[PATCH v4 8/9] Windows gdb: Implement AVX-512 register support

[Hannes Domani <ssbssa@yahoo.de>]

Similar to commit 01f9f808e2e86187c95e7cff4aeb014a421a53ce for Linux,
this patch adds support for the Intel AVX-512 registers for 32 and 64-bit
mode on Windows.
It enables accessing registers $ymm0 - $ymm31, $zmm0 - $zmm31, and
$k0 - $k7 where they are available.

After this patch gdb.arch/i386-avx512.exp passes on windows.
---
v3:
  - merged gdb+gdbserver parts, and split again AVX/AVX-512 parts
v4:
  - Add reference to equivalent Linux commit in commit message
  - Add check for enabled xstate_features in get_context_reg_ptr of
    x86-windows-nat.c
  - Changed all NULL to nullptr
---
 gdb/NEWS                    |  4 +++-
 gdb/nat/windows-nat.c       |  4 ++--
 gdb/x86-windows-nat.c       | 40 +++++++++++++++++++++++++++++++
 gdbserver/win32-i386-low.cc | 48 ++++++++++++++++++++++++++++++++++++-
 4 files changed, 92 insertions(+), 4 deletions(-)

diff --git a/gdb/NEWS b/gdb/NEWS
index da4bc811c3a..704e6a7c8ba 100644
--- a/gdb/NEWS
+++ b/gdb/NEWS
@@ -195,7 +195,9 @@ info locals
   The s390 64-bit target (s390x-*) remains supported.
 
 * Support for Intel AVX registers on Windows.
-  Support displaying and modifying Intel AVX registers $ymm0 - $ymm15.
+  Support displaying and modifying Intel AVX registers $ymm0 - $ymm31.
+  Support displaying and modifying Intel AVX-512 registers $zmm0 - $zmm31
+  and $k0 - $k7.
 
 * Configure changes
 
diff --git a/gdb/nat/windows-nat.c b/gdb/nat/windows-nat.c
index cd3c827a5d5..3940465d06b 100644
--- a/gdb/nat/windows-nat.c
+++ b/gdb/nat/windows-nat.c
@@ -290,7 +290,7 @@ windows_thread_info::zero_xstate_features ()
       if (zeroed_features == 0)
 	return;
 
-      for (int f = X86_XSTATE_AVX_ID; f <= X86_XSTATE_AVX_ID; f++)
+      for (int f = X86_XSTATE_AVX_ID; f <= X86_XSTATE_ZMM_ID; f++)
 	{
 	  DWORD64 flag = 1ULL << f;
 	  if ((zeroed_features & flag) != 0)
@@ -1373,7 +1373,7 @@ initialize_loadable ()
     {
       /* Available XState features masked with implemented features.  */
       xstate_features = (GetEnabledXStateFeatures ()
-			 & X86_XSTATE_AVX_MASK);
+			 & X86_XSTATE_AVX_AVX512_MASK);
       /* The extended XState functions are only needed if the available
 	 features exceed SSE.  */
       if ((xstate_features & ~X86_XSTATE_SSE_MASK) == 0)
diff --git a/gdb/x86-windows-nat.c b/gdb/x86-windows-nat.c
index 1e44a45171c..afc71b4ef61 100644
--- a/gdb/x86-windows-nat.c
+++ b/gdb/x86-windows-nat.c
@@ -275,6 +275,46 @@ get_context_reg_ptr (Context *context, int r, i386_gdbarch_tdep *tdep)
 	(context, X86_XSTATE_AVX_ID, nullptr);
       context_offset += 16 * (r - I387_YMM0H_REGNUM (tdep));
     }
+  else if ((xstate_features & X86_XSTATE_ZMM_H) != 0
+	   && I387_ZMM0H_REGNUM (tdep) > 0 && r >= I387_ZMM0H_REGNUM (tdep)
+	   && r < I387_ZMM16H_REGNUM (tdep) && r < I387_ZMMENDH_REGNUM (tdep))
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_H_ID, nullptr);
+      context_offset += 32 * (r - I387_ZMM0H_REGNUM (tdep));
+    }
+  else if ((xstate_features & X86_XSTATE_ZMM) != 0
+	   && I387_ZMM0H_REGNUM (tdep) > 0 && r >= I387_ZMM16H_REGNUM (tdep)
+	   && r < I387_ZMMENDH_REGNUM (tdep))
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_ID, nullptr);
+      context_offset += 32 + 64 * (r - I387_ZMM16H_REGNUM (tdep));
+    }
+  else if ((xstate_features & X86_XSTATE_K) != 0
+	   && I387_K0_REGNUM (tdep) > 0 && r >= I387_K0_REGNUM (tdep)
+	   && r < I387_KEND_REGNUM (tdep))
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_K_ID, nullptr);
+      context_offset += 8 * (r - I387_K0_REGNUM (tdep));
+    }
+  else if ((xstate_features & X86_XSTATE_ZMM) != 0
+	   && I387_YMM16H_REGNUM (tdep) > 0 && r >= I387_YMM16H_REGNUM (tdep)
+	   && r < I387_YMMH_AVX512_END_REGNUM (tdep))
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_ID, nullptr);
+      context_offset += 16 + 64 * (r - I387_YMM16H_REGNUM (tdep));
+    }
+  else if ((xstate_features & X86_XSTATE_ZMM) != 0
+	   && I387_XMM16_REGNUM (tdep) > 0 && r >= I387_XMM16_REGNUM (tdep)
+	   && r < I387_XMM_AVX512_END_REGNUM (tdep))
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_ID, nullptr);
+      context_offset += 64 * (r - I387_XMM16_REGNUM (tdep));
+    }
   else
     gdb_assert_not_reached ("invalid register number %d", r);
 
