[Patch V4 5/5] UefiCpuPkg: Eliminate the second INIT-SIPI-SIPI sequence.

["Yuanhao Xie" <yuanhao.xie@intel.com>]

When both the PEI and DXE phases operate in the same execution
mode(32-bit/64-bit), the BSP send a special start-up signal during
the DXE phase to awaken the Application APs.

To eliminate the need for the INIT-SIPI-SIPI sequence at the beginning
of the DXE phase, the BSP call the SwitchApContext function to trigger
the special  start-up signal. By writing the specified
StartupSignalValue to the designated StartupSignalAddress, the BSP
wakes up the APs from mwait mode. Once the APs receive the
MP_HAND_OFF_SIGNAL value, they are awakened and proceed to execute the
SwitchContextPerAp procedure. They enter another while loop,
transitioning their context from the PEI phase to the DXE phase.

The original state transitions for an AP during the procedure are as
follows:
Idle ----> Ready ----> Busy ----> Idle
      [BSP]      [AP]      [AP]

Instead of init-sipi-sipi sequence, we make use of a
start-up signal to awaken the APs and transfer their context from
PEI to DXE. Consequently, APs, rather than the BSP, to set their state
to CpuStateReady.

Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Eric Dong <eric.dong@intel.com>
Cc: Ray Ni <ray.ni@intel.com>
Cc: Rahul Kumar <rahul1.kumar@intel.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Yuanhao Xie <yuanhao.xie@intel.com>
---
 UefiCpuPkg/Library/MpInitLib/MpLib.c | 138 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++--
 UefiCpuPkg/Library/MpInitLib/MpLib.h |   9 +++++++++
 2 files changed, 145 insertions(+), 2 deletions(-)

diff --git a/UefiCpuPkg/Library/MpInitLib/MpLib.c b/UefiCpuPkg/Library/MpInitLib/MpLib.c
index f904751b0d..737e03ffc5 100644
--- a/UefiCpuPkg/Library/MpInitLib/MpLib.c
+++ b/UefiCpuPkg/Library/MpInitLib/MpLib.c
@@ -680,7 +680,7 @@ PlaceAPInMwaitLoopOrRunLoop (
       // Place AP in MWAIT-loop
       //
       AsmMonitor ((UINTN)ApStartupSignalBuffer, 0, 0);
-      if (*ApStartupSignalBuffer != WAKEUP_AP_SIGNAL) {
+      if ((*ApStartupSignalBuffer != WAKEUP_AP_SIGNAL) && (*ApStartupSignalBuffer != MP_HAND_OFF_SIGNAL)) {
         //
         // Check AP start-up signal again.
         // If AP start-up signal is not set, place AP into
@@ -701,7 +701,7 @@ PlaceAPInMwaitLoopOrRunLoop (
     // If AP start-up signal is written, AP is waken up
     // otherwise place AP in loop again
     //
-    if (*ApStartupSignalBuffer == WAKEUP_AP_SIGNAL) {
+    if ((*ApStartupSignalBuffer == WAKEUP_AP_SIGNAL) || (*ApStartupSignalBuffer == MP_HAND_OFF_SIGNAL)) {
       break;
     }
   }
@@ -729,6 +729,7 @@ ApWakeupFunction (
   UINT64            ApTopOfStack;
   UINTN             CurrentApicMode;
   AP_STACK_DATA     *ApStackData;
+  UINT32            OriginalValue;
 
   //
   // AP's local APIC settings will be lost after received INIT IPI
@@ -769,6 +770,15 @@ ApWakeupFunction (
       // Clear AP start-up signal when AP waken up
       //
       ApStartupSignalBuffer = CpuMpData->CpuData[ProcessorNumber].StartupApSignal;
+      OriginalValue         = InterlockedCompareExchange32 (
+                                (UINT32 *)ApStartupSignalBuffer,
+                                MP_HAND_OFF_SIGNAL,
+                                0
+                                );
+      if (OriginalValue == MP_HAND_OFF_SIGNAL) {
+        SetApState (&CpuMpData->CpuData[ProcessorNumber], CpuStateReady);
+      }
+
       InterlockedCompareExchange32 (
         (UINT32 *)ApStartupSignalBuffer,
         WAKEUP_AP_SIGNAL,
@@ -887,6 +897,32 @@ ApWakeupFunction (
   }
 }
 
+/**
+  This function serves as the entry point for APs when
+  they are awakened by the stores in the memory address
+  indicated by the MP_HANDOFF_INFO structure.
+
+  @param[in] CpuMpData        Pointer to PEI CPU MP Data
+**/
+VOID
+EFIAPI
+DxeApEntryPoint (
+  CPU_MP_DATA  *CpuMpData
+  )
+{
+  UINTN  ProcessorNumber;
+
+  GetProcessorNumber (CpuMpData, &ProcessorNumber);
+  InterlockedIncrement ((UINT32 *)&CpuMpData->FinishedCount);
+  RestoreVolatileRegisters (&CpuMpData->CpuData[0].VolatileRegisters, FALSE);
+  PlaceAPInMwaitLoopOrRunLoop (
+    CpuMpData->ApLoopMode,
+    CpuMpData->CpuData[ProcessorNumber].StartupApSignal,
+    CpuMpData->ApTargetCState
+    );
+  ApWakeupFunction (CpuMpData, ProcessorNumber);
+}
+
 /**
   Wait for AP wakeup and write AP start-up signal till AP is waken up.
 
