kasli_soc & zc706: Fix GTX Clock Path during INIT

- for example, current_clock csr can be connected to tx_init.done

flake.lock

@@ -11,11 +11,11 @@
         "src-pythonparser": "src-pythonparser"
       },
       "locked": {
-        "lastModified": 1697537883,
-        "narHash": "sha256-GfadmYHFkczltX+rPf08YpAHjYa/31ZmmVD578BcFow=",
+        "lastModified": 1699353408,
+        "narHash": "sha256-mJZ9PoRsOvN5gtrEl9ogj/+GRCK8O3tZbcyfxKvGG20=",
         "ref": "refs/heads/master",
-        "rev": "b168f0bb4be1697ff100475c20ee304dcc31fcc2",
-        "revCount": 8573,
+        "rev": "ec2b86b08d497a41e75c228385b754c6f3a4a8bf",
+        "revCount": 8585,
         "type": "git",
         "url": "https://github.com/m-labs/artiq.git"
       },
@@ -118,11 +118,11 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1697226376,
-        "narHash": "sha256-cumLLb1QOUtWieUnLGqo+ylNt3+fU8Lcv5Zl+tYbRUE=",
+        "lastModified": 1699169573,
+        "narHash": "sha256-cvUb1xZkvOp3W2SzylStrTirhVd9zCeo5utJl9nSIhw=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "898cb2064b6e98b8c5499f37e81adbdf2925f7c5",
+        "rev": "aeefe2054617cae501809b82b44a8e8f7be7cc4b",
         "type": "github"
       },
       "original": {
@@ -163,11 +163,11 @@
     "src-migen": {
       "flake": false,
       "locked": {
-        "lastModified": 1697013661,
-        "narHash": "sha256-qNCqgWyE4vTDmyjE2XMJqW1djuBxT25A36AzQfZqluU=",
+        "lastModified": 1699335478,
+        "narHash": "sha256-BsubN4Mfdj02QPK6ZCrl+YOaSg7DaLQdSCVP49ztWik=",
         "owner": "m-labs",
         "repo": "migen",
-        "rev": "aadc19df93b7aa9ca761aaebbb98a11e0cf2d7c7",
+        "rev": "fd0bf5855a1367eab14b0d6f7f8266178e25d78e",
         "type": "github"
       },
       "original": {
@@ -179,11 +179,11 @@
     "src-misoc": {
       "flake": false,
       "locked": {
-        "lastModified": 1693709836,
-        "narHash": "sha256-YiCk05RYLzZu1CYkQ2r7XtjwVEqkUGTQn388uOls9tI=",
+        "lastModified": 1699352904,
+        "narHash": "sha256-SglyTmXOPv8jJOjwAjJrj/WhAkItQfUbvKfUqrynwRg=",
         "ref": "refs/heads/master",
-        "rev": "58dc4ee60d165ce9145cf3d904241fc154b6407f",
-        "revCount": 2448,
+        "rev": "a53859f2167c31ab5225b6c09f30cf05527b94f4",
+        "revCount": 2452,
         "submodules": true,
         "type": "git",
         "url": "https://github.com/m-labs/misoc.git"

src/gateware/kasli_soc.py

@@ -237,12 +237,16 @@ class GenericMaster(SoCCore):
         gtx0 = self.gt_drtio.gtxs[0]
         self.specials += Instance("BUFG", i_I=gtx0.txoutclk, o_O=txout_buf)
 
+        ext_async_rst = Signal()
+
         self.submodules.bootstrap = GTPBootstrapClock(self.platform, clk_freq)
         self.submodules.sys_crg = zynq_clocking.SYSCRG(
             self.platform,
             self.ps7,
             txout_buf,
-            clk_sw=gtx0.tx_init.done)
+            clk_sw=self.gt_drtio.stable_clkin.storage,
+            clk_sw_status=gtx0.tx_init.done,
+            ext_async_rst=ext_async_rst)
         self.csr_devices.append("sys_crg")
         self.crg = self.ps7 # HACK for eem_7series to find the clock
         self.crg.cd_sys = self.sys_crg.cd_sys
@@ -250,6 +254,9 @@ class GenericMaster(SoCCore):
             self.bootstrap.cd_bootstrap.clk, self.sys_crg.cd_sys.clk)
         fix_serdes_timing_path(platform)
 
+        self.comb += ext_async_rst.eq(self.sys_crg.clk_sw_fsm.o_clk_sw & ~gtx0.tx_init.done)
+        self.specials += MultiReg(self.sys_crg.clk_sw_fsm.o_clk_sw & self.sys_crg.mmcm_locked, self.gt_drtio.clk_path_ready, odomain="bootstrap")
+
         self.config["HAS_SI5324"] = None
         self.config["SI5324_SOFT_RESET"] = None
 
@@ -419,12 +426,16 @@ class GenericSatellite(SoCCore):
         gtx0 = self.gt_drtio.gtxs[0]
         self.specials += Instance("BUFG", i_I=gtx0.txoutclk, o_O=txout_buf)
 
