Before: the function name was stored by the compiler as a constant string
and the run-time was printing it.
Now: the PC is stored instead and the run-time prints the full symbolized frame.
This adds a couple of instructions into every function with non-empty stack frame,
but also reduces the binary size because we store less strings (I saw 2% size reduction).
This change bumps the asan ABI version to v3.
compiler-rt part, llvm part will follow.
Example of report (now):
==31711==ERROR: AddressSanitizer: stack-buffer-overflow on address 0x7fffa77cf1c5 at pc 0x41feb0 bp 0x7fffa77cefb0 sp 0x7fffa77cefa8
READ of size 1 at 0x7fffa77cf1c5 thread T0
#0 0x41feaf in Frame0(int, char*, char*, char*) stack-oob-frames.cc:20
#1 0x41f7ff in Frame1(int, char*, char*) stack-oob-frames.cc:24
#2 0x41f477 in Frame2(int, char*) stack-oob-frames.cc:28
#3 0x41f194 in Frame3(int) stack-oob-frames.cc:32
#4 0x41eee0 in main stack-oob-frames.cc:38
#5 0x7f0c5566f76c (/lib/x86_64-linux-gnu/libc.so.6+0x2176c)
#6 0x41eb1c (/usr/local/google/kcc/llvm_cmake/a.out+0x41eb1c)
Address 0x7fffa77cf1c5 is located in stack of thread T0 at offset 293 in frame
#0 0x41f87f in Frame0(int, char*, char*, char*) stack-oob-frames.cc:12 <<<<<<<<<<<<<< this is new
This frame has 6 object(s):
[32, 36) 'frame.addr'
[96, 104) 'a.addr'
[160, 168) 'b.addr'
[224, 232) 'c.addr'
[288, 292) 's'
[352, 360) 'd'
llvm-svn: 177723
In the current implementation AsanThread::GetFrameNameByAddr scans the
stack for a magic guard value to locate base address of the stack
frame. This is not reliable, especially on ARM, where the code that
stores this magic value has to construct it in a register from two
small intermediates; this register can then end up stored in a random
stack location in the prologue of another function.
With this change, GetFrameNameByAddr scans the shadow memory for the
signature of a left stack redzone instead. It is now possible to
remove the magic from the instrumentation pass for additional
performance gain. We keep it there for now just to make sure the new
algorithm does not fail in some corner case.
llvm-svn: 156710
At the moment, asan internal Printf() uses %l modifier for printing
values of size_t and related types. This works, because we control
both the implementation of Printf and all its uses, but can be a
little misleading.
This change adds support for %z to Printf(). All callers that print
sizes and pointers as integers are switched to %zu / %zx.
llvm-svn: 153177
FakeStack on the worker threads.
This patch moves the AsanThread initialization into a separate
procedure that's called when AsanThread objects are called for worker
threads.
Patch by glider@google.com
llvm-svn: 146752
Kostya Serebryany