@@ -1457,6 +1493,32 @@ CalculateTimeout (
   }
 }
 
+/**
+  Switch Context for each AP.
+
+**/
+VOID
+EFIAPI
+SwitchContextPerAp (
+  VOID
+  )
+{
+  UINTN            ProcessorNumber;
+  CPU_MP_DATA      *CpuMpData;
+  CPU_INFO_IN_HOB  *CpuInfoInHob;
+
+  CpuMpData    = GetCpuMpData ();
+  CpuInfoInHob = (CPU_INFO_IN_HOB *)(UINTN)CpuMpData->CpuInfoInHob;
+  GetProcessorNumber (CpuMpData, &ProcessorNumber);
+
+  SwitchStack (
+    (SWITCH_STACK_ENTRY_POINT)(UINTN)DxeApEntryPoint,
+    (VOID *)(UINTN)CpuMpData,
+    NULL,
+    (VOID *)((UINTN)CpuInfoInHob[ProcessorNumber].ApTopOfStack)
+    );
+}
+
 /**
   Checks whether timeout expires.
 
@@ -1840,6 +1902,44 @@ GetBspNumber (
   return BspNumber;
 }
 
+/**
+  This function is intended to be invoked by the BSP in order
+  to wake up the AP. The BSP accomplishes this by triggering a
+  start-up signal, which in turn causes any APs that are
+  currently in a loop on the PEI-prepared memory to awaken and
+  begin running the procedure called SwitchContextPerAp.
+  This procedure allows the AP to switch to another section of
+  memory and continue its loop there.
+
+  @param[in] MpHandOff  Pointer to MP hand-off data structure.
+**/
+VOID
+SwitchApContext (
+  IN MP_HAND_OFF  *MpHandOff
+  )
+{
+  UINTN   Index;
+  UINT32  BspNumber;
+
+  BspNumber = GetBspNumber (MpHandOff);
+
+  for (Index = 0; Index < MpHandOff->CpuCount; Index++) {
+    if (Index != BspNumber) {
+      *(UINTN *)(UINTN)MpHandOff->Info[Index].StartupProcedureAddress = (UINTN)SwitchContextPerAp;
+      *(UINT32 *)(UINTN)MpHandOff->Info[Index].StartupSignalAddress   = MpHandOff->StartupSignalValue;
+    }
+  }
+
+  //
+  // Wait all APs waken up if this is not the 1st broadcast of SIPI
+  //
+  for (Index = 0; Index < MpHandOff->CpuCount; Index++) {
+    if (Index != BspNumber) {
+      WaitApWakeup ((UINT32 *)(UINTN)(MpHandOff->Info[Index].StartupSignalAddress));
+    }
+  }
+}
+
 /**
   Get pointer to MP_HAND_OFF GUIDed HOB.
 
@@ -2073,6 +2173,40 @@ MpInitLibInitialize (
       CpuInfoInHob[Index].ApicId           = MpHandOff->Info[Index].ApicId;
       CpuInfoInHob[Index].Health           = MpHandOff->Info[Index].Health;
     }
+
+    DEBUG ((DEBUG_INFO, "MpHandOff->WaitLoopExecutionMode: %04d, sizeof (VOID *): %04d\n", MpHandOff->WaitLoopExecutionMode, sizeof (VOID *)));
+    if (MpHandOff->WaitLoopExecutionMode == sizeof (VOID *)) {
+      ASSERT (CpuMpData->ApLoopMode != ApInHltLoop);
+
+      CpuMpData->FinishedCount = 0;
+      CpuMpData->InitFlag      = ApInitDone;
+      SaveCpuMpData (CpuMpData);
+      //
+      // In scenarios where both the PEI and DXE phases run in the same
+      // execution mode (32bit or 64bit), the BSP triggers
+      // a start-up signal during the DXE phase to wake up the APs. This causes any
+      // APs that are currently in a loop on the memory prepared during the PEI
+      // phase to awaken and run the SwitchContextPerAp procedure. This procedure
+      // enables the APs to switch to a different memory section and continue their
+      // looping process there.
+      //
+      SwitchApContext (MpHandOff);
+      ASSERT (CpuMpData->FinishedCount == (CpuMpData->CpuCount - 1));
+
+      //
+      // Set Apstate as Idle, otherwise Aps cannot be waken-up again.
+      // If any enabled AP is not idle, return EFI_NOT_READY during waken-up.
+      //
+      for (Index = 0; Index < CpuMpData->CpuCount; Index++) {
+        SetApState (&CpuMpData->CpuData[Index], CpuStateIdle);
+      }
+
+      //
+      // Initialize global data for MP support
+      //
+      InitMpGlobalData (CpuMpData);
+      return EFI_SUCCESS;
+    }
   }
 
   if (!GetMicrocodePatchInfoFromHob (
diff --git a/UefiCpuPkg/Library/MpInitLib/MpLib.h b/UefiCpuPkg/Library/MpInitLib/MpLib.h
index a7f36d323b..763db4963d 100644
--- a/UefiCpuPkg/Library/MpInitLib/MpLib.h
+++ b/UefiCpuPkg/Library/MpInitLib/MpLib.h
@@ -474,6 +474,15 @@ GetWakeupBuffer (
   IN UINTN  WakeupBufferSize
   );
 
+/**
+  Switch Context for each AP.
+
+**/
+VOID
+SwitchApContext (
+  IN MP_HAND_OFF  *MpHandOff
+  );
+
 /**
   Get available EfiBootServicesCode memory below 4GB by specified size.
 
-- 
2.36.1.windows.1