1
0
Commit Graph

226 Commits

Author SHA1 Message Date
Andrew Waterman
05cbdced78 Work around zero-entry vec issue in Chisel 2017-03-27 17:57:26 -07:00
Andrew Waterman
d42d8aaea7 Make SEIP writable 2017-03-27 16:37:09 -07:00
Andrew Waterman
c7c357e716 Add local interrupts to core (but not yet to coreplex) 2017-03-27 16:37:09 -07:00
Andrew Waterman
069858a20c rocket: separate page faults from physical memory access exceptions 2017-03-27 16:37:09 -07:00
Andrew Waterman
ea0714bfcb rocket: hard-wire UXL/SXL fields to 0
a2a3346e73
2017-03-27 16:37:09 -07:00
Wesley W. Terpstra
75eba294ec DCache: Release from the correct ID as well 2017-03-27 16:30:46 -07:00
Wesley W. Terpstra
4959771c97 Revert "For D$, use source 0 through N-1 for MMIO, not 1 through N"
This reverts commit 0538dc77ce.
2017-03-27 16:30:46 -07:00
Wesley W. Terpstra
fa7ead6357 Revert "Use Reg(Vec) instead of Seq(Reg) for DCache MMIO"
This reverts commit fb6498f2c3.
2017-03-27 16:30:46 -07:00
Megan Wachs
08c4f7cea6 RocketTile: Create a wrapper for SyncRocketTile as well (#616)
* RocketTile: Create a wrapper for SyncRocketTile as well

There is no guarantee that debugInterrupt is synchronous
to tlClk, even though it is true in the current implementation.
It will not be true in future implementations, as decoupling
this allows the debugInterrupt to be asserted across tlClk
gating/reset scenarios.

Therefore, even for SyncRocketTile, the debug interrupt needs to be
synchronized to coreClk, and for RationalRocketTile, 1 cycle
of synchronization is not sufficient.

Even though other interrupts may be synchronized, we just
synchronize them all to simplify the code at the expense of
a few cycles latency.

It could still be nice to use a parameter vs hard coding "3".

* RocketTile: Actually use the SyncRocketTile wrapper to get properly synchronized resets.
2017-03-27 02:45:37 -07:00
Andrew Waterman
5d1165c850 Express PMP mask generator using a carry chain
This allows it to be optimized like an adder, improving QoR when it
is on the critical path.
2017-03-26 14:20:16 -07:00
Henry Cook
996a31364a rocket: remove hard-coded paddrBits (#610)
Fall back on global variable but check that it is compatible with memory as seen from rocket's tilelink master port.
2017-03-24 22:30:18 -07:00
Andrew Waterman
17b1ee3037 Default to 8 PMPs; support 0 PMPs 2017-03-24 16:39:52 -07:00
Andrew Waterman
97006ab396 Don't modulate PMP privilege on passsthrough when !usingVM 2017-03-24 16:39:52 -07:00
Andrew Waterman
3f0d2fe826 Instantiate PTW unconditionally
This keeps the PMP datapaths intact.  The PTW itself will get optimized
away for the !usingVM case.
2017-03-24 16:39:52 -07:00
Andrew Waterman
30415215b8 Don't check for exceptions on ScratchpadSlavePort accesses 2017-03-24 16:39:52 -07:00
Andrew Waterman
ccd5bc9a91 Improve QoR of PMP homogeneity checker 2017-03-24 16:39:52 -07:00
Andrew Waterman
e9cadf29d2 Improve DCache MMIO QoR
No need to store the cmd field.  From the perspective of the cache, all
MMIO responses that have data can be treated the same as loads.
2017-03-24 16:39:52 -07:00
Andrew Waterman
fb6498f2c3 Use Reg(Vec) instead of Seq(Reg) for DCache MMIO 2017-03-24 16:39:52 -07:00
Andrew Waterman
0538dc77ce For D$, use source 0 through N-1 for MMIO, not 1 through N
This makes the code a bit cleaner.
2017-03-24 16:39:52 -07:00
Andrew Waterman
3951e57789 Force each TLB entry into its own clock-gate group
This ameliorates a PMP critical path.

