flake: update dependencies

This reverts commit 7aa6ddeaf2.

README.md

@@ -4,14 +4,13 @@ ARTIQ on Zynq
 How to use
 ----------
 
-1. Install ARTIQ-6 or newer.
+1. Install the ARTIQ version that corresponds to the artiq-zynq version you are targeting.
-2. Select the latest successful build on Hydra: https://nixbld.m-labs.hk/jobset/artiq/zynq
+2. To obtain firmware binaries, select the latest successful build on [Hydra](https://nixbld.m-labs.hk/) for the targeted artiq-zynq version, or use AFWS. If using Hydra, search for the job named ``<board>-<variant>-sd`` (for example: ``zc706-nist_clock-sd`` or ``zc706-nist_qc2-sd``).
-3. Search for the job named ``<board>-<variant>-sd`` (for example: ``zc706-nist_clock-sd`` or ``zc706-nist_qc2-sd``).
+3. Place the ``boot.bin`` file, obtained from Hydra's "binary distribution" download link or from AFWS, at the root of a FAT-formatted SD card.
-4. Download the ``boot.bin`` "binary distribution" and place it at the root of a FAT-formatted SD card.
+4. Optionally, create a ``config.txt`` configuration file at the root of the SD card containing ``key=value`` pairs on each line. Use the ``ip``, ``ip6`` and ``mac`` keys to respectively set the IPv4, IPv6 and MAC address of the board. Configuring an IPv6 address is entirely optional. If these keys are not found, the firmware will use default values that may or may not be compatible with your network.
-5. Optionally, create a ``config.txt`` configuration file at the root of the SD card containing ``key=value`` pairs on each line. Use the ``ip``, ``ip6`` and ``mac`` keys to respectively set the IPv4, IPv6 and MAC address of the board. Configuring an IPv6 address is entirely optional. If these keys are not found, the firmware will use default values that may or may not be compatible with your network.
+5. Insert the SD card into the board and set up the board to boot from the SD card. For the ZC706, this is achieved by placing the large DIP switch SW11 in the 00110 position.
-6. Insert the SD card into the board and set up the board to boot from the SD card. For the ZC706, this is achieved by placing the large DIP switch SW11 in the 00110 position.
+6. Power up the board. After the firmware starts successfully, it should respond to ping at its IP addresses, and boot messages can be observed from its UART at 115200bps.
-7. Power up the board. After the firmware starts successfully, it should respond to ping at its IP addresses, and boot messages can be observed from its UART at 115200bps.
+7. Create and use an ARTIQ device database as usual, but set ``"target": "cortexa9"`` in the arguments of the core device.
-8. Create and use an ARTIQ device database as usual, but set ``"target": "cortexa9"`` in the arguments of the core device.
 
 Configuration
 -------------
@@ -33,7 +32,7 @@ not implemented as it seems not very useful.
 Development instructions
 ------------------------
 
-ARTIQ on Zynq is packaged using the [Nix](https://nixos.org) Flakes system. Install Nix 2.4+ and enable flakes by adding ``experimental-features = nix-command flakes`` to ``nix.conf`` (e.g. ``~/.config/nix/nix.conf``). 
+ARTIQ on Zynq is packaged using the [Nix](https://nixos.org) Flakes system. Install Nix 2.8+ and enable flakes by adding ``experimental-features = nix-command flakes`` to ``nix.conf`` (e.g. ``~/.config/nix/nix.conf``).
 
 Pure build with Nix and execution on a remote JTAG server:
 
@@ -64,7 +63,7 @@ Notes:
 License
 -------
 
-Copyright (C) 2019-2022 M-Labs Limited.
+Copyright (C) 2019-2023 M-Labs Limited.
 
 ARTIQ is free software: you can redistribute it and/or modify
 it under the terms of the GNU Lesser General Public License as published by

examples/device_db.py

@@ -8,7 +8,7 @@ device_db = {
         "arguments": {
             "host": "192.168.1.52",
             "ref_period": 1e-9,
-            "ref_multiplier": 1,
+            "ref_multiplier": 8,
             "target": "cortexa9"
         }
     },
@@ -59,6 +59,14 @@ device_db["ad9914dds1"] = {
     "arguments": {"sysclk": 3e9, "bus_channel": 50, "channel": 1},
 }
 
+for i in range(4):
+    device_db["ttl"+str(i)+"_counter"] = {
+        "type": "local",
+        "module": "artiq.coredevice.edge_counter",
+        "class": "EdgeCounter",
+        "arguments": {"channel": 52+i}
+    }
+
 # for ARTIQ test suite
 device_db.update(
     loop_out="ttl0",

