diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h index 59c779c5790c..94a0d7bb6f3c 100644 --- a/tools/lib/bpf/libbpf_util.h +++ b/tools/lib/bpf/libbpf_util.h @@ -5,6 +5,7 @@ #define __LIBBPF_LIBBPF_UTIL_H #include +#include #ifdef __cplusplus extern "C" { @@ -15,29 +16,56 @@ extern "C" { * application that uses libbpf. */ #if defined(__i386__) || defined(__x86_64__) -# define libbpf_smp_rmb() asm volatile("" : : : "memory") -# define libbpf_smp_wmb() asm volatile("" : : : "memory") -# define libbpf_smp_mb() \ - asm volatile("lock; addl $0,-4(%%rsp)" : : : "memory", "cc") -/* Hinders stores to be observed before older loads. */ -# define libbpf_smp_rwmb() asm volatile("" : : : "memory") +# define libbpf_smp_store_release(p, v) \ + do { \ + asm volatile("" : : : "memory"); \ + WRITE_ONCE(*p, v); \ + } while (0) +# define libbpf_smp_load_acquire(p) \ + ({ \ + typeof(*p) ___p1 = READ_ONCE(*p); \ + asm volatile("" : : : "memory"); \ + ___p1; \ + }) #elif defined(__aarch64__) -# define libbpf_smp_rmb() asm volatile("dmb ishld" : : : "memory") -# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") -# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") -# define libbpf_smp_rwmb() libbpf_smp_mb() -#elif defined(__arm__) -/* These are only valid for armv7 and above */ -# define libbpf_smp_rmb() asm volatile("dmb ish" : : : "memory") -# define libbpf_smp_wmb() asm volatile("dmb ishst" : : : "memory") -# define libbpf_smp_mb() asm volatile("dmb ish" : : : "memory") -# define libbpf_smp_rwmb() libbpf_smp_mb() -#else -/* Architecture missing native barrier functions. */ -# define libbpf_smp_rmb() __sync_synchronize() -# define libbpf_smp_wmb() __sync_synchronize() -# define libbpf_smp_mb() __sync_synchronize() -# define libbpf_smp_rwmb() __sync_synchronize() +# define libbpf_smp_store_release(p, v) \ + asm volatile ("stlr %w1, %0" : "=Q" (*p) : "r" (v) : "memory") +# define libbpf_smp_load_acquire(p) \ + ({ \ + typeof(*p) ___p1; \ + asm volatile ("ldar %w0, %1" \ + : "=r" (___p1) : "Q" (*p) : "memory"); \ + __p1; \ + }) +#elif defined(__riscv) +# define libbpf_smp_store_release(p, v) \ + do { \ + asm volatile ("fence rw,w" : : : "memory"); \ + WRITE_ONCE(*p, v); \ + } while (0) +# define libbpf_smp_load_acquire(p) \ + ({ \ + typeof(*p) ___p1 = READ_ONCE(*p); \ + asm volatile ("fence r,rw" : : : "memory"); \ + ___p1; \ + }) +#endif + +#ifndef libbpf_smp_store_release +#define libbpf_smp_store_release(p, v) \ + do { \ + __sync_synchronize(); \ + WRITE_ONCE(*p, v); \ + } while (0) +#endif + +#ifndef libbpf_smp_load_acquire +#define libbpf_smp_load_acquire(p) \ + ({ \ + typeof(*p) ___p1 = READ_ONCE(*p); \ + __sync_synchronize(); \ + ___p1; \ + }) #endif #ifdef __cplusplus diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index e9f121f5d129..a9fdea87b5cd 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -96,7 +96,8 @@ static inline __u32 xsk_prod_nb_free(struct xsk_ring_prod *r, __u32 nb) * this function. Without this optimization it whould have been * free_entries = r->cached_prod - r->cached_cons + r->size. */ - r->cached_cons = *r->consumer + r->size; + r->cached_cons = libbpf_smp_load_acquire(r->consumer); + r->cached_cons += r->size; return r->cached_cons - r->cached_prod; } @@ -106,7 +107,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) __u32 entries = r->cached_prod - r->cached_cons; if (entries == 0) { - r->cached_prod = *r->producer; + r->cached_prod = libbpf_smp_load_acquire(r->producer); entries = r->cached_prod - r->cached_cons; } @@ -129,9 +130,7 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) /* Make sure everything has been written to the ring before indicating * this to the kernel by writing the producer pointer. */ - libbpf_smp_wmb(); - - *prod->producer += nb; + libbpf_smp_store_release(prod->producer, *prod->producer + nb); } static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) @@ -139,11 +138,6 @@ static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __ __u32 entries = xsk_cons_nb_avail(cons, nb); if (entries > 0) { - /* Make sure we do not speculatively read the data before - * we have received the packet buffers from the ring. - */ - libbpf_smp_rmb(); - *idx = cons->cached_cons; cons->cached_cons += entries; } @@ -161,9 +155,8 @@ static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb) /* Make sure data has been read before indicating we are done * with the entries by updating the consumer pointer. */ - libbpf_smp_rwmb(); + libbpf_smp_store_release(cons->consumer, *cons->consumer + nb); - *cons->consumer += nb; } static inline void *xsk_umem__get_data(void *umem_area, __u64 addr)