[PATCH] D77804: [DAG] Enable ISD::SRL SimplifyMultipleUseDemandedBits handling inside SimplifyDemandedBits

[Yonghong Song via Phabricator via llvm-commits]

yonghong-song added a comment.

Hi, we found a regression with some bpf code with this patch. The following shows the problem:

  [$ ~/tmp] cat run.sh
  /home/yhs/work/llvm-project/llvm/build.cur/install/bin/clang -target bpf -O2 -g -c t.c
  [$ ~/tmp] cat t.c
  typedef unsigned char u8;
  struct event {
    u8 tag;
    u8 hostname[84];
  };
  
  void *g;
  void bar(void *);
  
  int foo() {
    struct event event = {};
  
    event.tag = 1;
    __builtin_memcpy(&event.hostname, g, 84);
    bar(&event);
    return 0;
  }
  [$ ~/tmp] ./run.sh
  t.c:14:3: error: Looks like the BPF stack limit of 512 bytes is exceeded. Please move large on stack variables into BPF per-cpu array map.
  
    __builtin_memcpy(&event.hostname, g, 84);
    ^
  t.c:14:3: error: Looks like the BPF stack limit of 512 bytes is exceeded. Please move large on stack variables into BPF per-cpu array map.
  
  2 errors generated.
  [$ ~/tmp]

The BPF program enforces the stack size <= 512 bytes. For the above program, with this patch, the code after dag insn selection is worse and eventually in register allocation stage, the stack size is more than 512 and caused the above issue.

To illustrate the problem in more details, without this patch, the lowered machine code looks like

    STB killed %7:gpr, %stack.1.event.i, 0, debug-location !21355 :: (store (s8) into %ir.event.i, align 8, !tbaa !21356); tracecon/src/bpf/tracecon.bpf.c:78:12 @[ tracecon/src/b
  pf/tracecon.bpf.c:68:5 ]
    %8:gpr = LDB %6:gpr, 7, debug-location !21358 :: (load (s8) from %ir.call1.i + 7); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %8:gpr, %stack.1.event.i, 12, debug-location !21358 :: (store (s8) into %ir.hostname.i + 7); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.
  c:68:5 ]
    %9:gpr = LDB %6:gpr, 6, debug-location !21358 :: (load (s8) from %ir.call1.i + 6); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %9:gpr, %stack.1.event.i, 11, debug-location !21358 :: (store (s8) into %ir.hostname.i + 6); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.
  c:68:5 ]
    %10:gpr = LDB %6:gpr, 5, debug-location !21358 :: (load (s8) from %ir.call1.i + 5); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %10:gpr, %stack.1.event.i, 10, debug-location !21358 :: (store (s8) into %ir.hostname.i + 5); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf
  .c:68:5 ]
    %11:gpr = LDB %6:gpr, 4, debug-location !21358 :: (load (s8) from %ir.call1.i + 4); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %11:gpr, %stack.1.event.i, 9, debug-location !21358 :: (store (s8) into %ir.hostname.i + 4); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.
  c:68:5 ]
    %12:gpr = LDB %6:gpr, 3, debug-location !21358 :: (load (s8) from %ir.call1.i + 3); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %12:gpr, %stack.1.event.i, 8, debug-location !21358 :: (store (s8) into %ir.hostname.i + 3); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.
  c:68:5 ]
    %13:gpr = LDB %6:gpr, 2, debug-location !21358 :: (load (s8) from %ir.call1.i + 2); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %13:gpr, %stack.1.event.i, 7, debug-location !21358 :: (store (s8) into %ir.hostname.i + 2); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.
  c:68:5 ]
    %14:gpr = LDB %6:gpr, 1, debug-location !21358 :: (load (s8) from %ir.call1.i + 1); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %14:gpr, %stack.1.event.i, 6, debug-location !21358 :: (store (s8) into %ir.hostname.i + 1); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.
  c:68:5 ]
    %15:gpr = LDB %6:gpr, 0, debug-location !21358 :: (load (s8) from %ir.call1.i); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %15:gpr, %stack.1.event.i, 5, debug-location !21358 :: (store (s8) into %ir.hostname.i); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68
  :5 ]
    %16:gpr = LDB %6:gpr, 15, debug-location !21358 :: (load (s8) from %ir.call1.i + 15); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %16:gpr, %stack.1.event.i, 20, debug-location !21358 :: (store (s8) into %ir.hostname.i + 15); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bp
  f.c:68:5 ]
    %17:gpr = LDB %6:gpr, 14, debug-location !21358 :: (load (s8) from %ir.call1.i + 14); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %17:gpr, %stack.1.event.i, 19, debug-location !21358 :: (store (s8) into %ir.hostname.i + 14); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bp
  f.c:68:5 ]
  ...
    %88:gpr = LDB %6:gpr, 83, debug-location !21358 :: (load (s8) from %ir.call1.i + 83); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %88:gpr, %stack.1.event.i, 88, debug-location !21358 :: (store (s8) into %ir.hostname.i + 83); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %89:gpr = LDB %6:gpr, 82, debug-location !21358 :: (load (s8) from %ir.call1.i + 82); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %89:gpr, %stack.1.event.i, 87, debug-location !21358 :: (store (s8) into %ir.hostname.i + 82); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %90:gpr = LDB %6:gpr, 81, debug-location !21358 :: (load (s8) from %ir.call1.i + 81); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %90:gpr, %stack.1.event.i, 86, debug-location !21358 :: (store (s8) into %ir.hostname.i + 81); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %91:gpr = LDB %6:gpr, 80, debug-location !21358 :: (load (s8) from %ir.call1.i + 80); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB killed %91:gpr, %stack.1.event.i, 85, debug-location !21358 :: (store (s8) into %ir.hostname.i + 80); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]

