[PATCH v2 1/8] gdb/testsuite: Add Windows replacement for aligned_alloc

[PATCH v2 1/8] gdb/testsuite: Add Windows replacement for aligned_alloc

[Hannes Domani]

_aligned_malloc has swapped arguments, and you have to use _aligned_free
to free the memory afterwards.

This is enough to make i386-sse.exp pass, and i386-avx.exp will pass at
the end of this series.
---
v2:
  - Mention which test pass after the change in the commit message
---
 gdb/testsuite/gdb.arch/i386-avx.c         |  2 +-
 gdb/testsuite/gdb.arch/i386-sse.c         |  2 +-
 gdb/testsuite/lib/precise-aligned-alloc.c | 20 ++++++++++++++++++++
 3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/gdb/testsuite/gdb.arch/i386-avx.c b/gdb/testsuite/gdb.arch/i386-avx.c
index b6cd89e5bea..229093e5164 100644
--- a/gdb/testsuite/gdb.arch/i386-avx.c
+++ b/gdb/testsuite/gdb.arch/i386-avx.c
@@ -116,7 +116,7 @@ main (int argc, char **argv)
 
   puts ("Bye!"); /* second breakpoint here */
 
-  free (allocated_ptr);
+  aligned_free (allocated_ptr);
 
   return 0;
 }
diff --git a/gdb/testsuite/gdb.arch/i386-sse.c b/gdb/testsuite/gdb.arch/i386-sse.c
index 21264ed74e7..5210aee12c3 100644
--- a/gdb/testsuite/gdb.arch/i386-sse.c
+++ b/gdb/testsuite/gdb.arch/i386-sse.c
@@ -134,7 +134,7 @@ main (int argc, char **argv)
       puts ("Bye!"); /* second breakpoint here */
     }
 
-  free (allocated_ptr);
+  aligned_free (allocated_ptr);
 
   return 0;
 }
diff --git a/gdb/testsuite/lib/precise-aligned-alloc.c b/gdb/testsuite/lib/precise-aligned-alloc.c
index 888814f12ef..1db35528bc8 100644
--- a/gdb/testsuite/lib/precise-aligned-alloc.c
+++ b/gdb/testsuite/lib/precise-aligned-alloc.c
@@ -21,6 +21,26 @@
 #include <string.h>
 #include <stdint.h>
 
+#ifdef _WIN32
+static void *
+aligned_alloc (size_t alignment, size_t size)
+{
+  return _aligned_malloc (size, alignment);
+}
+
+static void
+aligned_free (void *ptr)
+{
+  _aligned_free (ptr);
+}
+#else
+static void
+aligned_free (void *ptr)
+{
+  free (ptr);
+}
+#endif
+
 /* Return true if address P is ALIGNMENT-byte aligned.  */
 
 static int
-- 
2.54.0

[PATCH v2 2/8] Windows gdb: Use allocated buffer for CONTEXT

[Hannes Domani]

This is done in preparation for the XState functions, because the
extended registers are stored directly after the CONTEXT, and its actual
size depends on the available XState features.
---
 gdb/aarch64-windows-nat.c      | 16 ++++++++--------
 gdb/nat/windows-nat.c          | 19 +++++++++++++++++++
 gdb/nat/windows-nat.h          | 16 ++++++++++++----
 gdb/windows-nat.c              |  1 +
 gdbserver/win32-aarch64-low.cc | 10 +++++-----
 gdbserver/win32-low.cc         |  1 +
 6 files changed, 46 insertions(+), 17 deletions(-)

diff --git a/gdb/aarch64-windows-nat.c b/gdb/aarch64-windows-nat.c
index ff2c9762467..630704a8caf 100644
--- a/gdb/aarch64-windows-nat.c
+++ b/gdb/aarch64-windows-nat.c
@@ -185,7 +185,7 @@ aarch64_windows_nat_target::cleanup_windows_arch ()
 void
 aarch64_windows_per_inferior::fill_thread_context (windows_thread_info *th)
 {
-  CONTEXT *context = &th->context;
+  CONTEXT *context = th->context;
 
   if (context->ContextFlags == 0)
     {
@@ -199,7 +199,7 @@ aarch64_windows_per_inferior::fill_thread_context (windows_thread_info *th)
 void
 aarch64_windows_per_inferior::invalidate_thread_context (windows_thread_info *th)
 {
-  CONTEXT *context = &th->context;
+  CONTEXT *context = th->context;
   context->ContextFlags = 0;
 }
 
@@ -209,7 +209,7 @@ void
 aarch64_windows_nat_target::thread_context_continue (windows_thread_info *th,
 						     int killed)
 {
-  CONTEXT *context = &th->context;
+  CONTEXT *context = th->context;
 
   if (th->debug_registers_changed)
     {
@@ -250,9 +250,9 @@ aarch64_windows_nat_target::thread_context_step (windows_thread_info *th,
 						 bool enable)
 {
   if (enable)
-    th->context.Cpsr |= 0x200000;
+    th->context->Cpsr |= 0x200000;
   else
-    th->context.Cpsr &= ~0x200000;
+    th->context->Cpsr &= ~0x200000;
 }
 
 /* See windows-nat.h.  */
@@ -263,7 +263,7 @@ aarch64_windows_nat_target::fetch_one_register (struct regcache *regcache,
 {
   gdb_assert (r >= 0);
 
-  char *context_ptr = (char *) &th->context;
+  char *context_ptr = (char *) th->context;
   char *context_offset = context_ptr + aarch64_windows_process.mappings[r];
   struct gdbarch *gdbarch = regcache->arch ();
 