flake.lock

@@ -11,21 +11,23 @@
         "src-pythonparser": "src-pythonparser"
       },
       "locked": {
-        "lastModified": 1654087576,
+        "lastModified": 1690427113,
-        "narHash": "sha256-d+LCvCXikhhEjsf4qBZakx3Sda85p+4vVZVwE1YuS90=",
+        "narHash": "sha256-10XRV7vbdyr/NKDKmBWcVs+9/iYbj6f2bulMRhwy0JY=",
-        "ref": "master",
+        "ref": "release-7",
-        "rev": "68ef0073ea66fe9c7f7c178979ecb8c681c47caa",
+        "rev": "21c6f57ce18cdd0c41f467434d58c0b9193da374",
-        "revCount": 8068,
+        "revCount": 8180,
         "type": "git",
         "url": "https://github.com/m-labs/artiq.git"
       },
       "original": {
+        "ref": "release-7",
         "type": "git",
         "url": "https://github.com/m-labs/artiq.git"
       }
     },
     "artiq-comtools": {
       "inputs": {
+        "flake-utils": "flake-utils",
         "nixpkgs": [
           "artiq",
           "nixpkgs"
@@ -36,11 +38,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1654007592,
+        "lastModified": 1664405593,
-        "narHash": "sha256-vaDFhE1ItjqtIcinC/6RAJGbj44pxxMUEeQUa3FtgEE=",
+        "narHash": "sha256-yP441NerlLGig7n+9xHsx8yCtZ+Ggd0VqfBSzc20E04=",
         "owner": "m-labs",
         "repo": "artiq-comtools",
-        "rev": "cb73281154656ee8f74db1866859e31bf42755cd",
+        "rev": "15ddac62813ef623a076ccf982b3bc63d314e651",
         "type": "github"
       },
       "original": {
@@ -49,14 +51,29 @@
         "type": "github"
       }
     },
+    "flake-utils": {
+      "locked": {
+        "lastModified": 1659877975,
+        "narHash": "sha256-zllb8aq3YO3h8B/U0/J1WBgAL8EX5yWf5pMj3G0NAmc=",
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "rev": "c0e246b9b83f637f4681389ecabcb2681b4f3af0",
+        "type": "github"
+      },
+      "original": {
+        "owner": "numtide",
+        "repo": "flake-utils",
+        "type": "github"
+      }
+    },
     "mozilla-overlay": {
       "flake": false,
       "locked": {
-        "lastModified": 1650459918,
+        "lastModified": 1687771476,
-        "narHash": "sha256-sroCK+QJTmoXtcRkwZyKOP9iAYOPID2Bwdxn4GkG16w=",
+        "narHash": "sha256-TSpqz6qYVRoqkEdOCawEQ4/cWt/4pracmvw17HK1tgE=",
         "owner": "mozilla",
         "repo": "nixpkgs-mozilla",
-        "rev": "e1f7540fc0a8b989fb8cf701dc4fd7fc76bcf168",
+        "rev": "3a44b8783514e7d6db4b63df96071b6c2b014b07",
         "type": "github"
       },
       "original": {
@@ -68,11 +85,11 @@
     "mozilla-overlay_2": {
       "flake": false,
       "locked": {
-        "lastModified": 1650459918,
+        "lastModified": 1687771476,
-        "narHash": "sha256-sroCK+QJTmoXtcRkwZyKOP9iAYOPID2Bwdxn4GkG16w=",
+        "narHash": "sha256-TSpqz6qYVRoqkEdOCawEQ4/cWt/4pracmvw17HK1tgE=",
         "owner": "mozilla",
         "repo": "nixpkgs-mozilla",
-        "rev": "e1f7540fc0a8b989fb8cf701dc4fd7fc76bcf168",
+        "rev": "3a44b8783514e7d6db4b63df96071b6c2b014b07",
         "type": "github"
       },
       "original": {
@@ -84,11 +101,11 @@
     "mozilla-overlay_3": {
       "flake": false,
       "locked": {
-        "lastModified": 1650459918,
+        "lastModified": 1684487559,
-        "narHash": "sha256-sroCK+QJTmoXtcRkwZyKOP9iAYOPID2Bwdxn4GkG16w=",
+        "narHash": "sha256-SZcJEM+NnLr8ctzeQf1BGAqBHzJ3jn+tdSeO7lszIJc=",
         "owner": "mozilla",
         "repo": "nixpkgs-mozilla",
-        "rev": "e1f7540fc0a8b989fb8cf701dc4fd7fc76bcf168",
+        "rev": "e6ca26fe8b9df914d4567604e426fbc185d9ef3e",
         "type": "github"
       },
       "original": {
@@ -99,11 +116,11 @@
     },
     "nixpkgs": {
       "locked": {
-        "lastModified": 1653920503,
+        "lastModified": 1685573264,
-        "narHash": "sha256-BBeCZwZImtjP3oYy4WogkQYy5OxNyfNciVSc1AfZgLQ=",
+        "narHash": "sha256-Zffu01pONhs/pqH07cjlF10NnMDLok8ix5Uk4rhOnZQ=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "a634c8f6c1fbf9b9730e01764999666f3436f10a",
+        "rev": "380be19fbd2d9079f677978361792cb25e8a3635",
         "type": "github"
       },
       "original": {
@@ -128,11 +145,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1654006751,
+        "lastModified": 1685540542,
-        "narHash": "sha256-OWAnoTCutvTQcYdtdtLQuL6uRtG+7Jz7sbRhcScv8bo=",
+        "narHash": "sha256-wQJwL3xc6QVQbiJrt71/Z9tp4Eq1yqdGddcEiv7sPCw=",
         "owner": "m-labs",
         "repo": "sipyco",
-        "rev": "b3d03a94c751a24769c54a61a0dbe9d6af52dade",
+        "rev": "f5bf2ba875340a31a135aea14ad184575ca800ac",
         "type": "github"
       },
       "original": {
@@ -144,11 +161,11 @@
     "src-migen": {
       "flake": false,
       "locked": {
-        "lastModified": 1650337393,
+        "lastModified": 1674045327,
-        "narHash": "sha256-rm1SlFmF2ASz0vIy2nDEzGlyRw2oYNeJRr8Kh8Mg2Qc=",
+        "narHash": "sha256-oYdeY0MbTReKbAwmSznnqw0wNawdInJoFJVWW3tesFA=",
         "owner": "m-labs",
         "repo": "migen",
-        "rev": "d4e3f34177c32f09904397179e6ed9c83175e528",
+        "rev": "ccaee68e14d3636e1d8fb2e0864dd89b1b1f7384",
         "type": "github"
       },
       "original": {
@@ -160,11 +177,11 @@
     "src-misoc": {
       "flake": false,
       "locked": {
-        "lastModified": 1649324486,
+        "lastModified": 1685415268,
-        "narHash": "sha256-Mw/fQS3lHFvCm7L1k63joRkz5uyijQfywcOq+X2+o2s=",
+        "narHash": "sha256-g4+yeSV+HtWjcllM5wk4vNBUVCXtDOzUSKhxXPT7Fyc=",
-        "ref": "master",
+        "ref": "refs/heads/master",
-        "rev": "f1dc58d2b8c222ba41c25cee4301626625f46e43",
+        "rev": "6d48ce77b6746d3226a682790fbc95b90340986e",
-        "revCount": 2420,
+        "revCount": 2440,
         "submodules": true,
         "type": "git",
         "url": "https://github.com/m-labs/misoc.git"
@@ -200,11 +217,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1654002148,
+        "lastModified": 1685182853,
-        "narHash": "sha256-Ztzx7ze8o0gdu+sDpc+PS2M88h/b22rwFq0b12wMqZQ=",
+        "narHash": "sha256-bEgE8Ph7MEHQr7S+xL33CxLuIm3AqvsaxBwUE1vHTdU=",
-        "ref": "master",
+        "ref": "refs/heads/master",
-        "rev": "6cd32f6ee0e7bb7ce5a279f8be943903a393a476",
+        "rev": "f20c0082645cfef34575661aeeff8d9c1ed1f127",
-        "revCount": 617,
+        "revCount": 625,
         "type": "git",
         "url": "https://git.m-labs.hk/m-labs/zynq-rs"
       },

