Bug 24457 - X87 FPU Special Purpose Registers

Summary:
  - For 'register read --all' command on x86_64-Linux Platform:

      -- Provide correct values of X87 FPU Special Purpose Registers
      -- Both 32-bit & 64-bit inferiors give correct values on this
         Platform

  - Added a Test Vector:
      -- To verify the expected behaviour of the command

Signed-off-by: Abhishek Aggarwal <abhishek.a.aggarwal@intel.com>

Reviewers: ashok.thirumurthi, granata.enrico, tfiala, clayborg

Differential Revision: http://reviews.llvm.org/D12592

llvm-svn: 246955

lldb/source/Plugins/Process/Linux/NativeRegisterContextLinux_x86_64.cpp

@@ -422,6 +422,10 @@ NativeRegisterContextLinux_x86_64::NativeRegisterContextLinux_x86_64 (const Arch
 
     // Clear out the FPR state.
     ::memset(&m_fpr, 0, sizeof(FPR));
+
+    // Store byte offset of fctrl (i.e. first register of FPR)
+    const RegisterInfo *reg_info_fctrl = GetRegisterInfoByName("fctrl");
+    m_fctrl_offset_in_userarea = reg_info_fctrl->byte_offset;
 }
 
 // CONSIDER after local and llgs debugging are merged, register set support can
@@ -559,8 +563,16 @@ NativeRegisterContextLinux_x86_64::ReadRegister (const RegisterInfo *reg_info, R
     }
 
     // Get pointer to m_fpr.xstate.fxsave variable and set the data from it.
-    assert (reg_info->byte_offset < sizeof(m_fpr));
-    uint8_t *src = (uint8_t *)&m_fpr + reg_info->byte_offset;
+
+    // Byte offsets of all registers are calculated wrt 'UserArea' structure.
+    // However, ReadFPR() reads fpu registers {using ptrace(PTRACE_GETFPREGS,..)}
+    // and stores them in 'm_fpr' (of type FPR structure). To extract values of fpu
+    // registers, m_fpr should be read at byte offsets calculated wrt to FPR structure.
+
+    // Since, FPR structure is also one of the member of UserArea structure.
+    // byte_offset(fpu wrt FPR) = byte_offset(fpu wrt UserArea) - byte_offset(fctrl wrt UserArea)
+    assert ( (reg_info->byte_offset - m_fctrl_offset_in_userarea) < sizeof(m_fpr));
+    uint8_t *src = (uint8_t *)&m_fpr + reg_info->byte_offset - m_fctrl_offset_in_userarea;
     switch (reg_info->byte_size)
     {
         case 2:
@@ -620,8 +632,16 @@ NativeRegisterContextLinux_x86_64::WriteRegister (const RegisterInfo *reg_info,
         else
         {
             // Get pointer to m_fpr.xstate.fxsave variable and set the data to it.
-            assert (reg_info->byte_offset < sizeof(m_fpr));
-            uint8_t *dst = (uint8_t *)&m_fpr + reg_info->byte_offset;
+
+            // Byte offsets of all registers are calculated wrt 'UserArea' structure.
+            // However, WriteFPR() takes m_fpr (of type FPR structure) and writes only fpu
+            // registers using ptrace(PTRACE_SETFPREGS,..) API. Hence fpu registers should
+            // be written in m_fpr at byte offsets calculated wrt FPR structure.
+
+            // Since, FPR structure is also one of the member of UserArea structure.
+            // byte_offset(fpu wrt FPR) = byte_offset(fpu wrt UserArea) - byte_offset(fctrl wrt UserArea)
+            assert ( (reg_info->byte_offset - m_fctrl_offset_in_userarea) < sizeof(m_fpr));
+            uint8_t *dst = (uint8_t *)&m_fpr + reg_info->byte_offset - m_fctrl_offset_in_userarea;
             switch (reg_info->byte_size)
             {
                 case 2:

lldb/source/Plugins/Process/Linux/NativeRegisterContextLinux_x86_64.h

@@ -136,6 +136,7 @@ namespace process_linux {
         YMM m_ymm_set;
         RegInfo m_reg_info;
         uint64_t m_gpr_x86_64[k_num_gpr_registers_x86_64];
+        uint32_t m_fctrl_offset_in_userarea;
 
         // Private member methods.
         bool IsRegisterSetAvailable (uint32_t set_index) const;

lldb/test/functionalities/register/Makefile

@@ -1,5 +1,5 @@
 LEVEL = ../../make
 
-CXX_SOURCES := main.cpp
+CXX_SOURCES := main.cpp a.cpp
 
 include $(LEVEL)/Makefile.rules

lldb/test/functionalities/register/TestRegisters.py

@@ -35,6 +35,13 @@ class RegisterCommandsTestCase(TestBase):
         self.buildDefault()
         self.fp_register_write()
 
+    def test_fp_special_purpose_register_read(self):
+        """Test commands that read fpu special purpose registers."""
+        if not self.getArchitecture() in ['amd64', 'i386', 'x86_64']:
+            self.skipTest("This test requires x86 or x86_64 as the architecture for the inferior")
+        self.buildDefault()
+        self.fp_special_purpose_register_read()
+
     def test_register_expressions(self):
         """Test expression evaluation with commands related to registers."""
         if not self.getArchitecture() in ['amd64', 'i386', 'x86_64']:
@@ -152,6 +159,69 @@ class RegisterCommandsTestCase(TestBase):
         self.expect("register read " + register,
             substrs = [register + ' = ', new_value])
 
