the state should be kept in IFU to control the f2_lastHalf register

* Invalid first instuction behind half-RVI

* Using separated selection instead of f2_hit Mux.

* reason: didn't flush wait_state when backend redirect

*ICache: The address is not aligned with the cache line
*IFU: fix instruciton valids width bug

* Now can pass compiling.

[WIP] comment out-of-date code in frontend

[WIP] move NewFtq to xiangshan.frontend and rename class to Ftq

Ibuffer: update sigal names for new IFU

[WIP] remove redundant NewFrontend

[WIP] set entry_fetch_status to f_sent once send req to buf

Fix syntax error in IFU

Fix syntax error in IFU/ICache/Ibuffer

[WIP] indent fix in ftq

BPU: Move GlobalHistory define from IFU.scala to BPU.scala

[WIP] fix some compilation errors

BPU: Remove HasIFUConst
and move some bundles from BPU.scala to frontendBundle.scala

[WIP] fix some compilation errors

[WIP] rename ftq-bpu ios

[WIP] recover some const definitions

[WIP] fix some compilation errors

[WIP]connect some IOs in frontend

BPU: fix syntax error

[WIP] fix compilation errors in predecode

BPU: fix RAS syntax error

[WIP] add some simulation perf counters back

BPU: Remove numBr redefine in ubtb and bim

* CSR: add csr access check for mstatus.tvm

tvm: trap virtual Memory.
when tvm is set, r/w the satp in S-mode will raise illegal-instr

* Fence: add tvm check that may disallow sfence

when tvm is set and at s-mode, sfence.vma will raise illegal-instr

* change the number of function units in MinimalConfig
* remove some hard-wired values

This commit adds support for a parameterized scheduler. A scheduler
can be parameterized via issue and dispatch ports.

Note: other parameters have not been tested.

This commit adds an non-parameterized scheduler containing all reservation stations.
Now IntegerBlock, FloatBlock, MemBlock contain only function units.
The Schduler connects dispatch with all function units.
Parameterization to be added later.

* PTW: Repeater support multi req by RRArbiter

* ptw: add parameter to choose repeater and filter(default)

simple ci test show that: the filter is critical for perf
like mcf(5m):
  old ptw:2.38
  new ptw with repeater: 2.41
  new ptw with filter: 2.58

* better select policy timing
* unified RS enqueue ports for 4 ALUs
* wrap imm extractor into a module
* backend,rs: wrap dataArray in RawDataModuleTemplate
* should only bypass data between the same addr when allocate.valid

* The instruction behind the taken one should be invalid

1. do not allow request enter ifu_req_buf while getting flush from ifu
2. code clean ups

* flush must wait for the state machine say that instructions are valid