from_user_ll);
 unsigned long __copy_from_user_ll_nozero(void *to, const void __user *from,
 					 unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 	if (movsl_is_ok(to, from, n))
 		__copy_user(to, from, n);
 	else
 		n = __copy_user_intel((void __user *)to,
 				      (const void *)from, n);
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nozero);
@@ -610,7 +610,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nozero
 unsigned long __copy_from_user_ll_nocache(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_zeroing_intel_nocache(to, from, n);
@@ -619,7 +619,7 @@ unsigned long __copy_from_user_ll_nocach
 #else
 	__copy_user_zeroing(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache);
@@ -627,7 +627,7 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocach
 unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
 					unsigned long n)
 {
-	stac();
+	__uaccess_begin();
 #ifdef CONFIG_X86_INTEL_USERCOPY
 	if (n > 64 && cpu_has_xmm2)
 		n = __copy_user_intel_nocache(to, from, n);
@@ -636,7 +636,7 @@ unsigned long __copy_from_user_ll_nocach
 #else
 	__copy_user(to, from, n);
 #endif
-	clac();
+	__uaccess_end();
 	return n;
 }
 EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);