[This commit contains an implementation for all targets except amd64-solaris
and x86-solaris, which will be completed shortly.]
In the baseline simulator, jumps to guest code addresses that are not known at
JIT time have to be looked up in a guest->host mapping table. That means:
indirect branches, indirect calls and most commonly, returns. Since there are
huge numbers of these (often 10+ million/second) the mapping mechanism needs
to be extremely cheap.
Currently, this is implemented using a direct-mapped cache, VG_(tt_fast), with
2^15 (guest_addr, host_addr) pairs. This is queried in handwritten assembly
in VG_(disp_cp_xindir) in dispatch-<arch>-<os>.S. If there is a miss in the
cache then we fall back out to C land, and do a slow lookup using
VG_(search_transtab).
Given that the size of the translation table(s) in recent years has expanded
significantly in order to keep pace with increasing application sizes, two bad
things have happened: (1) the cost of a miss in the fast cache has risen
significantly, and (2) the miss rate on the fast cache has also increased
significantly. This means that large (~ one-million-basic-blocks-JITted)
applications that run for a long time end up spending a lot of time in
VG_(search_transtab).
The proposed fix is to increase associativity of the fast cache, from 1
(direct mapped) to 4. Simulations of various cache configurations using
indirect-branch traces from a large application show that is the best of
various configurations. In an extreme case with 5.7 billion indirect
branches:
* The increase of associativity from 1 way to 4 way, whilst keeping the
overall cache size the same (32k guest/host pairs), reduces the miss rate by
around a factor of 3, from 4.02% to 1.30%.
* The use of a slightly better hash function than merely slicing off the
bottom 15 bits of the address, reduces the miss rate further, from 1.30% to
0.53%.
Overall the VG_(tt_fast) miss rate is almost unchanged on small workloads, but
reduced by a factor of up to almost 8 on large workloads.
By implementing each (4-entry) cache set using a move-to-front scheme in the
case of hits in ways 1, 2 or 3, the vast majority of hits can be made to
happen in way 0. Hence the cost of having this extra associativity is almost
zero in the case of a hit. The improved hash function costs an extra 2 ALU
shots (a shift and an xor) but overall this seems performance neutral to a
win.
Adding MIPS N32 ABI support.
BZ issue - #345763.
Contributed and maintained by mulitple people over the years:
Crestez Dan Leonard, Maran Pakkirisamy, Dimitrije Nikolic,
Aleksandar Rikalo, Tamara Vlahovic.
Replace use of daddi/addi with daddiu/addiu.
This is more R6-friendly and we actually want to use the instructions
that do not cause integer overflow exception.
Patch by Vicente Olivert Riera.
Related issue - BZ#356112.
git-svn-id: svn://svn.valgrind.org/valgrind/trunk@16018
Explanation by Matthias Schwarzott:
The linker will request an executable stack as soon as at least one
object file, that is linked in, wants an executable stack.
And the absence of the
.section .note.GNU-stack."",@progbits
is enough to tell the linker that an executable stack is needed.
So even an empty asm-file must at least contain this statement to not
force executable stacks on the whole executable.
* Define a helper macro MARK_STACK_NO_EXEC that disables the
executable stack.
* Instantiate this macro unconditionally at the end of each asm file.
Patch by Matthias Schwarzott <zzam@gentoo.org>.
git-svn-id: svn://svn.valgrind.org/valgrind/trunk@15692
Necessary changes to Valgrind to support MIPS64LE on Linux.
Minor cleanup/style changes embedded in the patch as well.
The change corresponds to r2687 in VEX.
Patch written by Dejan Jevtic and Petar Jovanovic.
More information about this issue:
https://bugs.kde.org/show_bug.cgi?id=313267
git-svn-id: svn://svn.valgrind.org/valgrind/trunk@13292
