Merge pull request #353 from tianrui-wei/master

fix: fix icache_tb not finishing correctly

README.md

@@ -103,14 +103,8 @@ 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):
@@ -128,6 +122,68 @@ 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

control.vhdl

@@ -64,8 +64,8 @@ architecture rtl of control is
 
     signal r_int, rin_int : reg_internal_type := reg_internal_init;
 
-    signal gpr_write_valid : std_ulogic := '0';
+    signal gpr_write_valid : std_ulogic;
-    signal cr_write_valid  : std_ulogic := '0';
+    signal cr_write_valid  : std_ulogic;
 
     type tag_register is record
         wr_gpr : std_ulogic;
@@ -245,6 +245,8 @@ begin
         end if;
 
         if rst = '1' then
+            gpr_write_valid <= '0';
+            cr_write_valid <= '0';
             v_int := reg_internal_init;
             valid_tmp := '0';
         end if;

core.vhdl

@@ -117,21 +117,20 @@ 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
-    signal rst_fetch1  : std_ulogic := '1';
+    signal rst_fetch1  : std_ulogic;
-    signal rst_fetch2  : std_ulogic := '1';
+    signal rst_fetch2  : std_ulogic;
-    signal rst_icache  : std_ulogic := '1';
+    signal rst_icache  : std_ulogic;
-    signal rst_dcache  : std_ulogic := '1';
+    signal rst_dcache  : std_ulogic;
-    signal rst_dec1    : std_ulogic := '1';
+    signal rst_dec1    : std_ulogic;
-    signal rst_dec2    : std_ulogic := '1';
+    signal rst_dec2    : std_ulogic;
-    signal rst_ex1     : std_ulogic := '1';
+    signal rst_ex1     : std_ulogic;
-    signal rst_fpu     : std_ulogic := '1';
+    signal rst_fpu     : std_ulogic;
-    signal rst_ls1     : std_ulogic := '1';
+    signal rst_ls1     : std_ulogic;
-    signal rst_wback   : std_ulogic := '1';
+    signal rst_wback   : std_ulogic;
-    signal rst_dbg     : std_ulogic := '1';
+    signal rst_dbg     : std_ulogic;
     signal alt_reset_d : std_ulogic;
 
     signal sim_cr_dump: std_ulogic;

core_debug.vhdl

@@ -154,6 +154,7 @@ 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

@@ -1121,7 +1121,6 @@ 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

@@ -42,6 +42,8 @@ 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

@@ -99,8 +99,8 @@ architecture behaviour of execute1 is
     signal mshort_p : std_ulogic_vector(31 downto 0) := (others => '0');
 
     signal valid_in : std_ulogic;
-    signal ctrl: ctrl_t := (others => (others => '0'));
+    signal ctrl: ctrl_t;
-    signal ctrl_tmp: ctrl_t := (others => (others => '0'));
+    signal ctrl_tmp: ctrl_t;
     signal right_shift, rot_clear_left, rot_clear_right: std_ulogic;
     signal rot_sign_ext: std_ulogic;
     signal rotator_result: std_ulogic_vector(63 downto 0);
@@ -113,8 +113,6 @@ 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;
 
@@ -406,6 +404,7 @@ begin
                 r <= reg_type_init;
                 ctrl.tb <= (others => '0');
                 ctrl.dec <= (others => '0');
+                ctrl.cfar <= (others => '0');
                 ctrl.msr <= (MSR_SF => '1', MSR_LE => '1', others => '0');
             else
                 r <= rin;

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
@@ -549,6 +549,10 @@ 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;

gpio.vhdl

@@ -40,8 +40,8 @@ architecture behaviour of gpio is
     constant GPIO_REG_DATA_CLR : std_ulogic_vector(GPIO_REG_BITS-1 downto 0) := "00101";
 
     -- Current output value and direction
-    signal reg_data : std_ulogic_vector(NGPIO - 1 downto 0) := (others => '0');
+    signal reg_data : std_ulogic_vector(NGPIO - 1 downto 0);
-    signal reg_dirn : std_ulogic_vector(NGPIO - 1 downto 0) := (others => '0');
+    signal reg_dirn : std_ulogic_vector(NGPIO - 1 downto 0);
     signal reg_in1  : std_ulogic_vector(NGPIO - 1 downto 0);
     signal reg_in2  : std_ulogic_vector(NGPIO - 1 downto 0);
 

