[PATCH v2 8/8] Windows gdbserver: Implement XState (Intel AVX) support

Equivalent support as previous patch for Intel AVX registers.
---
v2:
  - Remove PKRU support
  - Fixed context offset of $pl3_ssp
---
 gdbserver/win32-i386-low.cc | 114 ++++++++++++++++++++++++++++++++++--
 gdbserver/win32-low.cc      |  15 +++--
 2 files changed, 118 insertions(+), 11 deletions(-)

diff --git a/gdbserver/win32-i386-low.cc b/gdbserver/win32-i386-low.cc
index b77f6adc6ed..da1aa6fed5d 100644
--- a/gdbserver/win32-i386-low.cc
+++ b/gdbserver/win32-i386-low.cc
@@ -253,6 +253,11 @@ i386_get_thread_context (windows_thread_info *th)
 			       | WindowsContext<decltype(context)>::floating
 			       | WindowsContext<decltype(context)>::debug
 			       | extended_registers);
+      if (xstate_features != 0)
+	{
+	  context->ContextFlags |= CONTEXT_XSTATE_FLAG;
+	  set_xstate_features_mask (context, xstate_features);
+	}
 
       BOOL ret = get_thread_context (th->h, context);
       if (!ret)
@@ -267,6 +272,24 @@ i386_get_thread_context (windows_thread_info *th)
 
 	  error (_("GetThreadContext failure %ld\n"), (long) e);
 	}
+
+      DWORD64 features = 0;
+      if (xstate_features != 0
+	  && get_xstate_features_mask (context, &features))
+	{
+	  DWORD64 zeroed_features = xstate_features & ~features;
+	  for (int f = X86_XSTATE_AVX_ID; f <= X86_XSTATE_CET_U_ID; f++)
+	    {
+	      DWORD64 flag = 1ULL << f;
+	      if ((zeroed_features & flag) != 0)
+		{
+		  DWORD size = 0;
+		  void *loc = locate_xstate_feature (context, f, &size);
+		  if (loc != nullptr && size > 0)
+		    memset (loc, 0, size);
+		}
+	    }
+	}
     });
 }
 
@@ -292,6 +315,17 @@ i386_prepare_to_resume (windows_thread_info *th)
 
       th->debug_registers_changed = false;
     }
+
+  windows_process.with_context (th, [&] (auto *context)
+    {
+      DWORD debug_registers = WindowsContext<decltype(context)>::debug;
+      if (xstate_features != 0
+	  && (context->ContextFlags & ~debug_registers) != 0)
+	{
+	  context->ContextFlags |= CONTEXT_XSTATE_FLAG;
+	  set_xstate_features_mask (context, xstate_features);
+	}
+    });
 }
 
 static void
@@ -477,7 +511,7 @@ is_segment_register (int r)
 
 template<typename Context>
 static char *
-get_context_reg_ptr (Context *context, int r)
+get_context_reg_ptr (Context *context, int r, const target_desc *tdesc)
 {
   const int *mappings;
   int mappings_count;
@@ -494,9 +528,74 @@ get_context_reg_ptr (Context *context, int r)
       mappings_count = sizeof (i386_mappings) / sizeof (i386_mappings[0]);
     }
 
+  bool amd64 = register_size (tdesc, 0) == 8;
+  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)
     context_offset = (char *) context + mappings[r];
+  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, NULL);
+      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, NULL);
+      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, NULL);
+      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, NULL);
+      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, NULL);
+      context_offset += 64 * (r - xmm16_regnum);
+    }
+  else if ((xstate_features & X86_XSTATE_AVX) != 0
+	   && r >= (ymm0h_regnum = find_regno (tdesc, "ymm0h"))
+	   && r < ymm0h_regnum + num_xmm_registers)
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_AVX_ID, NULL);
+      context_offset += 16 * (r - ymm0h_regnum);
+    }
+  else if ((xstate_features & X86_XSTATE_CET_U) != 0
+	   && r == find_regno (tdesc, "pl3_ssp"))
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_CET_U_ID, NULL);
+      context_offset += 8;
+    }
   else
     gdb_assert_not_reached ("invalid register number %d", r);
 