+        ext_async_rst = Signal()
+
         self.submodules.bootstrap = GTPBootstrapClock(self.platform, clk_freq)
         self.submodules.sys_crg = zynq_clocking.SYSCRG(
             self.platform, 
             self.ps7,
             txout_buf,
-            clk_sw=gtx0.tx_init.done)
+            clk_sw=self.gt_drtio.stable_clkin.storage,
+            clk_sw_status=gtx0.tx_init.done,
+            ext_async_rst=ext_async_rst)
         platform.add_false_path_constraints(
             self.bootstrap.cd_bootstrap.clk, self.sys_crg.cd_sys.clk)
         self.csr_devices.append("sys_crg")
@@ -433,6 +444,9 @@ class GenericSatellite(SoCCore):
 
         fix_serdes_timing_path(platform)
 
+        self.comb += ext_async_rst.eq(self.sys_crg.clk_sw_fsm.o_clk_sw & ~gtx0.tx_init.done)
+        self.specials += MultiReg(self.sys_crg.clk_sw_fsm.o_clk_sw & self.sys_crg.mmcm_locked, self.gt_drtio.clk_path_ready, odomain="bootstrap")
+
         self.rtio_channels = []
         has_grabber = any(peripheral["type"] == "grabber" for peripheral in description["peripherals"])
         if has_grabber:

src/gateware/zc706.py

@@ -226,6 +226,7 @@ class _MasterBase(SoCCore):
         self.csr_devices.append("gt_drtio")
 
         self.submodules.rtio_tsc = rtio.TSC(glbl_fine_ts_width=3)
+        ext_async_rst = Signal()
         txout_buf = Signal()
         gtx0 = self.gt_drtio.gtxs[0]
         self.specials += Instance("BUFG", i_I=gtx0.txoutclk, o_O=txout_buf)
@@ -234,12 +235,17 @@ class _MasterBase(SoCCore):
             self.platform, 
             self.ps7, 
             txout_buf,
-            clk_sw=gtx0.tx_init.done,
+            clk_sw=self.gt_drtio.stable_clkin.storage,
+            clk_sw_status=gtx0.tx_init.done,
+            ext_async_rst=ext_async_rst,
             freq=clk_freq)
         platform.add_false_path_constraints(
             self.bootstrap.cd_bootstrap.clk, self.sys_crg.cd_sys.clk)
         self.csr_devices.append("sys_crg")
 
+        self.comb += ext_async_rst.eq(self.sys_crg.clk_sw_fsm.o_clk_sw & ~gtx0.tx_init.done)
+        self.specials += MultiReg(self.sys_crg.clk_sw_fsm.o_clk_sw & self.sys_crg.mmcm_locked, self.gt_drtio.clk_path_ready, odomain="bootstrap")
+
         drtio_csr_group = []
         drtioaux_csr_group = []
         drtioaux_memory_group = []
@@ -361,6 +367,7 @@ class _SatelliteBase(SoCCore):
             clk_freq=clk_freq)
         self.csr_devices.append("gt_drtio")
 
+        ext_async_rst = Signal()
         txout_buf = Signal()
         txout_buf.attr.add("keep")
         gtx0 = self.gt_drtio.gtxs[0]
@@ -373,12 +380,17 @@ class _SatelliteBase(SoCCore):
             self.platform, 
             self.ps7, 
             txout_buf,
-            clk_sw=gtx0.tx_init.done,
+            clk_sw=self.gt_drtio.stable_clkin.storage,
+            clk_sw_status=gtx0.tx_init.done,
+            ext_async_rst=ext_async_rst,
             freq=clk_freq)
         platform.add_false_path_constraints(
             self.bootstrap.cd_bootstrap.clk, self.sys_crg.cd_sys.clk)
         self.csr_devices.append("sys_crg")
 
+        self.comb += ext_async_rst.eq(self.sys_crg.clk_sw_fsm.o_clk_sw & ~gtx0.tx_init.done)
+        self.specials += MultiReg(self.sys_crg.clk_sw_fsm.o_clk_sw & self.sys_crg.mmcm_locked, self.gt_drtio.clk_path_ready, odomain="bootstrap")
+
         drtioaux_csr_group = []
         drtioaux_memory_group = []
         drtiorep_csr_group = []

src/gateware/zynq_clocking.py

@@ -65,7 +65,7 @@ class ClockSwitchFSM(Module):
 
 
 class SYSCRG(Module, AutoCSR):
-    def __init__(self, platform, ps7, main_clk, clk_sw=None, freq=125e6):
+    def __init__(self, platform, ps7, main_clk, clk_sw=None, clk_sw_status=None, freq=125e6, ext_async_rst=None, ):
         # assumes bootstrap clock is same freq as main and sys output
         self.clock_domains.cd_sys = ClockDomain()
         self.clock_domains.cd_sys4x = ClockDomain(reset_less=True)
@@ -88,7 +88,7 @@ class SYSCRG(Module, AutoCSR):
         else:
             self.comb += self.clk_sw_fsm.i_clk_sw.eq(clk_sw)
 
