[llvm] [AArch64][SME] Fix restoring callee-saves from FP with hazard padding (PR #143371)

[Eli Friedman via llvm-commits]

================
@@ -3143,3 +3143,833 @@ entry:
   call void @bar(ptr noundef nonnull %b)
   ret i32 0
 }
+
+
+define i32 @svecc_call_dynamic_alloca(<4 x i16> %P0, i32 %P1, i32 %P2, <vscale x 16 x i8> %P3, i16 %P4) "aarch64_pstate_sm_compatible" {
+; CHECK0-LABEL: svecc_call_dynamic_alloca:
+; CHECK0:       // %bb.0: // %entry
+; CHECK0-NEXT:    stp x29, x30, [sp, #-64]! // 16-byte Folded Spill
+; CHECK0-NEXT:    .cfi_def_cfa_offset 64
+; CHECK0-NEXT:    cntd x9
+; CHECK0-NEXT:    stp x27, x26, [sp, #32] // 16-byte Folded Spill
+; CHECK0-NEXT:    stp x9, x28, [sp, #16] // 16-byte Folded Spill
+; CHECK0-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
+; CHECK0-NEXT:    mov x29, sp
+; CHECK0-NEXT:    .cfi_def_cfa w29, 64
+; CHECK0-NEXT:    .cfi_offset w19, -8
+; CHECK0-NEXT:    .cfi_offset w20, -16
+; CHECK0-NEXT:    .cfi_offset w26, -24
+; CHECK0-NEXT:    .cfi_offset w27, -32
+; CHECK0-NEXT:    .cfi_offset w28, -40
+; CHECK0-NEXT:    .cfi_offset w30, -56
+; CHECK0-NEXT:    .cfi_offset w29, -64
+; CHECK0-NEXT:    addvl sp, sp, #-18
+; CHECK0-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
+; CHECK0-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 64 - 8 * VG
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 64 - 16 * VG
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 64 - 24 * VG
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 64 - 32 * VG
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 64 - 40 * VG
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 64 - 48 * VG
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 64 - 56 * VG
+; CHECK0-NEXT:    .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x40, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 64 - 64 * VG
----------------
efriedma-quic wrote:

Not directly connected to this patch, but the DWARF unwind seems to be missing some registers.

https://github.com/llvm/llvm-project/pull/143371