Fix vCont multi-threading support

Updates MRI core to version 1.1-20200510-0.

Refactored the vCont multi-threading support again to better handle any
combination of continue and/or stepping actions that are sent from GDB
in a single vCont command. This includes a modification to requirements
for ports implementing Platform_RtosSetThreadState() to now support a
thread-id of MRI_PLATFORM_ALL_FROZEN_THREADS. This new special
thread-id indicates to the port that it should update the state of any
threads still in the initial frozen state after the previously parsed
vCont actions have been applied. Ports now also have to implement a
Platform_RtosRestorePrevThreadState() API to restore the state of the
threads to match the way they were configured after the last exit from
mriDebugException(). This is used to restore the thawed/single-stepping
state of threads while stepping through a range of addresses. This
pushes the responsibility to know how each thread was configured at the
beginning of a ranged single step onto the port instead of the MRI core
where it tried to maintain it unsuccessfully before.

The big change in this commit is that vCont now parses its parameters
twice when a port supports Platform_RtosSetThreadState(). On the first
pass it is checking for parsing errors and determining the most
specific continue or single step action to apply to the currently
halted thread. This action is used to determine if the halted thread
should be advanced past a hard coded breakpoint and if single stepping
over a hardcoded breakpoint on the halted thread, it is enough to send
GDB a T packet and continue GDB command handling rather than actually
continuing execution in single step mode. The second pass is used to
call the Platform_RtosSetThreadState() for each action encountered in
the vCont command from GDB, letting the port's implementation manage
the resulting list of states for all of the threads and the MRI core
only needs to remember if it needs to enable single stepping or not.
This makes it much easier to handle an arbirary list of actions sent
from GDB and the core now needs to make very few assumptions about the
nature of the action lists (the count, order, combination of continue
and single step, etc).

I did need to increase the size of the mriDebuggerStack as the vCont
handler itself now uses 100 bytes of stack while parsing the action
list sent by GDB.

Only fill mriCortexMDebuggerStack @ init. Was previously filling it
before every entry into MRI but really only needs to be done once from
mriCortexMInit().

I also made some other KernelDebug/ThreadDebug updates while code
reviewing and running a test pass on the latest MRI updates:
* Renamed the DEBUG_*_BREAK_ON_SETUP defines to DEBUG_*_BREAK_IN_SETUP.
* Cleaned up some comments in the ThreadDebug sources.
* I decreased IDLE_THREAD_STACK_SIZE to free up space that was found to
  not be required by mriIdle() thread while running the test pass.
* Switched ThreadList::findThreadId() to use a binary search instead of
  a linear search.
* mriDebugMonitorHandler() always checks to see if it needs to
  re-enable DTW/FPB. There is no reason to skip this check.
* Added a g_controlC flag in addition to the control C flag in MRI
  itself since the flag in MRI doesn't get cleared until leaving
  mriDebugException(). There were race conditions that as breakpoints
  were enabled by GDB, they would fire and mriDebugMonitorHandler()
  would think that CTRL+C had just been sent when it hadn't.
* Related to the previous item, I updated mriDebugMonitorHandler() to
  ignore debug events that occur while inside MRI since GDB itself may
  read from addresses on which it has read watchpoints and we want to
  ignore such debug events.

Author: adamgreen

libraries/KernelDebug/examples/KernelDebug/KernelDebug.ino

@@ -5,7 +5,7 @@
 
 #include <KernelDebug.h>
 
-KernelDebug kernelDebug(SERIAL1_TX, SERIAL1_RX, USART1_IRQn, 230400, DEBUG_BREAK_ON_SETUP);
+KernelDebug kernelDebug(SERIAL1_TX, SERIAL1_RX, USART1_IRQn, 230400, DEBUG_BREAK_IN_SETUP);
 
 void setup() {
 

libraries/KernelDebug/src/KernelDebug.cpp

@@ -612,3 +612,7 @@ int Platform_RtosIsSetThreadStateSupported(void)
 void Platform_RtosSetThreadState(uint32_t threadId, PlatformThreadState state)
 {
 }
+
+void Platform_RtosRestorePrevThreadState(void)
+{
+}

libraries/KernelDebug/src/KernelDebug.h

@@ -36,17 +36,17 @@
 namespace arduino {
 
 // Pass as breakInSetup parameter of constructor to halt in setup().
-#define DEBUG_BREAK_ON_SETUP    true
+#define DEBUG_BREAK_IN_SETUP    true
 // Pass as breakInSetup parameter of constructors to NOT halt in setup().
-#define DEBUG_NO_BREAK_ON_SETUP false
+#define DEBUG_NO_BREAK_IN_SETUP false
 