-        mmcm_locked = Signal()
+        self.mmcm_locked = Signal()
         mmcm_sys = Signal()
         mmcm_sys4x = Signal()
         mmcm_sys5x = Signal()
@@ -96,7 +96,7 @@ class SYSCRG(Module, AutoCSR):
         mmcm_fb_clk = Signal()
         self.specials += [
             Instance("MMCME2_ADV",
-                p_STARTUP_WAIT="FALSE", o_LOCKED=mmcm_locked,
+                p_STARTUP_WAIT="FALSE", o_LOCKED=self.mmcm_locked,
                 p_BANDWIDTH="HIGH",
                 p_REF_JITTER1=0.001,
                 p_CLKIN1_PERIOD=period, i_CLKIN1=main_clk,
@@ -125,10 +125,19 @@ class SYSCRG(Module, AutoCSR):
             Instance("BUFG", i_I=mmcm_sys, o_O=self.cd_sys.clk),
             Instance("BUFG", i_I=mmcm_sys4x, o_O=self.cd_sys4x.clk),
             Instance("BUFG", i_I=mmcm_clk208, o_O=self.cd_clk200.clk),
-            AsyncResetSynchronizer(self.cd_sys, ~mmcm_locked),
-            AsyncResetSynchronizer(self.cd_clk200, ~mmcm_locked),
         ]
 
+        if ext_async_rst is not None:
+            self.specials += [
+                AsyncResetSynchronizer(self.cd_sys, ~self.mmcm_locked | ext_async_rst),
+                AsyncResetSynchronizer(self.cd_clk200, ~self.mmcm_locked | ext_async_rst),
+            ]
+        else:
+            self.specials += [
+                AsyncResetSynchronizer(self.cd_sys, ~self.mmcm_locked),
+                AsyncResetSynchronizer(self.cd_clk200, ~self.mmcm_locked),
+            ]
+
         reset_counter = Signal(4, reset=15)
         ic_reset = Signal(reset=1)
         self.sync.clk200 += \
@@ -139,4 +148,7 @@ class SYSCRG(Module, AutoCSR):
             )
         self.specials += Instance("IDELAYCTRL", i_REFCLK=ClockSignal("clk200"), i_RST=ic_reset)
 
-        self.comb += self.current_clock.status.eq(self.clk_sw_fsm.o_clk_sw)
+        if clk_sw_status is None:
+            self.comb += self.current_clock.status.eq(self.clk_sw_fsm.o_clk_sw)
+        else:
+            self.comb += self.current_clock.status.eq(clk_sw_status)

