Taking a sleeping lock to _only_ increment a variable is quite the overkill, and pretty much all users do this. Furthermore, some drivers (ie: infiniband and scif) that need pinned semantics can go to quite some trouble to actually delay via workqueue (un)accounting for pinned pages when not possible to acquire it. By making the counter atomic we no longer need to hold the mmap_sem and can simply some code around it for pinned_vm users. The counter is 64-bit such that we need not worry about overflows such as rdma user input controlled from userspace.
Showing the changes to include/linux (1 of 10 files). Show all
Unified · Split
| @@ -405,7 +405,7 @@ struct mm_struct { · 404 unmodified lines | ||
| 405 | 405 | |
| 406 | 406 | unsigned long total_vm; /* Total pages mapped */ |
| 407 | 407 | unsigned long locked_vm; /* Pages that have PG_mlocked set */ |
| 408 | − unsigned long pinned_vm; /* Refcount permanently increased */ | |
| 408 | + atomic64_t pinned_vm; /* Refcount permanently increased */ | |
| 409 | 409 | unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ |
| 410 | 410 | unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ |
| 411 | 411 | unsigned long stack_vm; /* VM_STACK */ |