vfio: Extend the device migration protocol with RUNNING_P2P

The RUNNING_P2P state is designed to support multiple devices in the same
VM that are doing P2P transactions between themselves. When in RUNNING_P2P
the device must be able to accept incoming P2P transactions but should not
generate outgoing P2P transactions.

As an optional extension to the mandatory states it is defined as
in between STOP and RUNNING:
   STOP -> RUNNING_P2P -> RUNNING -> RUNNING_P2P -> STOP

For drivers that are unable to support RUNNING_P2P the core code
silently merges RUNNING_P2P and RUNNING together. Unless driver support
is present, the new state cannot be used in SET_STATE.
Drivers that support this will be required to implement 4 FSM arcs
beyond the basic FSM. 2 of the basic FSM arcs become combination
transitions.

Compared to the v1 clarification, NDMA is redefined into FSM states and is
described in terms of the desired P2P quiescent behavior, noting that
halting all DMA is an acceptable implementation.

Link: https://lore.kernel.org/all/20220224142024.147653-11-yishaih@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>

1 files changed, 69 insertions, 18 deletions

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index b37ab27b511f..a4555014bd1e 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1577,39 +1577,56 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 			    enum vfio_device_mig_state new_fsm,
 			    enum vfio_device_mig_state *next_fsm)
 {
-	enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RESUMING + 1 };
+	enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RUNNING_P2P + 1 };
 	/*
-	 * The coding in this table requires the driver to implement 6
-	 * FSM arcs:
+	 * The coding in this table requires the driver to implement the
+	 * following FSM arcs:
 	 *         RESUMING -> STOP
-	 *         RUNNING -> STOP
 	 *         STOP -> RESUMING
-	 *         STOP -> RUNNING
 	 *         STOP -> STOP_COPY
 	 *         STOP_COPY -> STOP
 	 *
-	 * The coding will step through multiple states for these combination
-	 * transitions:
-	 *         RESUMING -> STOP -> RUNNING
+	 * If P2P is supported then the driver must also implement these FSM
+	 * arcs:
+	 *         RUNNING -> RUNNING_P2P
+	 *         RUNNING_P2P -> RUNNING
+	 *         RUNNING_P2P -> STOP
+	 *         STOP -> RUNNING_P2P
+	 * Without P2P the driver must implement:
+	 *         RUNNING -> STOP
+	 *         STOP -> RUNNING
+	 *
+	 * The coding will step through multiple states for some combination
+	 * transitions; if all optional features are supported, this means the
+	 * following ones:
+	 *         RESUMING -> STOP -> RUNNING_P2P
+	 *         RESUMING -> STOP -> RUNNING_P2P -> RUNNING
 	 *         RESUMING -> STOP -> STOP_COPY
-	 *         RUNNING -> STOP -> RESUMING
-	 *         RUNNING -> STOP -> STOP_COPY
+	 *         RUNNING -> RUNNING_P2P -> STOP
+	 *         RUNNING -> RUNNING_P2P -> STOP -> RESUMING
+	 *         RUNNING -> RUNNING_P2P -> STOP -> STOP_COPY
+	 *         RUNNING_P2P -> STOP -> RESUMING
+	 *         RUNNING_P2P -> STOP -> STOP_COPY
+	 *         STOP -> RUNNING_P2P -> RUNNING
 	 *         STOP_COPY -> STOP -> RESUMING
-	 *         STOP_COPY -> STOP -> RUNNING
+	 *         STOP_COPY -> STOP -> RUNNING_P2P
+	 *         STOP_COPY -> STOP -> RUNNING_P2P -> RUNNING
 	 */
 	static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = {
 		[VFIO_DEVICE_STATE_STOP] = {
 			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
-			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P,
 			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
 			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
+			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
 			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
 		},
 		[VFIO_DEVICE_STATE_RUNNING] = {
-			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
+			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P,
 			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
-			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
-			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
+			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P,
+			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P,
+			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
 			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
 		},
 		[VFIO_DEVICE_STATE_STOP_COPY] = {
@@ -1617,6 +1634,7 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
 			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
 			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
+			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
 			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
 		},
 		[VFIO_DEVICE_STATE_RESUMING] = {
@@ -1624,6 +1642,15 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
 			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
 			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
+			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
+			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
+		},
+		[VFIO_DEVICE_STATE_RUNNING_P2P] = {
+			[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
+			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
+			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
+			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
 			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
 		},
 		[VFIO_DEVICE_STATE_ERROR] = {
@@ -1631,17 +1658,41 @@ int vfio_mig_get_next_state(struct vfio_device *device,
 			[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR,
 			[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR,
 			[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR,
+			[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_ERROR,
 			[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
 		},
 	};
 
-	if (WARN_ON(cur_fsm >= ARRAY_SIZE(vfio_from_fsm_table)))
+	static const unsigned int state_flags_table[VFIO_DEVICE_NUM_STATES] = {
+		[VFIO_DEVICE_STATE_STOP] = VFIO_MIGRATION_STOP_COPY,
+		[VFIO_DEVICE_STATE_RUNNING] = VFIO_MIGRATION_STOP_COPY,
+		[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_MIGRATION_STOP_COPY,
+		[VFIO_DEVICE_STATE_RESUMING] = VFIO_MIGRATION_STOP_COPY,
+		[VFIO_DEVICE_STATE_RUNNING_P2P] =
+			VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P,
+		[VFIO_DEVICE_STATE_ERROR] = ~0U,
+	};
+
+	if (WARN_ON(cur_fsm >= ARRAY_SIZE(vfio_from_fsm_table) ||
+		    (state_flags_table[cur_fsm] & device->migration_flags) !=
+			state_flags_table[cur_fsm]))
 		return -EINVAL;
 
-	if (new_fsm >= ARRAY_SIZE(vfio_from_fsm_table))
+	if (new_fsm >= ARRAY_SIZE(vfio_from_fsm_table) ||
+	   (state_flags_table[new_fsm] & device->migration_flags) !=
+			state_flags_table[new_fsm])
 		return -EINVAL;
 
+	/*
+	 * Arcs touching optional and unsupported states are skipped over. The
+	 * driver will instead see an arc from the original state to the next
+	 * logical state, as per the above comment.
+	 */
 	*next_fsm = vfio_from_fsm_table[cur_fsm][new_fsm];
+	while ((state_flags_table[*next_fsm] & device->migration_flags) !=
+			state_flags_table[*next_fsm])
+		*next_fsm = vfio_from_fsm_table[*next_fsm][new_fsm];
+
 	return (*next_fsm != VFIO_DEVICE_STATE_ERROR) ? 0 : -EINVAL;
 }
 EXPORT_SYMBOL_GPL(vfio_mig_get_next_state);
@@ -1731,7 +1782,7 @@ static int vfio_ioctl_device_feature_migration(struct vfio_device *device,
 					       size_t argsz)
 {
 	struct vfio_device_feature_migration mig = {
-		.flags = VFIO_MIGRATION_STOP_COPY,
+		.flags = device->migration_flags,
 	};
 	int ret;