@@ -292,9 +292,9 @@ aarch64_windows_nat_target::store_one_register (const struct regcache *regcache,
 						windows_thread_info *th, int r)
 {
   gdb_assert (r >= 0);
-  gdb_assert (th->context.ContextFlags != 0);
+  gdb_assert (th->context->ContextFlags != 0);
 
-  char *context_ptr = (char *) &th->context;
+  char *context_ptr = (char *) th->context;
 
   regcache->raw_collect (r, context_ptr + aarch64_windows_process.mappings[r]);
 }
diff --git a/gdb/nat/windows-nat.c b/gdb/nat/windows-nat.c
index e975892f487..689601f3a82 100644
--- a/gdb/nat/windows-nat.c
+++ b/gdb/nat/windows-nat.c
@@ -291,6 +291,25 @@ windows_process_info::pid_to_exec_file (int pid)
   return path;
 }
 
+/* See windows-nat.h.  */
+
+void windows_process_info::initialize_context (windows_thread_info *th)
+{
+#ifdef __x86_64__
+  if (wow64_process)
+    {
+      th->context_buffer.reset (xmalloc (sizeof (WOW64_CONTEXT)));
+      th->wow64_context = (WOW64_CONTEXT *) th->context_buffer.get ();
+    }
+  else
+#endif
+    {
+      th->context_buffer.reset (xmalloc (sizeof (CONTEXT)));
+      th->context = (CONTEXT *) th->context_buffer.get ();
+    }
+  *context_flags_ptr (th) = 0;
+}
+
 /* Return the name of the DLL referenced by H at ADDRESS.  UNICODE
    determines what sort of string is read from the inferior.  Returns
    the name of the DLL, or NULL on error.  If a name is returned, it
diff --git a/gdb/nat/windows-nat.h b/gdb/nat/windows-nat.h
index 44b628c9bd1..76688fa90da 100644
--- a/gdb/nat/windows-nat.h
+++ b/gdb/nat/windows-nat.h
@@ -183,9 +183,9 @@ struct windows_thread_info
   /* The context of the thread, including any manipulations.  */
   union
   {
-    CONTEXT context {};
+    CONTEXT *context = nullptr;
 #ifdef __x86_64__
-    WOW64_CONTEXT wow64_context;
+    WOW64_CONTEXT *wow64_context;
 #endif
   };
 
@@ -204,6 +204,10 @@ struct windows_thread_info
 
   /* The name of the thread.  */
   gdb::unique_xmalloc_ptr<char> name;
+
+  /* The buffer for the thread context, including any XState registers if
+     available.  */
+  gdb::unique_xmalloc_ptr<void> context_buffer;
 };
 
 enum handle_exception_result
@@ -313,15 +317,19 @@ struct windows_process_info
 
   const char *pid_to_exec_file (int);
 
+  /* Allocate the context buffer for this thread.  */
+
+  void initialize_context (windows_thread_info *th);
+
   template<typename Function>
   auto with_context (windows_thread_info *th, Function function)
   {
 #ifdef __x86_64__
     if (wow64_process)
-      return function (th != nullptr ? &th->wow64_context : nullptr);
+      return function (th != nullptr ? th->wow64_context : nullptr);
     else
 #endif
-      return function (th != nullptr ? &th->context : nullptr);
+      return function (th != nullptr ? th->context : nullptr);
   }
 
   DWORD *context_flags_ptr (windows_thread_info *th)
diff --git a/gdb/windows-nat.c b/gdb/windows-nat.c
index def8fa606f4..4cd301d4959 100644
--- a/gdb/windows-nat.c
+++ b/gdb/windows-nat.c
@@ -515,6 +515,7 @@ windows_nat_target::add_thread (ptid_t ptid, HANDLE h, void *tlb,
 #endif
   windows_private_thread_info *th
     = new windows_private_thread_info (windows_process, ptid.lwp (), h, base);
+  windows_process->initialize_context (th);
 
   /* Add this new thread to the list of threads.
 
diff --git a/gdbserver/win32-aarch64-low.cc b/gdbserver/win32-aarch64-low.cc
index 5a7b72155db..e94548b6fef 100644
--- a/gdbserver/win32-aarch64-low.cc
+++ b/gdbserver/win32-aarch64-low.cc
@@ -169,7 +169,7 @@ aarch64_initial_stuff (process_info *proc)
 static void
 aarch64_get_thread_context (windows_thread_info *th)
 {
-  CONTEXT *context = &th->context;
+  CONTEXT *context = th->context;
 
   context->ContextFlags = (WindowsContext<decltype(context)>::full
 			   | WindowsContext<decltype(context)>::floating
@@ -193,7 +193,7 @@ aarch64_prepare_to_resume (windows_thread_info *th)
     {
       win32_require_context (th);
 
-      CONTEXT *context = &th->context;
+      CONTEXT *context = th->context;
 
       for (int i = 0; i < aarch64_num_bp_regs; i++)
 	{
@@ -223,7 +223,7 @@ aarch64_thread_added (windows_thread_info *th)
 static void
 aarch64_single_step (windows_thread_info *th)
 {
-  th->context.Cpsr |= 0x200000;
+  th->context->Cpsr |= 0x200000;
 }
 
 /* An array of offset mappings into a Win32 Context structure.
@@ -322,7 +322,7 @@ aarch64_fetch_inferior_register (struct regcache *regcache,
   int mappings_count;
   get_mappings (mappings, mappings_count);
 
