[PATCH 06/12] [i386] Add class xlogue_layout and new fields to struct machine_function

[Daniel Santos <daniel dot santos at pobox dot com>]

Of the new fields added to struct machine_function, call_ms2sysv is
initially set in ix86_expand_call, but may later be cleared when
ix86_compute_frame_layout is called (both of these are in subsequent
patch).  If it is not cleared, then the remaining new fields will be
set in ix86_compute_frame_layout (also a subsequent patch).

The new class xlogue_layout manages the layout of the stack area used by
the out-of-line save & restore stubs as well as any padding needed
before and after the save area.  It also provides the proper symbol rtx
for the requested stub based upon values of the new fields in struct
machine_function, which specify how many registers are being saved, what
padding is needed, etc.

xlouge_layout cannot be used until stack realign flags are finalized and
ix86_compute_frame_layout is called, at which point
xlouge_layout::get_instance may be used to retrieve the appropriate
(constant) instance of xlouge_layout.

Signed-off-by: Daniel Santos <daniel.santos@pobox.com>
---
 gcc/config/i386/i386.c | 262 +++++++++++++++++++++++++++++++++++++++++++++++++
 gcc/config/i386/i386.h |  18 ++++
 2 files changed, 280 insertions(+)

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 521116195cb..2da3da1f97a 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -93,6 +93,7 @@ static rtx legitimize_dllimport_symbol (rtx, bool);
 static rtx legitimize_pe_coff_extern_decl (rtx, bool);
 static rtx legitimize_pe_coff_symbol (rtx, bool);
 static void ix86_print_operand_address_as (FILE *, rtx, addr_space_t, bool);
+static bool ix86_save_reg (unsigned int, bool, bool);
 
 #ifndef CHECK_STACK_LIMIT
 #define CHECK_STACK_LIMIT (-1)
@@ -2432,6 +2433,267 @@ unsigned const x86_64_ms_sysv_extra_clobbered_registers[12] =
   XMM12_REG, XMM13_REG, XMM14_REG, XMM15_REG
 };
 