I can't figure out how to do this without asUInt/asTypeOf.
2017-03-24 16:39:52 -07:00
Andrew Waterman
8d7f1d777e Fix an embarrassing typo in the PMPHeterogeneityChecker 2017-03-24 16:39:52 -07:00
Andrew Waterman
10c39cb8d6 Disable mprv in D-mode 2017-03-24 16:39:52 -07:00
Andrew Waterman
d3bda9574c Put page homogeneity checker in PMP
Avoids redundancy between ITLB and DTLB
2017-03-24 16:39:52 -07:00
Andrew Waterman
9e05200e51 Don't require that PMP ranges be aligned to access size
e.g., if a range permits access to 0x0-0xb, allow 8-byte accesses 0x0-0x7.
2017-03-24 16:39:52 -07:00
Andrew Waterman
29e67279ba add comments 2017-03-24 16:39:52 -07:00
Andrew Waterman
4c8be13a4d Improve homogeneity circuit QoR 2017-03-24 16:39:52 -07:00
Andrew Waterman
59d6afa132 mideleg/medeleg not present without less-privileged traps 2017-03-24 16:39:52 -07:00
Andrew Waterman
38808f55d5 Share PMP mask gen between I$ and D$ 2017-03-24 16:39:52 -07:00
Andrew Waterman
86d84959cf More WIP on PMP 2017-03-24 16:39:52 -07:00
Andrew Waterman
2888779422 Flush pipeline from WB stage, not MEM
Fixes sptbr write -> instruction translation hazard.
2017-03-24 16:39:52 -07:00
Andrew Waterman
44ca3b60ab Retime PTW response valid bits
It's not just to save the gate delay; it also reduces wire delay by
allowing the flops to be closer to their respective TLBs.
2017-03-24 16:39:52 -07:00
Andrew Waterman
a03556220c Default TLB size = 32
@davidbiancolin
2017-03-24 16:39:52 -07:00
Andrew Waterman
1875407316 Get TLB permission checks off D$ clock gating critical path 2017-03-24 16:39:52 -07:00
Andrew Waterman
a4164348b4 Expose MXR to S-mode 2017-03-24 16:39:52 -07:00
Andrew Waterman
0380aed329 PUM -> SUM 2017-03-24 16:39:52 -07:00
Andrew Waterman
29414f3a23 Simplify interrupt-stack discipline
f2ed45b179
2017-03-24 16:39:52 -07:00
Andrew Waterman
723352c3e2 Mitigate some more PMP critical paths 2017-03-24 16:39:52 -07:00
Andrew Waterman
7484f27ed3 Don't gate exception-cause pipeline registers separately
They are too narrow to justify gating separately from the other pipeline
registers (and one of the clock gates was on the PMP critical path).
2017-03-24 16:39:52 -07:00
Andrew Waterman
487b8db5ef Address some PMP critical paths 2017-03-24 16:39:52 -07:00
Andrew Waterman
03fb334c4c Take mprv calculation off critical path 2017-03-24 16:39:52 -07:00
Andrew Waterman
f0796f0509 Pass correct access size information to PMP checker 2017-03-24 16:39:52 -07:00
Andrew Waterman
a6874c03f7 Remove DecoupledTLB 2017-03-24 16:39:52 -07:00
Andrew Waterman
78f9f6b9ef When SFENCE.VMA has rs2 != x0, don't flush global mappings 2017-03-24 16:39:52 -07:00
Andrew Waterman
1b950128e1 PTW should always use S-mode privilege
If an exception occurs while a page-table walk is coincidentally in
progress (e.g., an illegal instruction executes during data TLB refill),
then the processor might enter M-mode.  However, the PTW's accesses
should proceed without M privilege, to avoid bypassing PMPs.