-  char *context_ptr = (char *) &th->context;
+  char *context_ptr = (char *) th->context;
   char *context_offset;
   if (r < mappings_count)
     context_offset = context_ptr + mappings[r];
@@ -341,7 +341,7 @@ aarch64_store_inferior_register (struct regcache *regcache,
   int mappings_count;
   get_mappings (mappings, mappings_count);
 
-  char *context_ptr = (char *) &th->context;
+  char *context_ptr = (char *) th->context;
   char *context_offset;
   if (r < mappings_count)
     context_offset = context_ptr + mappings[r];
diff --git a/gdbserver/win32-low.cc b/gdbserver/win32-low.cc
index 7629beca213..3d85faf0785 100644
--- a/gdbserver/win32-low.cc
+++ b/gdbserver/win32-low.cc
@@ -152,6 +152,7 @@ child_add_thread (DWORD pid, DWORD tid, HANDLE h, void *tlb)
     base += 2 * 4096; /* page size = 4096 */
 #endif
   th = new windows_thread_info (&windows_process, tid, h, base);
+  windows_process.initialize_context (th);
 
   find_process_pid (pid)->add_thread (ptid, th);
 
-- 
2.54.0

[PATCH v2 3/8] Windows gdb: Remove mappings member from windows_per_inferior

[Hannes Domani]

It's not really that useful, and simplifies later XState changes.
---
 gdb/aarch64-windows-nat.c |  6 ++----
 gdb/windows-nat.h         | 18 ------------------
 gdb/x86-windows-nat.c     | 34 ++++++++++++++++++++++------------
 3 files changed, 24 insertions(+), 34 deletions(-)

diff --git a/gdb/aarch64-windows-nat.c b/gdb/aarch64-windows-nat.c
index 630704a8caf..be900439047 100644
--- a/gdb/aarch64-windows-nat.c
+++ b/gdb/aarch64-windows-nat.c
@@ -168,8 +168,6 @@ aarch64_windows_nat_target::initialize_windows_arch (bool attaching)
 {
   memset (&aarch64_windows_process.dr_state, 0,
 	  sizeof (aarch64_windows_process.dr_state));
-
-  aarch64_windows_process.mappings = aarch64_mappings;
 }
 
 /* See windows-nat.h.  */
@@ -264,7 +262,7 @@ aarch64_windows_nat_target::fetch_one_register (struct regcache *regcache,
   gdb_assert (r >= 0);
 
   char *context_ptr = (char *) th->context;
-  char *context_offset = context_ptr + aarch64_windows_process.mappings[r];
+  char *context_offset = context_ptr + aarch64_mappings[r];
   struct gdbarch *gdbarch = regcache->arch ();
 
   gdb_assert (!gdbarch_read_pc_p (gdbarch));
@@ -296,7 +294,7 @@ aarch64_windows_nat_target::store_one_register (const struct regcache *regcache,
 
   char *context_ptr = (char *) th->context;
 
-  regcache->raw_collect (r, context_ptr + aarch64_windows_process.mappings[r]);
+  regcache->raw_collect (r, context_ptr + aarch64_mappings[r]);
 }
 
 /* See windows-nat.h.  */
diff --git a/gdb/windows-nat.h b/gdb/windows-nat.h
index 3349755022b..d6977ff4c85 100644
--- a/gdb/windows-nat.h
+++ b/gdb/windows-nat.h
@@ -139,24 +139,6 @@ struct windows_per_inferior : public windows_nat::windows_process_info
   void *wow64_dbgbreak = nullptr;
 #endif
 
-  /* This vector maps GDB's idea of a register's number into an offset
-     in the windows exception context vector.
-
-     It also contains the bit mask needed to load the register in question.
-
-     The contents of this table can only be computed by the units
-     that provide CPU-specific support for Windows native debugging.
-
-     One day we could read a reg, we could inspect the context we
-     already have loaded, if it doesn't have the bit set that we need,
-     we read that set of registers in using GetThreadContext.  If the
-     context already contains what we need, we just unpack it.  Then to
-     write a register, first we have to ensure that the context contains
-     the other regs of the group, and then we copy the info in and set
-     out bit.  */
-
-  const int *mappings = nullptr;
-
   std::vector<windows_solib> solibs;
 
 #ifdef __CYGWIN__
diff --git a/gdb/x86-windows-nat.c b/gdb/x86-windows-nat.c
index 2f556e47b39..b3ad8594020 100644
--- a/gdb/x86-windows-nat.c
+++ b/gdb/x86-windows-nat.c
@@ -85,16 +85,10 @@ x86_windows_nat_target::initialize_windows_arch (bool attaching)
     = !attaching && x86_windows_process.wow64_process;
 
   if (!x86_windows_process.wow64_process)
-    {
-      x86_windows_process.mappings = amd64_mappings;
-      x86_windows_process.segment_register_p = amd64_windows_segment_register_p;
-    }
+    x86_windows_process.segment_register_p = amd64_windows_segment_register_p;
   else
 #endif
-    {
-      x86_windows_process.mappings = i386_mappings;
-      x86_windows_process.segment_register_p = i386_windows_segment_register_p;
-    }
+    x86_windows_process.segment_register_p = i386_windows_segment_register_p;
 }
 
 /* See windows-nat.h.  */
@@ -242,7 +236,15 @@ x86_windows_nat_target::fetch_one_register (struct regcache *regcache,
       return (char *) context;
     });
 