flake.nix

@@ -1,7 +1,7 @@
 {
   description = "ARTIQ port to the Zynq-7000 platform";
 
-  inputs.artiq.url = git+https://github.com/m-labs/artiq.git;
+  inputs.artiq.url = git+https://github.com/m-labs/artiq.git?ref=release-7;
   inputs.mozilla-overlay = { url = github:mozilla/nixpkgs-mozilla; flake = false; };
   inputs.zynq-rs.url = git+https://git.m-labs.hk/m-labs/zynq-rs;
   inputs.zynq-rs.inputs.nixpkgs.follows = "artiq/nixpkgs";

src/gateware/kasli_soc.py

@@ -15,6 +15,7 @@ from misoc.integration import cpu_interface
 from artiq.coredevice import jsondesc
 from artiq.gateware import rtio, eem_7series
 from artiq.gateware.rtio.phy import ttl_simple
+from artiq.gateware.rtio.xilinx_clocking import fix_serdes_timing_path
 from artiq.gateware.rtio.xilinx_clocking import RTIOClockMultiplier
 from artiq.gateware.drtio.transceiver import gtx_7series
 from artiq.gateware.drtio.siphaser import SiPhaser7Series
@@ -118,7 +119,7 @@ class GenericStandalone(SoCCore):
         platform.toolchain.bitstream_commands.extend([
             "set_property BITSTREAM.GENERAL.COMPRESS True [current_design]",
         ])
-        ident = self.__class__.__name__
+        ident = description["variant"]
         if self.acpki:
             ident = "acpki_" + ident
         SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
@@ -138,6 +139,7 @@ class GenericStandalone(SoCCore):
         self.platform.add_false_path_constraints(
             self.ps7.cd_sys.clk,
             self.rtio_crg.cd_rtio.clk)
+        fix_serdes_timing_path(platform)
 
         self.rtio_channels = []
         has_grabber = any(peripheral["type"] == "grabber" for peripheral in description["peripherals"])
@@ -204,7 +206,7 @@ class GenericMaster(SoCCore):
         platform.toolchain.bitstream_commands.extend([
             "set_property BITSTREAM.GENERAL.COMPRESS True [current_design]",
         ])
-        ident = self.__class__.__name__
+        ident = description["variant"]
         if self.acpki:
             ident = "acpki_" + ident
         SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
@@ -225,6 +227,7 @@ class GenericMaster(SoCCore):
         self.crg = self.ps7 # HACK for eem_7series to find the clock
         self.submodules.rtio_crg = RTIOClockMultiplier(rtio_clk_freq)
         self.csr_devices.append("rtio_crg")
+        fix_serdes_timing_path(platform)
 
         self.rustc_cfg["has_si5324"] = None
         self.rustc_cfg["si5324_soft_reset"] = None
@@ -308,7 +311,7 @@ class GenericMaster(SoCCore):
         self.submodules.routing_table = rtio.RoutingTableAccess(self.cri_con)
         self.csr_devices.append("routing_table")
 
-        self.submodules.rtio_analyzer = analyzer.Analyzer(self.rtio_tsc, self.rtio_core.cri,
+        self.submodules.rtio_analyzer = analyzer.Analyzer(self.rtio_tsc, self.cri_con.switch.slave,
                                                           self.ps7.s_axi_hp1)
         self.csr_devices.append("rtio_analyzer")
 
@@ -329,7 +332,7 @@ class GenericSatellite(SoCCore):
         platform.toolchain.bitstream_commands.extend([
             "set_property BITSTREAM.GENERAL.COMPRESS True [current_design]",
         ])
-        ident = self.__class__.__name__
+        ident = description["variant"]
         if self.acpki:
             ident = "acpki_" + ident
         SoCCore.__init__(self, platform=platform, csr_data_width=32, ident=ident)
@@ -341,6 +344,7 @@ class GenericSatellite(SoCCore):
         self.submodules.rtio_crg = RTIOClockMultiplier(rtio_clk_freq)
         self.csr_devices.append("rtio_crg")
         self.rustc_cfg["has_rtio_crg"] = None
+        fix_serdes_timing_path(platform)
         
         data_pads = [platform.request("sfp", i) for i in range(4)]
         

src/gateware/zc706.py

@@ -14,7 +14,7 @@ from misoc.integration import cpu_interface
 from misoc.cores import gpio
 
 from artiq.gateware import rtio, nist_clock, nist_qc2
-from artiq.gateware.rtio.phy import ttl_simple, ttl_serdes_7series, dds, spi2
+from artiq.gateware.rtio.phy import ttl_simple, ttl_serdes_7series, dds, spi2, edge_counter
 from artiq.gateware.rtio.xilinx_clocking import RTIOClockMultiplier, fix_serdes_timing_path
 from artiq.gateware.drtio.transceiver import gtx_7series
 from artiq.gateware.drtio.siphaser import SiPhaser7Series
@@ -320,7 +320,7 @@ class _MasterBase(SoCCore):
         self.submodules.rtio_moninj = rtio.MonInj(rtio_channels)
         self.csr_devices.append("rtio_moninj")
 
