diff for duplicates of <1536959337.12990.27.camel@intel.com> diff --git a/a/content_digest b/N1/content_digest index 148b7a7..3134c38 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -37,7 +37,9 @@ Mike Kravetz <mike.kravetz@oracle.com> Nadav Amit <nadav.amit@gmail.com> Oleg Nesterov <oleg@redhat.com> - " Pavel Machek <pavel@ucw.cz>\0" + Pavel Machek <pavel@ucw.cz> + ravi.v.shankar@intel.com + " vedvyas.shanbhogue@intel.com\0" "\00:1\0" "b\0" "On Fri, 2018-09-14 at 13:46 -0700, Dave Hansen wrote:\n" @@ -73,4 +75,4 @@ "Would mprotect() do copy_one_pte()? \302\240Otherwise it will not go through\n" ptep_set_wrprotect()? -5f2c039aed05f5dd8ffa7888b0463693ed80b0321776cd6ef7e385f6ec9b8bc5 +c971dff974c256b164269cf81bf5fc62d8c40186b38c95a56868268776e705dd
diff --git a/a/1.txt b/N2/1.txt index f335d0b..1023f72 100644 --- a/a/1.txt +++ b/N2/1.txt @@ -3,14 +3,14 @@ On Fri, 2018-09-14 at 13:46 -0700, Dave Hansen wrote: > > > > With the updated ptep_set_wrprotect() below, I did MADV_WILLNEED to a shadow > > stack of 8 MB, then 10,000 fork()'s, but could not prove it is more or less -> > efficient than the other. So can we say this is probably fine in terms of +> > efficient than the other. A So can we say this is probably fine in terms of > > efficiency? -> Well, the first fork() will do all the hard work. I don't think +> Well, the first fork() will do all the hard work.A A I don't think > subsequent fork()s will be affected. Are you talking about a recent commit: - 1b2de5d0 mm/cow: don't bother write protecting already write-protected pages +A A 1b2de5d0 mm/cow: don't bother write protecting already write-protected pages With that, subsequent fork()s will not do all the hard work. However, I have not done that for shadow stack PTEs (do we want to do that?). @@ -28,5 +28,5 @@ I think the additional benefit for shadow stack is small? > > might show it better. -Would mprotect() do copy_one_pte()? Otherwise it will not go through +Would mprotect() do copy_one_pte()? A Otherwise it will not go through ptep_set_wrprotect()? diff --git a/a/content_digest b/N2/content_digest index 148b7a7..fd0defa 100644 --- a/a/content_digest +++ b/N2/content_digest @@ -37,7 +37,9 @@ Mike Kravetz <mike.kravetz@oracle.com> Nadav Amit <nadav.amit@gmail.com> Oleg Nesterov <oleg@redhat.com> - " Pavel Machek <pavel@ucw.cz>\0" + Pavel Machek <pavel@ucw.cz> + ravi.v.shankar@intel.com + " vedvyas.shanbhogue@intel.com\0" "\00:1\0" "b\0" "On Fri, 2018-09-14 at 13:46 -0700, Dave Hansen wrote:\n" @@ -45,14 +47,14 @@ "> > \n" "> > With the updated ptep_set_wrprotect() below, I did MADV_WILLNEED to a shadow\n" "> > stack of 8 MB, then 10,000 fork()'s, but could not prove it is more or less\n" - "> > efficient than the other. \302\240So can we say this is probably fine in terms of\n" + "> > efficient than the other. A So can we say this is probably fine in terms of\n" "> > efficiency?\n" - "> Well, the first fork() will do all the hard work.\302\240\302\240I don't think\n" + "> Well, the first fork() will do all the hard work.A A I don't think\n" "> subsequent fork()s will be affected.\n" "\n" "Are you talking about a recent commit:\n" "\n" - "\302\240 \302\240 1b2de5d0 mm/cow: don't bother write protecting already write-protected pages\n" + "A A 1b2de5d0 mm/cow: don't bother write protecting already write-protected pages\n" "\n" "With that, subsequent fork()s will not do all the hard work.\n" "However, I have not done that for shadow stack PTEs (do we want to do that?).\n" @@ -70,7 +72,7 @@ "> \n" "> might show it better.\n" "\n" - "Would mprotect() do copy_one_pte()? \302\240Otherwise it will not go through\n" + "Would mprotect() do copy_one_pte()? A Otherwise it will not go through\n" ptep_set_wrprotect()? -5f2c039aed05f5dd8ffa7888b0463693ed80b0321776cd6ef7e385f6ec9b8bc5 +441a7dc22cf366afe872abc4952d95023644dc68f20b1ff008cb23233320302f
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.