-  char *context_offset = context_ptr + x86_windows_process.mappings[r];
+  const int *mappings;
+#ifdef __x86_64__
+  if (!x86_windows_process.wow64_process)
+    mappings = amd64_mappings;
+  else
+#endif
+    mappings = i386_mappings;
+
+  char *context_offset = context_ptr + mappings[r];
   struct gdbarch *gdbarch = regcache->arch ();
   i386_gdbarch_tdep *tdep = gdbarch_tdep<i386_gdbarch_tdep> (gdbarch);
 
@@ -308,6 +310,14 @@ x86_windows_nat_target::store_one_register (const struct regcache *regcache,
       return (char *) context;
     });
 
+  const int *mappings;
+#ifdef __x86_64__
+  if (!x86_windows_process.wow64_process)
+    mappings = amd64_mappings;
+  else
+#endif
+    mappings = i386_mappings;
+
   struct gdbarch *gdbarch = regcache->arch ();
   i386_gdbarch_tdep *tdep = gdbarch_tdep<i386_gdbarch_tdep> (gdbarch);
 
@@ -319,7 +329,7 @@ x86_windows_nat_target::store_one_register (const struct regcache *regcache,
     {
       gdb_byte bytes[4];
       regcache->raw_collect (r, bytes);
-      memcpy (context_ptr + x86_windows_process.mappings[r], bytes, 2);
+      memcpy (context_ptr + mappings[r], bytes, 2);
     }
   else if (r == I387_FOP_REGNUM (tdep))
     {
@@ -328,10 +338,10 @@ x86_windows_nat_target::store_one_register (const struct regcache *regcache,
       /* The value of FOP occupies the top two bytes in the context,
 	 so write the two low-order bytes from the cache into the
 	 appropriate spot.  */
-      memcpy (context_ptr + x86_windows_process.mappings[r] + 2, bytes, 2);
+      memcpy (context_ptr + mappings[r] + 2, bytes, 2);
     }
   else
-    regcache->raw_collect (r, context_ptr + x86_windows_process.mappings[r]);
+    regcache->raw_collect (r, context_ptr + mappings[r]);
 }
 
 /* See windows-nat.h.  */
-- 
2.54.0

[PATCH v2 4/8] Windows gdb: Refactor getting pointer to register inside context

[Hannes Domani]

These get_context_reg_ptr helper functions will be extended for XState
registers later.
---
 gdb/amd64-windows-nat.c     |  3 ++
 gdb/i386-windows-nat.c      |  3 ++
 gdb/windows-nat.h           |  6 +++
 gdb/x86-windows-nat.c       | 75 ++++++++++++++++++++++---------------
 gdbserver/win32-i386-low.cc | 46 +++++++++++++++--------
 5 files changed, 87 insertions(+), 46 deletions(-)

diff --git a/gdb/amd64-windows-nat.c b/gdb/amd64-windows-nat.c
index cca606b5200..9d83a5f8334 100644
--- a/gdb/amd64-windows-nat.c
+++ b/gdb/amd64-windows-nat.c
@@ -86,6 +86,9 @@ const int amd64_mappings[] =
 };
 #undef context_offset
 
+const int amd64_mappings_count
+  = sizeof (amd64_mappings) / sizeof (amd64_mappings[0]);
+
 /* segment_register_p_ftype implementation for amd64.  */
 
 int
diff --git a/gdb/i386-windows-nat.c b/gdb/i386-windows-nat.c
index 991f301cad1..151b778036c 100644
--- a/gdb/i386-windows-nat.c
+++ b/gdb/i386-windows-nat.c
@@ -74,6 +74,9 @@ const int i386_mappings[] =
 #undef context_offset
 #undef CONTEXT
 
+const int i386_mappings_count
+  = sizeof (i386_mappings) / sizeof (i386_mappings[0]);
+
 /* segment_register_p_ftype implementation for x86.  */
 
 int
diff --git a/gdb/windows-nat.h b/gdb/windows-nat.h
index d6977ff4c85..69be069e419 100644
--- a/gdb/windows-nat.h
+++ b/gdb/windows-nat.h
@@ -392,12 +392,18 @@ int i386_windows_segment_register_p (int regnum);
 /* context register offsets for x86.  */
 extern const int i386_mappings[];
 
+/* number of context register offests for x86.  */
+extern const int i386_mappings_count;
+
 #ifdef __x86_64__
 /* segment_register_p_ftype implementation for amd64.  */
 int amd64_windows_segment_register_p (int regnum);
 
 /* context register offsets for amd64.  */
 extern const int amd64_mappings[];
+
+/* number of context register offests for amd64.  */
+extern const int amd64_mappings_count;
 #endif
 
 /* Creates an iterator that works like all_matching_threads_iterator,
diff --git a/gdb/x86-windows-nat.c b/gdb/x86-windows-nat.c
index b3ad8594020..3af5ef4dae0 100644
--- a/gdb/x86-windows-nat.c
+++ b/gdb/x86-windows-nat.c
@@ -223,31 +223,53 @@ x86_windows_nat_target::thread_context_step (windows_thread_info *th,
     });
 }
 