-        self.submodules.rtio_analyzer = analyzer.Analyzer(self.rtio_tsc, self.rtio_core.cri,
+        self.submodules.rtio_analyzer = analyzer.Analyzer(self.rtio_tsc, self.cri_con.switch.slave,
                                                           self.ps7.s_axi_hp1)
         self.csr_devices.append("rtio_analyzer")
 
@@ -562,12 +562,16 @@ class _NIST_QC2_RTIO:
         platform.add_extension(pmod1_33)
 
         rtio_channels = []
+        edge_counter_phy = []
 
         # All TTL channels are In+Out capable
         for i in range(40):
             phy = ttl_serdes_7series.InOut_8X(platform.request("ttl", i))
             self.submodules += phy
             rtio_channels.append(rtio.Channel.from_phy(phy, ififo_depth=512))
+            # first four TTLs will also have edge counters
+            if i < 4:
+                edge_counter_phy.append(phy)
 
         # no SMA GPIO, replaced with PMOD1_0
         phy = ttl_serdes_7series.InOut_8X(platform.request("pmod1_33", 0))
@@ -606,6 +610,11 @@ class _NIST_QC2_RTIO:
                 platform.request("dds", backplane_offset), 12, onehot=True)
             self.submodules += phy
             rtio_channels.append(rtio.Channel.from_phy(phy, ififo_depth=4))
+        
+        for phy in edge_counter_phy:
+            counter = edge_counter.SimpleEdgeCounter(phy.input_state)
+            self.submodules += counter
+            rtio_channels.append(rtio.Channel.from_phy(counter))
 
         self.config["RTIO_LOG_CHANNEL"] = len(rtio_channels)
         rtio_channels.append(rtio.LogChannel())

src/libboard_artiq/src/io_expander.rs

@@ -0,0 +1,145 @@
+use libboard_zynq::i2c;
+use log::info;
+
+// Only the bare minimum registers. Bits/IO connections equivalent between IC types.
+struct Registers {
+    // PCA9539 equivalent register names in comments
+    iodira: u8, // Configuration Port 0
+    iodirb: u8, // Configuration Port 1
+    gpioa: u8,  // Output Port 0
+    gpiob: u8,  // Output Port 1
+}
+
+pub struct IoExpander<'a> {
+    i2c: &'a mut i2c::I2c,
+    address: u8,
+    iodir: [u8; 2],
+    out_current: [u8; 2],
+    out_target: [u8; 2],
+    registers: Registers,
+}
+
+
+impl<'a> IoExpander<'a> {
+    pub fn new(i2c: &'a mut i2c::I2c, index: u8) -> Result<Self, &'static str> {
+
+        // Both expanders on SHARED I2C bus
+        let mut io_expander = match index {
+            0 => IoExpander {
+                i2c,
+                address: 0x40,
+                iodir: [0xff; 2],
+                out_current: [0; 2],
+                out_target: [0; 2],
+                registers: Registers {
+                    iodira: 0x00,
+                    iodirb: 0x01,
+                    gpioa: 0x12,
+                    gpiob: 0x13,
+                },
+            },
+            1 => IoExpander {
+                i2c,
+                address: 0x42,
+                iodir: [0xff; 2],
+                out_current: [0; 2],
+                out_target: [0; 2],
+                registers: Registers {
+                    iodira: 0x00,
+                    iodirb: 0x01,
+                    gpioa: 0x12,
+                    gpiob: 0x13,
+                },
+            },
+            _ => return Err("incorrect I/O expander index"),
+        };
+        if !io_expander.check_ack()? {
+            info!(
+                "MCP23017 io expander {} not found. Checking for PCA9539.",
+                index
+            );
+            io_expander.address += 0xa8; // translate to PCA9539 addresses (see schematic)
+            io_expander.registers = Registers {
+                iodira: 0x06,
+                iodirb: 0x07,
+                gpioa: 0x02,
+                gpiob: 0x03,
+            };
+            if !io_expander.check_ack()? {
+                return Err("Neither MCP23017 nor PCA9539 io expander found.");
+            };
+        }
+        Ok(io_expander)
+    }
+
+    fn select(&mut self) -> Result<(), &'static str> {
+        self.i2c.pca954x_select(0x70, None)?;
+        self.i2c.pca954x_select(0x71, Some(3))?;
+        Ok(())
+    }
+
+    fn write(&mut self, addr: u8, value: u8) -> Result<(), &'static str> {
+        self.i2c.start()?;
+        self.i2c.write(self.address)?;
+        self.i2c.write(addr)?;
+        self.i2c.write(value)?;
+        self.i2c.stop()?;
+        Ok(())
+    }
+
+    fn check_ack(&mut self) -> Result<bool, &'static str> {
+        // Check for ack from io expander
+        self.select()?;
+        self.i2c.start()?;
+        let ack = self.i2c.write(self.address)?;
+        self.i2c.stop()?;
+        Ok(ack)
+    }
+
+    fn update_iodir(&mut self) -> Result<(), &'static str> {
+        self.write(self.registers.iodira, self.iodir[0])?;
+        self.write(self.registers.iodirb, self.iodir[1])?;
+        Ok(())
+    }
+
+    pub fn init(&mut self) -> Result<(), &'static str> {
+        self.select()?;
+        self.update_iodir()?;
+
+        self.out_current[0] = 0x00;
+        self.write(self.registers.gpioa, 0x00)?;
+        self.out_current[1] = 0x00;
+        self.write(self.registers.gpiob, 0x00)?;
+        Ok(())
+    }
+
+    pub fn set_oe(&mut self, port: u8, outputs: u8) -> Result<(), &'static str> {
+        self.iodir[port as usize] &= !outputs;
+        self.update_iodir()?;
+        Ok(())
+    }
+
+    pub fn set(&mut self, port: u8, bit: u8, high: bool) {
+        if high {
+            self.out_target[port as usize] |= 1 << bit;
+        } else {
+            self.out_target[port as usize] &= !(1 << bit);
+        }
+    }
+
+    pub fn service(&mut self) -> Result<(), &'static str> {
+        if self.out_target != self.out_current {
+            self.select()?;
+            if self.out_target[0] != self.out_current[0] {
+                self.write(self.registers.gpioa, self.out_target[0])?;
+                self.out_current[0] = self.out_target[0];
+            }
+            if self.out_target[1] != self.out_current[1] {
+                self.write(self.registers.gpiob, self.out_target[1])?;
+                self.out_current[1] = self.out_target[1];
+            }
+        }
+
+        Ok(())
+    }
+}

