diff options
Diffstat (limited to 'arch/riscv/include/asm/barrier.h')
| -rw-r--r-- | arch/riscv/include/asm/barrier.h | 72 |
1 files changed, 48 insertions, 24 deletions
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h index 3f1737f301cc..e1d9bf1deca6 100644 --- a/arch/riscv/include/asm/barrier.h +++ b/arch/riscv/include/asm/barrier.h @@ -11,36 +11,23 @@ #define _ASM_RISCV_BARRIER_H #ifndef __ASSEMBLY__ +#include <asm/cmpxchg.h> +#include <asm/fence.h> #define nop() __asm__ __volatile__ ("nop") +#define __nops(n) ".rept " #n "\nnop\n.endr\n" +#define nops(n) __asm__ __volatile__ (__nops(n)) -#define RISCV_FENCE(p, s) \ - __asm__ __volatile__ ("fence " #p "," #s : : : "memory") /* These barriers need to enforce ordering on both devices or memory. */ -#define mb() RISCV_FENCE(iorw,iorw) -#define rmb() RISCV_FENCE(ir,ir) -#define wmb() RISCV_FENCE(ow,ow) +#define __mb() RISCV_FENCE(iorw, iorw) +#define __rmb() RISCV_FENCE(ir, ir) +#define __wmb() RISCV_FENCE(ow, ow) /* These barriers do not need to enforce ordering on devices, just memory. */ -#define __smp_mb() RISCV_FENCE(rw,rw) -#define __smp_rmb() RISCV_FENCE(r,r) -#define __smp_wmb() RISCV_FENCE(w,w) - -#define __smp_store_release(p, v) \ -do { \ - compiletime_assert_atomic_type(*p); \ - RISCV_FENCE(rw,w); \ - WRITE_ONCE(*p, v); \ -} while (0) - -#define __smp_load_acquire(p) \ -({ \ - typeof(*p) ___p1 = READ_ONCE(*p); \ - compiletime_assert_atomic_type(*p); \ - RISCV_FENCE(r,rw); \ - ___p1; \ -}) +#define __smp_mb() RISCV_FENCE(rw, rw) +#define __smp_rmb() RISCV_FENCE(r, r) +#define __smp_wmb() RISCV_FENCE(w, w) /* * This is a very specific barrier: it's currently only used in two places in @@ -58,8 +45,45 @@ do { \ * The AQ/RL pair provides a RCpc critical section, but there's not really any * way we can take advantage of that here because the ordering is only enforced * on that one lock. Thus, we're just doing a full fence. + * + * Since we allow writeX to be called from preemptive regions we need at least + * an "o" in the predecessor set to ensure device writes are visible before the + * task is marked as available for scheduling on a new hart. While I don't see + * any concrete reason we need a full IO fence, it seems safer to just upgrade + * this in order to avoid any IO crossing a scheduling boundary. In both + * instances the scheduler pairs this with an mb(), so nothing is necessary on + * the new hart. */ -#define smp_mb__after_spinlock() RISCV_FENCE(rw,rw) +#define smp_mb__after_spinlock() RISCV_FENCE(iorw, iorw) + +#define __smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + RISCV_FENCE(rw, w); \ + WRITE_ONCE(*p, v); \ +} while (0) + +#define __smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = READ_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + RISCV_FENCE(r, rw); \ + ___p1; \ +}) + +#ifdef CONFIG_RISCV_ISA_ZAWRS +#define smp_cond_load_relaxed(ptr, cond_expr) ({ \ + typeof(ptr) __PTR = (ptr); \ + __unqual_scalar_typeof(*ptr) VAL; \ + for (;;) { \ + VAL = READ_ONCE(*__PTR); \ + if (cond_expr) \ + break; \ + __cmpwait_relaxed(ptr, VAL); \ + } \ + (typeof(*ptr))VAL; \ +}) +#endif #include <asm-generic/barrier.h> |