README.md

@@ -103,8 +103,14 @@ sudo dnf install fusesoc
 
 ```
 fusesoc init
-fusesoc fetch uart16550
-fusesoc library add microwatt /path/to/microwatt
+```
+
+- Create a working directory and point FuseSoC at microwatt:
+
+```
+mkdir microwatt-fusesoc
+cd microwatt-fusesoc
+fusesoc library add microwatt /path/to/microwatt/
 ```
 
 - Build using FuseSoC. For hello world (Replace nexys_video with your FPGA board such as --target=arty_a7-100):
@@ -122,68 +128,6 @@ You should then be able to see output via the serial port of the board (/dev/tty
 fusesoc run --target=nexys_video microwatt
 ```
 
-## Linux on Microwatt
-
-Mainline Linux supports Microwatt as of v5.14. The Arty A7 is the best tested
-platform, but it's also been tested on the OrangeCrab and ButterStick.
-
-1. Use buildroot to create a userspace
-
-   A small change is required to glibc in order to support the VMX/AltiVec-less
-   Microwatt, as float128 support is mandiatory and for this in GCC requires
-   VSX/AltiVec. This change is included in Joel's buildroot fork, along with a
-   defconfig:
-   ```
-   git clone -b microwatt https://github.com/shenki/buildroot
-   cd buildroot
-   make ppc64le_microwatt_defconfig
-   make
-   ```
-
-   The output is `output/images/rootfs.cpio`.
-
-2. Build the Linux kernel
-   ```
-   git clone https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-   cd linux
-   make ARCH=powerpc microwatt_defconfig
-   make ARCH=powerpc CROSS_COMPILE=powerpc64le-linux-gnu- \
-     CONFIG_INITRAMFS_SOURCE=/buildroot/output/images/rootfs.cpio -j`nproc`
-   ```
-
-   The output is `arch/powerpc/boot/dtbImage.microwatt.elf`.
-
-3. Build gateware using FuseSoC
-
-   First configure FuseSoC as above.
-   ```
-   fusesoc run --build --target=arty_a7-100 microwatt --no_bram --memory_size=0
-   ```
-
-   The output is `build/microwatt_0/arty_a7-100-vivado/microwatt_0.bit`.
-
-4. Program the flash
-
-   This operation will overwrite the contents of your flash.
-
-   For the Arty A7 A100, set `FLASH_ADDRESS` to `0x400000` and pass `-f a100`.
-
-   For the Arty A7 A35, set `FLASH_ADDRESS` to `0x300000` and pass `-f a35`.
-   ```
-   microwatt/openocd/flash-arty -f a100 build/microwatt_0/arty_a7-100-vivado/microwatt_0.bit
-   microwatt/openocd/flash-arty -f a100 dtbImage.microwatt.elf -t bin -a $FLASH_ADDRESS
-   ```
-
-5. Connect to the second USB TTY device exposed by the FPGA
-
-   ```
-   minicom -D /dev/ttyUSB1
-   ```
-
-   The gateware has firmware that will look at `FLASH_ADDRESS` and attempt to
-   parse an ELF there, loading it to the address specified in the ELF header
-   and jumping to it.
-
 ## Testing
 
 - A simple test suite containing random execution test cases and a couple of

core.vhdl

@@ -117,6 +117,7 @@ architecture behave of core is
     signal complete: instr_tag_t;
     signal terminate: std_ulogic;
     signal core_rst: std_ulogic;
+    signal icache_inv: std_ulogic;
     signal do_interrupt: std_ulogic;
 
     -- Delayed/Latched resets and alt_reset

core_debug.vhdl

@@ -154,7 +154,6 @@ begin
                 stopping <= '0';
                 terminated <= '0';
                 log_trigger_delay <= 0;
-                gspr_index <= (others => '0');
             else
                 if do_log_trigger = '1' or log_trigger_delay /= 0 then
                     if log_trigger_delay = 255 then

dcache.vhdl

@@ -1121,6 +1121,7 @@ begin
     rams: for i in 0 to NUM_WAYS-1 generate
 	signal do_read  : std_ulogic;
 	signal rd_addr  : std_ulogic_vector(ROW_BITS-1 downto 0);
+	signal do_write : std_ulogic;
 	signal wr_addr  : std_ulogic_vector(ROW_BITS-1 downto 0);
