Commit Graph

420 Commits

Author SHA1 Message Date
jon
259d34618c A design that actually passes one performance monitor trace from
TestRig.  The example counted redirections, which happend to match
between Flute and Toooba for this example.
2020-12-01 18:02:11 +00:00
Jonathan Woodruff
0289bfe17d Fix a couple errors due to changes somehow merged over from the rich_predicted_state branch. 2020-11-09 11:14:11 +00:00
Jonathan Woodruff
69c697daf7 Changes needed to build for FPGA. 2020-11-06 11:44:33 +00:00
Peter Rugg
bf77ac74ba Fix performance reporting requests for multicore 2020-11-04 12:11:31 +00:00
Peter Rugg
61b88ef987 Generate elf files the correct size 2020-11-02 11:23:07 +00:00
Marno van der Maas
328592b068 Added missing slash in readme 2020-10-29 15:45:17 +00:00
PeterRugg
844bfd5e79 Merge pull request #5 from nwf/capdirty
Add CHERI PTE CapDirty flag
2020-10-02 17:17:24 +01:00
Marno van der Maas
ed9541e8d0 Put all dirs for source description in code blocks 2020-10-02 13:09:51 +01:00
Nathaniel Filardo
d4308f0f03 Slightly rework CHERI PTE to add CapDirty flag
Permissions are consistently checked before dirty flags, now, too.
2020-09-30 15:40:50 +01:00
jon
00ffdd7228 Enable to build with latest BSC compiler. 2020-08-11 14:46:28 +01:00
jon
8896bb27f1 Revert "Remove the special flush from the Fetch3 stage."
This reverts commit 4fe24c9cd5.
2020-07-29 11:40:00 +01:00
jon
4fe24c9cd5 Remove the special flush from the Fetch3 stage.
This is an intermediate simplification for moving to SupFifo-based picking.
2020-07-29 07:40:15 +01:00
Peter Rugg
3132f9f55f Trap when writing PCC, rather than silently ignoring 2020-07-28 12:57:13 +01:00
Jessica Clarke
73dedec309 FetchStage: Use map rather than for loop
Also add some spaces in the following line.
2020-07-24 20:02:10 +01:00
Jessica Clarke
0b3ad23c24 Fix typo 2020-07-24 19:10:11 +01:00
Jessica Clarke
1bad5b080b Various updates to README.md
* Fix the arch string
 * Document the RVFI-DII build directories
 * Don't tell people to build RTL using them
 * Bluesim build configurations exist
2020-07-24 19:06:56 +01:00
Jessica Clarke
44d49a52c0 Drop removed CHERI directory from README.md (Closes: #3)
27947f4df7 moved the SCRs into the main
CSR register file, and that was the only thing in this directory.
2020-07-24 18:47:26 +01:00
jon
40af067a71 Fix RVFI_DII build in the presence of 2-byte bundles. 2020-07-24 17:30:29 +01:00
jon
1f968b0c07 2-byte aligned instruction memory to simplify compressed instruction
fetch.
2020-07-24 12:38:37 +01:00
Peter Rugg
ecce475b97 Merge branch 'mem_perm_checks' into CHERI 2020-07-23 16:53:14 +01:00
Peter Rugg
27082ee2a9 Report writes to PCC as illegal instruction, not ASR violation 2020-07-23 15:40:28 +01:00
Peter Rugg
97d89086a6 Bump cheri-cap-lib 2020-07-23 11:20:30 +01:00
Peter Rugg
e8aa873c2e Prevent 'insufficient type info' warning 2020-07-23 11:18:31 +01:00
Peter Rugg
a6b40e946b Prevent using CCSeal to 'seal over' other types 2020-07-23 11:18:07 +01:00
Peter Rugg
c693462f6b Add tag-clearing due to cap load perm and PTE bits 2020-07-22 15:54:49 +01:00
Peter Rugg
0040b05ada Add page table cap store checking 2020-07-21 16:02:37 +01:00
Jessica Clarke
2f4f5ca838 FetchStage: Reduce diff to upstream 2020-07-21 14:36:36 +01:00
Jessica Clarke
0516db5e8d Bump BSV-RVFI-DII and refactor to support new parcel-based interface
This means FetchStage should now behave in the same way with RVFI-DII as
with an I-Cache. A Dii_Parcel_Id is fed alongside PC everywhere relevant
and follows very similar logic, but, importantly it's just extra state
on the side, it doesn't affect what we do with the branch predictor and
parcel combining/instruction decoding logic.