src/libboard_artiq/src/lib.rs

@@ -27,6 +27,8 @@ pub mod drtioaux_async;
 #[cfg(has_drtio)]
 #[path = "../../../build/mem.rs"]
 pub mod mem;
+#[cfg(feature = "target_kasli_soc")]
+pub mod io_expander;
 
 use core::{cmp, str};
 use libboard_zynq::slcr;

src/runtime/src/comms.rs

@@ -427,8 +427,8 @@ pub fn main(timer: GlobalTimer, cfg: Config) {
     moninj::start(timer, aux_mutex, drtio_routing_table);
 
     let control: Rc<RefCell<kernel::Control>> = Rc::new(RefCell::new(kernel::Control::start()));
-    let idle_kernel = Rc::new(cfg.read("idle").ok());
+    let idle_kernel = Rc::new(cfg.read("idle_kernel").ok());
-    if let Ok(buffer) = cfg.read("startup") {
+    if let Ok(buffer) = cfg.read("startup_kernel") {
         info!("Loading startup kernel...");
         if let Ok(()) = task::block_on(load_kernel(&buffer, &control, None)) {
             info!("Starting startup kernel...");

src/runtime/src/kernel/dma.rs

@@ -116,7 +116,7 @@ pub extern fn dma_record_output(target: i32, word: i32) {
     }
 }
 
-pub extern fn dma_record_output_wide(target: i32, words: CSlice<i32>) {
+pub extern fn dma_record_output_wide(target: i32, words: &CSlice<i32>) {
     assert!(words.len() <= 16); // enforce the hardware limit
 
     unsafe {

src/runtime/src/main.rs

@@ -21,6 +21,8 @@ use void::Void;
 use libconfig::Config;
 use libcortex_a9::l2c::enable_l2_cache;
 use libboard_artiq::{logger, identifier_read, init_gateware, pl};
+#[cfg(feature = "target_kasli_soc")]
+use libboard_artiq::io_expander;
 
 const ASYNC_ERROR_COLLISION: u8 = 1 << 0;
 const ASYNC_ERROR_BUSY: u8 = 1 << 1;
@@ -109,10 +111,25 @@ pub fn main_core0() {
     gic::InterruptController::gic(mpcore::RegisterBlock::mpcore()).enable_interrupts();
 
     init_gateware();
-    info!("detected gateware: {}", identifier_read(&mut [0; 64]));
+    info!("gateware ident: {}", identifier_read(&mut [0; 64]));
 
     i2c::init();
 
+    #[cfg(feature = "target_kasli_soc")]
+    {
+        let i2c = unsafe { (&mut i2c::I2C_BUS).as_mut().unwrap() };
+        for expander_i in 0..=1 {
+            let mut io_expander = io_expander::IoExpander::new(i2c, expander_i).unwrap();
+            io_expander.init().expect("I2C I/O expander #0 initialization failed");
+            // Actively drive TX_DISABLE to false on SFP0..3
+            io_expander.set_oe(0, 1 << 1).unwrap();
+            io_expander.set_oe(1, 1 << 1).unwrap();
+            io_expander.set(0, 1, false);
+            io_expander.set(1, 1, false);
+            io_expander.service().unwrap();
+        }
+    }
+
     let cfg = match Config::new() {
         Ok(cfg) => cfg,
         Err(err) => {

src/runtime/src/rpc.rs

@@ -15,22 +15,85 @@ use crate::proto_async;
 use self::tag::{Tag, TagIterator, split_tag};
 
 #[inline]
-fn alignment_offset(alignment: isize, ptr: isize) -> isize {
+fn round_up(val: usize, power_of_two: usize) -> usize {
-    (alignment - ptr % alignment) % alignment
+    assert!(power_of_two.is_power_of_two());
+    let max_rem = power_of_two - 1;
+    (val + max_rem) & (!max_rem)
 }
 
+#[inline]
+unsafe fn round_up_mut<T>(ptr: *mut T, power_of_two: usize) -> *mut T {
+    round_up(ptr as usize, power_of_two) as *mut T
+}
+
+#[inline]
+unsafe fn round_up_const<T>(ptr: *const T, power_of_two: usize) -> *const T {
+    round_up(ptr as usize, power_of_two) as *const T
+}
+
+#[inline]
 unsafe fn align_ptr<T>(ptr: *const ()) -> *const T {
-    let alignment = core::mem::align_of::<T>() as isize;
+    round_up_const(ptr, core::mem::align_of::<T>()) as *const T
-    let fix = alignment_offset(alignment, ptr as isize);
-    ((ptr as isize) + fix) as *const T
 }
 
+#[inline]
 unsafe fn align_ptr_mut<T>(ptr: *mut ()) -> *mut T {
-    let alignment = core::mem::align_of::<T>() as isize;
+    round_up_mut(ptr, core::mem::align_of::<T>()) as *mut T
-    let fix = alignment_offset(alignment, ptr as isize);
-    ((ptr as isize) + fix) as *mut T
 }
 
