[PATCH v2 7/8] Windows gdb: Implement XState (Intel AVX) support

This adds support for the Intel AVX and AVX-512 registers on Windows.
It enables accessing registers $ymm0 - $ymm31, $zmm0 - $zmm31, and
$k0 - $k7 where they are available.

It also enables reading the shadow stack pointer register $pl3_ssp (for
executables marked compatible with CET shadow stack [1]), but modifying
it seems to be restricted restricted by windows.

After this patch the tests gdb.arch/i386-avx.exp and gdb.arch/i386-avx512.exp
pass on windows.

[1] https://learn.microsoft.com/en-us/cpp/build/reference/cetcompat
---
v2:
  - Extended commit message and NEWS entry
  - Remove PKRU support
  - Fixed context offset of $pl3_ssp
---
 gdb/NEWS              |   6 +++
 gdb/x86-windows-nat.c | 108 ++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 111 insertions(+), 3 deletions(-)

diff --git a/gdb/NEWS b/gdb/NEWS
index 8f40ca5cb11..71ff5508d6d 100644
--- a/gdb/NEWS
+++ b/gdb/NEWS
@@ -116,6 +116,12 @@
   intent to remove it in a future release.
   The s390 64-bit target (s390x-*) remains supported.
 
+* Support for Intel AVX registers on Windows.
+  Support displaying and modifying Intel AVX registers $ymm0 - $ymm31.
+  Support displaying and modifying Intel AVX-512 registers $zmm0 - $zmm31
+  and $k0 - $k7.
+  Support displaying the shadow stack pointer register $pl3_ssp.
+
 * Configure changes
 
 ** --with-babeltrace has been removed.  The babeltrace library was
diff --git a/gdb/x86-windows-nat.c b/gdb/x86-windows-nat.c
index 3af5ef4dae0..270f9eae8e7 100644
--- a/gdb/x86-windows-nat.c
+++ b/gdb/x86-windows-nat.c
@@ -27,6 +27,9 @@
 
 #include "i386-tdep.h"
 #include "i387-tdep.h"
+#ifdef __x86_64__
+#include "amd64-tdep.h"
+#endif
 
 using namespace windows_nat;
 
@@ -70,6 +73,8 @@ struct x86_windows_nat_target final : public x86_nat_target<windows_nat_target>
 			   windows_thread_info *th, int r) override;
 
   bool is_sw_breakpoint (const EXCEPTION_RECORD *er) const override;
+
+  const struct target_desc *read_description () override;
 };
 
 /* The current process.  */
@@ -109,7 +114,31 @@ x86_windows_per_inferior::fill_thread_context (windows_thread_info *th)
       if (context->ContextFlags == 0)
 	{
 	  context->ContextFlags = WindowsContext<decltype(context)>::all;
+	  if (xstate_features != 0)
+	    {
+	      context->ContextFlags |= CONTEXT_XSTATE_FLAG;
+	      set_xstate_features_mask (context, xstate_features);
+	    }
 	  CHECK (get_thread_context (th->h, context));
+
+	  if (xstate_features != 0)
+	    {
+	      DWORD64 features = 0;
+	      CHECK (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);
+		    }
+		}
+	    }
 	}
     });
 }
@@ -198,6 +227,14 @@ x86_windows_nat_target::thread_context_continue (windows_thread_info *th,
 	  if (GetExitCodeThread (th->h, &ec)
 	      && ec == STILL_ACTIVE)
 	    {
+	      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);
+		}
+
 	      BOOL status = set_thread_context (th->h, context);
 
 	      if (!killed)
@@ -227,7 +264,7 @@ x86_windows_nat_target::thread_context_step (windows_thread_info *th,
 
 template<typename Context>
 static char *
-get_context_reg_ptr (Context *context, int r)
+get_context_reg_ptr (Context *context, int r, i386_gdbarch_tdep *tdep)
 {
   const int *mappings;
   int mappings_count;
@@ -247,6 +284,54 @@ get_context_reg_ptr (Context *context, int r)
   char *context_offset;
   if (r < mappings_count)
     context_offset = (char *) context + mappings[r];
+  else if (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, NULL);
+      context_offset += 32 * (r - I387_ZMM0H_REGNUM (tdep));
+    }
+  else if (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, NULL);
+      context_offset += 32 + 64 * (r - I387_ZMM16H_REGNUM (tdep));
+    }
+  else if (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, NULL);
+      context_offset += 8 * (r - I387_K0_REGNUM (tdep));
+    }
+  else if (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, NULL);
+      context_offset += 16 + 64 * (r - I387_YMM16H_REGNUM (tdep));
+    }
+  else if (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, NULL);
+      context_offset += 64 * (r - I387_XMM16_REGNUM (tdep));
+    }
+  else if (I387_YMM0H_REGNUM (tdep) > 0 && r >= I387_YMM0H_REGNUM (tdep)
+	   && r < I387_YMMENDH_REGNUM (tdep))
+    {
+      context_offset = (char *) locate_xstate_feature
+	(context, X86_XSTATE_AVX_ID, NULL);
+      context_offset += 16 * (r - I387_YMM0H_REGNUM (tdep));
+    }
+  else if (tdep->ssp_regnum > 0 && r == tdep->ssp_regnum)
+    {
+      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);
 
@@ -267,7 +352,7 @@ x86_windows_nat_target::fetch_one_register (struct regcache *regcache,
   char *context_offset
     = x86_windows_process.with_context (th, [&] (auto *context)
     {
-      return get_context_reg_ptr (context, r);
+      return get_context_reg_ptr (context, r, tdep);
     });
 
   gdb_assert (!gdbarch_read_pc_p (gdbarch));
@@ -333,7 +418,7 @@ x86_windows_nat_target::store_one_register (const struct regcache *regcache,
     = x86_windows_process.with_context (th, [&] (auto *context)
     {
       gdb_assert (context->ContextFlags != 0);
-      return get_context_reg_ptr (context, r);
+      return get_context_reg_ptr (context, r, tdep);
     });
 
   /* GDB treats some registers as 32-bit, where they are in fact only
@@ -368,6 +453,23 @@ x86_windows_nat_target::is_sw_breakpoint (const EXCEPTION_RECORD *er) const
 	  || er->ExceptionCode == STATUS_WX86_BREAKPOINT);
 }
 
+const struct target_desc *
+x86_windows_nat_target::read_description ()
+{
+  if (inferior_ptid == null_ptid)
+    return this->beneath ()->read_description ();
+
+  if (xstate_features == 0)
+    return nullptr;
+
+#ifdef __x86_64__
+  if (!x86_windows_process.wow64_process)
+    return amd64_target_description (xstate_features, false);
+  else
+#endif
+    return i386_target_description (xstate_features, false);
+}
+
 /* Hardware watchpoint support, adapted from go32-nat.c code.  */
 
 /* Pass the address ADDR to the inferior in the I'th debug register.
-- 
2.54.0