+enum xlogue_stub {
+  XLOGUE_STUB_SAVE,
+  XLOGUE_STUB_RESTORE,
+  XLOGUE_STUB_RESTORE_TAIL,
+  XLOGUE_STUB_SAVE_HFP,
+  XLOGUE_STUB_RESTORE_HFP,
+  XLOGUE_STUB_RESTORE_HFP_TAIL,
+
+  XLOGUE_STUB_COUNT
+};
+
+enum xlogue_stub_sets {
+  XLOGUE_SET_ALIGNED,
+  XLOGUE_SET_ALIGNED_PLUS_8,
+  XLOGUE_SET_HFP_ALIGNED_OR_REALIGN,
+  XLOGUE_SET_HFP_ALIGNED_PLUS_8,
+
+  XLOGUE_SET_COUNT
+};
+
+/* Register save/restore layout used by out-of-line stubs.  */
+class xlogue_layout {
+public:
+  struct reginfo
+  {
+    unsigned regno;
+    HOST_WIDE_INT offset;	/* Offset used by stub base pointer (rax or
+				   rsi) to where each register is stored.  */
+  };
+
+  unsigned get_nregs () const			{return m_nregs;}
+  HOST_WIDE_INT get_stack_align_off_in () const	{return m_stack_align_off_in;}
+
+  const reginfo &get_reginfo (unsigned reg) const
+  {
+    gcc_assert (reg < m_nregs);
+    return m_regs[reg];
+  }
+
+  const char *get_stub_name (enum xlogue_stub stub,
+			     unsigned n_extra_args) const;
+  /* Returns an rtx for the stub's symbol based upon
+       1.) the specified stub (save, restore or restore_ret) and
+       2.) the value of cfun->machine->call_ms2sysv_extra_regs and
+       3.) rather or not stack alignment is being performed.  */
+  rtx get_stub_rtx (enum xlogue_stub stub) const;
+
+  /* Returns the amount of stack space (including padding) that the stub
+     needs to store registers based upon data in the machine_function.  */
+  HOST_WIDE_INT get_stack_space_used () const
+  {
+    const struct machine_function &m = *cfun->machine;
+    unsigned last_reg = m.call_ms2sysv_extra_regs + MIN_REGS - 1;
+
+    gcc_assert (m.call_ms2sysv_extra_regs <= MAX_EXTRA_REGS);
+    return m_regs[last_reg].offset
+	    + (m.call_ms2sysv_pad_out ? 8 : 0)
+	    + STUB_INDEX_OFFSET;
+  }
+
+  /* Returns the offset for the base pointer used by the stub.  */
+  HOST_WIDE_INT get_stub_ptr_offset () const
+  {
+    return STUB_INDEX_OFFSET + m_stack_align_off_in;
+  }
+
+  static const struct xlogue_layout &get_instance ();
+  static unsigned compute_stub_managed_regs (HARD_REG_SET &stub_managed_regs);
+
+  static const HOST_WIDE_INT STUB_INDEX_OFFSET = 0x70;
+  static const unsigned MIN_REGS = NUM_X86_64_MS_CLOBBERED_REGS;
+  static const unsigned MAX_REGS = 18;
+  static const unsigned MAX_EXTRA_REGS = MAX_REGS - MIN_REGS;
+  static const unsigned VARIANT_COUNT = MAX_EXTRA_REGS + 1;
+  static const unsigned STUB_NAME_MAX_LEN = 16;
+  static const char * const STUB_BASE_NAMES[XLOGUE_STUB_COUNT];
+  static const unsigned REG_ORDER[MAX_REGS];
+  static const unsigned REG_ORDER_REALIGN[MAX_REGS];
+
+private:
+  xlogue_layout ();
+  xlogue_layout (HOST_WIDE_INT stack_align_off_in, bool hfp);
+  xlogue_layout (const xlogue_layout &);
+
+  /* True if hard frame pointer is used.  */
+  bool m_hfp;
+
+  /* Max number of register this layout manages.  */
+  unsigned m_nregs;
+
+  /* Incoming offset from 16-byte alignment.  */
+  HOST_WIDE_INT m_stack_align_off_in;
+
+  /* Register order and offsets.  */
+  struct reginfo m_regs[MAX_REGS];
+
+  /* Lazy-inited cache of symbol names for stubs.  */
+  char m_stub_names[XLOGUE_STUB_COUNT][VARIANT_COUNT][STUB_NAME_MAX_LEN];
+
+  static const struct xlogue_layout GTY(()) s_instances[XLOGUE_SET_COUNT];
+};
+
+const char * const xlogue_layout::STUB_BASE_NAMES[XLOGUE_STUB_COUNT] = {
+  "savms64",
+  "resms64",
+  "resms64x",
+  "savms64f",
+  "resms64f",
+  "resms64fx"
+};
+
+const unsigned xlogue_layout::REG_ORDER[xlogue_layout::MAX_REGS] = {
+/* The below offset values are where each register is stored for the layout
+   relative to incoming stack pointer.  The value of each m_regs[].offset will
+   be relative to the incoming base pointer (rax or rsi) used by the stub.
+
+    s_instances:   0		1		2		3
+    Offset:					realigned or	aligned + 8
+    Register	   aligned	aligned + 8	aligned w/HFP	w/HFP	*/
+    XMM15_REG,	/* 0x10		0x18		0x10		0x18	*/
+    XMM14_REG,	/* 0x20		0x28		0x20		0x28	*/
+    XMM13_REG,	/* 0x30		0x38		0x30		0x38	*/
+    XMM12_REG,	/* 0x40		0x48		0x40		0x48	*/
+    XMM11_REG,	/* 0x50		0x58		0x50		0x58	*/
+    XMM10_REG,	/* 0x60		0x68		0x60		0x68	*/
+    XMM9_REG,	/* 0x70		0x78		0x70		0x78	*/
+    XMM8_REG,	/* 0x80		0x88		0x80		0x88	*/
+    XMM7_REG,	/* 0x90		0x98		0x90		0x98	*/
+    XMM6_REG,	/* 0xa0		0xa8		0xa0		0xa8	*/
+    SI_REG,	/* 0xa8		0xb0		0xa8		0xb0	*/
+    DI_REG,	/* 0xb0		0xb8		0xb0		0xb8	*/
+    BX_REG,	/* 0xb8		0xc0		0xb8		0xc0	*/
+    BP_REG,	/* 0xc0		0xc8		N/A		N/A	*/
+    R12_REG,	/* 0xc8		0xd0		0xc0		0xc8	*/
+    R13_REG,	/* 0xd0		0xd8		0xc8		0xd0	*/
+    R14_REG,	/* 0xd8		0xe0		0xd0		0xd8	*/
+    R15_REG,	/* 0xe0		0xe8		0xd8		0xe0	*/
+};
+
+/* Instantiates all xlogue_layout instances.  */
+const struct xlogue_layout GTY(())
+xlogue_layout::s_instances[XLOGUE_SET_COUNT] = {
+  xlogue_layout (0, false),
+  xlogue_layout (8, false),
+  xlogue_layout (0, true),
+  xlogue_layout (8, true)
+};
+
+/* Return an appropriate const instance of xlogue_layout based upon values
+   in cfun->machine and crtl.  */
+const struct xlogue_layout &xlogue_layout::get_instance ()
+{
+  enum xlogue_stub_sets stub_set;
+  bool aligned_plus_8 = cfun->machine->call_ms2sysv_pad_in;
+
+  if (stack_realign_fp)
+    stub_set = XLOGUE_SET_HFP_ALIGNED_OR_REALIGN;
+  else if (frame_pointer_needed)
+    stub_set = aligned_plus_8
+	      ? XLOGUE_SET_HFP_ALIGNED_PLUS_8
+	      : XLOGUE_SET_HFP_ALIGNED_OR_REALIGN;
+  else
+    stub_set = aligned_plus_8 ? XLOGUE_SET_ALIGNED_PLUS_8 : XLOGUE_SET_ALIGNED;
+
+  return s_instances[stub_set];
+}
+
+/* Determine which clobbered registers can be saved by the stub and store
+   them in stub_managed_regs.  Returns the count of registers the stub will
+   save and restore.  */
+unsigned
+xlogue_layout::compute_stub_managed_regs (HARD_REG_SET &stub_managed_regs)
+{
+  bool hfp = frame_pointer_needed || stack_realign_fp;
+
+  unsigned i, count;
+  unsigned regno;
+
+  for (i = 0; i < NUM_X86_64_MS_CLOBBERED_REGS; ++i)
+    {
+      regno = x86_64_ms_sysv_extra_clobbered_registers[i];
+      if (regno == BP_REG && hfp)
+	continue;
+      if (!ix86_save_reg (regno, false, false))
+	return 0;
+    }
+
+  for (count = i = 0; i < MAX_REGS; ++i)
+    {
+      regno = REG_ORDER[i];
+      if (regno == BP_REG && hfp)
+	continue;
+      if (!ix86_save_reg (regno, false, false))
+	break;
+      add_to_hard_reg_set (&stub_managed_regs, DImode, regno);
+      ++count;
+    }
+    gcc_assert (count >= MIN_REGS && count <= MAX_REGS);
+    return count;
+}
+
+/* Constructor for xlogue_layout.  */
+xlogue_layout::xlogue_layout (HOST_WIDE_INT stack_align_off_in, bool hfp)
+  : m_hfp (hfp) , m_nregs (hfp ? 17 : 18),
+    m_stack_align_off_in (stack_align_off_in)
+{
+  memset (m_regs, 0, sizeof (m_regs));
+  memset (m_stub_names, 0, sizeof (m_stub_names));
+
+  HOST_WIDE_INT offset = stack_align_off_in;
+  unsigned i, j;
+  for (i = j = 0; i < MAX_REGS; ++i)
+    {
+      unsigned regno = REG_ORDER[i];
+
+      if (regno == BP_REG && hfp)
+	continue;
+      if (SSE_REGNO_P (regno))
+	{
+	  offset += 16;
+	  /* Verify that SSE regs are always aligned.  */
+	  gcc_assert (!((stack_align_off_in + offset) & 15));
+	}
+      else
+	offset += 8;
+
+      m_regs[j].regno    = regno;
+      m_regs[j++].offset = offset - STUB_INDEX_OFFSET;
+    }
+    gcc_assert (j == m_nregs);
+}
+
+const char *xlogue_layout::get_stub_name (enum xlogue_stub stub,
+					  unsigned n_extra_regs) const
+{
+  xlogue_layout *writey_this = const_cast<xlogue_layout*>(this);
+  char *name = writey_this->m_stub_names[stub][n_extra_regs];
+
+  /* Lazy init */
+  if (!*name)
+    {
+      int res = snprintf (name, STUB_NAME_MAX_LEN, "__%s_%u",
+			  STUB_BASE_NAMES[stub], MIN_REGS + n_extra_regs);
+      gcc_checking_assert (res <= (int)STUB_NAME_MAX_LEN);
+    }
+
+  return name;
+}
+
+/* Return rtx of a symbol ref for the entry point (based upon
+   cfun->machine->call_ms2sysv_extra_regs) of the specified stub.  */
+rtx xlogue_layout::get_stub_rtx (enum xlogue_stub stub) const
+{
+  const unsigned n_extra_regs = cfun->machine->call_ms2sysv_extra_regs;
+  gcc_checking_assert (n_extra_regs <= MAX_EXTRA_REGS);
+  gcc_assert (stub < XLOGUE_STUB_COUNT);
+  gcc_assert (crtl->stack_realign_finalized);
+
+  return gen_rtx_SYMBOL_REF (Pmode, get_stub_name (stub, n_extra_regs));
+}
+
 /* Define the structure for the machine field in struct function.  */
 