+/// Reads (deserializes) `length` array or list elements of type `tag` from `stream`,
+/// writing them into the buffer given by `storage`.
+///
+/// `alloc` is used for nested allocations (if elements themselves contain
+/// lists/arrays), see [recv_value].
+#[async_recursion(?Send)]
+async unsafe fn recv_elements<F>(
+    stream: &TcpStream,
+    elt_tag: Tag<'async_recursion>,
+    length: usize,
+    storage: *mut (),
+    alloc: &(impl Fn(usize) -> F + 'async_recursion)
+) -> Result<(), smoltcp::Error>
+where
+    F: Future<Output=*mut ()>,
+{
+    // List of simple types are special-cased in the protocol for performance.
+    match elt_tag {
+        Tag::Bool => {
+            let dest = core::slice::from_raw_parts_mut(storage as *mut u8, length);
+            proto_async::read_chunk(stream, dest).await?;
+        },
+        Tag::Int32 => {
+            let ptr = storage as *mut u32;
+            let dest = core::slice::from_raw_parts_mut(ptr as *mut u8, length * 4);
+            proto_async::read_chunk(stream, dest).await?;
+            drop(dest);
+            let dest = core::slice::from_raw_parts_mut(ptr, length);
+            NativeEndian::from_slice_u32(dest);
+        },
+        Tag::Int64 | Tag::Float64 => {
+            let ptr = storage as *mut u64;
+            let dest = core::slice::from_raw_parts_mut(ptr as *mut u8, length * 8);
+            proto_async::read_chunk(stream, dest).await?;
+            drop(dest);
+            let dest = core::slice::from_raw_parts_mut(ptr, length);
+            NativeEndian::from_slice_u64(dest);
+        },
+        _ => {
+            let mut data = storage;
+            for _ in 0..length {
+                recv_value(stream, elt_tag, &mut data, alloc).await?
+            }
+        }
+    }
+    Ok(())
+}
+
+/// Reads (deserializes) a value of type `tag` from `stream`, writing the results to
+/// the kernel-side buffer `data` (the passed pointer to which is incremented to point
+/// past the just-received data). For nested allocations (lists/arrays), `alloc` is
+/// invoked any number of times with the size of the required allocation as a parameter
+/// (which is assumed to be correctly aligned for all payload types).
 #[async_recursion(?Send)]
 async unsafe fn recv_value<F>(stream: &TcpStream, tag: Tag<'async_recursion>, data: &mut *mut (),
                               alloc: &(impl Fn(usize) -> F + 'async_recursion))
@@ -71,120 +134,63 @@ async unsafe fn recv_value<F>(stream: &TcpStream, tag: Tag<'async_recursion>, da
             })
         }
         Tag::Tuple(it, arity) => {
-            *data = (*data).offset(alignment_offset(tag.alignment() as isize, *data as isize));
+            let alignment = tag.alignment();
+            *data = round_up_mut(*data, alignment);
             let mut it = it.clone();
             for _ in 0..arity {
                 let tag = it.next().expect("truncated tag");
-                recv_value(stream, tag, data, alloc).await?;
+                recv_value(stream, tag, data, alloc).await?
             }
+            // Take into account any tail padding (if element(s) with largest alignment
+            // are not at the end).
+            *data = round_up_mut(*data, alignment);
             Ok(())
         }
         Tag::List(it) => {
             #[repr(C)]
-            struct List { elements: *mut (), length: u32 }
+            struct List { elements: *mut (), length: usize }
-            consume_value!(*mut List, |ptr| {
+            consume_value!(*mut List, |ptr_to_list| {
-                let length = proto_async::read_i32(stream).await? as usize;
                 let tag = it.clone().next().expect("truncated tag");
-                let data_size = tag.size() * length as usize +
+                let length = proto_async::read_i32(stream).await? as usize;
-                    match tag {
-                        Tag::Int64 | Tag::Float64 => 4,
-                        _ => 0
-                    };
-                let data = alloc(data_size + 8).await as *mut u8;
-                *ptr = data as *mut List;
-                let ptr = data as *mut List;
-                let data = data.offset(8);
 
-                let alignment = tag.alignment();
+                // To avoid multiple kernel CPU roundtrips, use a single allocation for
-                let mut data = data.offset(alignment_offset(alignment as isize, data as isize)) as *mut ();
+                // both the pointer/length List (slice) and the backing storage for the
-                (*ptr).length  = length as u32;
+                // elements. We can assume that alloc() is aligned suitably, so just
-                (*ptr).elements = data;
+                // need to take into account any extra padding required.
-                match tag {
+                // (Note: At the time of writing, there will never actually be any types
-                    Tag::Bool => {
+                // with alignment larger than 8 bytes, so storage_offset == 0 always.)
-                        let ptr = data as *mut u8;
+                let list_size = 4 + 4;
-                        let dest = core::slice::from_raw_parts_mut(ptr, length);
+                let storage_offset = round_up(list_size, tag.alignment());
-                        proto_async::read_chunk(stream, dest).await?;
+                let storage_size = tag.size() * length;
-                    },
+
-                    Tag::Int32 => {
+                let allocation = alloc(storage_offset + storage_size).await as *mut u8;
-                        let ptr = data as *mut u32;
+                *ptr_to_list = allocation as *mut List;
-                        // reading as raw bytes and do endianness conversion later
+                let storage = allocation.offset(storage_offset as isize) as *mut ();
-                        let dest = core::slice::from_raw_parts_mut(ptr as *mut u8, length * 4);
+
-                        proto_async::read_chunk(stream, dest).await?;
+                (**ptr_to_list).length = length;
-                        drop(dest);
+                (**ptr_to_list).elements = storage;
-                        let dest = core::slice::from_raw_parts_mut(ptr, length);
+                recv_elements(stream, tag, length, storage, alloc).await
-                        NativeEndian::from_slice_u32(dest);
-                    },
-                    Tag::Int64 | Tag::Float64 => {
-                        let ptr = data as *mut u64;
-                        let dest = core::slice::from_raw_parts_mut(ptr as *mut u8, length * 8);
-                        proto_async::read_chunk(stream, dest).await?;
-                        drop(dest);
-                        let dest = core::slice::from_raw_parts_mut(ptr, length);
-                        NativeEndian::from_slice_u64(dest);
-                    },
-                    _ => {
-                        for _ in 0..(*ptr).length as usize {
-                            recv_value(stream, tag, &mut data, alloc).await?
-                        }
-                    }
-                }
-                Ok(())
             })
         }
         Tag::Array(it, num_dims) => {
             consume_value!(*mut (), |buffer| {
-                let mut total_len: u32 = 1;
+                // Deserialize length along each dimension and compute total number of
+                // elements.
+                let mut total_len: usize = 1;
                 for _ in 0..num_dims {
-                    let len = proto_async::read_i32(stream).await? as u32;
+                    let len = proto_async::read_i32(stream).await? as usize;
                     total_len *= len;
-                    consume_value!(u32, |ptr| *ptr = len )
+                    consume_value!(usize, |ptr| *ptr = len )
                 }
 