 
 class KernelDebug {
 public:
     // You must declare your KernelDebug object as a global.
     // Example:
     //      KernelDebug debug(SERIAL1_TX, SERIAL1_RX, USART1_IRQn, 230400, DEBUG_BREAK_ON_SETUP);
-    KernelDebug(PinName txPin, PinName rxPin, IRQn_Type irq, uint32_t baudRate=230400, bool breakInSetup=DEBUG_BREAK_ON_SETUP);
+    KernelDebug(PinName txPin, PinName rxPin, IRQn_Type irq, uint32_t baudRate=230400, bool breakInSetup=DEBUG_BREAK_IN_SETUP);
 
     // You should never let your DebugSerial object go out of scope. Make it global or static. To warn you if you do
     // let it go out of scope by mistake, this destructor will break into GDB and then enter an infinite loop.

libraries/KernelDebug/src/armv7-m_asm.S

@@ -109,20 +109,14 @@ mriExceptionHandler:
     bl      mriCortexHandleDebuggerFault
     pop     {r1, pc}
 
-    /* Fill debugger stack with 0xDEADBEEF before switching MSP to it. */
+    /* Point R0 to the top of the debugger stack, where MSP should be pointed. */
 1$: ldr     r0, =mriCortexMDebuggerStack
-    ldr     r1, =CORTEXM_DEBUGGER_STACK_FILL
-    mov     r2, r1
-    ldr     r3, =CORTEXM_DEBUGGER_STACK_SIZE
-2$: cbz     r3, 3$
-    strd    r1, r2, [r0], #8
-    subs    r3, #1
-    b       2$
-    /* R0 is now pointing to top of stack, where MSP should be pointed to. */
+    ldr     r1, =CORTEXM_DEBUGGER_STACK_SIZE * 8
+    add     r0, r0, r1
 
     /* Save away copy of MSP value at the time of the fault into R0. */
 3$: mrs     r1, msp
-    /* Set MSP to top of debugger stack returned from mriCortexMDebuggerStack. */
+    /* Set MSP to top of debugger stack. */
     msr     msp, r0
 
     /* Saving integer registers to debugger stack. */

libraries/MRI/src/architectures/armv7-m/armv7-m.h

@@ -46,9 +46,9 @@
 */
 #define CORTEXM_DEBUGGER_STACK_FILL            0xDEADBEEF
 #if MRI_DEVICE_HAS_FPU
-    #define CORTEXM_DEBUGGER_STACK_SIZE        180
+    #define CORTEXM_DEBUGGER_STACK_SIZE        193
 #else
-    #define CORTEXM_DEBUGGER_STACK_SIZE        45
+    #define CORTEXM_DEBUGGER_STACK_SIZE        58
 #endif
 
 

libraries/MRI/src/architectures/armv7-m/armv7-m.x

@@ -131,6 +131,7 @@ static const char g_targetXml[] =
 void mriExceptionHandler(void);
 
 
+static void fillDebuggerStack(void);
 static void clearState(void);
 static void determineSubPriorityBitCount(void);
 static void configureDWTandFPB(void);
@@ -147,6 +148,7 @@ void mriCortexMInit(Token* pParameterTokens, uint8_t debugMonPriority, IRQn_Type
     }
     (void)pParameterTokens;
 
+    fillDebuggerStack();
     clearState();
     determineSubPriorityBitCount();
     configureDWTandFPB();
@@ -163,6 +165,15 @@ void mriCortexMInit(Token* pParameterTokens, uint8_t debugMonPriority, IRQn_Type
         enableDebugMonitorAtSpecifiedPriority(debugMonPriority);
 }
 
+static void fillDebuggerStack(void)
+{
+    uint64_t fillValue = ((uint64_t)CORTEXM_DEBUGGER_STACK_FILL << 32) | (uint64_t)CORTEXM_DEBUGGER_STACK_FILL;
+    size_t i;
+
+    for (i = 0 ; i < sizeof(mriCortexMDebuggerStack)/sizeof(mriCortexMDebuggerStack[0]) ; i++)
+        mriCortexMDebuggerStack[i] = fillValue;
+}
+
 static void clearState(void)
 {
     memset(&mriCortexMState, 0, sizeof(mriCortexMState));