 struct GTY(()) stack_local_entry {
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 645b239a768..5366f1fc88f 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2578,6 +2578,24 @@ struct GTY(()) machine_function {
      pass arguments and can be used for indirect sibcall.  */
   BOOL_BITFIELD arg_reg_available : 1;
 
+  /* If true, we're out-of-lining reg save/restore for regs clobbered
+     by ms_abi functions calling a sysv function.  */
+  BOOL_BITFIELD call_ms2sysv : 1;
+
+  /* If true, the incoming 16-byte aligned stack has an offset (of 8) and
+     needs padding.  */
+  BOOL_BITFIELD call_ms2sysv_pad_in : 1;
+
+  /* If true, the size of the stub save area plus inline int reg saves will
+     result in an 8 byte offset, so needs padding.  */
+  BOOL_BITFIELD call_ms2sysv_pad_out : 1;
+
+  /* This is the number of extra registers saved by stub (valid range is
+     0-6). Each additional register is only saved/restored by the stubs
+     if all successive ones are. (Will always be zero when using a hard
+     frame pointer.) */
+  unsigned int call_ms2sysv_extra_regs:3;
+
   /* During prologue/epilogue generation, the current frame state.
      Otherwise, the frame state at the end of the prologue.  */
   struct machine_frame_state fs;
-- 
2.11.0