diff mbox series

[v4,6/8] mm: userfaultfd: document and enable new UFFDIO_POISON feature

Message ID 20230707215540.2324998-7-axelrasmussen@google.com (mailing list archive)
State Accepted
Commit f442ab50f5fb581804e4c4b6f8ead394fe975589
Headers show
Series add UFFDIO_POISON to simulate memory poisoning with UFFD | expand

Commit Message

Axel Rasmussen July 7, 2023, 9:55 p.m. UTC 
Update the userfaultfd API to advertise this feature as part of feature
flags and supported ioctls (returned upon registration).

Add basic documentation describing the new feature.

Acked-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
---
 Documentation/admin-guide/mm/userfaultfd.rst | 15 +++++++++++++++
 include/uapi/linux/userfaultfd.h             |  9 ++++++---
 2 files changed, 21 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/Documentation/admin-guide/mm/userfaultfd.rst b/Documentation/admin-guide/mm/userfaultfd.rst
index 7c304e432205..4349a8c2b978 100644
--- a/Documentation/admin-guide/mm/userfaultfd.rst
+++ b/Documentation/admin-guide/mm/userfaultfd.rst
@@ -244,6 +244,21 @@  write-protected (so future writes will also result in a WP fault). These ioctls
 support a mode flag (``UFFDIO_COPY_MODE_WP`` or ``UFFDIO_CONTINUE_MODE_WP``
 respectively) to configure the mapping this way.
 
+Memory Poisioning Emulation
+---------------------------
+
+In response to a fault (either missing or minor), an action userspace can
+take to "resolve" it is to issue a ``UFFDIO_POISON``. This will cause any
+future faulters to either get a SIGBUS, or in KVM's case the guest will
+receive an MCE as if there were hardware memory poisoning.
+
+This is used to emulate hardware memory poisoning. Imagine a VM running on a
+machine which experiences a real hardware memory error. Later, we live migrate
+the VM to another physical machine. Since we want the migration to be
+transparent to the guest, we want that same address range to act as if it was
+still poisoned, even though it's on a new physical host which ostensibly
+doesn't have a memory error in the exact same spot.
+
 QEMU/KVM
 ========
 
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index b5f07eacc697..62151706c5a3 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -39,7 +39,8 @@ 
 			   UFFD_FEATURE_MINOR_SHMEM |		\
 			   UFFD_FEATURE_EXACT_ADDRESS |		\
 			   UFFD_FEATURE_WP_HUGETLBFS_SHMEM |	\
-			   UFFD_FEATURE_WP_UNPOPULATED)
+			   UFFD_FEATURE_WP_UNPOPULATED |	\
+			   UFFD_FEATURE_POISON)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -49,12 +50,14 @@ 
 	 (__u64)1 << _UFFDIO_COPY |		\
 	 (__u64)1 << _UFFDIO_ZEROPAGE |		\
 	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
-	 (__u64)1 << _UFFDIO_CONTINUE)
+	 (__u64)1 << _UFFDIO_CONTINUE |		\
+	 (__u64)1 << _UFFDIO_POISON)
 #define UFFD_API_RANGE_IOCTLS_BASIC		\
 	((__u64)1 << _UFFDIO_WAKE |		\
 	 (__u64)1 << _UFFDIO_COPY |		\
+	 (__u64)1 << _UFFDIO_WRITEPROTECT |	\
 	 (__u64)1 << _UFFDIO_CONTINUE |		\
-	 (__u64)1 << _UFFDIO_WRITEPROTECT)
+	 (__u64)1 << _UFFDIO_POISON)
 
 /*
  * Valid ioctl command number range with this API is from 0x00 to