@@ -510,7 +609,7 @@ i386_fetch_inferior_register (struct regcache *regcache,
 {
   char *context_offset = windows_process.with_context (th, [&] (auto *context)
     {
-      return get_context_reg_ptr (context, r);
+      return get_context_reg_ptr (context, r, regcache->tdesc);
     });
 
   /* GDB treats some registers as 32-bit, where they are in fact only
@@ -538,7 +637,7 @@ i386_store_inferior_register (struct regcache *regcache,
 {
   char *context_offset = windows_process.with_context (th, [&] (auto *context)
     {
-      return get_context_reg_ptr (context, r);
+      return get_context_reg_ptr (context, r, regcache->tdesc);
     });
 
   /* GDB treats some registers as 32-bit, where they are in fact only
@@ -571,14 +670,17 @@ i386_arch_setup (void)
 {
  target_desc_up tdesc;
 
+  DWORD64 xcr0 = xstate_features;
+  if (xcr0 == 0)
+    xcr0 = X86_XSTATE_SSE_MASK;
+
 #ifdef __x86_64__
-  tdesc = amd64_create_target_description (X86_XSTATE_SSE_MASK, false,
-					   false, false);
+  tdesc = amd64_create_target_description (xcr0, false, false, false);
   init_target_desc (tdesc.get (), amd64_expedite_regs, WINDOWS_OSABI);
   win32_tdesc = std::move (tdesc);
 #endif
 
-  tdesc = i386_create_target_description (X86_XSTATE_SSE_MASK, false, false);
+  tdesc = i386_create_target_description (xcr0, false, false);
   init_target_desc (tdesc.get (), i386_expedite_regs, WINDOWS_OSABI);
 #ifdef __x86_64__
   wow64_win32_tdesc = std::move (tdesc);
diff --git a/gdbserver/win32-low.cc b/gdbserver/win32-low.cc
index 3d85faf0785..ea5b6f8900e 100644
--- a/gdbserver/win32-low.cc
+++ b/gdbserver/win32-low.cc
@@ -33,6 +33,7 @@
 #include <process.h>
 #include "gdbsupport/gdb_tilde_expand.h"
 #include "gdbsupport/common-inferior.h"
+#include "tdesc.h"
 
 using namespace windows_nat;
 
@@ -427,8 +428,9 @@ child_fetch_inferior_registers (struct regcache *regcache, int r)
   int regno;
   windows_thread_info *th = windows_process.find_thread (current_thread->id);
   win32_require_context (th);
-  if (r == -1 || r > NUM_REGS)
-    child_fetch_inferior_registers (regcache, NUM_REGS);
+  if (r == -1)
+    child_fetch_inferior_registers (regcache,
+				    regcache->tdesc->reg_defs.size ());
   else
     for (regno = 0; regno < r; regno++)
       (*the_low_target.fetch_inferior_register) (regcache, th, regno);
@@ -442,8 +444,9 @@ child_store_inferior_registers (struct regcache *regcache, int r)
   int regno;
   windows_thread_info *th = windows_process.find_thread (current_thread->id);
   win32_require_context (th);
-  if (r == -1 || r == 0 || r > NUM_REGS)
-    child_store_inferior_registers (regcache, NUM_REGS);
+  if (r == -1)
+    child_store_inferior_registers (regcache,
+				    regcache->tdesc->reg_defs.size ());
   else
     for (regno = 0; regno < r; regno++)
       (*the_low_target.store_inferior_register) (regcache, th, regno);
@@ -1350,7 +1353,9 @@ void
 initialize_low (void)
 {
   set_target_ops (&the_win32_target);
-  the_low_target.arch_setup ();
 
   initialize_loadable ();
+  /* Has to be done after initialize_loadable, because it uses the xstate
+     functions if available.  */
+  the_low_target.arch_setup ();
 }
-- 
2.54.0