[NativeProcessLinux] Use fast memory reads, if the system supports it

Summary:
Memory reads using the ptrace API need to be executed on a designated thread
and in 4-byte increments. The process_vm_read syscall has no such requirements
and it is about 50 times faster. This patch makes lldb-server use the faster
API if the target kernel supports it. Kernel support for this feature is
determined at runtime. Using process_vm_writev in the same manner is more
complicated since this syscall (unlike ptrace) respects page protection settings
and so it cannot be used to set a breakpoint, since code pages are typically
read-only. However, memory writes are not currently a performance bottleneck as
they happen much more rarely.

Test Plan: all tests continue to pass

Reviewers: ovyalov, vharron

Subscribers: tberghammer, lldb-commits

Differential Revision: http://reviews.llvm.org/D10488

llvm-svn: 239924

1 files changed, 11 insertions, 1 deletions

diff --git a/lldb/source/Host/android/LibcGlue.cpp b/lldb/source/Host/android/LibcGlue.cpp
index d443a92724e..d127d6b01ad 100644
--- a/lldb/source/Host/android/LibcGlue.cpp
+++ b/lldb/source/Host/android/LibcGlue.cpp
@@ -11,12 +11,14 @@
 
 #include <android/api-level.h>
 
+#include <sys/syscall.h>
+#include <lldb/Host/linux/Uio.h>
+
 #if __ANDROID_API__ < 21
 
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-#include <sys/syscall.h>
 #include <signal.h>
 
 #include "lldb/Host/Time.h"
@@ -37,3 +39,11 @@ int posix_openpt(int flags)
 }
 
 #endif
+
+ssize_t process_vm_readv(::pid_t pid,
+			 const struct iovec *local_iov, unsigned long liovcnt,
+			 const struct iovec *remote_iov, unsigned long riovcnt,
+			 unsigned long flags)
+{
+    return syscall(__NR_process_vm_readv, pid, local_iov, liovcnt, remote_iov, riovcnt, flags);
+}