An industry-wide issue was found in the way many modern microprocessor designs have implemented speculative execution of instructions past bounds check. The flaw relies on the presence of a precisely-defined instruction sequence in the privileged code and the fact that memory writes occur to an address which depends on the untrusted value. Such writes cause an update into the microprocessorβs data cache even for speculatively executed instructions that never actually commit (retire). As a result, an unprivileged attacker could use this flaw to influence speculative execution and/or read privileged memory by conducting targeted cache side-channel attacks.
bugzilla.redhat.com/show_bug.cgi?id=1581650
www.cve.org/CVERecord?id=CVE-2018-3693 https://nvd.nist.gov/vuln/detail/CVE-2018-3693 https://01.org/security/advisories/intel-oss-10002 https://access.redhat.com/solutions/3523601 https://people.csail.mit.edu/vlk/spectre11.pdf https://software.intel.com/sites/default/files/managed/4e/a1/337879-analyzing-potential-bounds-Check-bypass-vulnerabilities.pdf