stable.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Mark Rutland <mark.rutland@arm.com>,
	Will Deacon <will.deacon@arm.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Kees Cook <keescook@chromium.org>,
	linux-arch@vger.kernel.org, Jonathan Corbet <corbet@lwn.net>,
	Peter Zijlstra <peterz@infradead.org>,
	kernel-hardening@lists.openwall.com,
	torvalds@linux-foundation.org, alan@linux.intel.com
Subject: [PATCH 4.15 32/60] Documentation: Document array_index_nospec
Date: Mon,  5 Feb 2018 10:23:05 -0800	[thread overview]
Message-ID: <20180205182215.274202516@linuxfoundation.org> (raw)
In-Reply-To: <20180205182213.902626065@linuxfoundation.org>

4.15-stable review patch.  If anyone has any objections, please let me know.

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

From: Mark Rutland mark.rutland@arm.com

commit f84a56f73dddaeac1dba8045b007f742f61cd2da

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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>


---
 Documentation/speculation.txt |   90 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)

--- /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];
+		}
+	}

  parent reply	other threads:[~2018-02-05 18:25 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-05 18:22 [PATCH 4.15 00/60] 4.15.2-stable review Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 01/60] KVM: x86: Make indirect calls in emulator speculation safe Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 02/60] KVM: VMX: Make indirect call " Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 03/60] module/retpoline: Warn about missing retpoline in module Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 04/60] x86/cpufeatures: Add CPUID_7_EDX CPUID leaf Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 05/60] x86/cpufeatures: Add Intel feature bits for Speculation Control Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 06/60] x86/cpufeatures: Add AMD " Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 07/60] x86/msr: Add definitions for new speculation control MSRs Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 08/60] x86/pti: Do not enable PTI on CPUs which are not vulnerable to Meltdown Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 09/60] x86/cpufeature: Blacklist SPEC_CTRL/PRED_CMD on early Spectre v2 microcodes Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 10/60] x86/speculation: Add basic IBPB (Indirect Branch Prediction Barrier) support Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 11/60] x86/alternative: Print unadorned pointers Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 12/60] x86/nospec: Fix header guards names Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 13/60] x86/bugs: Drop one "mitigation" from dmesg Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 15/60] x86/cpufeatures: Clean up Spectre v2 related CPUID flags Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 16/60] x86/retpoline: Simplify vmexit_fill_RSB() Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 17/60] x86/speculation: Simplify indirect_branch_prediction_barrier() Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 18/60] auxdisplay: img-ascii-lcd: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 19/60] iio: adc/accel: Fix up module licenses Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 20/60] pinctrl: pxa: pxa2xx: add missing MODULE_DESCRIPTION/AUTHOR/LICENSE Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 21/60] ASoC: pcm512x: " Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 23/60] KVM: VMX: introduce alloc_loaded_vmcs Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 24/60] objtool: Improve retpoline alternative handling Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 25/60] objtool: Add support for alternatives at the end of a section Greg Kroah-Hartman
2018-02-05 18:22 ` [PATCH 4.15 26/60] objtool: Warn on stripped section symbol Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 27/60] x86/mm: Fix overlap of i386 CPU_ENTRY_AREA with FIX_BTMAP Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 28/60] x86/spectre: Check CONFIG_RETPOLINE in command line parser Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 29/60] x86/entry/64: Remove the SYSCALL64 fast path Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 30/60] x86/entry/64: Push extra regs right away Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 31/60] x86/asm: Move status from thread_struct to thread_info Greg Kroah-Hartman
2018-02-05 18:23 ` Greg Kroah-Hartman [this message]
2018-02-05 18:23 ` [PATCH 4.15 33/60] array_index_nospec: Sanitize speculative array de-references Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 34/60] x86: Implement array_index_mask_nospec Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 35/60] x86: Introduce barrier_nospec Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 36/60] x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 37/60] x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end} Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 38/60] x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 39/60] x86/get_user: Use pointer masking to limit speculation Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 40/60] x86/syscall: Sanitize syscall table de-references under speculation Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 41/60] vfs, fdtable: Prevent bounds-check bypass via speculative execution Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 42/60] nl80211: Sanitize array index in parse_txq_params Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 43/60] x86/spectre: Report get_user mitigation for spectre_v1 Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 44/60] x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable" Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 45/60] x86/cpuid: Fix up "virtual" IBRS/IBPB/STIBP feature bits on Intel Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 47/60] x86/paravirt: Remove noreplace-paravirt cmdline option Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 48/60] KVM: VMX: make MSR bitmaps per-VCPU Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 49/60] x86/kvm: Update spectre-v1 mitigation Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 50/60] x86/retpoline: Avoid retpolines for built-in __init functions Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 51/60] x86/spectre: Simplify spectre_v2 command line parsing Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 52/60] x86/pti: Mark constant arrays as __initconst Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 53/60] x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 55/60] KVM/x86: Add IBPB support Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 56/60] KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 57/60] KVM/VMX: Allow direct access to MSR_IA32_SPEC_CTRL Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 58/60] KVM/SVM: " Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 59/60] serial: core: mark port as initialized after successful IRQ change Greg Kroah-Hartman
2018-02-05 18:23 ` [PATCH 4.15 60/60] fpga: region: release of_parse_phandle nodes after use Greg Kroah-Hartman
2018-02-05 22:14 ` [PATCH 4.15 00/60] 4.15.2-stable review Shuah Khan
2018-02-06 10:33   ` Greg Kroah-Hartman
2018-02-05 23:58 ` Dan Rue
2018-02-06 10:33   ` Greg Kroah-Hartman
2018-02-06 14:30 ` Guenter Roeck
2018-02-06 14:32 ` Guenter Roeck
2018-02-06 17:00   ` Greg Kroah-Hartman

Reply instructions:

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

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

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

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

  git send-email \
    --in-reply-to=20180205182215.274202516@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=alan@linux.intel.com \
    --cc=corbet@lwn.net \
    --cc=dan.j.williams@intel.com \
    --cc=keescook@chromium.org \
    --cc=kernel-hardening@lists.openwall.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=peterz@infradead.org \
    --cc=stable@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=will.deacon@arm.com \
    /path/to/YOUR_REPLY

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

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).