Commit Graph

7 Commits

Author SHA1 Message Date
Adhemerval Zanella 19074450ee [MSan] Enable MSAN for aarch64
This patch enabled msan for aarch64 with 39-bit VMA and 42-bit VMA.
As defined by lib/msan/msan.h the memory layout used is for 39-bit is:

   00 0000 0000 - 40 0000 0000:  invalid
   40 0000 0000 - 43 0000 0000:  shadow
   43 0000 0000 - 46 0000 0000:  origin
   46 0000 0000 - 55 0000 0000:  invalid
   55 0000 0000 - 56 0000 0000:  app (low)
   56 0000 0000 - 70 0000 0000:  invalid
   70 0000 0000 - 80 0000 0000:  app (high)

And for 42-bit VMA:

   000 0000 0000 - 100 0000 0000:  invalid
   100 0000 0000 - 11b 0000 0000:  shadow
   11b 0000 0000 - 120 0000 0000:  invalid
   120 0000 0000 - 13b 0000 0000:  origin
   13b 0000 0000 - 2aa 0000 0000:  invalid
   2aa 0000 0000 - 2ab 0000 0000:  app (low)
   2ab 0000 0000 - 3f0 0000 0000:  invalid
   3f0 0000 0000 - 400 0000 0000:  app (high)

Most of tests are passing with exception of:

   * Linux/mallinfo.cc
   * chained_origin_limits.cc
   * dlerror.cc
   * param_tls_limit.cc
   * signal_stress_test.cc
   * nonnull-arg.cpp

The 'Linux/mallinfo.cc' is due the fact AArch64 returns the sret in 'x8'
instead of default first argument 'x1'.  So a function prototype that
aims  to mimic (by using first argument as the return of function) won't
work. For GCC one can make a register alias (register var asm ("r8")), but
for clang it detects is an unused variable and generate wrong code.

The 'chained_origin_limits' is probably due a wrong code generation,
since it fails only when origin memory is used
(-fsanitize-memory-track-origins=2) and only in the returned code
(return buf[50]).

The 'signal_streess_test' and 'nonnull-arg' are due currently missing variadic
argument handling in memory sanitizer code instrumentation on LLVM side.

Both 'dlerror' and 'param_tls_test' are unknown failures that require
further investigation.

All the failures are XFAIL for aarch64 for now.

llvm-svn: 247809
2015-09-16 15:12:25 +00:00
Alexey Samsonov d06aa3dc00 [MSan] Remove explicit -m64 from RUN lines.
Target-specific flags should usually be configured by CMake/lit.

llvm-svn: 230999
2015-03-02 19:34:27 +00:00
Evgeniy Stepanov 36974a7061 [msan] Make chained_origin_limits test faster.
llvm-svn: 217361
2014-09-08 09:04:45 +00:00
Evgeniy Stepanov f1741f52ad [msan] Fix origin_history_per_stack_limit=0 behavior.
It disables the per-stack limit.

llvm-svn: 217030
2014-09-03 12:15:59 +00:00
Evgeniy Stepanov 4e2d5edb0c [msan] Limit stack origin chain length.
Stack origins were created with unlimited length by mistake.

llvm-svn: 212036
2014-06-30 11:22:42 +00:00
Evgeniy Stepanov b163f0276f [msan] Fix bad interaction between with-calls mode and chained origin tracking.
Origin history should only be recorded for uninitialized values, because it is
meaningless otherwise. This change moves __msan_chain_origin to the runtime
library side and makes it conditional on the corresponding shadow value.

Previous code was correct, but _very_ inefficient.

llvm-svn: 211700
2014-06-25 14:41:57 +00:00
Evgeniy Stepanov 208aae8ee0 [msan] Chained origins re-design.
Generalize StackDepot and create a new specialized instance of it to
efficiently (i.e. without duplicating stack trace data) store the
origin history tree.

This reduces memory usage for chained origins roughly by an order of
magnitude.

Most importantly, this new design allows us to put two limits on
stored history data (exposed in MSAN_OPTIONS) that help avoid
exponential growth in used memory on certain workloads.

See comments in lib/msan/msan_origin.h for more details.

llvm-svn: 209284
2014-05-21 09:02:13 +00:00