Pretty straightforward byte load and stores and the corresponding stack after register allocation,

  # *** IR Dump After Greedy Register Allocator (greedy) ***:
  # Machine code for function tcp_v4_connect_exit: NoPHIs, TracksLiveness, TiedOpsRewritten, TracksDebugUserValues
  Frame Objects:
    fi#0: size=4, align=4, at location [SP]
    fi#1: size=89, align=8, at location [SP]
    fi#2: size=4, align=4, at location [SP]
  Function Live Ins: $r1 in %0

But this patch, the code becomes very complex,

    %8:gpr = LDB %6:gpr, 71, debug-location !21358 :: (load (s8) from %ir.call1.i + 71); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %9:gpr = SLL_ri %8:gpr(tied-def 0), 8, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %10:gpr = LDB %6:gpr, 70, debug-location !21358 :: (load (s8) from %ir.call1.i + 70); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %11:gpr = OR_rr %9:gpr(tied-def 0), killed %10:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %12:gpr = LDB %6:gpr, 15, debug-location !21358 :: (load (s8) from %ir.call1.i + 15); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %13:gpr = SLL_ri %12:gpr(tied-def 0), 8, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %14:gpr = LDB %6:gpr, 14, debug-location !21358 :: (load (s8) from %ir.call1.i + 14); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %15:gpr = OR_rr %13:gpr(tied-def 0), killed %14:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
  ...
    %71:gpr = OR_rr %69:gpr(tied-def 0), killed %70:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %72:gpr = LDB %6:gpr, 77, debug-location !21358 :: (load (s8) from %ir.call1.i + 77); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %73:gpr = SLL_ri %72:gpr(tied-def 0), 8, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %74:gpr = LDB %6:gpr, 76, debug-location !21358 :: (load (s8) from %ir.call1.i + 76); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %75:gpr = OR_rr %73:gpr(tied-def 0), killed %74:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %76:gpr = LDB %6:gpr, 79, debug-location !21358 :: (load (s8) from %ir.call1.i + 79); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %77:gpr = SLL_ri %76:gpr(tied-def 0), 8, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %78:gpr = LDB %6:gpr, 78, debug-location !21358 :: (load (s8) from %ir.call1.i + 78); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %79:gpr = OR_rr %77:gpr(tied-def 0), killed %78:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %80:gpr = SLL_ri %27:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %81:gpr = OR_rr %80:gpr(tied-def 0), killed %23:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %82:gpr = SLL_ri %19:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %83:gpr = OR_rr %82:gpr(tied-def 0), killed %71:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %84:gpr = SLL_ri %15:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %85:gpr = OR_rr %84:gpr(tied-def 0), killed %67:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %86:gpr = SLL_ri %11:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %87:gpr = OR_rr %86:gpr(tied-def 0), killed %63:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %88:gpr = SLL_ri %43:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
  ...