src/libboard_artiq/src/drtioaux_proto.rs

@@ -19,6 +19,46 @@ impl From<IoError> for Error {
     }
 }
 
+#[derive(PartialEq, Clone, Copy, Debug)]
+#[repr(u8)]
+pub enum PayloadStatus {
+    Middle = 0,
+    First = 1,
+    Last = 2,
+    FirstAndLast = 3,
+}
+
+impl From<u8> for PayloadStatus {
+    fn from(value: u8) -> PayloadStatus {
+        match value {
+            0 => PayloadStatus::Middle,
+            1 => PayloadStatus::First,
+            2 => PayloadStatus::Last,
+            3 => PayloadStatus::FirstAndLast,
+            _ => unreachable!(),
+        }
+    }
+}
+
+impl PayloadStatus {
+    pub fn is_first(self) -> bool {
+        self == PayloadStatus::First || self == PayloadStatus::FirstAndLast
+    }
+
+    pub fn is_last(self) -> bool {
+        self == PayloadStatus::Last || self == PayloadStatus::FirstAndLast
+    }
+
+    pub fn from_status(first: bool, last: bool) -> PayloadStatus {
+        match (first, last) {
+            (true, true) => PayloadStatus::FirstAndLast,
+            (true, false) => PayloadStatus::First,
+            (false, true) => PayloadStatus::Last,
+            (false, false) => PayloadStatus::Middle,
+        }
+    }
+}
+
 #[derive(PartialEq, Debug)]
 pub enum Packet {
     EchoRequest,
@@ -159,7 +199,7 @@ pub enum Packet {
     DmaAddTraceRequest {
         destination: u8,
         id: u32,
-        last: bool,
+        status: PayloadStatus,
         length: u16,
         trace: [u8; MASTER_PAYLOAD_MAX_SIZE],
     },
@@ -192,7 +232,7 @@ pub enum Packet {
     SubkernelAddDataRequest {
         destination: u8,
         id: u32,
-        last: bool,
+        status: PayloadStatus,
         length: u16,
         data: [u8; MASTER_PAYLOAD_MAX_SIZE],
     },
@@ -228,7 +268,7 @@ pub enum Packet {
     SubkernelMessage {
         destination: u8,
         id: u32,
-        last: bool,
+        status: PayloadStatus,
         length: u16,
         data: [u8; MASTER_PAYLOAD_MAX_SIZE],
     },
@@ -391,14 +431,14 @@ impl Packet {
             0xb0 => {
                 let destination = reader.read_u8()?;
                 let id = reader.read_u32()?;
-                let last = reader.read_bool()?;
+                let status = PayloadStatus::from(reader.read_u8()?);
                 let length = reader.read_u16()?;
                 let mut trace: [u8; MASTER_PAYLOAD_MAX_SIZE] = [0; MASTER_PAYLOAD_MAX_SIZE];
                 reader.read_exact(&mut trace[0..length as usize])?;
                 Packet::DmaAddTraceRequest {
                     destination: destination,
                     id: id,
-                    last: last,
+                    status: status,
                     length: length as u16,
                     trace: trace,
                 }
@@ -432,14 +472,14 @@ impl Packet {
             0xc0 => {
                 let destination = reader.read_u8()?;
                 let id = reader.read_u32()?;
-                let last = reader.read_bool()?;
+                let status = PayloadStatus::from(reader.read_u8()?);
                 let length = reader.read_u16()?;
                 let mut data: [u8; MASTER_PAYLOAD_MAX_SIZE] = [0; MASTER_PAYLOAD_MAX_SIZE];
                 reader.read_exact(&mut data[0..length as usize])?;
                 Packet::SubkernelAddDataRequest {
                     destination: destination,
                     id: id,
-                    last: last,
+                    status: status,
                     length: length as u16,
                     data: data,
                 }
@@ -482,14 +522,14 @@ impl Packet {
             0xcb => {
                 let destination = reader.read_u8()?;
                 let id = reader.read_u32()?;
-                let last = reader.read_bool()?;
+                let status = PayloadStatus::from(reader.read_u8()?);
                 let length = reader.read_u16()?;
                 let mut data: [u8; MASTER_PAYLOAD_MAX_SIZE] = [0; MASTER_PAYLOAD_MAX_SIZE];
                 reader.read_exact(&mut data[0..length as usize])?;
                 Packet::SubkernelMessage {
                     destination: destination,
                     id: id,
-                    last: last,
+                    status: status,
                     length: length as u16,
                     data: data,
                 }
@@ -713,14 +753,14 @@ impl Packet {
             Packet::DmaAddTraceRequest {
                 destination,
                 id,
-                last,
+                status,
                 trace,
                 length,
             } => {
                 writer.write_u8(0xb0)?;
                 writer.write_u8(destination)?;
                 writer.write_u32(id)?;
-                writer.write_bool(last)?;
+                writer.write_u8(status as u8)?;
                 // trace may be broken down to fit within drtio aux memory limit
                 // will be reconstructed by satellite
                 writer.write_u16(length)?;
@@ -771,14 +811,14 @@ impl Packet {
             Packet::SubkernelAddDataRequest {
                 destination,
                 id,
-                last,
+                status,
                 data,
                 length,
             } => {
                 writer.write_u8(0xc0)?;
                 writer.write_u8(destination)?;
                 writer.write_u32(id)?;
-                writer.write_bool(last)?;
+                writer.write_u8(status as u8)?;
                 writer.write_u16(length)?;
                 writer.write_all(&data[0..length as usize])?;
             }
@@ -822,14 +862,14 @@ impl Packet {
             Packet::SubkernelMessage {
                 destination,
                 id,
-                last,
+                status,
                 data,
                 length,
             } => {
                 writer.write_u8(0xcb)?;
                 writer.write_u8(destination)?;
                 writer.write_u32(id)?;
-                writer.write_bool(last)?;
+                writer.write_u8(status as u8)?;
                 writer.write_u16(length)?;
                 writer.write_all(&data[0..length as usize])?;
             }

src/libboard_artiq/src/lib.rs

@@ -19,7 +19,7 @@ pub mod drtioaux;
 #[cfg(has_drtio)]
 pub mod drtioaux_async;
 pub mod drtioaux_proto;
-#[cfg(feature = "target_kasli_soc")]
+#[cfg(all(feature = "target_kasli_soc", has_drtio))]
 pub mod io_expander;
 pub mod logger;
 #[cfg(has_drtio)]

src/runtime/src/comms.rs

@@ -458,6 +458,20 @@ async fn handle_run_kernel(
                     Err(SubkernelError::Timeout) => (kernel::SubkernelStatus::Timeout, 0),
                     Err(SubkernelError::IncorrectState) => (kernel::SubkernelStatus::IncorrectState, 0),
                     Err(SubkernelError::CommLost) => (kernel::SubkernelStatus::CommLost, 0),
+                    Err(SubkernelError::SubkernelException) => {
+                        error!("Exception in subkernel");
+                        // just retrieve the exception
+                        let status = subkernel::await_finish(aux_mutex, routing_table, timer, id, timeout)
+                            .await
+                            .unwrap();
+                        match stream {
+                            None => (),
+                            Some(stream) => {
+                                write_chunk(stream, &status.exception.unwrap()).await?;
+                            }
+                        }
+                        (kernel::SubkernelStatus::OtherError, 0)
+                    }
                     Err(_) => (kernel::SubkernelStatus::OtherError, 0),
                 };
                 control

src/runtime/src/main.rs

@@ -8,14 +8,14 @@
 #[macro_use]
 extern crate alloc;
 