hello_world/head.S

@@ -60,11 +60,25 @@ _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 */
-	LOAD_IMM64(%r1, STACK_TOP - 0x100)
+2:	LOAD_IMM64(%r1,__stack_top)
+	li	%r0,0
+	stdu	%r0,-32(%r1)
 	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
-3c20000048000004
+3d40000048000004
+794a07c6614a0000
+614a1900654a0000
+616b00003d600000
+656b0000796b07c6
+7d6a5850616b1980
+796bd183396b003f
+7d6903a641820014
+394a00407c0057ec
+3c2000004200fff8
 782107c660210000
-60211f0064210000
+6021398064210000
-618c00003d800000
+f801ffe138000000
-658c0000798c07c6
+3d8000007c1243a6
-7d8903a6618c1014
+798c07c6618c0000
-480000004e800421
+618c1000658c0000
-0000000000000000
+4e8004217d8903a6
-0000000000000000
+4800000000000200
-0000000000000000
-0000000000000000
-0000000000000000
-0000000000000000
-0000000000000000
-0000000000000000
-0000000000000000
-0000000000000000
-0000000000000000
 0000000000000000
 0000000000000000
 0000000000000000
@@ -510,150 +510,150 @@ a64b5a7d14004a39
 0000000000000000
 0000000000000000
 0000000000000000
-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
-0000000000000000
-384298003c400001
-8922809060000000
-3942808860000000
-4182002c2c090000
-39290014e92a0000
-7d204eaa7c0004ac
-4182ffec71290020
-7c0004ace92a0000
-4e8000207c604faa
-39290010e92a0000
-7d204eea7c0004ac
-4082ffec71290008
-e94a00005469063e
-7d2057ea7c0004ac
-000000004e800020
-0000000000000000
 384298003c400001
 fbe1fff87c0802a6
-3be3fffffbc1fff0
 f821ffd1f8010010
-2c3e00008fdf0001
+60000000480001ed
-3821003040820010
+3862800060000000
-4bfffe4438600000
+6000000048000155
-4082000c281e000a
+6000000048000049
-4bffff453860000d
+5463063e7c7f1b78
-4bffff3d7fc3f378
+480000b957ff063e
+2c1f000d60000000
+3860000a4082ffe0
+60000000480000a5
 000000004bffffd0
-0000028001000000
+0000018001000000
-386000007c691b78
-2c0a00007d4918ae
-386300014d820020
-000000004bfffff0
-0000000000000000
 384298003c400001
-614a00203d40c000
+8922810860000000
-7c0004ac794a0020
+3942810060000000
-3d20c0007d4056ea
+418200302c090000
-61290008794a0600
+39290014e92a0000
-7c0004ac79290020
+7d204eaa7c0004ac
-712900207d204eea
+4182ffec71290001
-3d20c00041820018
+7c0004ace86a0000
-7929002061290040
+5463063e7c601eaa
-7d204eea7c0004ac
+e92a00004e800020
-3d00c0007929f804
-6108200079290fc3
-6000000079080020
-3d00001cf9028088
-7d4a439261082000
-6000000041820084
-9922809039200001
-6108200c3d00c000
-790800203920ff80
-7d2047aa7c0004ac
-7c0004ace9228088
-e92280887d404faa
-39290004794ac202
-7d404faa7c0004ac
-39400003e9228088
-7c0004ac3929000c
-e92280887d404faa
 7c0004ac39290010
-e92280887d404faa
+712900017d204eea
-3929000839400007
+e86a00004082ffec
-7d404faa7c0004ac
+7c0004ac38630008
-600000004e800020
+4bffffd07c601eea
-99228090394affff
-612920183d20c000
-7c0004ac79290020
-4e8000207d404fea
 0000000000000000
 3c40000100000000
 6000000038429800
-2c24000089228090
+6000000089228108
-600000002f890000
+2c09000039428100
-419e0030e9228088
+e92a00004182002c
-3940000241820024
+7c0004ac39290014
-418200082c230000
+712900207d204eaa
-39290004614a0001
+e92a00004182ffec
+7c604faa7c0004ac
+e92a00004e800020
+7c0004ac39290010
+712900087d204eea
+5469063e4082ffec
+7c0004ace94a0000
+4e8000207d2057ea
+0000000000000000
+3c40000100000000
+7c0802a638429800
+fbc1fff0fbe1fff8
+f80100103be3ffff
+8fdf0001f821ffd1
+408200102c3e0000
+3860000038210030
+281e000a480001e8
+3860000d4082000c
+7fc3f3784bffff45
+4bffffd04bffff3d
+0100000000000000
+7c691b7800000280
+7d4918ae38600000
+4d8200202c0a0000
+4bfffff038630001
+0000000000000000
+3c40000100000000
+3d40c00038429800
+794a0020614a0020
+7d4056ea7c0004ac
+794a06003d20c000
+7929002061290008
+7d204eea7c0004ac
+4182001871290020
+612900403d20c000
+7c0004ac79290020
+7929f8047d204eea
+79290fc33d00c000
+7908002061082000
+f902810060000000
+610820003d00001c
+418200847d4a4392
+3920000160000000
+3d00c00099228108
+3920ff806108200c
+7c0004ac79080020
+e92281007d2047aa
 7d404faa7c0004ac
-394000004e800020
+794ac202e9228100
-418200084bffffe0
+7c0004ac39290004
+e92281007d404faa
+3929000c39400003
+7d404faa7c0004ac
+39290010e9228100
+7d404faa7c0004ac
+39400007e9228100
+7c0004ac39290008
+4e8000207d404faa
+394affff60000000
+3d20c00099228108
+7929002061292018
+7d404fea7c0004ac
+000000004e800020
+0000000000000000
+384298003c400001
+8922810860000000
+600000002c090000
+41820024e9228100
+78840e282c230000
+6084000141820008
+7c0004ac39290004
+4e8000207c804faa
+418200082c240000
 3929002060630002
 7c604fea7c0004ac
 000000004e800020
 0000000000000000
-0000000000000010
+e8010010ebc1fff0
-0141780400527a01
+7c0803a6ebe1fff8
-0000001800010c1b
+000000104e800020
-fffffc4800000018
+00527a0100000000
-300e460000000070
+00010c1b01417804
-000000019f7e4111
+0000001800000018
-0000000000000010
+00000070fffffc40
-0141780400527a01
+9f7e4111300e4600
-0000001000010c1b
+0000001000000001
-fffffc8800000018
+00527a0100000000
-0000000000000084
+00010c1b01417804
-0000002c00000010
+0000001800000010
-00000080fffffcf8
+00000084fffffc80
-0000002800000000
+0000001000000000
-fffffd6400000040
+fffffcf00000002c
-4109450000000060
+0000000000000080
-300e43029e019f00
+0000004000000028
-42000e0a447e4111
+00000060fffffd5c
-0000000b4106dedf
+9e019f0041094500
-0000006c00000010
+447e4111300e4302
-00000028fffffd98
+4106dedf42000e0a
+000000100000000b
+fffffd900000006c
+0000000000000028
+0000008000000010
+0000012cfffffda4
 0000001000000000
-fffffdac00000080
+fffffebc00000094
-000000000000012c
+0000000000000068
-0000009400000010
+0000000000000000
-00000074fffffec4
 0000000000000000
 0000000000000000
 0000000000000000