    %100:gpr = LDB %6:gpr, 74, debug-location !21358 :: (load (s8) from %ir.call1.i + 74); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %101:gpr = LDB %6:gpr, 75, debug-location !21358 :: (load (s8) from %ir.call1.i + 75); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %102:gpr = SLL_ri %101:gpr(tied-def 0), 8, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %103:gpr = OR_rr %102:gpr(tied-def 0), %100:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %104:gpr = SLL_ri %103:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %105:gpr = OR_rr %104:gpr(tied-def 0), killed %99:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %106:gpr = SLL_ri %79:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %107:gpr = OR_rr %106:gpr(tied-def 0), killed %75:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %108:gpr = LDB %6:gpr, 64, debug-location !21358 :: (load (s8) from %ir.call1.i + 64); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %109:gpr = LDB %6:gpr, 65, debug-location !21358 :: (load (s8) from %ir.call1.i + 65); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %110:gpr = SLL_ri %109:gpr(tied-def 0), 8, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %111:gpr = OR_rr %110:gpr(tied-def 0), %108:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %112:gpr = LDB %6:gpr, 66, debug-location !21358 :: (load (s8) from %ir.call1.i + 66); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %113:gpr = LDB %6:gpr, 67, debug-location !21358 :: (load (s8) from %ir.call1.i + 67); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %114:gpr = SLL_ri %113:gpr(tied-def 0), 8, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %115:gpr = OR_rr %114:gpr(tied-def 0), %112:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %116:gpr = SLL_ri %115:gpr(tied-def 0), 16, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %117:gpr = OR_rr %116:gpr(tied-def 0), killed %111:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
  ...
    %225:gpr = OR_rr %224:gpr(tied-def 0), killed %117:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %226:gpr = SLL_ri %107:gpr(tied-def 0), 32, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    %227:gpr = OR_rr %226:gpr(tied-def 0), killed %105:gpr, debug-location !21358; tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB %193:gpr, %stack.1.event.i, 8, debug-location !21358 :: (store (s8) into %ir.hostname.i + 3); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5
   ]
    STB %192:gpr, %stack.1.event.i, 7, debug-location !21358 :: (store (s8) into %ir.hostname.i + 2); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB %189:gpr, %stack.1.event.i, 6, debug-location !21358 :: (store (s8) into %ir.hostname.i + 1); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB %188:gpr, %stack.1.event.i, 5, debug-location !21358 :: (store (s8) into %ir.hostname.i); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68:5 ]
    STB %183:gpr, %stack.1.event.i, 16, debug-location !21358 :: (store (s8) into %ir.hostname.i + 11); tracecon/src/bpf/tracecon.bpf.c:79:2 @[ tracecon/src/bpf/tracecon.bpf.c:68
  :5 ]
  ...

And the code becomes very complex and inefficient and this caused later larger stack size,

  # *** IR Dump After Greedy Register Allocator (greedy) ***:
  # Machine code for function tcp_v4_connect_exit: NoPHIs, TracksLiveness, TiedOpsRewritten, TracksDebugUserValues
  Frame Objects:
    fi#0: size=4, align=4, at location [SP]
    fi#1: size=89, align=8, at location [SP]
    fi#2: size=4, align=4, at location [SP]
    fi#3: size=8, align=8, at location [SP]
  ...
    fi#57: size=8, align=8, at location [SP]
    fi#58: size=8, align=8, at location [SP]
    fi#59: size=8, align=8, at location [SP]
    fi#60: size=8, align=8, at location [SP]
  Function Live Ins: $r1 in %0

Could you help take a look at this problem and suggest how to fix it?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D77804/new/

https://reviews.llvm.org/D77804