docs/devel/multi-thread-tcg.rst

41 In the general case of running translated code there should be no
53 Even when there is no code being generated there are a number of
61 As TB linking only occurs when blocks are in the same page this code
63 most common reason to exit the generated code.
71 are only taken when code generation is required or TranslationBlocks
80 We need to protect the entire code generation cycle including any post
81 generation patching of the translated code. This also implies a shared
82 translation buffer which contains code running on all cores. Any
84 mutex for code generation. This also includes times when we need flush
85 code or entries from any shared lookups/caches. Structures held on a
89 DESIGN REQUIREMENT: Add locking around all code generation and TB
94 Code generation is serialised with mmap_lock().
105 Currently the whole system shares a single code generation buffer
122   - code modification (self modify code, patching code)
131 to the C code.
155 tb_set_jmp_target() code. Modification to the linked lists that allow
167 Parallel code generation is supported. QHT is used at insertion time
169 keep track of a single TranslationBlock for each guest code block.
174 The memory handling code is fairly critical to the speed of memory
175 access in the emulated system. The SoftMMU code is designed so the
176 hot-path can be handled entirely within translated code. This is
179 translated code. It is possible to set flags in the TLB address which
184   - Dirty page tracking (for code gen, SMC detection, migration and display)
237 push the use of the lock as far down into the TCG code as possible to
301 operations if code generation is being done in a parallel context. The
319 are often seen when code modification has taken place to ensure the
362 The code also includes a fall-back for cases where multi-threaded TCG