-#[cfg(feature = "target_kasli_soc")]
+#[cfg(all(feature = "target_kasli_soc", has_drtio))]
 use core::cell::RefCell;
 
 use ksupport;
 use libasync::task;
 #[cfg(has_drtio_eem)]
 use libboard_artiq::drtio_eem;
-#[cfg(feature = "target_kasli_soc")]
+#[cfg(all(feature = "target_kasli_soc", has_drtio))]
 use libboard_artiq::io_expander;
 use libboard_artiq::{identifier_read, logger, pl};
 use libboard_zynq::{gic, mpcore, timer::GlobalTimer};
@@ -38,7 +38,7 @@ mod rtio_mgt;
 #[cfg(has_drtio)]
 mod subkernel;
 
-#[cfg(feature = "target_kasli_soc")]
+#[cfg(all(feature = "target_kasli_soc", has_drtio))]
 async fn io_expanders_service(
     i2c_bus: RefCell<&mut libboard_zynq::i2c::I2c>,
     io_expander0: RefCell<io_expander::IoExpander>,
@@ -93,15 +93,11 @@ pub fn main_core0() {
     info!("gateware ident: {}", identifier_read(&mut [0; 64]));
 
     ksupport::i2c::init();
-    #[cfg(feature = "target_kasli_soc")]
-    let i2c_bus = unsafe { (ksupport::i2c::I2C_BUS).as_mut().unwrap() };
-
-    #[cfg(feature = "target_kasli_soc")]
-    let (mut io_expander0, mut io_expander1);
-    #[cfg(feature = "target_kasli_soc")]
+    #[cfg(all(feature = "target_kasli_soc", has_drtio))]
     {
-        io_expander0 = io_expander::IoExpander::new(i2c_bus, 0).unwrap();
-        io_expander1 = io_expander::IoExpander::new(i2c_bus, 1).unwrap();
+        let i2c_bus = unsafe { (ksupport::i2c::I2C_BUS).as_mut().unwrap() };
+        let mut io_expander0 = io_expander::IoExpander::new(i2c_bus, 0).unwrap();
+        let mut io_expander1 = io_expander::IoExpander::new(i2c_bus, 1).unwrap();
         io_expander0
             .init(i2c_bus)
             .expect("I2C I/O expander #0 initialization failed");
@@ -115,6 +111,11 @@ pub fn main_core0() {
         io_expander1.set(1, 1, false);
         io_expander0.service(i2c_bus).unwrap();
         io_expander1.service(i2c_bus).unwrap();
+        task::spawn(io_expanders_service(
+            RefCell::new(i2c_bus),
+            RefCell::new(io_expander0),
+            RefCell::new(io_expander1),
+        ));
     }
 
     let cfg = match Config::new() {
@@ -135,11 +136,5 @@ pub fn main_core0() {
 
     task::spawn(ksupport::report_async_rtio_errors());
 
-    #[cfg(feature = "target_kasli_soc")]
-    task::spawn(io_expanders_service(
-        RefCell::new(i2c_bus),
-        RefCell::new(io_expander0),
-        RefCell::new(io_expander1),
-    ));
     comms::main(timer, cfg);
 }

src/runtime/src/rtio_mgt.rs

@@ -13,8 +13,10 @@ pub mod drtio {
     use ksupport::{resolve_channel_name, ASYNC_ERROR_BUSY, ASYNC_ERROR_COLLISION, ASYNC_ERROR_SEQUENCE_ERROR,
                    SEEN_ASYNC_ERRORS};
     use libasync::{delay, task};
-    use libboard_artiq::{drtioaux::Error, drtioaux_async, drtioaux_async::Packet,
-                         drtioaux_proto::MASTER_PAYLOAD_MAX_SIZE};
+    use libboard_artiq::{drtioaux::Error,
+                         drtioaux_async,
+                         drtioaux_async::Packet,
+                         drtioaux_proto::{PayloadStatus, MASTER_PAYLOAD_MAX_SIZE}};
     use libboard_zynq::time::Milliseconds;
     use log::{error, info, warn};
 