 	signal wr_data  : std_ulogic_vector(wishbone_data_bits-1 downto 0);
 	signal wr_sel   : std_ulogic_vector(ROW_SIZE-1 downto 0);

divider.vhdl

@@ -42,8 +42,6 @@ begin
                 quot <= (others => '0');
                 running <= '0';
                 count <= "0000000";
-                is_32bit <= '0';
-                overflow <= '0';
             elsif d_in.valid = '1' then
                 if d_in.is_extended = '1'  then
                     dend <= '0' & d_in.dividend & x"0000000000000000";

execute1.vhdl

@@ -113,6 +113,8 @@ architecture behaviour of execute1 is
     signal misc_result: std_ulogic_vector(63 downto 0);
     signal muldiv_result: std_ulogic_vector(63 downto 0);
     signal spr_result: std_ulogic_vector(63 downto 0);
+    signal result_mux_sel: std_ulogic_vector(2 downto 0);
+    signal sub_mux_sel: std_ulogic_vector(2 downto 0);
     signal next_nia : std_ulogic_vector(63 downto 0);
     signal current: Decode2ToExecute1Type;
 

fpu.vhdl

@@ -16,7 +16,7 @@ entity fpu is
         clk : in std_ulogic;
         rst : in std_ulogic;
 
-        e_in  : in  Execute1ToFPUType;
+        e_in  : in  Execute1toFPUType;
         e_out : out FPUToExecute1Type;
 
         w_out : out FPUToWritebackType
@@ -549,10 +549,6 @@ begin
                 r.do_intr <= '0';
                 r.fpscr <= (others => '0');
                 r.writing_back <= '0';
-                r.dest_fpr <= (others =>'0');
-                r.cr_mask <= (others =>'0');
-                r.cr_result <= (others =>'0');
-                r.instr_tag.valid <= '0';
             else
                 assert not (r.state /= IDLE and e_in.valid = '1') severity failure;
                 r <= rin;

hello_world/head.S

@@ -60,25 +60,11 @@ _start:
 
 .global boot_entry
 boot_entry:
-	LOAD_IMM64(%r10,__bss_start)
-	LOAD_IMM64(%r11,__bss_end)
-	subf	%r11,%r10,%r11
-	addi	%r11,%r11,63
-	srdi.	%r11,%r11,6
-	beq	2f
-	mtctr	%r11
-1:	dcbz	0,%r10
-	addi	%r10,%r10,64
-	bdnz	1b
-
 	/* setup stack */
-2:	LOAD_IMM64(%r1,__stack_top)
-	li	%r0,0
-	stdu	%r0,-32(%r1)
+	LOAD_IMM64(%r1, STACK_TOP - 0x100)
 	LOAD_IMM64(%r12, main)
-	mtctr	%r12
+	mtctr	%r12,
 	bctrl
-	attn // terminate on exit
 	b .
 
 #define EXCEPTION(nr)		\

hello_world/hello_world.hex

@@ -35,24 +35,24 @@ a64b5a7d14004a39
 a602487d05009f42
 a64b5a7d14004a39
 2402004ca64b7b7d
-3d40000048000004
-794a07c6614a0000
-614a1900654a0000
-616b00003d600000
-656b0000796b07c6
-7d6a5850616b1980
-796bd183396b003f
-7d6903a641820014
-394a00407c0057ec
-3c2000004200fff8
+3c20000048000004
 782107c660210000
-6021398064210000
-f801ffe138000000
-3d8000007c1243a6
-798c07c6618c0000
-618c1000658c0000
-4e8004217d8903a6
-4800000000000200
+60211f0064210000
+618c00003d800000
+658c0000798c07c6
+7d8903a6618c1014
+480000004e800421
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
+0000000000000000
 0000000000000000
 0000000000000000
 0000000000000000
@@ -510,150 +510,150 @@ f801ffe138000000
 0000000000000000
 0000000000000000
 0000000000000000
-384298003c400001
-fbe1fff87c0802a6
-f821ffd1f8010010
-60000000480001ed
-3862800060000000
-6000000048000155
-6000000048000049
-5463063e7c7f1b78
-480000b957ff063e
-2c1f000d60000000
-3860000a4082ffe0
-60000000480000a5
+e8010010ebc1fff0
+7c0803a6ebe1fff8
+3c4000014e800020
+7c0802a638429800
+f8010010fbe1fff8
+480001edf821ffd1
+6000000060000000
+4800015538628000
+4800004960000000
+7c7f1b7860000000
+57ff063e5463063e
+60000000480000b9
+4082ffe02c1f000d
+480000a53860000a
+4bffffd060000000
+0100000000000000
+3c40000100000180
+6000000038429800
+6000000089228090
+2c09000039428088
