1iTLB multihit
2=============
3
4iTLB multihit is an erratum where some processors may incur a machine check
5error, possibly resulting in an unrecoverable CPU lockup, when an
6instruction fetch hits multiple entries in the instruction TLB. This can
7occur when the page size is changed along with either the physical address
8or cache type. A malicious guest running on a virtualized system can
9exploit this erratum to perform a denial of service attack.
10
11
12Affected processors
13-------------------
14
15Variations of this erratum are present on most Intel Core and Xeon processor
16models. The erratum is not present on:
17
18   - non-Intel processors
19
20   - Some Atoms (Airmont, Bonnell, Goldmont, GoldmontPlus, Saltwell, Silvermont)
21
22   - Intel processors that have the PSCHANGE_MC_NO bit set in the
23     IA32_ARCH_CAPABILITIES MSR.
24
25
26Related CVEs
27------------
28
29The following CVE entry is related to this issue:
30
31   ==============  =================================================
32   CVE-2018-12207  Machine Check Error Avoidance on Page Size Change
33   ==============  =================================================
34
35
36Problem
37-------
38
39Privileged software, including OS and virtual machine managers (VMM), are in
40charge of memory management. A key component in memory management is the control
41of the page tables. Modern processors use virtual memory, a technique that creates
42the illusion of a very large memory for processors. This virtual space is split
43into pages of a given size. Page tables translate virtual addresses to physical
44addresses.
45
46To reduce latency when performing a virtual to physical address translation,
47processors include a structure, called TLB, that caches recent translations.
48There are separate TLBs for instruction (iTLB) and data (dTLB).
49
50Under this errata, instructions are fetched from a linear address translated
51using a 4 KB translation cached in the iTLB. Privileged software modifies the
52paging structure so that the same linear address using large page size (2 MB, 4
53MB, 1 GB) with a different physical address or memory type.  After the page
54structure modification but before the software invalidates any iTLB entries for
55the linear address, a code fetch that happens on the same linear address may
56cause a machine-check error which can result in a system hang or shutdown.
57
58
59Attack scenarios
60----------------
61
62Attacks against the iTLB multihit erratum can be mounted from malicious
63guests in a virtualized system.
64
65
66iTLB multihit system information
67--------------------------------
68
69The Linux kernel provides a sysfs interface to enumerate the current iTLB
70multihit status of the system:whether the system is vulnerable and which
71mitigations are active. The relevant sysfs file is:
72
73/sys/devices/system/cpu/vulnerabilities/itlb_multihit
74
75The possible values in this file are:
76
77.. list-table::
78
79     * - Not affected
80       - The processor is not vulnerable.
81     * - KVM: Mitigation: Split huge pages
82       - Software changes mitigate this issue.
83     * - KVM: Mitigation: VMX unsupported
84       - KVM is not vulnerable because Virtual Machine Extensions (VMX) is not supported.
85     * - KVM: Mitigation: VMX disabled
86       - KVM is not vulnerable because Virtual Machine Extensions (VMX) is disabled.
87     * - KVM: Vulnerable
88       - The processor is vulnerable, but no mitigation enabled
89
90
91Enumeration of the erratum
92--------------------------------
93
94A new bit has been allocated in the IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) msr
95and will be set on CPU's which are mitigated against this issue.
96
97   =======================================   ===========   ===============================
98   IA32_ARCH_CAPABILITIES MSR                Not present   Possibly vulnerable,check model
99   IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO]    '0'           Likely vulnerable,check model
100   IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO]    '1'           Not vulnerable
101   =======================================   ===========   ===============================
102
103
104Mitigation mechanism
105-------------------------
106
107This erratum can be mitigated by restricting the use of large page sizes to
108non-executable pages.  This forces all iTLB entries to be 4K, and removes
109the possibility of multiple hits.
110
111In order to mitigate the vulnerability, KVM initially marks all huge pages
112as non-executable. If the guest attempts to execute in one of those pages,
113the page is broken down into 4K pages, which are then marked executable.
114
115If EPT is disabled or not available on the host, KVM is in control of TLB
116flushes and the problematic situation cannot happen.  However, the shadow
117EPT paging mechanism used by nested virtualization is vulnerable, because
118the nested guest can trigger multiple iTLB hits by modifying its own
119(non-nested) page tables.  For simplicity, KVM will make large pages
120non-executable in all shadow paging modes.
121
122Mitigation control on the kernel command line and KVM - module parameter
123------------------------------------------------------------------------
124
125The KVM hypervisor mitigation mechanism for marking huge pages as
126non-executable can be controlled with a module parameter "nx_huge_pages=".
127The kernel command line allows to control the iTLB multihit mitigations at
128boot time with the option "kvm.nx_huge_pages=".
129
130The valid arguments for these options are:
131
132  ==========  ================================================================
133  force       Mitigation is enabled. In this case, the mitigation implements
134              non-executable huge pages in Linux kernel KVM module. All huge
135              pages in the EPT are marked as non-executable.
136              If a guest attempts to execute in one of those pages, the page is
137              broken down into 4K pages, which are then marked executable.
138
139  off	      Mitigation is disabled.
140
141  auto        Enable mitigation only if the platform is affected and the kernel
142              was not booted with the "mitigations=off" command line parameter.
143	      This is the default option.
144  ==========  ================================================================
145
146
147Mitigation selection guide
148--------------------------
149
1501. No virtualization in use
151^^^^^^^^^^^^^^^^^^^^^^^^^^^
152
153   The system is protected by the kernel unconditionally and no further
154   action is required.
155
1562. Virtualization with trusted guests
157^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
158
159   If the guest comes from a trusted source, you may assume that the guest will
160   not attempt to maliciously exploit these errata and no further action is
161   required.
162
1633. Virtualization with untrusted guests
164^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
165   If the guest comes from an untrusted source, the guest host kernel will need
166   to apply iTLB multihit mitigation via the kernel command line or kvm
167   module parameter.
168