8000 [LA64_DYNAREC] Fixed LOCK XCHG byte opcode fallback path by ksco · Pull Request #1519 · ptitSeb/box64 · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

[LA64_DYNAREC] Fixed LOCK XCHG byte opcode fallback path #1519

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 22, 2024
Merged

[LA64_DYNAREC] Fixed LOCK XCHG byte opcode fallback path #1519

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
86c209d
[LA64_DYNAREC] Fixed LOCK XCHG byte opcode fallback path
ksco May 22, 2024
40ac3a6
fix
ksco May 22, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 34 additions & 4 deletions src/dynarec/la64/dynarec_la64_00.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -772,7 +772,7 @@ uintptr_t dynarec64_00(dynarec_la64_t* dyn, uintptr_t addr, uintptr_t ip, int ni
emit_test32(dyn, ninst, rex, ed, gd, x3, x4, x5);
break;
case 0x86:
INST_NAME("(LOCK)XCHG Eb, Gb");
INST_NAME("(LOCK) XCHG Eb, Gb");
nextop = F8;
if (MODREG) {
GETGB(x1);
Expand All @@ -786,9 +786,39 @@ uintptr_t dynarec64_00(dynarec_la64_t* dyn, uintptr_t addr, uintptr_t ip, int ni
AMSWAP_DB_B(x1, gd, ed);
else {
SMDMB();
LD_BU(x1, ed, 0);
ST_B(gd, ed, 0);
SMDMB();

// calculate shift amount
ANDI(x1, ed, 0x3);
SLLI_D(x1, x1, 3);

// align address to 4-bytes to use ll.w/sc.w
ADDI_D(x4, xZR, 0xffc);
AND(x6, ed, x4);

// load aligned data
LD_WU(x5, x6, 0);

// insert gd byte into the aligned data
ADDI_D(x4, xZR, 0xff);
SLL_D(x4, x4, x1);
NOR(x4, x4, xZR);
AND(x4, x5, x4);
SLL_D(x5, gd, x1);
OR(x4, x4, x5);

// do aligned ll/sc sequence
MARKLOCK;
LL_W(x1, x6, 0);
MV(x5, x4);
SC_W(x5, x6, 0);
BEQZ_MARKLOCK(x5);

// calculate shift amount again
ANDI(x4, ed, 0x3);
SLLI_D(x4, x4, 3);

// extract loaded byte
SRL_D(x1, x1, x4);
}
BSTRINS_D(gb1, x1, gb2 + 7, gb2);
}
Expand Down
0