Non-Transparent Sharing of Microarchitectural Resources

Hardware structures shared across execution contexts (e.g., caches and branch predictors) can violate the expected architecture isolation between contexts.


Description

Modern processors use techniques such as out-of-order execution, speculation, prefetching, data forwarding, and caching to increase performance. Details about the implementation of these techniques are hidden from the programmer’s view. This is problematic when the hardware implementation of these techniques results in resources being shared across supposedly isolated contexts. Contention for shared resources between different contexts opens covert channels that allow malicious programs executing in one context to recover information from another context.

Some examples of shared micro-architectural resources that have been used to leak information between contexts are caches, branch prediction logic, and load or store buffers. Speculative and out-of-order execution provides an attacker with increased control over which data is leaked through the covert channel.

If the extent of resource sharing between contexts in the design microarchitecture is undocumented, it is extremely difficult to ensure system assets are protected against disclosure.

Demonstrations

The following examples help to illustrate the nature of this weakness and describe methods or techniques which can be used to mitigate the risk.

Note that the examples here are by no means exhaustive and any given weakness may have many subtle varieties, each of which may require different detection methods or runtime controls.

Example One

Secure programs perform bounds checking before accessing an array if the source of the array index is provided by an untrusted source such as user input. In the code below, data from array1 will not be accessed if x is out of bounds. However, if this code executes on a processor that performs speculative execution the outcome of the if statement could be mis-predicted and the access on the next line will occur with a value of x that can point to arbitrary locations in the program’s memory (out-of-bounds).

Even though the processor rolls back the architectural effects of the mis-predicted branch, the memory accesses alter data cache state, which is not rolled back after the branch is resolved. The cache state can reveal array1[x] thereby providing a mechanism to recover any word in this program’s memory space.

if (x < array1_size)
    						y = array2[array1[x] * 4096];

Code snippet is from the Spectre paper: https://spectreattack.com/spectre.pdf.

See Also

Privilege Separation and Access Control Issues

Weaknesses in this category are related to features and mechanisms providing hardware-based isolation and access control (e.g., identity, policy, locking control) of s...

Comprehensive CWE Dictionary

This view (slice) covers all the elements in CWE.

Weaknesses without Software Fault Patterns

CWE identifiers in this view are weaknesses that do not have associated Software Fault Patterns (SFPs), as covered by the CWE-888 view. As such, they represent gaps in...

Weaknesses Introduced During Implementation

This view (slice) lists weaknesses that can be introduced during implementation.


Common Weakness Enumeration content on this website is copyright of The MITRE Corporation unless otherwise specified. Use of the Common Weakness Enumeration and the associated references on this website are subject to the Terms of Use as specified by The MITRE Corporation.