-/* See windows-nat.h.  */
+/* Get pointer to register R inside CONTEXT.  */
 
-void
-x86_windows_nat_target::fetch_one_register (struct regcache *regcache,
-					    windows_thread_info *th, int r)
+template<typename Context>
+static char *
+get_context_reg_ptr (Context *context, int r)
 {
-  gdb_assert (r >= 0);
-
-  char *context_ptr = x86_windows_process.with_context (th, [] (auto *context)
-    {
-      return (char *) context;
-    });
-
   const int *mappings;
+  int mappings_count;
 #ifdef __x86_64__
   if (!x86_windows_process.wow64_process)
-    mappings = amd64_mappings;
+    {
+      mappings = amd64_mappings;
+      mappings_count = amd64_mappings_count;
+    }
   else
 #endif
-    mappings = i386_mappings;
+    {
+      mappings = i386_mappings;
+      mappings_count = i386_mappings_count;
+    }
+
+  char *context_offset;
+  if (r < mappings_count)
+    context_offset = (char *) context + mappings[r];
+  else
+    gdb_assert_not_reached ("invalid register number %d", r);
+
+  return context_offset;
+}
+
+/* See windows-nat.h.  */
+
+void
+x86_windows_nat_target::fetch_one_register (struct regcache *regcache,
+					    windows_thread_info *th, int r)
+{
+  gdb_assert (r >= 0);
 
-  char *context_offset = context_ptr + mappings[r];
   struct gdbarch *gdbarch = regcache->arch ();
   i386_gdbarch_tdep *tdep = gdbarch_tdep<i386_gdbarch_tdep> (gdbarch);
 
+  char *context_offset
+    = x86_windows_process.with_context (th, [&] (auto *context)
+    {
+      return get_context_reg_ptr (context, r);
+    });
+
   gdb_assert (!gdbarch_read_pc_p (gdbarch));
   gdb_assert (gdbarch_pc_regnum (gdbarch) >= 0);
   gdb_assert (!gdbarch_write_pc_p (gdbarch));
@@ -304,23 +326,16 @@ x86_windows_nat_target::store_one_register (const struct regcache *regcache,
 {
   gdb_assert (r >= 0);
 
-  char *context_ptr = x86_windows_process.with_context (th, [] (auto *context)
+  struct gdbarch *gdbarch = regcache->arch ();
+  i386_gdbarch_tdep *tdep = gdbarch_tdep<i386_gdbarch_tdep> (gdbarch);
+
+  char *context_offset
+    = x86_windows_process.with_context (th, [&] (auto *context)
     {
       gdb_assert (context->ContextFlags != 0);
-      return (char *) context;
+      return get_context_reg_ptr (context, r);
     });
 
-  const int *mappings;
-#ifdef __x86_64__
-  if (!x86_windows_process.wow64_process)
-    mappings = amd64_mappings;
-  else
-#endif
-    mappings = i386_mappings;
-
-  struct gdbarch *gdbarch = regcache->arch ();
-  i386_gdbarch_tdep *tdep = gdbarch_tdep<i386_gdbarch_tdep> (gdbarch);
-
   /* GDB treats some registers as 32-bit, where they are in fact only
      16 bits long.  These cases must be handled specially to avoid
      overwriting other registers in the context.  */
@@ -329,7 +344,7 @@ x86_windows_nat_target::store_one_register (const struct regcache *regcache,
     {
       gdb_byte bytes[4];
       regcache->raw_collect (r, bytes);
-      memcpy (context_ptr + mappings[r], bytes, 2);
+      memcpy (context_offset, bytes, 2);
     }
   else if (r == I387_FOP_REGNUM (tdep))
     {
@@ -338,10 +353,10 @@ x86_windows_nat_target::store_one_register (const struct regcache *regcache,
       /* The value of FOP occupies the top two bytes in the context,
 	 so write the two low-order bytes from the cache into the
 	 appropriate spot.  */
-      memcpy (context_ptr + mappings[r] + 2, bytes, 2);
+      memcpy (context_offset + 2, bytes, 2);
     }
   else
-    regcache->raw_collect (r, context_ptr + mappings[r]);
+    regcache->raw_collect (r, context_offset);
 }
 
 /* See windows-nat.h.  */
diff --git a/gdbserver/win32-i386-low.cc b/gdbserver/win32-i386-low.cc
index 1aacd302074..b77f6adc6ed 100644
--- a/gdbserver/win32-i386-low.cc
+++ b/gdbserver/win32-i386-low.cc
@@ -473,22 +473,44 @@ is_segment_register (int r)
     return r >= I386_CS_REGNUM && r <= I386_GS_REGNUM;
 }
 
-/* Fetch register from gdbserver regcache data.  */
-static void
-i386_fetch_inferior_register (struct regcache *regcache,
-			      windows_thread_info *th, int r)
+/* Get pointer to register R inside CONTEXT.  */
+
+template<typename Context>
+static char *
+get_context_reg_ptr (Context *context, int r)
 {
   const int *mappings;
+  int mappings_count;
 #ifdef __x86_64__
   if (!windows_process.wow64_process)
-    mappings = amd64_mappings;
+    {
+      mappings = amd64_mappings;
+      mappings_count = sizeof (amd64_mappings) / sizeof (amd64_mappings[0]);
+    }
   else
 #endif
-    mappings = i386_mappings;
+    {
+      mappings = i386_mappings;
+      mappings_count = sizeof (i386_mappings) / sizeof (i386_mappings[0]);
+    }
+
+  char *context_offset;
+  if (r < mappings_count)
+    context_offset = (char *) context + mappings[r];
+  else
+    gdb_assert_not_reached ("invalid register number %d", r);
+
+  return context_offset;
+}
 