2020-07-21 14:36:36 +01:00
jon
7d98946103 Working compressed instruction support. 2020-07-20 19:49:52 +01:00
jon
d7a4d3497b Keep unaligned instruction fetch from breaking DII. 2020-07-17 16:39:13 +01:00
jon
4d2f971767 Assign the correct PC to fetched instructions. 2020-07-17 11:07:19 +01:00
Jessica Clarke
72f49a1109 Regenerate verilog 2020-07-16 19:35:51 +01:00
Jessica Clarke
2b8e5f1dad FetchStage: Inline unnecessary local variable 2020-07-16 18:13:43 +01:00
Peter Rugg
a74596c956 Fix CCall being impossible
The cap to be checked (rs1) was being overwritten with the unsealed jump
target before the type was checked
2020-07-16 14:06:26 +01:00
Jessica Clarke
5efd7d5cd8 Partially bring back tval
We need this to determine which 16b parcel of a 32b instruction caused
the fault (omitting this caused rv64uc-v-rvc to fail).
2020-07-15 04:27:25 +01:00
Jessica Clarke
682ff10d72 Regenerate verilog 2020-07-15 03:16:24 +01:00
Jessica Clarke
7eff218288 Replace enums-for-constants with structs wrapping a plain Bit#(n)
BSC does not play nicely with enums whose labels do not start at 0 and
increase linearly. Instead, in such cases, it generates a whole bunch of
conditions to "legalise" any read values, which causes an explosion of
logic in places like the ROB. Thus, use this ugly (but still typed)
alternative that, other than naming conventions enforced by BSC, looks
almost the same as an enum.
2020-07-15 03:16:24 +01:00
Jessica Clarke
b65576b112 Copy TAP file generation code from Flute 2020-07-15 03:16:24 +01:00
Peter Rugg
b44a912756 Don't require ASR to read PCC
The dInst.scr field was accidentally left populated in this case,
causing the check to occur
2020-07-14 22:41:51 +01:00
Jessica Clarke
e8c1de7793 Regenerate verilog 2020-07-14 19:01:47 +01:00
Jessica Clarke
956c9686a6 src_SSITH_P3: Optimise unspecified values
We have a lot of ?s floating around that needlessly constrain logic. As
with Flute, enable optimisations on these in the hope that timing and/or
area improve further.
2020-07-14 17:53:01 +01:00
Jessica Clarke
6356d5f8a1 Drop check against whether the ROB row already has a trap
The only other thing setting this is enq, but RenameStage marks
already-trapping instuctions as Executed so they should never go to the
ALU.
2020-07-14 16:46:29 +01:00
Jessica Clarke
f2d9c78824 Drop unused exception parameter on FPU ROB ports
This gives traceBundle its own set of ports. Also fix the nonsensical
calculations for those Ehr ports; the number of FPUs should not be
calculated as ALUs/2!
2020-07-14 16:37:59 +01:00
Jessica Clarke
0b7d635cbf Drop unused store_data/store_data_BE arguments when TV is disabled 2020-07-14 16:23:10 +01:00
Jessica Clarke
5a42b0102a Turn pc back into a Reg
This is from before we fed bounds all the way back to the BTB and RAS.
We no longer need this and can go back to what upstream does.
2020-07-14 16:22:52 +01:00
Jessica Clarke
9bdf71ee4e Only store the actual address for completed loads/stores
This is only needed for RVFI tracing and for xtval if we trap, so we
never need the full capability.
2020-07-14 16:22:50 +01:00
Peter Rugg
675caad0ac Trap for permission failures on mem access 2020-07-14 15:34:38 +01:00
Jessica Clarke
e89f7a8130 Regenerate verilog 2020-07-13 18:54:53 +01:00
Jessica Clarke
26a5376f9c FetchStage: Tidy up comment that no longer applies
Block is now entirely for debugging only.
2020-07-13 18:23:01 +01:00
jon
83b734ed87 Remove commented-out code. 2020-07-13 18:20:56 +01:00