diff --git a/gdbserver/win32-i386-low.cc b/gdbserver/win32-i386-low.cc
index 1a45b15e0cf..8c62787a31b 100644
--- a/gdbserver/win32-i386-low.cc
+++ b/gdbserver/win32-i386-low.cc
@@ -515,8 +515,11 @@ get_context_reg_ptr (Context *context, int r, const target_desc *tdesc)
       amd64 = false;
     }
 
-  int ymm0h_regnum;
+  int ymm0h_regnum, zmm0h_regnum, k0_regnum;
+  int xmm16_regnum, ymm16h_regnum, zmm16h_regnum;
   const int num_xmm_registers = amd64 ? 16 : 8;
+  const int num_zmm_high_registers = amd64 ? 16 : 0;
+  const int num_avx512_k_registers = 8;
 
   char *context_offset;
   if (r < mappings_count)
@@ -529,6 +532,49 @@ get_context_reg_ptr (Context *context, int r, const target_desc *tdesc)
 	(context, X86_XSTATE_AVX_ID, nullptr);
       context_offset += 16 * (r - ymm0h_regnum);
     }
+  else if ((xstate_features & X86_XSTATE_ZMM_H) != 0
+	   && r >= (zmm0h_regnum = find_regno (tdesc, "zmm0h"))
+	   && r < zmm0h_regnum + num_xmm_registers)
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_H_ID, nullptr);
+      context_offset += 32 * (r - zmm0h_regnum);
+    }
+  else if ((xstate_features & X86_XSTATE_ZMM) != 0
+	   && num_zmm_high_registers != 0
+	   && r >= (zmm16h_regnum = find_regno (tdesc, "zmm16h"))
+	   && r < zmm16h_regnum + num_zmm_high_registers)
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_ID, nullptr);
+      context_offset += 32 + 64 * (r - zmm16h_regnum);
+    }
+  else if ((xstate_features & X86_XSTATE_K) != 0
+	   && r >= (k0_regnum = find_regno (tdesc, "k0"))
+	   && r < k0_regnum + num_avx512_k_registers)
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_K_ID, nullptr);
+      context_offset += 8 * (r - k0_regnum);
+    }
+  else if ((xstate_features & X86_XSTATE_ZMM) != 0
+	   && num_zmm_high_registers != 0
+	   && r >= (ymm16h_regnum = find_regno (tdesc, "ymm16h"))
+	   && r < ymm16h_regnum + num_zmm_high_registers)
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_ID, nullptr);
+      context_offset += 16 + 64 * (r - ymm16h_regnum);
+    }
+  else if ((xstate_features & X86_XSTATE_ZMM) != 0
+	   && num_zmm_high_registers != 0
+	   && r >= (xmm16_regnum = find_regno (tdesc, "xmm16"))
+	   && r < xmm16_regnum + num_zmm_high_registers)
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_ZMM_ID, nullptr);
+      context_offset += 64 * (r - xmm16_regnum);
+    }
   else
     gdb_assert_not_reached ("invalid register number %d", r);
 
-- 
2.55.0