+/* Fetch register from gdbserver regcache data.  */
+static void
+i386_fetch_inferior_register (struct regcache *regcache,
+			      windows_thread_info *th, int r)
+{
   char *context_offset = windows_process.with_context (th, [&] (auto *context)
     {
-      return (char *) context + mappings[r];
+      return get_context_reg_ptr (context, r);
     });
 
   /* GDB treats some registers as 32-bit, where they are in fact only
@@ -514,17 +536,9 @@ static void
 i386_store_inferior_register (struct regcache *regcache,
 			      windows_thread_info *th, int r)
 {
-  const int *mappings;
-#ifdef __x86_64__
-  if (!windows_process.wow64_process)
-    mappings = amd64_mappings;
-  else
-#endif
-    mappings = i386_mappings;
-
   char *context_offset = windows_process.with_context (th, [&] (auto *context)
     {
-      return (char *) context + mappings[r];
+      return get_context_reg_ptr (context, r);
     });
 
   /* GDB treats some registers as 32-bit, where they are in fact only
-- 
2.54.0

[PATCH v2 5/8] Windows gdb: Prepare XState functions

[Hannes Domani]

These functions will then be used to access the XState registers.
---
 gdb/nat/windows-nat.c |  31 +++++++++++
 gdb/nat/windows-nat.h | 116 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 147 insertions(+)

diff --git a/gdb/nat/windows-nat.c b/gdb/nat/windows-nat.c
index 689601f3a82..cd1f9e7bc64 100644
--- a/gdb/nat/windows-nat.c
+++ b/gdb/nat/windows-nat.c
@@ -73,6 +73,19 @@ InitializeProcThreadAttributeList_ftype *InitializeProcThreadAttributeList;
 UpdateProcThreadAttribute_ftype *UpdateProcThreadAttribute;
 DeleteProcThreadAttributeList_ftype *DeleteProcThreadAttributeList;
 
+#if defined __i386__ || defined __x86_64__
+GetEnabledXStateFeatures_ftype *GetEnabledXStateFeatures;
+InitializeContext_ftype *InitializeContext;
+GetXStateFeaturesMask_ftype *GetXStateFeaturesMask;
+SetXStateFeaturesMask_ftype *SetXStateFeaturesMask;
+LocateXStateFeature_ftype *LocateXStateFeature;
+#ifdef __x86_64__
+RtlGetExtendedFeaturesMask_ftype *RtlGetExtendedFeaturesMask;
+RtlSetExtendedFeaturesMask_ftype *RtlSetExtendedFeaturesMask;
+RtlLocateExtendedFeature_ftype *RtlLocateExtendedFeature;
+#endif
+#endif
+
 /* Note that 'debug_events' must be locally defined in the relevant
    functions.  */
 #define DEBUG_EVENTS(fmt, ...) \
@@ -1191,6 +1204,14 @@ initialize_loadable ()
       GPA (hm, InitializeProcThreadAttributeList);
       GPA (hm, UpdateProcThreadAttribute);
       GPA (hm, DeleteProcThreadAttributeList);
+
+#if defined __i386__ || defined __x86_64__
+      GPA (hm, GetEnabledXStateFeatures);
+      GPA (hm, InitializeContext);
+      GPA (hm, GetXStateFeaturesMask);
+      GPA (hm, SetXStateFeaturesMask);
+      GPA (hm, LocateXStateFeature);
+#endif
     }
 
   /* Set variables to dummy versions of these processes if the function
@@ -1256,6 +1277,16 @@ initialize_loadable ()
 	GPA (hm, GetThreadDescription);
     }
 
+#ifdef __x86_64__
+  hm = LoadLibrary (TEXT ("ntdll.dll"));
+  if (hm)
+    {
+      GPA (hm, RtlGetExtendedFeaturesMask);
+      GPA (hm, RtlSetExtendedFeaturesMask);
+      GPA (hm, RtlLocateExtendedFeature);
+    }
+#endif
+
 #undef GPA
 
   return result;
diff --git a/gdb/nat/windows-nat.h b/gdb/nat/windows-nat.h
index 76688fa90da..a344b0a966f 100644
--- a/gdb/nat/windows-nat.h
+++ b/gdb/nat/windows-nat.h
@@ -35,6 +35,9 @@
 #define CONTEXT_EXTENDED_REGISTERS 0
 #endif
 
+#define CONTEXT_EXTENDED_REGISTERS_FLAG	0x20
+#define CONTEXT_XSTATE_FLAG		0x40
+
 namespace windows_nat
 {
 
@@ -456,6 +459,14 @@ extern BOOL create_process (const wchar_t *image, wchar_t *command_line,
 #define InitializeProcThreadAttributeList dyn_InitializeProcThreadAttributeList
 #define UpdateProcThreadAttribute dyn_UpdateProcThreadAttribute
 #define DeleteProcThreadAttributeList dyn_DeleteProcThreadAttributeList
+#define GetEnabledXStateFeatures	dyn_GetEnabledXStateFeatures
+#define InitializeContext		dyn_InitializeContext
+#define GetXStateFeaturesMask		dyn_GetXStateFeaturesMask
+#define SetXStateFeaturesMask		dyn_SetXStateFeaturesMask
+#define LocateXStateFeature		dyn_LocateXStateFeature
+#define RtlGetExtendedFeaturesMask	dyn_RtlGetExtendedFeaturesMask
+#define RtlSetExtendedFeaturesMask	dyn_RtlSetExtendedFeaturesMask
+#define RtlLocateExtendedFeature	dyn_RtlLocateExtendedFeature
 
 typedef BOOL WINAPI (AdjustTokenPrivileges_ftype) (HANDLE, BOOL,
 						   PTOKEN_PRIVILEGES,
@@ -550,6 +561,35 @@ extern DeleteProcThreadAttributeList_ftype *DeleteProcThreadAttributeList;
 
 extern bool disable_randomization_available ();
 