+e92a000041820030
+7c0004ac39290014
+712900017d204eaa
+e86a00004182ffec
+7c601eaa7c0004ac
+4e8000205463063e
+39290010e92a0000
+7d204eea7c0004ac
+4082ffec71290001
+38630008e86a0000
+7c601eea7c0004ac
 000000004bffffd0
-0000018001000000
+0000000000000000
 384298003c400001
-8922810860000000
-3942810060000000
-418200302c090000
+8922809060000000
+3942808860000000
+4182002c2c090000
 39290014e92a0000
 7d204eaa7c0004ac
-4182ffec71290001
-7c0004ace86a0000
-5463063e7c601eaa
-e92a00004e800020
-7c0004ac39290010
-712900017d204eea
-e86a00004082ffec
-7c0004ac38630008
-4bffffd07c601eea
-0000000000000000
-3c40000100000000
-6000000038429800
-6000000089228108
-2c09000039428100
-e92a00004182002c
-7c0004ac39290014
-712900207d204eaa
-e92a00004182ffec
-7c604faa7c0004ac
-e92a00004e800020
-7c0004ac39290010
-712900087d204eea
-5469063e4082ffec
-7c0004ace94a0000
-4e8000207d2057ea
+4182ffec71290020
+7c0004ace92a0000
+4e8000207c604faa
+39290010e92a0000
+7d204eea7c0004ac
+4082ffec71290008
+e94a00005469063e
+7d2057ea7c0004ac
+000000004e800020
 0000000000000000
-3c40000100000000
-7c0802a638429800
-fbc1fff0fbe1fff8
-f80100103be3ffff
-8fdf0001f821ffd1
-408200102c3e0000
-3860000038210030
-281e000a480001e8
-3860000d4082000c
-7fc3f3784bffff45
-4bffffd04bffff3d
-0100000000000000
-7c691b7800000280
-7d4918ae38600000
-4d8200202c0a0000
-4bfffff038630001
+384298003c400001
+fbe1fff87c0802a6
+3be3fffffbc1fff0
+f821ffd1f8010010
+2c3e00008fdf0001
+3821003040820010
+4bfffe4438600000
+4082000c281e000a
+4bffff453860000d
+4bffff3d7fc3f378
+000000004bffffd0
+0000028001000000
+386000007c691b78
+2c0a00007d4918ae
+386300014d820020
+000000004bfffff0
 0000000000000000
-3c40000100000000
-3d40c00038429800
-794a0020614a0020
-7d4056ea7c0004ac
-794a06003d20c000
-7929002061290008
-7d204eea7c0004ac
-4182001871290020
-612900403d20c000
+384298003c400001
+614a00203d40c000
+7c0004ac794a0020
+3d20c0007d4056ea
+61290008794a0600
 7c0004ac79290020
-7929f8047d204eea
-79290fc33d00c000
-7908002061082000
-f902810060000000
-610820003d00001c
-418200847d4a4392
-3920000160000000
-3d00c00099228108
-3920ff806108200c
-7c0004ac79080020
-e92281007d2047aa
-7d404faa7c0004ac
-794ac202e9228100
-7c0004ac39290004
-e92281007d404faa
-3929000c39400003
+712900207d204eea
+3d20c00041820018
+7929002061290040
+7d204eea7c0004ac
+3d00c0007929f804
+6108200079290fc3
+6000000079080020
+3d00001cf9028088
+7d4a439261082000
+6000000041820084
+9922809039200001
+6108200c3d00c000
+790800203920ff80
+7d2047aa7c0004ac
+7c0004ace9228088
+e92280887d404faa
+39290004794ac202
 7d404faa7c0004ac
-39290010e9228100
+39400003e9228088
+7c0004ac3929000c
+e92280887d404faa
+7c0004ac39290010
+e92280887d404faa
+3929000839400007
 7d404faa7c0004ac
-39400007e9228100
-7c0004ac39290008
-4e8000207d404faa
-394affff60000000
-3d20c00099228108
-7929002061292018
-7d404fea7c0004ac
-000000004e800020
+600000004e800020
+99228090394affff
+612920183d20c000
+7c0004ac79290020
+4e8000207d404fea
 0000000000000000
-384298003c400001
-8922810860000000
-600000002c090000
-41820024e9228100
-78840e282c230000
-6084000141820008
-7c0004ac39290004
-4e8000207c804faa
-418200082c240000
+3c40000100000000
+6000000038429800
+2c24000089228090
+600000002f890000
+419e0030e9228088
+3940000241820024
+418200082c230000
+39290004614a0001
+7d404faa7c0004ac
+394000004e800020
+418200084bffffe0
 3929002060630002
 7c604fea7c0004ac
 000000004e800020
 0000000000000000
-e8010010ebc1fff0
-7c0803a6ebe1fff8
-000000104e800020
-00527a0100000000
-00010c1b01417804
-0000001800000018
-00000070fffffc40
-9f7e4111300e4600
-0000001000000001
-00527a0100000000
-00010c1b01417804
-0000001800000010
-00000084fffffc80
-0000001000000000
-fffffcf00000002c
