XEth cleanup

bugfix with idle too long triggered after peer switch

* In case of uncle mining (e.g. same TS) the miner would stop if all
  threads happened to mine a potential uncle

- reset bestIdleTimer when launching head section process
- log chain head events
- common.Hash key in activateChain map

Update ethash lib

* Refund of value

a7081bc update tests
d2678cb update random tests
ca0401b update tests

git-subtree-dir: tests/files
git-subtree-split: a7081bc54e9d72cc480218cb4b218dbb04c7cde7

* Value XFER are refunded back to the sender if the execution fails

8f3fbe6 Pv59 changes
2633cce JS fails
748f803 Merge remote-tracking branch 'origin' into develop
2e60a20 JS failure
2673f14 Incorrect Test deletion
345261d More Transaction Tests
300998f add blockchain tests - uncle gen 0 - in-chain-uncle
7e8585a gas counter overflow
5af1002 check overflow of v value in tx tests
53ee775 memory stress tests 28
46045b7 add 1024 stack size tests
4678ee8 add 1024 stack size limit tests
3b870f6 rm test
7c51854 fix test
74f1e91 cpp fail
ce9535a add cppjit fail
2e17a2e SDIV tests
cd38e05 first JS failures
d5e80d5 Delete st201503181858GO.json

git-subtree-dir: tests/files
git-subtree-split: 8f3fbe63f92c413fda1fc68cf27a9dbb69681168