Note, the same argument doesn't apply to the nonblocking cache's replay
queues, because those accesses have already been checked against the PMPs.
The cache correctly ignores access exceptions reported on replays,
provided no exceptions were reported on the initial access.
2017-03-24 16:39:52 -07:00
Andrew Waterman
aace526857 WIP on PMP 2017-03-24 16:39:52 -07:00
Andrew Waterman
b1b405404d Set PRV=M when entering debug mode
Debug mode mostly behaves like M-mode, so this approach avoids having
to check the debug bit in most permission checks.
2017-03-24 16:39:52 -07:00
Andrew Waterman
cf168e419b Support SFENCE.VMA rs1 argument
This one's a little invasive.  To flush a specific entry from the TLB, you
need to reuse its CAM port.  Since the TLB lookup can be on the critical
path, we wish to avoid muxing in another address.

This is simple on the data side, where the datapath already carries rs1 to
the TLB (it's the same path as the AMO address calculation).  It's trickier
for the I$, where the TLB lookup address comes from the fetch stage PC.
The trick is to temporarily redirect the PC to rs1, then redirect the PC
again to the instruction after SFENCE.VMA.
2017-03-24 16:39:52 -07:00
Henry Cook
055b8ba1f0 rocket: avoid LinkedHashMap.keys to preserve traversal order (#603) 2017-03-22 14:38:33 -07:00
Andrew Waterman
3609254e4a There's no structural hazard on MMIO store responses
So don't stall as though there were.
2017-03-21 14:17:32 -07:00
Yunsup Lee
5eae7e1da4 make DCache s1_nack less conservative for pipelined MMIO requests 2017-03-21 11:16:51 -07:00
Wesley W. Terpstra
4c00066746 rocket: describe dcache as two clients (fifo+cached) 2017-03-21 11:16:51 -07:00
Wesley W. Terpstra
278f6fea24 tilelink2: define is{Request,Response} based on spec 2017-03-20 13:41:02 -07:00
Wesley W. Terpstra
0c92283a61 rocket icache: tie off b ready 2017-03-19 17:18:50 -07:00
Andrew Waterman
d6f571cbbb Implement mstatus.TSR 2017-03-13 14:50:06 -07:00
Andrew Waterman
1fea0460ba Support superpage entries in TLB 2017-03-13 14:50:06 -07:00
Andrew Waterman
2d267b4940 Support corner cases in TLBPermissions
Don't crap out if the yes-set or no-set is empty.
2017-03-13 14:50:06 -07:00
Wesley W. Terpstra
c847559853 TLB: add a helper API to determine homogeneous page permissions 2017-03-13 14:50:06 -07:00
Henry Cook
dbc8f4b30b last => done 2017-03-10 15:58:38 -08:00
Andrew Waterman
380c10f7bd Zap conflicting TLB entries, preparing for superpage support
Superpages create the possibility that two entries in the TLB may match.
This corresponds to a software bug, but we can't return complete garbage;
we must return either the old translation or the new translation.  This
isn't compatible with the Mux1H approach.  So, flush the TLB and report
a miss on duplicate entries.
2017-03-10 15:58:23 -08:00
Andrew Waterman
b24c43badb Don't double-count release traffic in perfctrs 2017-03-09 16:49:02 -08:00
Andrew Waterman
4f8f05d635 Add performance counter facility 2017-03-09 13:58:50 -08:00
Andrew Waterman
24a2278fc4 Perform all illegal-instruction detection in ID stage
This is simpler, reduces what would have become a critical path in
the commit stage, and will make it easier to support the mbadinst
CSR if it is implemented.
2017-03-09 11:29:51 -08:00
Andrew Waterman
7668827741 Support unrolling the integer divider 2017-03-09 11:29:51 -08:00
Andrew Waterman
74d8d672bf Improve BTB critical path at slight accuracy cost
Make entries fully associative on lower 14 bits only, not full address.
2017-03-09 11:29:51 -08:00
Andrew Waterman
11c8857b5d Don't re-read I$ RAMs on stall 2017-03-09 11:29:51 -08:00
Andrew Waterman
db0a02b78e WIP on priv-1.10 2017-03-09 11:29:51 -08:00
Wesley W. Terpstra
43dea38ee9 dcache: we need the bits within the beat so select the right word (#575)
We now have confirmation that it fixed the problem.
2017-03-08 00:19:09 -08:00
Henry Cook
d0ae087587 rocket: allow scratchpad address to be configurable (#570) 2017-03-06 21:35:45 -08:00
Wesley W. Terpstra
676974281a rocket: describe dcache scratchpad as memory 2017-03-03 02:54:48 -08:00
Wesley W. Terpstra
8e4f348dda rocket: if no MMU, don't print it in DTS 2017-03-03 00:48:26 -08:00
Wesley W. Terpstra
4535de2669 rocket: use diplomatic interrupts
This makes it possible for the PLIC to work with heterogenous cores.
2017-03-02 21:19:23 -08:00
Wesley W. Terpstra
5bd9f18e5b rocket: add dts cpu description 2017-03-02 21:19:22 -08:00
Wesley W. Terpstra
fd972f5c67 icache: back-pressure is unnecessary (#564)
* icache: back-pressure is unnecessary
* icache: require that the response arrives after the request
2017-02-24 21:01:56 -08:00
Wesley W. Terpstra
3931b0faff coreplex: assume L1 runs no slower than L2 2017-02-17 15:15:41 +01:00
Henry Cook
e8c8d2af71 Heterogeneous Tiles (#550)
Fundamental new features:

* Added tile package: This package is intended to hold components re-usable across different types of tile. Will be the future location of TL2-RoCC accelerators and new diplomatic versions of intra-tile interfaces.
* Adopted [ModuleName]Params convention: Code base was very inconsistent about what to name case classes that provide parameters to modules. Settled on calling them [ModuleName]Params to distinguish them from config.Parameters and config.Config. So far applied mostly only to case classes defined within rocket and tile.
* Defined RocketTileParams: A nested case class containing case classes for all the components of a tile (L1 caches and core). Allows all such parameters to vary per-tile.
* Defined RocketCoreParams: All the parameters that can be varied per-core.
* Defined L1CacheParams: A trait defining the parameters common to L1 caches, made concrete in different derived case classes.
* Defined RocketTilesKey: A sequence of RocketTileParams, one for every tile to be created.
* Provided HeterogeneousDualCoreConfig: An example of making a heterogeneous chip with two cores, one big and one little.
* Changes to legacy code: ReplacementPolicy moved to package util. L1Metadata moved to package tile. Legacy L2 cache agent removed because it can no longer share the metadata array implementation with the L1. Legacy GroundTests on life support.

Additional changes that got rolled in along the way:

* rocket: 	Fix critical path through BTB for I$ index bits > pgIdxBits
* coreplex: tiles connected via :=*
* groundtest: updated to use TileParams
* tilelink: cache cork requirements are relaxed to allow more cacheless masters
2017-02-09 13:59:09 -08:00
Andrew Waterman
8225676a86 For FMIN(sNaN, x) and FMIN(qNaN, qNaN), return canonical NaN
See https://github.com/riscv/riscv-isa-sim/issues/76
2017-02-02 11:55:08 -08:00
Andrew Waterman
75edf42323 Set xPIE=1 on xRET
We were setting xPIE=0 instead.  This is a benign bug, but still a bug.
2017-02-02 11:55:08 -08:00
Wesley W. Terpstra
9ca8f514c0 rocket: creating Bundles in an object also break dedup! 2017-01-31 14:45:11 -08:00
Wesley W. Terpstra
e5af59db68 rocketchip: work-around ucb-bar/chisel3#472 2017-01-31 14:20:02 -08:00
Wesley W. Terpstra
972953868c uncore: switch to new diplomacy Node API
Most adapters should work on multiple ports.
This patch changes them all.
2017-01-29 15:54:45 -08:00
Wesley W. Terpstra
03f2fe02ac coreplex: support rational crossing to L2 (#534) 2017-01-27 17:09:43 -08:00
Wesley W. Terpstra
5d70265e86 rocket: L1 only needs cache-line transfer sizes 2017-01-19 19:07:14 -08:00
Wesley W. Terpstra
bf7823f1c8 tilelink2: split suportsAcquire into T and B variants 2017-01-19 19:07:13 -08:00
Henry Cook
c1b7c84f09 [rocket] bugfix: RoccExampleConfig looks up PAddrBits too early 2017-01-19 17:48:04 -08:00
Henry Cook
307f938b88 [rocket] bugfix: fixes #517 2017-01-19 17:48:04 -08:00