+#if defined __i386__ || defined __x86_64__
+typedef DWORD64 (WINAPI GetEnabledXStateFeatures_ftype) ();
+extern GetEnabledXStateFeatures_ftype *GetEnabledXStateFeatures;
+
+typedef BOOL (WINAPI InitializeContext_ftype) (PVOID, DWORD,
+					       PCONTEXT*, PDWORD);
+extern InitializeContext_ftype *InitializeContext;
+
+typedef BOOL (WINAPI GetXStateFeaturesMask_ftype) (PCONTEXT, PDWORD64);
+extern GetXStateFeaturesMask_ftype *GetXStateFeaturesMask;
+
+typedef BOOL (WINAPI SetXStateFeaturesMask_ftype) (PCONTEXT, DWORD64);
+extern SetXStateFeaturesMask_ftype *SetXStateFeaturesMask;
+
+typedef PVOID (WINAPI LocateXStateFeature_ftype) (PCONTEXT, DWORD, PDWORD);
+extern LocateXStateFeature_ftype *LocateXStateFeature;
+
+#ifdef __x86_64__
+typedef DWORD64 (WINAPI RtlGetExtendedFeaturesMask_ftype) (PVOID);
+extern RtlGetExtendedFeaturesMask_ftype *RtlGetExtendedFeaturesMask;
+
+typedef VOID (WINAPI RtlSetExtendedFeaturesMask_ftype) (PVOID, DWORD64);
+extern RtlSetExtendedFeaturesMask_ftype *RtlSetExtendedFeaturesMask;
+
+typedef PVOID (WINAPI RtlLocateExtendedFeature_ftype) (PVOID, DWORD, PDWORD);
+extern RtlLocateExtendedFeature_ftype *RtlLocateExtendedFeature;
+#endif
+#endif
+
 /* Helper classes to get the correct ContextFlags values based on the
    used type (CONTEXT or WOW64_CONTEXT).  */
 
@@ -615,16 +655,69 @@ enum_process_modules (CONTEXT *, HANDLE process,
   return EnumProcessModules (process, modules, size, needed);
 }
 
+#if defined __i386__ || defined __x86_64__
+static inline BOOL
+get_xstate_features_mask (CONTEXT *context, DWORD64 *mask)
+{
+  return GetXStateFeaturesMask (context, mask);
+}
+
+static inline BOOL
+set_xstate_features_mask (CONTEXT *context, DWORD64 mask)
+{
+  return SetXStateFeaturesMask (context, mask);
+}
+
+static inline PVOID
+locate_xstate_feature (CONTEXT *context, DWORD feature, DWORD *length)
+{
+  return LocateXStateFeature (context, feature, length);
+}
+#endif
+
 #ifdef __x86_64__
 static inline BOOL
 get_thread_context (HANDLE h, WOW64_CONTEXT *context)
 {
+  if ((context->ContextFlags & CONTEXT_XSTATE_FLAG) != 0)
+    {
+      /* Wow64GetThreadContext doesn't handle CONTEXT_EXTENDED_REGISTERS and
+	 CONTEXT_XSTATE combined correctly, but separate they work fine.  */
+      DWORD flags = context->ContextFlags;
+      context->ContextFlags &= ~CONTEXT_EXTENDED_REGISTERS_FLAG;
+      BOOL ret = Wow64GetThreadContext (h, context);
+      context->ContextFlags = flags;
+      if (!ret)
+	return FALSE;
+
+      context->ContextFlags &= ~CONTEXT_XSTATE_FLAG;
+      ret = Wow64GetThreadContext (h, context);
+      context->ContextFlags = flags;
+      return ret;
+    }
+
   return Wow64GetThreadContext (h, context);
 }
 
 static inline BOOL
 set_thread_context (HANDLE h, WOW64_CONTEXT *context)
 {
+  if ((context->ContextFlags & CONTEXT_XSTATE_FLAG) != 0)
+    {
+      /* Same limitation as Wow64GetThreadContext above.  */
+      DWORD flags = context->ContextFlags;
+      context->ContextFlags &= ~CONTEXT_EXTENDED_REGISTERS_FLAG;
+      BOOL ret = Wow64SetThreadContext (h, context);
+      context->ContextFlags = flags;
+      if (!ret)
+	return FALSE;
+
+      context->ContextFlags &= ~CONTEXT_XSTATE_FLAG;
+      ret = Wow64SetThreadContext (h, context);
+      context->ContextFlags = flags;
+      return ret;
+    }
+
   return Wow64SetThreadContext (h, context);
 }
 
@@ -642,6 +735,29 @@ enum_process_modules (WOW64_CONTEXT *, HANDLE process,
   return EnumProcessModulesEx (process, modules, size, needed,
 			       LIST_MODULES_32BIT);
 }
+
+static inline BOOL
+get_xstate_features_mask (WOW64_CONTEXT *context, DWORD64 *mask)
+{
+  /* Use lower level function, since there is no Wow64GetXStateFeaturesMask.  */
+  *mask = RtlGetExtendedFeaturesMask (context + 1);
+  return TRUE;
+}
+
+static inline BOOL
+set_xstate_features_mask (WOW64_CONTEXT *context, DWORD64 mask)
+{
+  /* Use lower level function, since there is no Wow64SetXStateFeaturesMask.  */
+  RtlSetExtendedFeaturesMask (context + 1, mask);
+  return TRUE;
+}
+
+static inline PVOID
+locate_xstate_feature (WOW64_CONTEXT *context, DWORD feature, DWORD *length)
+{
+  /* Use lower level function, since there is no Wow64LocateXStateFeature.  */
+  return RtlLocateExtendedFeature (context + 1, feature, length);
+}
 #endif
 
