ARM: Detect and skip udelay() functions in linux kernel.

This change speeds up booting, especially in MP cases, by not executing
udelay() on the core but instead skipping ahead tha amount of time that is being
delayed.

6 files changed, 96 insertions, 0 deletions

diff --git a/src/arch/arm/linux/system.cc b/src/arch/arm/linux/system.cc
index 38024c058..7aff2b6ef 100644
--- a/src/arch/arm/linux/system.cc
+++ b/src/arch/arm/linux/system.cc
@@ -47,9 +47,11 @@
 #include "base/loader/object_file.hh"
 #include "base/loader/symtab.hh"
 #include "cpu/thread_context.hh"
+#include "kern/linux/events.hh"
 #include "mem/physical.hh"
 
 using namespace ArmISA;
+using namespace Linux;
 
 LinuxArmSystem::LinuxArmSystem(Params *p)
     : ArmSystem(p)
@@ -96,6 +98,24 @@ LinuxArmSystem::LinuxArmSystem(Params *p)
     if (!kernelPanicEvent)
         panic("could not find kernel symbol \'panic\'");
 #endif
+
+    // With ARM udelay() is #defined to __udelay
+    Addr addr = 0;
+    if (kernelSymtab->findAddress("__udelay", addr)) {
+        uDelaySkipEvent = new UDelayEvent(&pcEventQueue, "__udelay",
+                fixFuncEventAddr(addr), 1000, 0);
+    } else {
+        panic("couldn't find kernel symbol \'udelay\'");
+    }
+
+    // constant arguments to udelay() have some precomputation done ahead of
+    // time. Constant comes from code.
+    if (kernelSymtab->findAddress("__const_udelay", addr)) {
+        constUDelaySkipEvent = new UDelayEvent(&pcEventQueue, "__const_udelay",
+                fixFuncEventAddr(addr), 1000, 107374);
+    } else {
+        panic("couldn't find kernel symbol \'udelay\'");
+    }
 }
 
 void
@@ -115,6 +135,10 @@ LinuxArmSystem::initState()
 
 LinuxArmSystem::~LinuxArmSystem()
 {
+    if (uDelaySkipEvent)
+        delete uDelaySkipEvent;
+    if (constUDelaySkipEvent)
+        delete constUDelaySkipEvent;
 }
 
 LinuxArmSystem *
diff --git a/src/arch/arm/linux/system.hh b/src/arch/arm/linux/system.hh
index 4e5ebcd73..2ef65fea2 100644
--- a/src/arch/arm/linux/system.hh
+++ b/src/arch/arm/linux/system.hh
@@ -74,6 +74,19 @@ class LinuxArmSystem : public ArmSystem
     /** Event to halt the simulator if the kernel calls panic()  */
     BreakPCEvent *kernelPanicEvent;
 #endif
+    /**
+     * PC based event to skip udelay(<time>) calls and quiesce the
+     * processor for the appropriate amount of time. This is not functionally
+     * required but does speed up simulation.
+     */
+    Linux::UDelayEvent *uDelaySkipEvent;
+
+    /** Another PC based skip event for const_udelay(). Similar to the udelay
+     * skip, but this function precomputes the first multiply that is done
+     * in the generic case since the parameter is known at compile time.
+     * Thus we need to do some division to get back to us.
+     */
+    Linux::UDelayEvent *constUDelaySkipEvent;
 };
 
 #endif // __ARCH_ARM_LINUX_SYSTEM_HH__
diff --git a/src/cpu/simple/atomic.cc b/src/cpu/simple/atomic.cc
index 27635d3ce..6aa0eb64e 100644
--- a/src/cpu/simple/atomic.cc
+++ b/src/cpu/simple/atomic.cc
@@ -641,6 +641,9 @@ AtomicSimpleCPU::tick()
             checkForInterrupts();
 
         checkPcEventQueue();
+        // We must have just got suspended by a PC event
+        if (_status == Idle)
+            return;
 
         Fault fault = NoFault;
 
diff --git a/src/cpu/simple/timing.cc b/src/cpu/simple/timing.cc
index 632e83356..aca48e5d4 100644
--- a/src/cpu/simple/timing.cc
+++ b/src/cpu/simple/timing.cc
@@ -714,6 +714,10 @@ TimingSimpleCPU::fetch()
 
     checkPcEventQueue();
 
+    // We must have just got suspended by a PC event
+    if (_status == Idle)
+        return;
+
     TheISA::PCState pcState = thread->pcState();
     bool needToFetch = !isRomMicroPC(pcState.microPC()) && !curMacroStaticInst;
 
diff --git a/src/kern/linux/events.cc b/src/kern/linux/events.cc
index 60aa857ac..75c2b6f7f 100644
--- a/src/kern/linux/events.cc
+++ b/src/kern/linux/events.cc
@@ -44,11 +44,13 @@
 #include <sstream>
 
 #include "base/trace.hh"
+#include "arch/utility.hh"
 #include "cpu/thread_context.hh"
 #include "kern/linux/events.hh"
 #include "kern/linux/printk.hh"
 #include "kern/system_events.hh"
 #include "sim/arguments.hh"
+#include "sim/pseudo_inst.hh"
 #include "sim/system.hh"
 
 namespace Linux {
@@ -66,4 +68,27 @@ DebugPrintkEvent::process(ThreadContext *tc)
     SkipFuncEvent::process(tc);
 }
 
+void
+UDelayEvent::process(ThreadContext *tc)
+{
+    int arg_num  = 0;
+
+    // Get the time in native size
+    uint64_t time = TheISA::getArgument(tc, arg_num,  (uint16_t)-1, false);
+
+    // convert parameter to ns
+    if (argDivToNs)
+        time /= argDivToNs;
+
+    time *= argMultToNs;
+
+    // Convert ns to ticks
+    time *= SimClock::Int::ns;
+
+    SkipFuncEvent::process(tc);
+
+    PseudoInst::quiesceNs(tc, time);
+}
+
+
 } // namespace linux
diff --git a/src/kern/linux/events.hh b/src/kern/linux/events.hh
index e36a72dde..3f5f2526f 100644
--- a/src/kern/linux/events.hh
+++ b/src/kern/linux/events.hh
@@ -44,6 +44,33 @@ class DebugPrintkEvent : public SkipFuncEvent
     virtual void process(ThreadContext *xc);
 };
 
+/** A class to skip udelay() and related calls in the kernel.
+ * This class has two additional parameters that take the argument to udelay and
+ * manipulated it to come up with ns and eventually ticks to quiesce for.
+ * See descriptions of argDivToNs and argMultToNs below.
+ */
+class UDelayEvent : public SkipFuncEvent
+{
+  private:
+    /** value to divide arg by to create ns. This is present beacues the linux
+     * kernel code sometime precomputes the first multiply that is done in
+     * udelay() if the parameter is a constant. We need to undo it so here is
+     * how. */
+    uint64_t argDivToNs;
+
+    /** value to multiple arg by to create ns. Nominally, this is 1000 to
+     * convert us to ns, but since linux can do some preprocessing of constant
+     * values something else might be required. */
+    uint64_t argMultToNs;
+
+  public:
+    UDelayEvent(PCEventQueue *q, const std::string &desc, Addr addr,
+            uint64_t mult, uint64_t div)
+        : SkipFuncEvent(q, desc, addr), argDivToNs(div), argMultToNs(mult) {}
+    virtual void process(ThreadContext *xc);
+};
+
+
 }
 
 #endif