scsi, file-posix: add support for persistent reservation management

It is a common requirement for virtual machine to send persistent
reservations, but this currently requires either running QEMU with
CAP_SYS_RAWIO, or using out-of-tree patches that let an unprivileged
QEMU bypass Linux's filter on SG_IO commands.

As an alternative mechanism, the next patches will introduce a
privileged helper to run persistent reservation commands without
expanding QEMU's attack surface unnecessarily.

The helper is invoked through a "pr-manager" QOM object, to which
file-posix.c passes SG_IO requests for PERSISTENT RESERVE OUT and
PERSISTENT RESERVE IN commands.  For example:

  $ qemu-system-x86_64
      -device virtio-scsi \
      -object pr-manager-helper,id=helper0,path=/var/run/qemu-pr-helper.sock
      -drive if=none,id=hd,driver=raw,file.filename=/dev/sdb,file.pr-manager=helper0
      -device scsi-block,drive=hd

or:

  $ qemu-system-x86_64
      -device virtio-scsi \
      -object pr-manager-helper,id=helper0,path=/var/run/qemu-pr-helper.sock
      -blockdev node-name=hd,driver=raw,file.driver=host_device,file.filename=/dev/sdb,file.pr-manager=helper0
      -device scsi-block,drive=hd

Multiple pr-manager implementations are conceivable and possible, though
only one is implemented right now.  For example, a pr-manager could:

- talk directly to the multipath daemon from a privileged QEMU
  (i.e. QEMU links to libmpathpersist); this makes reservation work
  properly with multipath, but still requires CAP_SYS_RAWIO

- use the Linux IOC_PR_* ioctls (they require CAP_SYS_ADMIN though)

- more interestingly, implement reservations directly in QEMU
  through file system locks or a shared database (e.g. sqlite)

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 56 insertions, 0 deletions

diff --git a/include/scsi/pr-manager.h b/include/scsi/pr-manager.h
new file mode 100644
index 0000000000..b2b37d63bc
--- /dev/null
+++ b/include/scsi/pr-manager.h
@@ -0,0 +1,56 @@
+#ifndef PR_MANAGER_H
+#define PR_MANAGER_H
+
+#include "qom/object.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/visitor.h"
+#include "qom/object_interfaces.h"
+#include "block/aio.h"
+
+#define TYPE_PR_MANAGER "pr-manager"
+
+#define PR_MANAGER_CLASS(klass) \
+     OBJECT_CLASS_CHECK(PRManagerClass, (klass), TYPE_PR_MANAGER)
+#define PR_MANAGER_GET_CLASS(obj) \
+     OBJECT_GET_CLASS(PRManagerClass, (obj), TYPE_PR_MANAGER)
+#define PR_MANAGER(obj) \
+     OBJECT_CHECK(PRManager, (obj), TYPE_PR_MANAGER)
+
+struct sg_io_hdr;
+
+typedef struct PRManager {
+    /* <private> */
+    Object parent;
+} PRManager;
+
+/**
+ * PRManagerClass:
+ * @parent_class: the base class
+ * @run: callback invoked in thread pool context
+ */
+typedef struct PRManagerClass {
+    /* <private> */
+    ObjectClass parent_class;
+
+    /* <public> */
+    int (*run)(PRManager *pr_mgr, int fd, struct sg_io_hdr *hdr);
+} PRManagerClass;
+
+BlockAIOCB *pr_manager_execute(PRManager *pr_mgr,
+                               AioContext *ctx, int fd,
+                               struct sg_io_hdr *hdr,
+                               BlockCompletionFunc *complete,
+                               void *opaque);
+
+#ifdef CONFIG_LINUX
+PRManager *pr_manager_lookup(const char *id, Error **errp);
+#else
+static inline PRManager *pr_manager_lookup(const char *id, Error **errp)
+{
+    /* The classes do not exist at all!  */
+    error_setg(errp, "No persistent reservation manager with id '%s'", id);
+    return NULL;
+}
+#endif
+
+#endif