Re:Spectre is here to stay: An analysis of side-channels and...
by rurban on Saturday February 16, 2019 @02:02AM
(#19177481)
mprotect does not issue a memory barrier (mfence), so whilst theoretically protected it is practically delayed and can still be read from the cache via sidechannels.
Same issue with the unsafe bzero call. A compiler barrier is not safe enough to delete secrets.
[ Parent
| on HN ]
Re:Spectre is here to stay: An analysis of side-channels and...
by gpderetta on Saturday February 16, 2019 @10:35AM
(#19179022)
Mprotect should work because even under speculation the CPU shouldn't allow a read to an invalid address to be executed. Meltdown shows that some CPUs speculate even this sort of checks, but it seems that it is not inherently required for an high performance implementation.