+                // Allocate backing storage for elements; deserialize them.
                 let elt_tag = it.clone().next().expect("truncated tag");
-                let data_size = elt_tag.size() * total_len as usize +
+                *buffer = alloc(elt_tag.size() * total_len).await;
-                    match elt_tag {
+                recv_elements(stream, elt_tag, total_len, *buffer, alloc).await
-                        Tag::Int64 | Tag::Float64 => 4,
-                        _ => 0
-                    };
-                let mut data = alloc(data_size).await;
-
-                let alignment = tag.alignment();
-                data = data.offset(alignment_offset(alignment as isize, data as isize));
-                *buffer = data;
-                let length = total_len as usize;
-                match elt_tag {
-                    Tag::Bool => {
-                        let ptr = data as *mut u8;
-                        let dest = core::slice::from_raw_parts_mut(ptr, length);
-                        proto_async::read_chunk(stream, dest).await?;
-                    },
-                    Tag::Int32 => {
-                        let ptr = data as *mut u32;
-                        let dest = core::slice::from_raw_parts_mut(ptr as *mut u8, length * 4);
-                        proto_async::read_chunk(stream, dest).await?;
-                        drop(dest);
-                        let dest = core::slice::from_raw_parts_mut(ptr, length);
-                        NativeEndian::from_slice_u32(dest);
-                    },
-                    Tag::Int64 | Tag::Float64 => {
-                        let ptr = data as *mut u64;
-                        let dest = core::slice::from_raw_parts_mut(ptr as *mut u8, length * 8);
-                        proto_async::read_chunk(stream, dest).await?;
-                        drop(dest);
-                        let dest = core::slice::from_raw_parts_mut(ptr, length);
-                        NativeEndian::from_slice_u64(dest);
-                    },
-                    _ => {
-                        for _ in 0..length {
-                            recv_value(stream, elt_tag, &mut data, alloc).await?
-                        }
-                    }
-                }
-                Ok(())
             })
         }
         Tag::Range(it) => {
-            *data = (*data).offset(alignment_offset(tag.alignment() as isize, *data as isize));
+            *data = round_up_mut(*data, tag.alignment());
             let tag = it.clone().next().expect("truncated tag");
             recv_value(stream, tag, data, alloc).await?;
             recv_value(stream, tag, data, alloc).await?;
@@ -211,6 +217,36 @@ pub async fn recv_return<F>(stream: &TcpStream, tag_bytes: &[u8], data: *mut (),
     Ok(())
 }
 
