A flaw was found in the implementation of Intel Transactional Synchronization Extensions (TSX) abortion where a local authenticated attacker with the ability to monitor execution time is able to infer TSX memory state by comparing abort execution times.

This could allow information disclosure via this observed sidechannel for any TSX transaction being executed while an attacker is able to observe abort timing.

A flaw was found in Intel processors where a local attacker is able to gain information about registers used for vector calculations by observing register states from other processes running on the system. This results in a race condition where store buffers, which were not cleared, could be read by another process or a CPU sibling. The highest threat from this vulnerability is data confidentiality where an attacker could read arbitrary data as it passes through the processor.

A flaw was found during cache eviction on some Intel processors which may allow a local attacker to infer cache contents and disclose information through this side-channel.

Reference: ---------- -> https://access.redhat.com/solutions/l1d-cache-eviction-and-vector-register-sampling

Additional information: ----------------------- -> https://en.wikipedia.org/wiki/Vectorprocessor -> https://software.intel.com/en-us/articles/introduction-to-intel-advanced-vector-extensions

A flaw was found in hw. In certain processors with Intel's Enhanced Indirect Branch Restricted Speculation (eIBRS) capabilities, soon after VM exit or IBPB command event, the linear address following the most recent near CALL instruction prior to a VM exit may be used as the Return Stack Buffer (RSB) prediction.