Messages in this thread | | | From | "Huang, Kai" <> | Subject | Re: [PATCH v5] x86/sgx: Resolves SECS reclaim vs. page fault for EAUG race | Date | Thu, 27 Jul 2023 03:11:50 +0000 |
| |
On Thu, 2023-07-27 at 02:50 +0000, Huang, Kai wrote: > > An enclave can not run nor generate page faults without a resident SECS > > page. > > > > I am not sure whether "nor generate page faults without a resident SECS page" is > accurate? When SECS is swapped out, I suppose the first EENTER should trigger a > #PF on the TSC page and in the #PF handler the SECS will be swapped in first. > > I guess you can just remove this sentence?
Hmm.. Probably I should interpret this sentence as the enclave "code" itself cannot generate page faults without a resident SECS. This is true. So feel free to ignore this comment.
| |