hello_world/powerpc.lds

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

icache.vhdl

@@ -555,7 +555,11 @@ 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.valid <= r.hit_valid;
 	i_out.nia <= r.hit_nia;
 	i_out.stop_mark <= r.hit_smark;
@@ -820,4 +824,7 @@ begin
         end process;
         log_out <= log_data;
     end generate;
+
+    events <= ev;
+
 end;

icache_tb.vhdl

@@ -74,6 +74,9 @@ 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

@@ -275,10 +275,27 @@ 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;
@@ -286,6 +303,8 @@ 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;

soc.vhdl

@@ -61,6 +61,7 @@ entity soc is
         HAS_BTC            : boolean := true;
         HAS_SHORT_MULT     : boolean := false;
 	DISABLE_FLATTEN_CORE : boolean := false;
+        ALT_RESET_ADDRESS  : std_logic_vector(63 downto 0) := (23 downto 0 => '0', others => '1');
 	HAS_DRAM           : boolean  := false;
 	DRAM_SIZE          : integer := 0;
         DRAM_INIT_SIZE     : integer := 0;
@@ -222,15 +223,15 @@ architecture behaviour of soc is
     signal dmi_core_ack   : std_ulogic;
 
     -- Delayed/latched resets and alt_reset
-    signal rst_core    : std_ulogic := '1';
+    signal rst_core    : std_ulogic;
-    signal rst_uart    : std_ulogic := '1';
+    signal rst_uart    : std_ulogic;
-    signal rst_xics    : std_ulogic := '1';
+    signal rst_xics    : std_ulogic;
-    signal rst_spi     : std_ulogic := '1';
+    signal rst_spi     : std_ulogic;
-    signal rst_gpio    : std_ulogic := '1';
+    signal rst_gpio    : std_ulogic;
-    signal rst_bram    : std_ulogic := '1';
+    signal rst_bram    : std_ulogic;
-    signal rst_dtm     : std_ulogic := '1';
+    signal rst_dtm     : std_ulogic;
-    signal rst_wbar    : std_ulogic := '1';
+    signal rst_wbar    : std_ulogic;
-    signal rst_wbdb    : std_ulogic := '1';
+    signal rst_wbdb    : std_ulogic;
     signal alt_reset_d : std_ulogic;
 