@@ -61,11 +63,11 @@ pub mod drtio {
             Packet::SubkernelMessage {
                 id,
                 destination: from,
-                last,
+                status,
                 length,
                 data,
             } => {
-                subkernel::message_handle_incoming(id, last, length as usize, &data).await;
+                subkernel::message_handle_incoming(id, status, length as usize, &data).await;
                 // acknowledge receiving part of the message
                 let _lock = aux_mutex.async_lock().await;
                 drtioaux_async::send(linkno, &Packet::SubkernelMessageAck { destination: from })
@@ -463,7 +465,7 @@ pub mod drtio {
         reply_handler_f: HandlerF,
     ) -> Result<(), &'static str>
     where
-        PacketF: Fn(&[u8; MASTER_PAYLOAD_MAX_SIZE], bool, usize) -> Packet,
+        PacketF: Fn(&[u8; MASTER_PAYLOAD_MAX_SIZE], PayloadStatus, usize) -> Packet,
         HandlerF: Fn(&Packet) -> Result<(), &'static str>,
     {
         let mut i = 0;
@@ -474,10 +476,12 @@ pub mod drtio {
             } else {
                 data.len() - i
             } as usize;
+            let first = i == 0;
             let last = i + len == data.len();
             slice[..len].clone_from_slice(&data[i..i + len]);
             i += len;
-            let packet = packet_f(&slice, last, len);
+            let status = PayloadStatus::from_status(first, last);
+            let packet = packet_f(&slice, status, len);
             let reply = aux_transact(aux_mutex, linkno, &packet, timer).await?;
             reply_handler_f(&reply)?;
         }
@@ -498,10 +502,10 @@ pub mod drtio {
             aux_mutex,
             timer,
             trace,
-            |slice, last, len| Packet::DmaAddTraceRequest {
+            |slice, status, len| Packet::DmaAddTraceRequest {
                 id: id,
                 destination: destination,
-                last: last,
+                status: status,
                 length: len as u16,
                 trace: *slice,
             },
@@ -655,10 +659,10 @@ pub mod drtio {
             aux_mutex,
             timer,
             data,
-            |slice, last, len| Packet::SubkernelAddDataRequest {
+            |slice, status, len| Packet::SubkernelAddDataRequest {
                 id: id,
                 destination: destination,
-                last: last,
+                status: status,
                 length: len as u16,
                 data: *slice,
             },
@@ -742,10 +746,10 @@ pub mod drtio {
             aux_mutex,
             timer,
             message,
-            |slice, last, len| Packet::SubkernelMessage {
+            |slice, status, len| Packet::SubkernelMessage {
                 destination: destination,
                 id: id,
-                last: last,
+                status: status,
                 length: len as u16,
                 data: *slice,
             },

src/runtime/src/subkernel.rs

@@ -1,7 +1,8 @@
 use alloc::{collections::BTreeMap, rc::Rc, vec::Vec};
 
 use libasync::task;
-use libboard_artiq::{drtio_routing::RoutingTable, drtioaux_proto::MASTER_PAYLOAD_MAX_SIZE};
+use libboard_artiq::{drtio_routing::RoutingTable,
+                     drtioaux_proto::{PayloadStatus, MASTER_PAYLOAD_MAX_SIZE}};
 use libboard_zynq::{time::Milliseconds, timer::GlobalTimer};
 use libcortex_a9::mutex::Mutex;
 use log::error;
@@ -28,6 +29,7 @@ pub enum Error {
     Timeout,
     IncorrectState,
     SubkernelNotFound,
+    SubkernelException,
     CommLost,
     DrtioError(&'static str),
 }
@@ -123,11 +125,13 @@ pub async fn subkernel_finished(id: u32, with_exception: bool) {
     // called upon receiving DRTIO SubkernelRunDone
     // may be None if session ends and is cleared
     if let Some(subkernel) = SUBKERNELS.async_lock().await.get_mut(&id) {
-        subkernel.state = SubkernelState::Finished {
-            status: match with_exception {
-                true => FinishStatus::Exception,
-                false => FinishStatus::Ok,
-            },
+        if subkernel.state == SubkernelState::Running {
+            subkernel.state = SubkernelState::Finished {
+                status: match with_exception {
+                    true => FinishStatus::Exception,
+                    false => FinishStatus::Ok,
+                },
+            }
         }
     }
 }
@@ -220,13 +224,27 @@ static MESSAGE_QUEUE: Mutex<Vec<Message>> = Mutex::new(Vec::new());
 // currently under construction message(s) (can be from multiple sources)
 static CURRENT_MESSAGES: Mutex<BTreeMap<u32, Message>> = Mutex::new(BTreeMap::new());
 
-pub async fn message_handle_incoming(id: u32, last: bool, length: usize, data: &[u8; MASTER_PAYLOAD_MAX_SIZE]) {
+pub async fn message_handle_incoming(
+    id: u32,
+    status: PayloadStatus,
+    length: usize,
+    data: &[u8; MASTER_PAYLOAD_MAX_SIZE],
+) {
     // called when receiving a message from satellite
-    if SUBKERNELS.async_lock().await.get(&id).is_none() {
-        // do not add messages for non-existing or deleted subkernels
-        return;
+    {
+        let subkernel_lock = SUBKERNELS.async_lock().await;
+        let subkernel = subkernel_lock.get(&id);
+        if subkernel.is_none() || subkernel.unwrap().state != SubkernelState::Running {
+            // do not add messages for non-existing or deleted subkernels
+            return;
+        }
     }
     let mut current_messages = CURRENT_MESSAGES.async_lock().await;
+
+    if status.is_first() {
+        current_messages.remove(&id);
+    }
+
     match current_messages.get_mut(&id) {
         Some(message) => message.data.extend(&data[..length]),
         None => {
@@ -240,7 +258,7 @@ pub async fn message_handle_incoming(id: u32, last: bool, length: usize, data: &
             );
         }
     };
-    if last {
+    if status.is_last() {
         // when done, remove from working queue
         MESSAGE_QUEUE
             .async_lock()
@@ -269,6 +287,15 @@ pub async fn message_await(id: u32, timeout: u64, timer: GlobalTimer) -> Result<
                 }
             }
         }
+        match SUBKERNELS.async_lock().await.get(&id).unwrap().state {
+            SubkernelState::Finished {
+                status: FinishStatus::CommLost,
+            } => return Err(Error::CommLost),
+            SubkernelState::Finished {
+                status: FinishStatus::Exception,
+            } => return Err(Error::SubkernelException),
+            _ => (),
+        }
         task::r#yield().await;
     }
     Err(Error::Timeout)