-0000000000000080
-0000004000000028
-00000060fffffd5c
-9e019f0041094500
-447e4111300e4302
-4106dedf42000e0a
-000000100000000b
-fffffd900000006c
-0000000000000028
-0000008000000010
-0000012cfffffda4
+0000000000000010
+0141780400527a01
+0000001800010c1b
+fffffc4800000018
+300e460000000070
+000000019f7e4111
+0000000000000010
+0141780400527a01
+0000001000010c1b
+fffffc8800000018
+0000000000000084
+0000002c00000010
+00000080fffffcf8
+0000002800000000
+fffffd6400000040
+4109450000000060
+300e43029e019f00
+42000e0a447e4111
+0000000b4106dedf
+0000006c00000010
+00000028fffffd98
 0000001000000000
-fffffebc00000094
-0000000000000068
-0000000000000000
+fffffdac00000080
+000000000000012c
+0000009400000010
+00000074fffffec4
 0000000000000000
 0000000000000000
 0000000000000000

hello_world/powerpc.lds

@@ -1,27 +1,13 @@
 SECTIONS
 {
-	. = 0;
 	_start = .;
+	. = 0;
 	.head : {
 		KEEP(*(.head))
-	}
+ 	}
 	. = 0x1000;
-	.text : { *(.text) *(.text.*) *(.rodata) *(.rodata.*) }
+	.text : { *(.text) }
 	. = 0x1800;
-	.data : { *(.data) *(.data.*) *(.got) *(.toc) }
-	. = ALIGN(0x80);
-	__bss_start = .;
-	.bss : {
-		*(.dynsbss)
-		*(.sbss)
-		*(.scommon)
-		*(.dynbss)
-		*(.bss)
-		*(.common)
-		*(.bss.*)
-	}
-	. = ALIGN(0x80);
-	__bss_end = .;
-	. = . + 0x2000;
-	__stack_top = .;
+	.data : { *(.data) }
+	.bss : { *(.bss) }
 }

icache.vhdl

@@ -555,11 +555,7 @@ begin
 	--       I prefer not to do just yet as it would force fetch2 to know about
 	--       some of the cache geometry information.
 	--
-	if r.hit_valid = '1' then
-            i_out.insn <= read_insn_word(r.hit_nia, cache_out(r.hit_way));
-	else
-            i_out.insn <= (others => '0');
-	end if;
+        i_out.insn <= read_insn_word(r.hit_nia, cache_out(r.hit_way));
 	i_out.valid <= r.hit_valid;
 	i_out.nia <= r.hit_nia;
 	i_out.stop_mark <= r.hit_smark;
@@ -824,7 +820,4 @@ begin
         end process;
         log_out <= log_data;
     end generate;
-
-    events <= ev;
-
 end;

icache_tb.vhdl

@@ -74,9 +74,6 @@ begin
         i_out.req <= '0';
         i_out.nia <= (others => '0');
         i_out.stop_mark <= '0';
-        i_out.priv_mode <= '1';
-        i_out.virt_mode <= '0';
-        i_out.big_endian <= '0';
 
         m_out.tlbld <= '0';
         m_out.tlbie <= '0';

loadstore1.vhdl

@@ -275,27 +275,10 @@ begin
         if rising_edge(clk) then
             if rst = '1' then
                 r1.req.valid <= '0';
-                r1.req.tlbie <= '0';
-                r1.req.is_slbia <= '0';
-                r1.req.instr_fault <= '0';
-                r1.req.load <= '0';
-                r1.req.priv_mode <= '0';
-                r1.req.sprn <= (others => '0');
-                r1.req.xerc <= xerc_init;
-
                 r2.req.valid <= '0';
-                r2.req.tlbie <= '0';
-                r2.req.is_slbia <= '0';
-                r2.req.instr_fault <= '0';
-                r2.req.load <= '0';
-                r2.req.priv_mode <= '0';
-                r2.req.sprn <= (others => '0');
-                r2.req.xerc <= xerc_init;
-
                 r2.wait_dc <= '0';
                 r2.wait_mmu <= '0';
                 r2.one_cycle <= '0';
-
                 r3.dar <= (others => '0');
                 r3.dsisr <= (others => '0');
                 r3.state <= IDLE;
@@ -303,8 +286,6 @@ begin
                 r3.interrupt <= '0';
                 r3.stage1_en <= '1';
                 r3.convert_lfs <= '0';
-                r3.events.load_complete <= '0';
-                r3.events.store_complete <= '0';
                 flushing <= '0';
             else
                 r1 <= r1in;