How does a mutex lock and unlock functions prevents CPU reordering?

by

The short answer is that the body of the pthread_mutex_lock and pthread_mutex_unlock calls will include the necessary platform-specific memory barriers which will prevent the CPU from moving memory accesses within the critical section outside of it. The instruction flow will move from the calling code into the lock and unlock functions via a call instruction, and it is this dynamic instruction trace you have to consider for the purposes of reordering – not the static sequence you see in an assembly listing.

On x86 specifically, you probably won’t find explicit, standalone memory barriers inside those methods, since you’ll already have lock-prefixed instructions in order to perform the actual locking and unlocking atomically, and these instructions imply a full memory barrier, which prevents the CPU reordering you are concerned about.

For example, on my Ubuntu 16.04 system with glibc 2.23, pthread_mutex_lock is implemented using a lock cmpxchg (compare-and-exchange) and pthread_mutex_unlock is implemented using lock dec (decrement), both of which have full barrier semantics.

More Related Contents:

  1. function returns address of local variable, but it still compile in c, why?
  2. Assembly code fsqrt and fmul instructions
  3. Can x86’s MOV really be “free”? Why can’t I reproduce this at all?
  4. Why does mulss take only 3 cycles on Haswell, different from Agner’s instruction tables? (Unrolling FP loops with multiple accumulators)
  5. Using LEA on values that aren’t addresses / pointers?
  6. Can I use Intel syntax of x86 assembly with GCC?
  7. How to get c code to execute hex machine code?
  8. Stack allocation, padding, and alignment
  9. What is exactly the base pointer and stack pointer? To what do they point?
  10. Is it safe to read past the end of a buffer within the same page on x86 and x64?
  11. Syscall implementation of exit()
  12. What is the instruction that gives branchless FP min and max on x86?
  13. Loop with function call faster than an empty loop
  14. Efficient integer compare function
  15. What is the fastest way to convert float to int on x86
  16. What parts of this HelloWorld assembly code are essential if I were to write the program in assembly?
  17. x86_64 ASM – maximum bytes for an instruction?
  18. How to power down the computer from a freestanding environment?
  19. Fastest way to calculate a 128-bit integer modulo a 64-bit integer
  20. multi-word addition using the carry flag
  21. Getting max value in a __m128i vector with SSE?
  22. Why GCC compiled C program needs .eh_frame section?
  23. Calling C functions from x86 assembly language
  24. calling assembly function from c
  25. Very fast memcpy for image processing?
  26. Is it possible to call a non-exported function that resides in an exe?
  27. Writing a Linux int 80h system-call wrapper in GNU C inline assembly [duplicate]
  28. Why is gcc allowed to speculatively load from a struct?
  29. Bit popcount for large buffer, with Core 2 CPU (SSSE3)
  30. What is the effect of second argument in _builtin_prefetch()?

Leave a Comment