diff for duplicates of <1531868435.3541.18.camel@intel.com> diff --git a/a/content_digest b/N1/content_digest index 98d4a6e..d7fdd94 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -28,7 +28,8 @@ Nadav Amit <nadav.amit@gmail.com> Oleg Nesterov <oleg@redhat.com> Pavel Machek <pavel@ucw.cz> - " Ravi V. Shan\0" + Ravi V. Shankar <ravi.v.shankar@intel.com> + " Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com>\0" "\00:1\0" "b\0" "On Wed, 2018-07-11 at 11:29 +0200, Peter Zijlstra wrote:\n" @@ -67,4 +68,4 @@ "\n" Yu-cheng -aceb7b02ad695e005c2407795346a5ab89a6ce97f09603433aaca8b306da3eea +4c2d7ca6ad4780b777c667864b7ad760462f3b0411b1056e5d0c46e86351933f
diff --git a/a/1.txt b/N2/1.txt index 2339993..84e4227 100644 --- a/a/1.txt +++ b/N2/1.txt @@ -33,3 +33,7 @@ to pte_dirty(). The latter would be less obvious. Or can we create a can_follow_write_shstk_pte()? Yu-cheng +-- +To unsubscribe from this list: send the line "unsubscribe linux-doc" in +the body of a message to majordomo@vger.kernel.org +More majordomo info at http://vger.kernel.org/majordomo-info.html diff --git a/a/content_digest b/N2/content_digest index 98d4a6e..841f39b 100644 --- a/a/content_digest +++ b/N2/content_digest @@ -28,7 +28,8 @@ Nadav Amit <nadav.amit@gmail.com> Oleg Nesterov <oleg@redhat.com> Pavel Machek <pavel@ucw.cz> - " Ravi V. Shan\0" + Ravi V. Shankar <ravi.v.shankar@intel.com> + " Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com>\0" "\00:1\0" "b\0" "On Wed, 2018-07-11 at 11:29 +0200, Peter Zijlstra wrote:\n" @@ -65,6 +66,10 @@ "to pte_dirty(). \302\240The latter would be less obvious. \302\240Or can we\n" "create a can_follow_write_shstk_pte()?\n" "\n" - Yu-cheng + "Yu-cheng\n" + "--\n" + "To unsubscribe from this list: send the line \"unsubscribe linux-doc\" in\n" + "the body of a message to majordomo@vger.kernel.org\n" + More majordomo info at http://vger.kernel.org/majordomo-info.html -aceb7b02ad695e005c2407795346a5ab89a6ce97f09603433aaca8b306da3eea +c0de16d444b05f966745cb25c8115b31b4bc9bfa307dcd1f07e1fbec2998aa9d
diff --git a/a/1.txt b/N3/1.txt index 2339993..66aa9d6 100644 --- a/a/1.txt +++ b/N3/1.txt @@ -3,9 +3,9 @@ On Wed, 2018-07-11 at 11:29 +0200, Peter Zijlstra wrote: > > > > There are three possible shadow stack PTE settings: > > -> > Normal SHSTK PTE: (R/O + DIRTY_HW) -> > SHSTK PTE COW'ed: (R/O + DIRTY_HW) -> > SHSTK PTE shared as R/O data: (R/O + DIRTY_SW) +> > A Normal SHSTK PTE: (R/O + DIRTY_HW) +> > A SHSTK PTE COW'ed: (R/O + DIRTY_HW) +> > A SHSTK PTE shared as R/O data: (R/O + DIRTY_SW) > I count _2_ distinct states there. > > > @@ -21,15 +21,15 @@ When a SHSTK PTE is shared, it is (R/O + DIRTY_SW); otherwise it is When we (FOLL_WRITE | FOLL_FORCE) on a SHSTK PTE, the following must be true: - - It has been COW'ed at least once (FOLL_COW is set); - - It still is not shared, i.e. PTE is (R/O + DIRTY_HW); +A - It has been COW'ed at least once (FOLL_COW is set); +A - It still is not shared, i.e. PTE is (R/O + DIRTY_HW); > > Also, the code is a right mess :/ Can't we try harder to not let this > shadow stack stuff escape arch code. We either check here if the VMA is SHSTK mapping or move the logic -to pte_dirty(). The latter would be less obvious. Or can we +to pte_dirty(). A The latter would be less obvious. A Or can we create a can_follow_write_shstk_pte()? Yu-cheng diff --git a/a/content_digest b/N3/content_digest index 98d4a6e..3ff7ccc 100644 --- a/a/content_digest +++ b/N3/content_digest @@ -28,7 +28,8 @@ Nadav Amit <nadav.amit@gmail.com> Oleg Nesterov <oleg@redhat.com> Pavel Machek <pavel@ucw.cz> - " Ravi V. Shan\0" + Ravi V. Shankar <ravi.v.shankar@intel.com> + " Vedvyas Shanbhogue <vedvyas.shanbhogue@intel.com>\0" "\00:1\0" "b\0" "On Wed, 2018-07-11 at 11:29 +0200, Peter Zijlstra wrote:\n" @@ -36,9 +37,9 @@ "> > \n" "> > There are three possible shadow stack PTE settings:\n" "> > \n" - "> > \302\240 Normal SHSTK PTE: (R/O + DIRTY_HW)\n" - "> > \302\240 SHSTK PTE COW'ed: (R/O + DIRTY_HW)\n" - "> > \302\240 SHSTK PTE shared as R/O data: (R/O + DIRTY_SW)\n" + "> > A Normal SHSTK PTE: (R/O + DIRTY_HW)\n" + "> > A SHSTK PTE COW'ed: (R/O + DIRTY_HW)\n" + "> > A SHSTK PTE shared as R/O data: (R/O + DIRTY_SW)\n" "> I count _2_ distinct states there.\n" "> \n" "> > \n" @@ -54,17 +55,17 @@ "When we (FOLL_WRITE | FOLL_FORCE) on a SHSTK PTE, the following\n" "must be true:\n" "\n" - "\302\240 - It has been COW'ed at least once (FOLL_COW is set);\n" - "\302\240 - It still is not shared, i.e. PTE is (R/O + DIRTY_HW);\n" + "A - It has been COW'ed at least once (FOLL_COW is set);\n" + "A - It still is not shared, i.e. PTE is (R/O + DIRTY_HW);\n" "\n" "> \n" "> Also, the code is a right mess :/ Can't we try harder to not let this\n" "> shadow stack stuff escape arch code.\n" "\n" "We either check here if the VMA is SHSTK mapping or move the logic\n" - "to pte_dirty(). \302\240The latter would be less obvious. \302\240Or can we\n" + "to pte_dirty(). A The latter would be less obvious. A Or can we\n" "create a can_follow_write_shstk_pte()?\n" "\n" Yu-cheng -aceb7b02ad695e005c2407795346a5ab89a6ce97f09603433aaca8b306da3eea +030deb3c6983cbd93a3c087b09e0d3dfadcf4961c6f51a19e8b4a9c173e5c289
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.