summaryrefslogtreecommitdiff
path: root/src/arch/riscv
diff options
context:
space:
mode:
authorGabe Black <gabeblack@google.com>2017-12-22 01:07:55 -0800
committerGabe Black <gabeblack@google.com>2017-12-22 23:16:03 +0000
commitb7618c69a511e3fde5cdb674a91e5683f92e770f (patch)
treee7f472f1014db9e41a98a5b7df759d88db917742 /src/arch/riscv
parent4ac0a01e2fdeee8f17d15636409acd7208d9187e (diff)
downloadgem5-b7618c69a511e3fde5cdb674a91e5683f92e770f.tar.xz
arch,cpu: "virtualize" the TLB interface.
CPUs have historically instantiated the architecture specific version of the TLBs to avoid a virtual function call, making them a little bit more dependent on what the current ISA is. Some simple performance measurement, the x86 twolf regression on the atomic CPU, shows that there isn't actually any performance benefit, and if anything the simulator goes slightly faster (although still within margin of error) when the TLB functions are virtual. This change switches everything outside of the architectures themselves to use the generic BaseTLB type, and then inside the ISA for them to cast that to their architecture specific type to call into architecture specific interfaces. The ARM TLB needed the most adjustment since it was using non-standard translation function signatures. Specifically, they all took an extra "type" parameter which defaulted to normal, and translateTiming returned a Fault. translateTiming actually doesn't need to return a Fault because everywhere that consumed it just stored it into a structure which it then deleted(?), and the fault is stored in the Translation object when the translation is done. A little more work is needed to fully obviate the arch/tlb.hh header, so the TheISA::TLB type is still visible outside of the ISAs. Specifically, the TlbEntry type is used in the generic PageTable which lives in src/mem. Change-Id: I51b68ee74411f9af778317eff222f9349d2ed575 Reviewed-on: https://gem5-review.googlesource.com/6921 Maintainer: Gabe Black <gabeblack@google.com> Reviewed-by: Jason Lowe-Power <jason@lowepower.com>
Diffstat (limited to 'src/arch/riscv')
-rw-r--r--src/arch/riscv/tlb.cc7
-rw-r--r--src/arch/riscv/tlb.hh16
2 files changed, 7 insertions, 16 deletions
diff --git a/src/arch/riscv/tlb.cc b/src/arch/riscv/tlb.cc
index c47260e76..0c5962ece 100644
--- a/src/arch/riscv/tlb.cc
+++ b/src/arch/riscv/tlb.cc
@@ -341,13 +341,6 @@ TLB::translateTiming(RequestPtr req, ThreadContext *tc,
}
Fault
-TLB::translateFunctional(RequestPtr req, ThreadContext *tc, Mode mode)
-{
- panic("Not implemented\n");
- return NoFault;
-}
-
-Fault
TLB::finalizePhysical(RequestPtr req, ThreadContext *tc, Mode mode) const
{
return NoFault;
diff --git a/src/arch/riscv/tlb.hh b/src/arch/riscv/tlb.hh
index 92d66f137..ce63fd33a 100644
--- a/src/arch/riscv/tlb.hh
+++ b/src/arch/riscv/tlb.hh
@@ -111,15 +111,13 @@ class TLB : public BaseTLB
void regStats() override;
- Fault translateAtomic(RequestPtr req, ThreadContext *tc, Mode mode);
- void translateTiming(RequestPtr req, ThreadContext *tc,
- Translation *translation, Mode mode);
-
- /** Function stub for CheckerCPU compilation issues. RISC-V does not
- * support the Checker model at the moment.
- */
- Fault translateFunctional(RequestPtr req, ThreadContext *tc, Mode mode);
- Fault finalizePhysical(RequestPtr req, ThreadContext *tc, Mode mode) const;
+ Fault translateAtomic(
+ RequestPtr req, ThreadContext *tc, Mode mode) override;
+ void translateTiming(
+ RequestPtr req, ThreadContext *tc,
+ Translation *translation, Mode mode) override;
+ Fault finalizePhysical(
+ RequestPtr req, ThreadContext *tc, Mode mode) const override;
private:
Fault translateInst(RequestPtr req, ThreadContext *tc);