Implicit integrity for cryptographic computing
In one embodiment, a processor includes a memory hierarchy and a core coupled to the memory hierarchy. The memory hierarchy stores encrypted data, and the core includes circuitry to access the encrypted data stored in the memory hierarchy, decrypt the encrypted data to yield decrypted data, perform an entropy test on the decrypted data, and update a processor state based on a result of the entropy test. The entropy test may include determining a number of data entities in the decrypted data whose values are equal to one another, determining a number of adjacent data entities in the decrypted data whose values are equal to one another, determining a number of data entities in the decrypted data whose values are equal to at least one special value from a set of special values, or determining a sum of n highest data entity value frequencies.
1. A processor comprising:
a memory hierarchy storing encrypted data; and
a core coupled to the memory hierarchy, the core comprising circuitry to:
access the encrypted data stored in the memory hierarchy;
decrypt the encrypted data to yield decrypted data;
perform an entropy test on the decrypted data; and
update a processor state based on a result of the entropy test.
2. The processor of claim 1 , wherein the circuitry to perform the entropy test is to perform a set of operations, the set of operations comprising at least one of:
determining a number of data entities in the decrypted data whose values are equal to one another;
determining a number of adjacent data entities in the decrypted data whose values are equal to one another;
determining a number of data entities in the decrypted data whose values are equal to at least one special value from a set of special values; and
determining a sum of n highest data entity value frequencies.
3. The processor of claim 2 , wherein the circuitry to perform the entropy test is further to:
generate a Boolean output for each operation in the set of operations based on a comparison of a number determined by the operation with a respective threshold;
perform a logical OR operation on the generated Boolean outputs; and
update the processor state based on an output of the logical OR operation.
4. The processor of claim 2 , wherein the circuitry to perform the entropy test is further to:
determine, for each operation, an entropy index based on a number determined by the operation;
determine a maximum entropy index of the determined entropy indices;
compare the maximum entropy index with a threshold; and
update the processor state based on the comparison.
5. The processor of claim 2 , wherein the data entities comprise one of a byte, a 16-bit word, a 32-bit doubleword, and a nibble.
6. The processor of claim 2 , wherein the circuitry to determine the sum of n highest data entity value frequencies is to perform one or more of:
determining a sum of n highest nibble frequencies;
determining a sum of n highest most significant nibble frequencies; and
determining a sum of n highest least significant nibble frequencies.
7. The processor of claim 6 , wherein n=2.
8. The processor of claim 1 , wherein the processor further comprises an RFLAGS register, and the core circuitry is to update the processor state by updating a bit in the RFLAGS register.
9. The processor of claim 1 , wherein the processor further comprises a Model-Specific Register (MSR), and the core circuitry is to update the processor state by storing in the MSR information about one or more patterns detected in the decrypted data and a number of entities demonstrating the one or more patterns.
10. The processor of claim 1 , wherein the processor further comprises a Model-Specific Register (MSR), and the core circuitry is to update the processor state by storing in the MSR at least one measure of entropy determined by the entropy test.
11. The processor of claim 1 , wherein the memory hierarchy comprises one or more of a Level-1 (L1) cache, a Level-2 (L2) cache, and a Level-3 (L3) cache.
12. A method comprising:
receiving, at a processor core, encrypted data from a memory hierarchy;
decrypting the encrypted data in the processor core;
determining whether the decrypted data is of low entropy; and
updating a processor state maintained in a processor register based on a determination that the data is of low entropy.
13. The method of claim 12 , wherein determining whether the decrypted data is of low entropy comprises performing a set of operations comprising at least one of:
determining a number of data entities in the decrypted data whose values are equal to one another;
determining a number of adjacent data entities in the decrypted data whose values are equal to one another;
determining a number of data entities in the decrypted data whose values are equal to at least one special value from a set of special values; and
determining a sum of n highest data entity value frequencies.
14. The method of claim 13 , wherein determining whether the decrypted data is of low entropy further comprises:
generating a Boolean output for each operation in the set of operations based on a comparison of a number determined by the operation with a respective threshold; and
performing a logical OR operation on the generated Boolean outputs;
wherein updating the processor state is based on an output of the logical OR operation.
15. The method of claim 13 , wherein determining whether the decrypted data is of low entropy further comprises:
determining, for each operation, an entropy index based on a number determined by the operation;
determining a maximum entropy index of the determined entropy indices; and
comparing the maximum entropy index with a threshold;
wherein updating the processor state is based on the comparison.
16. A non-transitory computer-readable medium storing instructions that when executed by a data processing apparatus are to:
access encrypted data stored in a memory hierarchy;
decrypt the encrypted data to yield decrypted data;
perform an entropy test on the decrypted data; and
update a processor state maintained in a register of the data processing apparatus based on a result of the entropy test.
17. The computer-readable medium of claim 16 , wherein the instructions to perform the entropy test are to perform a set of operations comprising at least one of:
determining a number of data entities in the decrypted data whose values are equal to one another;
determining a number of adjacent data entities in the decrypted data whose values are equal to one another;
determining a number of data entities in the decrypted data whose values are equal to at least one special value from a set of special values; and
determining a sum of n highest data entity value frequencies.
18. The computer-readable medium of claim 17 , wherein the instructions to perform the entropy test are further to:
generate a Boolean output for each operation in the set of operations based on a comparison of a number determined by the operation with a respective threshold;
perform a logical OR operation on the generated Boolean outputs; and
update the processor state based on an output of the logical OR operation.
19. The computer-readable medium of claim 17 , wherein the instructions to perform the entropy test are further to:
determine, for each operation, an entropy index based on a number determined by the operation;
determine a maximum entropy index of the determined entropy indices;
compare the maximum entropy index with a threshold; and
update the processor state based on the comparison.
20. The computer-readable medium of claim 16 , wherein the instructions to update the processor state are to update one or more bits of an RFLAGS register or a Model-Specific Register (MSR).