mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-03 03:06:46 +07:00
fd851a3cdc
Current busy-wait loops are implemented by repeatedly calling cpu_relax() to give an arch option for a low-latency option to improve power and/or SMT resource contention. This poses some difficulties for powerpc, which has SMT priority setting instructions (priorities determine how ifetch cycles are apportioned). powerpc's cpu_relax() is implemented by setting a low priority then setting normal priority. This has several problems: - Changing thread priority can have some execution cost and potential impact to other threads in the core. It's inefficient to execute them every time around a busy-wait loop. - Depending on implementation details, a `low ; medium` sequence may not have much if any affect. Some software with similar pattern actually inserts a lot of nops between, in order to cause a few fetch cycles with the low priority. - The busy-wait loop runs with regular priority. This might only be a few fetch cycles, but if there are several threads running such loops, they could cause a noticable impact on a non-idle thread. Implement spin_begin, spin_end primitives that can be used around busy wait loops, which default to no-ops. And spin_cpu_relax which defaults to cpu_relax. This will allow architectures to hook the entry and exit of busy-wait loops, and will allow powerpc to set low SMT priority at entry, and normal priority at exit. Suggested-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
71 lines
2.1 KiB
C
71 lines
2.1 KiB
C
/* Misc low level processor primitives */
|
|
#ifndef _LINUX_PROCESSOR_H
|
|
#define _LINUX_PROCESSOR_H
|
|
|
|
#include <asm/processor.h>
|
|
|
|
/*
|
|
* spin_begin is used before beginning a busy-wait loop, and must be paired
|
|
* with spin_end when the loop is exited. spin_cpu_relax must be called
|
|
* within the loop.
|
|
*
|
|
* The loop body should be as small and fast as possible, on the order of
|
|
* tens of instructions/cycles as a guide. It should and avoid calling
|
|
* cpu_relax, or any "spin" or sleep type of primitive including nested uses
|
|
* of these primitives. It should not lock or take any other resource.
|
|
* Violations of these guidelies will not cause a bug, but may cause sub
|
|
* optimal performance.
|
|
*
|
|
* These loops are optimized to be used where wait times are expected to be
|
|
* less than the cost of a context switch (and associated overhead).
|
|
*
|
|
* Detection of resource owner and decision to spin or sleep or guest-yield
|
|
* (e.g., spin lock holder vcpu preempted, or mutex owner not on CPU) can be
|
|
* tested within the loop body.
|
|
*/
|
|
#ifndef spin_begin
|
|
#define spin_begin()
|
|
#endif
|
|
|
|
#ifndef spin_cpu_relax
|
|
#define spin_cpu_relax() cpu_relax()
|
|
#endif
|
|
|
|
/*
|
|
* spin_cpu_yield may be called to yield (undirected) to the hypervisor if
|
|
* necessary. This should be used if the wait is expected to take longer
|
|
* than context switch overhead, but we can't sleep or do a directed yield.
|
|
*/
|
|
#ifndef spin_cpu_yield
|
|
#define spin_cpu_yield() cpu_relax_yield()
|
|
#endif
|
|
|
|
#ifndef spin_end
|
|
#define spin_end()
|
|
#endif
|
|
|
|
/*
|
|
* spin_until_cond can be used to wait for a condition to become true. It
|
|
* may be expected that the first iteration will true in the common case
|
|
* (no spinning), so that callers should not require a first "likely" test
|
|
* for the uncontended case before using this primitive.
|
|
*
|
|
* Usage and implementation guidelines are the same as for the spin_begin
|
|
* primitives, above.
|
|
*/
|
|
#ifndef spin_until_cond
|
|
#define spin_until_cond(cond) \
|
|
do { \
|
|
if (unlikely(!(cond))) { \
|
|
spin_begin(); \
|
|
do { \
|
|
spin_cpu_relax(); \
|
|
} while (!(cond)); \
|
|
spin_end(); \
|
|
} \
|
|
} while (0)
|
|
|
|
#endif
|
|
|
|
#endif /* _LINUX_PROCESSOR_H */
|