Merge branch 'main' into p/clang-x86-fuchsia-safestack

Author: frobtech

clang/include/clang/Driver/aarch64-mlr-for-calls-only.c renamed to clang/test/Driver/aarch64-mlr-for-calls-only.c

@@ -241,7 +241,5 @@ def json_data(self):
         return {
             "name": self.name,
             "standards": self.standards,
-            "includes": [
-                str(file) for file in sorted({COMMON_HEADER} | self.includes())
-            ],
+            "includes": sorted(str(file) for file in {COMMON_HEADER} | self.includes()),
         }

libc/utils/hdrgen/hdrgen/header.py

@@ -373,6 +373,26 @@ static void doAtomicBinOpExpansion(const RISCVInstrInfo *TII, MachineInstr &MI,
         .addReg(ScratchReg)
         .addImm(-1);
     break;
+  case AtomicRMWInst::Max:
+    BuildMI(LoopMBB, DL, TII->get(RISCV::MAX), ScratchReg)
+        .addReg(DestReg)
+        .addReg(IncrReg);
+    break;
+  case AtomicRMWInst::Min:
+    BuildMI(LoopMBB, DL, TII->get(RISCV::MIN), ScratchReg)
+        .addReg(DestReg)
+        .addReg(IncrReg);
+    break;
+  case AtomicRMWInst::UMax:
+    BuildMI(LoopMBB, DL, TII->get(RISCV::MAXU), ScratchReg)
+        .addReg(DestReg)
+        .addReg(IncrReg);
+    break;
+  case AtomicRMWInst::UMin:
+    BuildMI(LoopMBB, DL, TII->get(RISCV::MINU), ScratchReg)
+        .addReg(DestReg)
+        .addReg(IncrReg);
+    break;
   }
   BuildMI(LoopMBB, DL, TII->get(getSCForRMW(Ordering, Width, STI)), ScratchReg)
       .addReg(ScratchReg)
@@ -682,6 +702,9 @@ bool RISCVExpandAtomicPseudo::expandAtomicMinMaxOp(
     MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI,
     AtomicRMWInst::BinOp BinOp, bool IsMasked, int Width,
     MachineBasicBlock::iterator &NextMBBI) {
+  // Using MIN(U)/MAX(U) is preferrable if permitted
+  if (STI->hasPermissiveZalrsc() && STI->hasStdExtZbb() && !IsMasked)
+    return expandAtomicBinOp(MBB, MBBI, BinOp, IsMasked, Width, NextMBBI);
 
   MachineInstr &MI = *MBBI;
   DebugLoc DL = MI.getDebugLoc();

llvm/lib/Target/RISCV/RISCVExpandAtomicPseudoInsts.cpp

@@ -1906,6 +1906,25 @@ def FeatureForcedAtomics : SubtargetFeature<
 def HasAtomicLdSt
     : Predicate<"Subtarget->hasStdExtZalrsc() || Subtarget->hasForcedAtomics()">;
 
+// The RISC-V Unprivileged Architecture - ISA Volume 1 (Version: 20250508)
+// [https://docs.riscv.org/reference/isa/_attachments/riscv-unprivileged.pdf]
+// in section 13.3. Eventual Success of Store-Conditional Instructions, defines
+// _constrained_ LR/SC loops:
+//   The dynamic code executed between the LR and SC instructions can only
+//   contain instructions from the base ''I'' instruction set, excluding loads,
+//   stores, backward jumps, taken backward branches, JALR, FENCE, and SYSTEM
+//   instructions. Compressed forms of the aforementioned ''I'' instructions in
+//   the Zca and Zcb extensions are also permitted.
+// LR/SC loops that do not adhere to the above are _unconstrained_ LR/SC loops,
+// and success is implementation specific. For implementations which know that
+// non-base instructions (such as the ''B'' extension) will not violate any
+// forward progress guarantees, using these instructions to reduce the LR/SC
+// sequence length is desirable.
+def FeaturePermissiveZalrsc
+    : SubtargetFeature<
+          "permissive-zalrsc", "HasPermissiveZalrsc", "true",
+          "Implementation permits non-base instructions between LR/SC pairs">;
+
 def FeatureTaggedGlobals : SubtargetFeature<"tagged-globals",
     "AllowTaggedGlobals",
     "true", "Use an instruction sequence for taking the address of a global "