     -- IO branch split:
@@ -336,7 +337,7 @@ begin
             HAS_BTC => HAS_BTC,
             HAS_SHORT_MULT => HAS_SHORT_MULT,
 	    DISABLE_FLATTEN => DISABLE_FLATTEN_CORE,
-	    ALT_RESET_ADDRESS => (23 downto 0 => '0', others => '1'),
+	    ALT_RESET_ADDRESS => ALT_RESET_ADDRESS,
             LOG_LENGTH => LOG_LENGTH,
             ICACHE_NUM_LINES => ICACHE_NUM_LINES,
             ICACHE_NUM_WAYS => ICACHE_NUM_WAYS,

spi_flash_ctrl.vhdl

@@ -50,7 +50,7 @@ architecture rtl of spi_flash_ctrl is
     constant SPI_REG_INVALID      : std_ulogic_vector(SPI_REG_BITS-1 downto 0) := "111";
 
     -- Control register
-    signal ctrl_reg    : std_ulogic_vector(15 downto 0) := (others => '0');
+    signal ctrl_reg    : std_ulogic_vector(15 downto 0);
     alias  ctrl_reset  : std_ulogic is ctrl_reg(0);
     alias  ctrl_cs     : std_ulogic is ctrl_reg(1);
     alias  ctrl_rsrv1  : std_ulogic is ctrl_reg(2);
@@ -58,7 +58,7 @@ architecture rtl of spi_flash_ctrl is
     alias  ctrl_div    : std_ulogic_vector(7 downto 0) is ctrl_reg(15 downto 8);
 
     -- Auto mode config register
-    signal auto_cfg_reg     : std_ulogic_vector(29 downto 0) := (others => '0');
+    signal auto_cfg_reg     : std_ulogic_vector(29 downto 0);
     alias  auto_cfg_cmd     : std_ulogic_vector(7 downto 0) is auto_cfg_reg(7 downto 0);
     alias  auto_cfg_dummies : std_ulogic_vector(2 downto 0) is auto_cfg_reg(10 downto 8);
     alias  auto_cfg_mode    : std_ulogic_vector(1 downto 0) is auto_cfg_reg(12 downto 11);
@@ -126,9 +126,9 @@ architecture rtl of spi_flash_ctrl is
     signal auto_latch_adr : std_ulogic;
 
     -- Automatic mode latches
-    signal auto_data      : std_ulogic_vector(wb_out.dat'left downto 0) := (others => '0');
+    signal auto_data      : std_ulogic_vector(wb_out.dat'left downto 0);
-    signal auto_cnt       : integer range 0 to 63 := 0;
+    signal auto_cnt       : integer range 0 to 63;
-    signal auto_state     : auto_state_t := AUTO_BOOT;
+    signal auto_state     : auto_state_t;
     signal auto_last_addr : std_ulogic_vector(31 downto 0);
 
 begin
@@ -351,6 +351,8 @@ begin
             if rst = '1' then
                 auto_last_addr <= (others => '0');
                 auto_state <= AUTO_BOOT;
+                auto_cnt <= 0;
+                auto_data  <= (others => '0');
             else
                 auto_state <= auto_next;
                 auto_cnt   <= auto_cnt_next;

spi_rxtx.vhdl

@@ -126,10 +126,10 @@ architecture rtl of spi_rxtx is
     signal dat_ack_l : std_ulogic;
 
     -- Delayed recv signal for the read machine
-    signal sck_recv_d : std_ulogic := '0';
+    signal sck_recv_d : std_ulogic;
 
     -- Input shift register (use fifo ?)
-    signal ireg       : std_ulogic_vector(7 downto 0) := (others => '0');
+    signal ireg       : std_ulogic_vector(7 downto 0);
 
     -- Bit counter
     signal bit_count  : std_ulogic_vector(2 downto 0);
@@ -157,7 +157,7 @@ architecture rtl of spi_rxtx is
     end;
 
     type state_t is (STANDBY, DATA);
-    signal state : state_t := STANDBY;
+    signal state : state_t;
 begin
 
     -- We don't support multiple data lines at this point
@@ -349,6 +349,9 @@ begin
     shift_in: process(clk)
     begin
         if rising_edge(clk) then
+            if rst = '1' then
+                ireg <= (others => '0');
+            end if;
 
             -- Delay the receive signal to match the input latch
             if state = DATA then