 /* This is available starting with Windows 10.  */
-- 
2.54.0

[PATCH v2 6/8] Windows gdb: Get available XState features

[Hannes Domani]

Also prepares the thread context for the additional registers.
---
v2:
  - Remove PKRU from the implemented features mask
---
 gdb/nat/windows-nat.c | 54 ++++++++++++++++++++++++++++++++++++++++++-
 gdb/nat/windows-nat.h |  5 ++++
 2 files changed, 58 insertions(+), 1 deletion(-)

diff --git a/gdb/nat/windows-nat.c b/gdb/nat/windows-nat.c
index cd1f9e7bc64..28678b9f1a7 100644
--- a/gdb/nat/windows-nat.c
+++ b/gdb/nat/windows-nat.c
@@ -20,6 +20,7 @@
 #include "gdbsupport/common-debug.h"
 #include "gdbsupport/gdb_signals.h"
 #include "gdbsupport/gdb_wait.h"
+#include "gdbsupport/x86-xstate.h"
 #include "target/target.h"
 
 #undef GetModuleFileNameEx
@@ -84,6 +85,8 @@ RtlGetExtendedFeaturesMask_ftype *RtlGetExtendedFeaturesMask;
 RtlSetExtendedFeaturesMask_ftype *RtlSetExtendedFeaturesMask;
 RtlLocateExtendedFeature_ftype *RtlLocateExtendedFeature;
 #endif
+
+DWORD64 xstate_features;
 #endif
 
 /* Note that 'debug_events' must be locally defined in the relevant
@@ -308,12 +311,38 @@ windows_process_info::pid_to_exec_file (int pid)
 
 void windows_process_info::initialize_context (windows_thread_info *th)
 {
+#if defined __i386__ || defined __x86_64__
+  if (xstate_features != 0)
+    {
+      DWORD context_flags = with_context (nullptr, [] (auto *context)
+	{
+	  return WindowsContext<decltype(context)>::all;
+	});
+      context_flags |= CONTEXT_XSTATE_FLAG;
+      DWORD xstate_size = 0;
+      InitializeContext (NULL, context_flags, NULL, &xstate_size);
+      th->context_buffer.reset (xmalloc (xstate_size));
+      CONTEXT *context = nullptr;
+      if (!InitializeContext (th->context_buffer.get (),
+			      context_flags, &context, &xstate_size))
+	error ("InitializeContext failure %lu\n", GetLastError ());
 #ifdef __x86_64__
-  if (wow64_process)
+      /* InitializeContext actually initializes a WOW64_CONTEXT when
+	 context_flags contains a WOW64_CONTEXT_* value, so a cast is needed.
+	 */
+      if (wow64_process)
+	th->wow64_context = (WOW64_CONTEXT *) context;
+      else
+#endif
+	th->context = context;
+    }
+#ifdef __x86_64__
+  else if (wow64_process)
     {
       th->context_buffer.reset (xmalloc (sizeof (WOW64_CONTEXT)));
       th->wow64_context = (WOW64_CONTEXT *) th->context_buffer.get ();
     }
+#endif
   else
 #endif
     {
@@ -1289,6 +1318,29 @@ initialize_loadable ()
 
 #undef GPA
 
+#if defined __i386__ || defined __x86_64__
+  if (GetEnabledXStateFeatures != nullptr
+      && InitializeContext != nullptr
+      && GetXStateFeaturesMask != nullptr
+      && SetXStateFeaturesMask != nullptr
+      && LocateXStateFeature != nullptr
+#ifdef __x86_64__
+      && RtlGetExtendedFeaturesMask != nullptr
+      && RtlSetExtendedFeaturesMask != nullptr
+      && RtlLocateExtendedFeature != nullptr
+#endif
+  )
+    {
+      /* Available XState features masked with implemented features.  */
+      xstate_features = GetEnabledXStateFeatures ()
+	& (X86_XSTATE_AVX_AVX512_MASK | X86_XSTATE_CET_U);
+      /* The extended XState functions are only needed if the available
+	 features exceed SSE.  */
+      if ((xstate_features & ~X86_XSTATE_SSE_MASK) == 0)
+	xstate_features = 0;
+    }
+#endif
+
   return result;
 }
 
diff --git a/gdb/nat/windows-nat.h b/gdb/nat/windows-nat.h
index a344b0a966f..8fcf5e339cb 100644
--- a/gdb/nat/windows-nat.h
+++ b/gdb/nat/windows-nat.h
@@ -760,6 +760,11 @@ locate_xstate_feature (WOW64_CONTEXT *context, DWORD feature, DWORD *length)
 }
 #endif
 
+#if defined __i386__ || defined __x86_64__
+/* Available XState features.  */
+extern DWORD64 xstate_features;
+#endif
+
 /* This is available starting with Windows 10.  */
 #ifndef DBG_REPLY_LATER
 # define DBG_REPLY_LATER 0x40010001L
-- 
2.54.0

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

[Hannes Domani]

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

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

[Hannes Domani]

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