[RISCV] Add a test case to show the bug in RISCVFrameLowering.

[HsiangKai]

Summary

If the number of arguments is too large to use register passing, it
needs to occupy stack space to pass the arguments to the callee. There
are two scenarios. One is to reserve the space in prologue and the other
is to reserve the space before the function calls. When we need to
reserve the stack space before function calls, the stack pointer is
adjusted. Under the scenario, we should not use stack pointer to access
the stack objects. It looks like,

callseq_start -> sp = sp - reserved_space

We should not use SP to access stack objects in this area.
//
call @foo
callseq_end -> sp = sp + reserved_space

[frasercrmck]

LGTM. Craig's comment in D114246 has helped pinpoint the problem for me. I dunno if it's worth commenting that in the test file or not.

[HsiangKai]

Add comments.

[jrtc27]

Don't put comments in the middle of generated CHECK lines, they will be moved on the next regenerate. Though I guess if this is going to be immediately fixed in a subsequent commit maybe it's about the only time it's ok...

[HsiangKai]

In D114245#3160080, @jrtc27 wrote:

Don't put comments in the middle of generated CHECK lines, they will be moved on the next regenerate. Though I guess if this is going to be immediately fixed in a subsequent commit maybe it's about the only time it's ok...

Thanks.
I will commit this one and D114246 together. In D114246, the comments will be removed.

llvm/test/CodeGen/RISCV/rvv/no-reserved-frame.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -verify-machineinstrs \
+; RUN:   < %s | FileCheck %s
+
+define signext i32 @foo(i32 signext %aa) #0 {
+; CHECK-LABEL: foo:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    addi sp, sp, -64
+; CHECK-NEXT:    .cfi_def_cfa_offset 64
+; CHECK-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset ra, -8
+; CHECK-NEXT:    .cfi_offset s0, -16
+; CHECK-NEXT:    addi s0, sp, 64
+; CHECK-NEXT:    .cfi_def_cfa s0, 0
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    sub sp, sp, a1
+; CHECK-NEXT:    andi sp, sp, -8
+; CHECK-NEXT:    lw t0, 36(sp)
+; CHECK-NEXT:    lw a2, 32(sp)
+; CHECK-NEXT:    lw a3, 28(sp)
+; CHECK-NEXT:    lw a4, 24(sp)
+; CHECK-NEXT:    lw a5, 20(sp)
+; CHECK-NEXT:    lw a6, 16(sp)
+; CHECK-NEXT:    lw a7, 12(sp)
+; CHECK-NEXT:    lw t1, 8(sp)
+; CHECK-NEXT:    lw t2, 4(sp)
+; CHECK-NEXT:    lw a1, 0(sp)
+; CHECK-NEXT:    sw a0, 44(sp)
+; CHECK-NEXT:    sw a0, 40(sp)
+; CHECK-NEXT:    addi sp, sp, -32
+; CHECK-NEXT:    sd a1, 16(sp)
+; CHECK-NEXT:    sd t2, 8(sp)
+; CHECK-NEXT:    addi a1, sp, 40
+; This is the incorrect calculation. It's after the addi sp, sp, -32. The 40
+; doesn't consider the -32 adjustment that was made.
+; CHECK-NEXT:    sd t1, 0(sp)
+; CHECK-NEXT:    mv a0, t0
+; CHECK-NEXT:    call gfunc@plt
+; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    li a0, 0
+; CHECK-NEXT:    addi sp, s0, -64
+; CHECK-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    addi sp, sp, 64
+; CHECK-NEXT:    ret
+entry:
+  %aa.addr = alloca i32, align 4
+  %local = alloca i32, align 4
+  %a = alloca i32, align 4
+  %b = alloca i32, align 4
+  %c = alloca i32, align 4
+  %d = alloca i32, align 4
+  %e = alloca i32, align 4
+  %f = alloca i32, align 4
+  %g = alloca i32, align 4
+  %h = alloca i32, align 4
+  %i = alloca i32, align 4
+  %j = alloca i32, align 4
+  %local_v = alloca <vscale x 2 x i32>, align 4
+  store i32 %aa, i32* %aa.addr, align 4
+  %0 = load i32, i32* %aa.addr, align 4
+  store i32 %0, i32* %local, align 4
+  %1 = load i32, i32* %a, align 4
+  %2 = load i32, i32* %b, align 4
+  %3 = load i32, i32* %c, align 4
+  %4 = load i32, i32* %d, align 4
+  %5 = load i32, i32* %e, align 4
+  %6 = load i32, i32* %f, align 4
+  %7 = load i32, i32* %g, align 4
+  %8 = load i32, i32* %h, align 4
+  %9 = load i32, i32* %i, align 4
+  %10 = load i32, i32* %j, align 4
+  call void @gfunc(i32 signext %1, i32* %local, i32 signext %2, i32 signext %3, i32 signext %4, i32 signext %5, i32 signext %6, i32 signext %7, i32 %8, i32 %9, i32 %10)
+  ret i32 0
+}
+
+declare void @gfunc(i32 signext, i32*, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32 signext, i32, i32, i32) #1
+
+attributes #0 = { "stackrealign" }
+attributes #1 = { "stackrealign" }