+    def fp_special_purpose_register_read(self):
+        exe = os.path.join(os.getcwd(), "a.out")
+
+        # Create a target by the debugger.
+        target = self.dbg.CreateTarget(exe)
+        self.assertTrue(target, VALID_TARGET)
+
+        # Find the line number to break inside a.cpp.
+        self.line = line_number('a.cpp', '// Set break point at this line.')
+
+        # Set breakpoint
+        lldbutil.run_break_set_by_file_and_line (self, "a.cpp", self.line, num_expected_locations=1, loc_exact=True)
+
+        # Launch the process, and do not stop at the entry point.
+        self.runCmd ("run", RUN_SUCCEEDED)
+
+        process = target.GetProcess()
+        self.assertTrue(process.GetState() == lldb.eStateStopped,
+                        PROCESS_STOPPED)
+
+        thread = process.GetThreadAtIndex(0)
+        self.assertTrue(thread.IsValid(), "current thread is valid")
+
+        currentFrame = thread.GetFrameAtIndex(0)
+        self.assertTrue(currentFrame.IsValid(), "current frame is valid")
+
+        # Extract the value of fstat and ftag flag at the point just before
+        # we start pushing floating point values on st% register stack
+        value = currentFrame.FindValue("fstat", lldb.eValueTypeRegister)
+        error = lldb.SBError()
+        reg_value_fstat_initial = value.GetValueAsUnsigned(error, 0)
+
+        self.assertTrue(error.Success(), "reading a value for fstat")
+        value = currentFrame.FindValue("ftag", lldb.eValueTypeRegister)
+        error = lldb.SBError()
+        reg_value_ftag_initial = value.GetValueAsUnsigned(error, 0)
+
+        self.assertTrue(error.Success(), "reading a value for ftag")
+        fstat_top_pointer_initial = (reg_value_fstat_initial & 0x3800)>>11
+
+        # Execute 'si' aka 'thread step-inst' instruction 5 times and with
+        # every execution verify the value of fstat and ftag registers
+        for x in range(0,5):
+            # step into the next instruction to push a value on 'st' register stack
+            self.runCmd ("si", RUN_SUCCEEDED)
+
+            # Verify fstat and save it to be used for verification in next execution of 'si' command
+            if not (reg_value_fstat_initial & 0x3800):
+                self.expect("register read fstat",
+                    substrs = ['fstat' + ' = ', str("0x%0.4x" %((reg_value_fstat_initial & ~(0x3800))| 0x3800))])
+                reg_value_fstat_initial = ((reg_value_fstat_initial & ~(0x3800))| 0x3800)
+                fstat_top_pointer_initial = 7
+            else :
+                self.expect("register read fstat",
+                    substrs = ['fstat' + ' = ', str("0x%0.4x" % (reg_value_fstat_initial - 0x0800))])
+                reg_value_fstat_initial = (reg_value_fstat_initial - 0x0800)
+                fstat_top_pointer_initial -= 1
+
+            # Verify ftag and save it to be used for verification in next execution of 'si' command
+            self.expect("register read ftag",
+                substrs = ['ftag' + ' = ', str("0x%0.4x" % (reg_value_ftag_initial | (1<< fstat_top_pointer_initial)))])
+            reg_value_ftag_initial = reg_value_ftag_initial | (1<< fstat_top_pointer_initial)
+
     def fp_register_write(self):
         exe = os.path.join(os.getcwd(), "a.out")
 

lldb/test/functionalities/register/a.cpp

@@ -0,0 +1,40 @@
+//===-- a.cpp ------------------------------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+#include <stdio.h>
+
+long double
+return_long_double (long double value)
+{
+  float a=2, b=4,c=8, d=16, e=32, f=64, k=128, l=256, add=0;
+__asm__ ( "fld %1 ;"
+	"fld %2 ;"
+	"fld %3 ;"
+	"fld %4 ;"
+	"fld %5 ;"
+	"fld %6 ;"
+	"fld %7 ;"
+	"fadd ;" : "=g" (add) : "g" (a), "g" (b), "g" (c), "g" (d), "g" (e), "g" (f), "g" (k), "g" (l) );  // Set break point at this line.
+  return value;
+}
+
+long double
+outer_return_long_double (long double value)
+{
+  long double val = return_long_double(value);
+  val *= 2 ;
+  return val;
+}
+
+long double
+outermost_return_long_double (long double value)
+{
+  long double val = outer_return_long_double(value);
+  val *= 2 ;
+  return val;
+}

lldb/test/functionalities/register/main.cpp

@@ -15,6 +15,8 @@
 #include <chrono>
 #include <thread>
 
+long double outermost_return_long_double (long double my_long_double);
+
 int main (int argc, char const *argv[])
 {
 #if defined(__linux__)
@@ -32,6 +34,7 @@ int main (int argc, char const *argv[])
 
     char my_string[] = {'a', 'b', 'c', 'd', 'e', 'f', 'g', 0};
     double my_double = 1234.5678;
+    long double my_long_double = 1234.5678;
 
     // For simplicity assume that any cmdline argument means wait for attach.
     if (argc > 1)
@@ -43,5 +46,6 @@ int main (int argc, char const *argv[])
 
     printf("my_string=%s\n", my_string);
     printf("my_double=%g\n", my_double);
+    outermost_return_long_double (my_long_double);
     return 0;
 }