src/satman/src/dma.rs

@@ -1,6 +1,6 @@
 use alloc::{collections::btree_map::BTreeMap, vec::Vec};
 
-use libboard_artiq::pl::csr;
+use libboard_artiq::{drtioaux_proto::PayloadStatus, pl::csr};
 use libcortex_a9::cache::dcci_slice;
 
 const ALIGNMENT: usize = 64;
@@ -50,10 +50,10 @@ impl Manager {
         }
     }
 
-    pub fn add(&mut self, id: u32, last: bool, trace: &[u8], trace_len: usize) -> Result<(), Error> {
+    pub fn add(&mut self, id: u32, status: PayloadStatus, trace: &[u8], trace_len: usize) -> Result<(), Error> {
         let entry = match self.entries.get_mut(&id) {
             Some(entry) => {
-                if entry.complete {
+                if entry.complete || status.is_first() {
                     // replace entry
                     self.entries.remove(&id);
                     self.entries.insert(
@@ -83,7 +83,7 @@ impl Manager {
         };
         entry.trace.extend(&trace[0..trace_len]);
 
-        if last {
+        if status.is_last() {
             entry.trace.push(0);
             let data_len = entry.trace.len();
 

src/satman/src/main.rs

@@ -162,7 +162,7 @@ fn process_aux_packet(
                             &drtioaux::Packet::SubkernelMessage {
                                 destination: destination,
                                 id: kernel_manager.get_current_id().unwrap(),
-                                last: meta.last,
+                                status: meta.status,
                                 length: meta.len as u16,
                                 data: data_slice,
                             },
@@ -494,12 +494,12 @@ fn process_aux_packet(
         drtioaux::Packet::DmaAddTraceRequest {
             destination: _destination,
             id,
-            last,
+            status,
             length,
             trace,
         } => {
             forward!(_routing_table, _destination, *_rank, _repeaters, &packet, timer);
-            let succeeded = dma_manager.add(id, last, &trace, length as usize).is_ok();
+            let succeeded = dma_manager.add(id, status, &trace, length as usize).is_ok();
             drtioaux::send(0, &drtioaux::Packet::DmaAddTraceReply { succeeded: succeeded })
         }
         drtioaux::Packet::DmaRemoveTraceRequest {
@@ -527,12 +527,12 @@ fn process_aux_packet(
         drtioaux::Packet::SubkernelAddDataRequest {
             destination: _destination,
             id,
-            last,
+            status,
             length,
             data,
         } => {
             forward!(_routing_table, _destination, *_rank, _repeaters, &packet, timer);
-            let succeeded = kernel_manager.add(id, last, &data, length as usize).is_ok();
+            let succeeded = kernel_manager.add(id, status, &data, length as usize).is_ok();
             drtioaux::send(0, &drtioaux::Packet::SubkernelAddDataReply { succeeded: succeeded })
         }
         drtioaux::Packet::SubkernelLoadRunRequest {
@@ -562,7 +562,7 @@ fn process_aux_packet(
             drtioaux::send(
                 0,
                 &drtioaux::Packet::SubkernelException {
-                    last: meta.last,
+                    last: meta.status.is_last(),
                     length: meta.len,
                     data: data_slice,
                 },
@@ -571,12 +571,12 @@ fn process_aux_packet(
         drtioaux::Packet::SubkernelMessage {
             destination,
             id: _id,
-            last,
+            status,
             length,
             data,
         } => {
             forward!(_routing_table, destination, *_rank, _repeaters, &packet, timer);
-            kernel_manager.message_handle_incoming(last, length as usize, &data);
+            kernel_manager.message_handle_incoming(status, length as usize, &data);
             drtioaux::send(
                 0,
                 &drtioaux::Packet::SubkernelMessageAck {
@@ -596,7 +596,7 @@ fn process_aux_packet(
                         &drtioaux::Packet::SubkernelMessage {
                             destination: *_rank,
                             id: kernel_manager.get_current_id().unwrap(),
-                            last: meta.last,
+                            status: meta.status,
                             length: meta.len as u16,
                             data: data_slice,
                         },