Henry Cook
74b6a8d02b Refactor Tile to use cake pattern (#502)
* [rocket] Refactor Tile into cake pattern with traits
* [rocket] cacheDataBits &etc in HasCoreParameters
* [rocket] pass TLEdgeOut implicitly rather than relying on val edge in HasCoreParameters
* [rocket] frontend and icache now diplomatic
* [rocket] file name capitalization
* [rocket] re-add hook for inserting externally-defined Cores
* [rocket] add FPUCoreIO
* [groundtest] move TL1 Config instances to where they are used
* [unittest] remove legacy unit tests
* [groundtest] remove legacy device tests
2017-01-16 18:24:08 -08:00
Andrew Waterman
71c4b000b3 Don't special-case power-of-2 replacement policy for BTB
PLRU wasn't implemented correctly for the BTB, since it wasn't
increasing the priority on replacement, only on usage.  Regardless,
this should be a second-order effect, so using FIFO always is fine.
2017-01-11 13:21:55 -08:00
Henry Cook
540502f96d Convert frontend and icache to diplomacy/tl2 (#486)
* [rocket] file capitalization

* [rocket] cacheDataBits &etc in HasCoreParameters

* [rocket] pass TLEdgeOut implicitly rather than relying on val edge in HasCoreParameters

* [rocket] frontend and icache now diplomatic
2016-12-12 17:38:55 -08:00
Wesley W. Terpstra
020fbe8be9 diplomacy: make config.Parameters available in bundle connect()
This makes it posisble to use Parameters to control Monitors.
However, we need to make all LazyModules carry Parameters.
2016-12-07 12:24:01 -08:00
Andrew Waterman
915697cb09 Fix FEQ flag generation (#479)
FEQ is not a signaling comparison (i.e., qNaN is not an invalid input).

Also, minor code cleanup.
2016-12-06 11:54:29 -08:00
Schuyler Eldridge
36fe024671 CacheName no longer needed in RoCCInterface
With dcacheParams passed to a RoCC, the CacheName no longer needs to be
specified.
2016-12-04 19:01:39 -08:00
Schuyler Eldridge
624db2034b Make instantiated RoCC use dcacheParams 2016-12-04 19:01:39 -08:00
Wesley W. Terpstra
b7963eca4e copyright: ran scripts/modify-copyright 2016-11-27 22:15:43 -08:00
Wesley W. Terpstra
4146f6a792 TLB: do not access illegal addresses (#460) 2016-11-26 15:11:42 -08:00
Wesley W. Terpstra
1e0aca7358 dcache: the high bit of s2_req.typ is the SIGN bit (not size) (#455) 2016-11-25 15:26:22 -08:00
Henry Cook
38c5af5bad [rocket] cleanup mshr logic 2016-11-23 12:09:56 -08:00
Henry Cook
dae6772624 factor out common cache subcomponents into uncore.util 2016-11-23 12:09:35 -08:00
Henry Cook
c65c255815 [coreplex] TileId moved to groundtest 2016-11-23 12:08:45 -08:00
Andrew Waterman
5f3fb64ef0 Per ABI, only x1 and x5 should be treated as function returns
We were doing so for x3 and x7, as well, which could reduce performance
for compilers that happen to perform indirect jumps via t2 (x7).
2016-11-22 12:01:05 -08:00
Wesley W. Terpstra
5fe107bb07 rocket: pass scratchpad address to block dcache 2016-11-21 21:13:26 -08:00