+unsafe fn send_elements<W>(writer: &mut W, elt_tag: Tag, length: usize, data: *const ())
+                          -> Result<(), Error>
+    where W: Write + ?Sized
+{
+    writer.write_u8(elt_tag.as_u8())?;
+    match elt_tag {
+        // we cannot use NativeEndian::from_slice_i32 as the data is not mutable,
+        // and that is not needed as the data is already in native endian
+        Tag::Bool => {
+            let slice = core::slice::from_raw_parts(data as *const u8, length);
+            writer.write_all(slice)?;
+        },
+        Tag::Int32 => {
+            let slice = core::slice::from_raw_parts(data as *const u8, length * 4);
+            writer.write_all(slice)?;
+        },
+        Tag::Int64 | Tag::Float64 => {
+            let slice = core::slice::from_raw_parts(data as *const u8, length * 8);
+            writer.write_all(slice)?;
+        },
+        _ => {
+            let mut data = data;
+            for _ in 0..length {
+                send_value(writer, elt_tag, &mut data)?;
+            }
+        }
+    }
+    Ok(())
+}
+
 unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
                        -> Result<(), Error>
     where W: Write + ?Sized
@@ -244,46 +280,23 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
         Tag::Tuple(it, arity) => {
             let mut it = it.clone();
             writer.write_u8(arity)?;
+            let mut max_alignment = 0;
             for _ in 0..arity {
                 let tag = it.next().expect("truncated tag");
+                max_alignment = core::cmp::max(max_alignment, tag.alignment());
                 send_value(writer, tag, data)?
             }
+            *data = round_up_const(*data, max_alignment);
             Ok(())
         }
         Tag::List(it) => {
             #[repr(C)]
             struct List { elements: *const (), length: u32 }
             consume_value!(&List, |ptr| {
-                let length = (**ptr).length as isize;
+                let length = (**ptr).length as usize;
                 writer.write_u32((*ptr).length)?;
                 let tag = it.clone().next().expect("truncated tag");
-                let mut data = (**ptr).elements;
+                send_elements(writer, tag, length, (**ptr).elements)
-                writer.write_u8(tag.as_u8())?;
-                match tag {
-                    Tag::Bool => {
-                        // we can pretend this is u8...
-                        let ptr1 = align_ptr::<u8>(data);
-                        let slice = core::slice::from_raw_parts(ptr1, length as usize);
-                        writer.write_all(slice)?;
-                    },
-                    Tag::Int32 => {
-                        let ptr1 = align_ptr::<i32>(data);
-                        let slice = core::slice::from_raw_parts(ptr1 as *const u8, length as usize * 4);
-                        writer.write_all(slice)?;
-                    },
-                    Tag::Int64 | Tag::Float64 => {
-                        let ptr1 = align_ptr::<i64>(data);
-                        let slice = core::slice::from_raw_parts(ptr1 as *const u8, length as usize * 8);
-                        writer.write_all(slice)?;
-                    },
-                    // non-primitive types, not sure if this would happen but we can handle it...
-                    _ => {
-                        for _ in 0..length {
-                            send_value(writer, tag, &mut data)?;
-                        }
-                    }
-                };
-                Ok(())
             })
         }
         Tag::Array(it, num_dims) => {
@@ -298,33 +311,8 @@ unsafe fn send_value<W>(writer: &mut W, tag: Tag, data: &mut *const ())
                         total_len *= *len;
                     })
                 }
-                let mut data = *buffer;
+                let length = total_len as usize;
-                let length = total_len as isize;
+                send_elements(writer, elt_tag, length, *buffer)
-                writer.write_u8(elt_tag.as_u8())?;
-                match elt_tag {
-                    Tag::Bool => {
-                        let ptr1 = align_ptr::<u8>(data);
-                        let slice = core::slice::from_raw_parts(ptr1, length as usize);
-                        writer.write_all(slice)?;
-                    },
-                    Tag::Int32 => {
-                        let ptr1 = align_ptr::<i32>(data);
-                        let slice = core::slice::from_raw_parts(ptr1 as *const u8, length as usize * 4);
-                        writer.write_all(slice)?;
-                    },
-                    Tag::Int64 | Tag::Float64 => {
-                        let ptr1 = align_ptr::<i64>(data);
-                        let slice = core::slice::from_raw_parts(ptr1 as *const u8, length as usize * 8);
-                        writer.write_all(slice)?;
-                    },
-                    // non-primitive types, not sure if this would happen but we can handle it...
-                    _ => {
-                        for _ in 0..length {
-                            send_value(writer, elt_tag, &mut data)?;
-                        }
-                    }
-                };
-                Ok(())
             })
         }
         Tag::Range(it) => {
@@ -448,18 +436,15 @@ mod tag {
                     let it = it.clone();
                     it.take(3).map(|t| t.alignment()).max().unwrap()
                 }
-                // CSlice basically
+                // the ptr/length(s) pair is basically CSlice
-                Tag::Bytes | Tag::String | Tag::ByteArray =>
+                Tag::Bytes | Tag::String | Tag::ByteArray | Tag::List(_) | Tag::Array(_, _) =>
                     core::mem::align_of::<CSlice<()>>(),
-                // array buffer is allocated, so no need for alignment first
+                Tag::Keyword(_) => unreachable!("Tag::Keyword should not appear in composite types"),
-                Tag::List(_) | Tag::Array(_, _) => 1,
+                Tag::Object => core::mem::align_of::<u32>(),
-                // will not be sent from the host
-                _ => unreachable!("unexpected tag from host")
             }
         }
 
         pub fn size(self) -> usize {
-            use super::alignment_offset;
             match self {
                 Tag::None => 0,
                 Tag::Bool => 1,
@@ -471,13 +456,18 @@ mod tag {
                 Tag::ByteArray => 8,
                 Tag::Tuple(it, arity) => {
                     let mut size = 0;
+                    let mut max_alignment = 0;
                     let mut it = it.clone();
                     for _ in 0..arity {
                         let tag = it.next().expect("truncated tag");
+                        let alignment = tag.alignment();
+                        max_alignment = core::cmp::max(max_alignment, alignment);
+                        size = super::round_up(size, alignment);
                         size += tag.size();
-                        // includes padding
-                        size += alignment_offset(tag.alignment() as isize, size as isize) as usize;
                     }
+                    // Take into account any tail padding (if element(s) with largest
+                    // alignment are not at the end).
+                    size = super::round_up(size, max_alignment);
                     size
                 }
                 Tag::List(_) => 4,

src/runtime/src/rtio_csr.rs

@@ -94,7 +94,7 @@ pub extern fn output(target: i32, data: i32) {
     }
 }
 
-pub extern fn output_wide(target: i32, data: CSlice<i32>) {
+pub extern fn output_wide(target: i32, data: &CSlice<i32>) {
     unsafe {
         csr::rtio::target_write(target as u32);
         // writing target clears o_data

src/satman/src/main.rs

@@ -22,6 +22,8 @@ use libboard_zynq::{i2c::I2c, timer::GlobalTimer, time::Milliseconds, print, pri
 use libsupport_zynq::ram;
 #[cfg(has_si5324)]
 use libboard_artiq::si5324;
+#[cfg(feature = "target_kasli_soc")]
+use libboard_artiq::io_expander;
 use libboard_artiq::{pl::csr, drtio_routing, drtioaux, logger, identifier_read, init_gateware};
 use libcortex_a9::{spin_lock_yield, interrupt_handler, regs::{MPIDR, SP}, notify_spin_lock, asm, l2c::enable_l2_cache};
 use libregister::{RegisterW, RegisterR};
@@ -468,6 +470,19 @@ pub extern fn main_core0() -> i32 {
 
     let mut i2c = I2c::i2c0();
     i2c.init().expect("I2C initialization failed");
+    #[cfg(feature = "target_kasli_soc")]
+    {
+        for expander_i in 0..=1 {
+            let mut io_expander = io_expander::IoExpander::new(&mut i2c, expander_i).unwrap();
+            io_expander.init().expect("I2C I/O expander #0 initialization failed");
+            // Actively drive TX_DISABLE to false on SFP0..3
+            io_expander.set_oe(0, 1 << 1).unwrap();
+            io_expander.set_oe(1, 1 << 1).unwrap();
+            io_expander.set(0, 1, false);
+            io_expander.set(1, 1, false);
+            io_expander.service().unwrap();
+        }
+    }
 
     #[cfg(has_si5324)]
     si5324::setup(&mut i2c, &SI5324_SETTINGS, si5324::Input::Ckin1, &mut timer).expect("cannot initialize Si5324");