src/satman/src/subkernel.rs

@@ -8,7 +8,7 @@ use core_io::{Error as IoError, Write};
 use cslice::AsCSlice;
 use io::{Cursor, ProtoWrite};
 use ksupport::{eh_artiq, kernel, rpc};
-use libboard_artiq::{drtioaux_proto::{MASTER_PAYLOAD_MAX_SIZE, SAT_PAYLOAD_MAX_SIZE},
+use libboard_artiq::{drtioaux_proto::{PayloadStatus, MASTER_PAYLOAD_MAX_SIZE, SAT_PAYLOAD_MAX_SIZE},
                      pl::csr};
 use libboard_zynq::{time::Milliseconds, timer::GlobalTimer};
 use libcortex_a9::sync_channel::Receiver;
@@ -133,24 +133,23 @@ pub struct SubkernelFinished {
 
 pub struct SliceMeta {
     pub len: u16,
-    pub last: bool,
+    pub status: PayloadStatus,
 }
 
 macro_rules! get_slice_fn {
     ($name:tt, $size:expr) => {
         pub fn $name(&mut self, data_slice: &mut [u8; $size]) -> SliceMeta {
-            if self.data.len() == 0 {
-                return SliceMeta { len: 0, last: true };
-            }
+            let first = self.it == 0;
             let len = min($size, self.data.len() - self.it);
             let last = self.it + len == self.data.len();
+            let status = PayloadStatus::from_status(first, last);
 
             data_slice[..len].clone_from_slice(&self.data[self.it..self.it + len]);
             self.it += len;
 
             SliceMeta {
                 len: len as u16,
-                last: last,
+                status: status,
             }
         }
     };
@@ -175,8 +174,11 @@ impl MessageManager {
         }
     }
 
-    pub fn handle_incoming(&mut self, last: bool, length: usize, data: &[u8; MASTER_PAYLOAD_MAX_SIZE]) {
+    pub fn handle_incoming(&mut self, status: PayloadStatus, length: usize, data: &[u8; MASTER_PAYLOAD_MAX_SIZE]) {
         // called when receiving a message from master
+        if status.is_first() {
+            self.in_buffer = None;
+        }
         match self.in_buffer.as_mut() {
             Some(message) => message.data.extend(&data[..length]),
             None => {
@@ -186,7 +188,7 @@ impl MessageManager {
                 });
             }
         };
-        if last {
+        if status.is_last() {
             // when done, remove from working queue
             self.in_queue.push_back(self.in_buffer.take().unwrap());
         }
@@ -218,7 +220,7 @@ impl MessageManager {
             return None;
         }
         let meta = self.out_message.as_mut()?.get_slice_master(data_slice);
-        if meta.last {
+        if meta.status.is_last() {
             // clear the message slot
             self.out_message = None;
             // notify kernel with a flag that message is sent
@@ -265,10 +267,10 @@ impl<'a> Manager<'_> {
         }
     }
 
-    pub fn add(&mut self, id: u32, last: bool, data: &[u8], data_len: usize) -> Result<(), Error> {
+    pub fn add(&mut self, id: u32, status: PayloadStatus, data: &[u8], data_len: usize) -> Result<(), Error> {
         let kernel = match self.kernels.get_mut(&id) {
             Some(kernel) => {
-                if kernel.complete {
+                if kernel.complete || status.is_first() {
                     // replace entry
                     self.kernels.remove(&id);
                     self.kernels.insert(
@@ -296,7 +298,7 @@ impl<'a> Manager<'_> {
         };
         kernel.library.extend(&data[0..data_len]);
 
-        kernel.complete = last;
+        kernel.complete = status.is_last();
         Ok(())
     }
 
@@ -325,11 +327,16 @@ impl<'a> Manager<'_> {
         Ok(())
     }
 
-    pub fn message_handle_incoming(&mut self, last: bool, length: usize, slice: &[u8; MASTER_PAYLOAD_MAX_SIZE]) {
+    pub fn message_handle_incoming(
+        &mut self,
+        status: PayloadStatus,
+        length: usize,
+        slice: &[u8; MASTER_PAYLOAD_MAX_SIZE],
+    ) {
         if !self.running() {
             return;
         }
-        self.session.messages.handle_incoming(last, length, slice);
+        self.session.messages.handle_incoming(status, length, slice);
     }
 
     pub fn message_get_slice(&mut self, slice: &mut [u8; MASTER_PAYLOAD_MAX_SIZE]) -> Option<SliceMeta> {
@@ -378,7 +385,10 @@ impl<'a> Manager<'_> {
     pub fn exception_get_slice(&mut self, data_slice: &mut [u8; SAT_PAYLOAD_MAX_SIZE]) -> SliceMeta {
         match self.session.last_exception.as_mut() {
             Some(exception) => exception.get_slice_sat(data_slice),
-            None => SliceMeta { len: 0, last: true },
+            None => SliceMeta {
+                len: 0,
+                status: PayloadStatus::FirstAndLast,
+            },
         }
     }