Add Linux perf JIT support (/tmp/perf-$pid.map)

'perf' is the standard builtin tool for performance analysis on recent
Linux kernel. Its source code is shipped within the kernel repository.

'perf' has basic support for JIT. For each process, it can read a file
named /tmp/perf-$PID.map. This file contains mapping from address
range to function name in the format:

  41187e2a 1a EmuCode_804a33fc

with the following entries:

 1. beginning of the range (hexadecimal);
 2. size of the range (hexadecimal);
 3. name of the function.

We supply the PowerPC address of the basic block as function name.

Usage:

    DOLPHIN_PERF_DIR=/tmp dolphin-emu &
    perf record -F99 -p $(pgrep dolphin-emu) --call-graph dwarf
    perf script | stackcollapse-perf.pl | grep EmuCode__ | flamegraph.pl > profile.svg

Issue: perf does not have support for region invalidation. It reads
the file in postprocessing. It probably does not work very well if a
JIT region is reused for another basic block: wrong results should be
expected in this case. Currently, nothing is done to prevent this.

Source/Core/Core/PowerPC/JitCommon/JitCache.cpp

@@ -9,6 +9,14 @@
 // performance hit, it's not enabled by default, but it's useful for
 // locating performance issues.
 
+#include <cinttypes>
+
+#ifdef _WIN32
+#include <process.h>
+#else
+#include <unistd.h>
+#endif
+
 #include "disasm.h"
 
 #include "Common/CommonTypes.h"
@@ -50,6 +58,15 @@ using namespace Gen;
 #if defined USE_OPROFILE && USE_OPROFILE
 		agent = op_open_agent();
 #endif
+
+		const char* perf_dir = getenv("DOLPHIN_PERF_DIR");
+		if (perf_dir && perf_dir[0])
+		{
+			std::string filename = StringFromFormat("%s/perf-%d.map",
+			  perf_dir, getpid());
+			m_perf_map_file.open(filename, std::ios::trunc);
+		}
+
 		iCache.fill(JIT_ICACHE_INVALID_BYTE);
 		iCacheEx.fill(JIT_ICACHE_INVALID_BYTE);
 		iCacheVMEM.fill(JIT_ICACHE_INVALID_BYTE);
@@ -69,6 +86,9 @@ using namespace Gen;
 #ifdef USE_VTUNE
 		iJIT_NotifyEvent(iJVM_EVENT_TYPE_SHUTDOWN, nullptr);
 #endif
+
+		if (m_perf_map_file.is_open())
+			m_perf_map_file.close();
 	}
 
 	// This clears the JIT cache. It's called from JitCache.cpp when the JIT cache
@@ -179,6 +199,13 @@ using namespace Gen;
 		jmethod.method_name = b.blockName;
 		iJIT_NotifyEvent(iJVM_EVENT_TYPE_METHOD_LOAD_FINISHED, (void*)&jmethod);
 #endif
+
+		if (m_perf_map_file.is_open())
+		{
+			m_perf_map_file << StringFromFormat(
+			  "%" PRIx64 " %x EmuCode_%x\n",
+			  (u64)blockCodePointers[block_num], b.codeSize, b.originalAddress);
+		}
 	}
 
 	const u8 **JitBaseBlockCache::GetCodePointers()

Source/Core/Core/PowerPC/JitCommon/JitCache.h

@@ -6,6 +6,7 @@
 
 #include <array>
 #include <bitset>
+#include <fstream>
 #include <map>
 #include <memory>
 #include <vector>
@@ -119,6 +120,8 @@ class JitBaseBlockCache
 
 	bool m_initialized;
 
+	std::ofstream m_perf_map_file;
+
 	bool RangeIntersect(int s1, int e1, int s2, int e2) const;
 	void LinkBlockExits(int i);
 	void LinkBlock(int i);