diff options
Diffstat (limited to 'tools/include/linux')
| -rw-r--r-- | tools/include/linux/bitops.h | 7 | ||||
| -rw-r--r-- | tools/include/linux/bits.h | 26 | ||||
| -rw-r--r-- | tools/include/linux/err.h | 7 | ||||
| -rw-r--r-- | tools/include/linux/lockdep.h | 3 | ||||
| -rw-r--r-- | tools/include/linux/nmi.h | 0 | ||||
| -rw-r--r-- | tools/include/linux/ring_buffer.h | 73 |
6 files changed, 111 insertions, 5 deletions
diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index acc704bd3998..0b0ef3abc966 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -3,8 +3,6 @@ #define _TOOLS_LINUX_BITOPS_H_ #include <asm/types.h> -#include <linux/compiler.h> - #ifndef __WORDSIZE #define __WORDSIZE (__SIZEOF_LONG__ * 8) #endif @@ -12,10 +10,9 @@ #ifndef BITS_PER_LONG # define BITS_PER_LONG __WORDSIZE #endif +#include <linux/bits.h> +#include <linux/compiler.h> -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -#define BITS_PER_BYTE 8 #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long)) #define BITS_TO_U64(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64)) #define BITS_TO_U32(nr) DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32)) diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h new file mode 100644 index 000000000000..2b7b532c1d51 --- /dev/null +++ b/tools/include/linux/bits.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BITS_H +#define __LINUX_BITS_H +#include <asm/bitsperlong.h> + +#define BIT(nr) (1UL << (nr)) +#define BIT_ULL(nr) (1ULL << (nr)) +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) +#define BIT_ULL_MASK(nr) (1ULL << ((nr) % BITS_PER_LONG_LONG)) +#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG) +#define BITS_PER_BYTE 8 + +/* + * Create a contiguous bitmask starting at bit position @l and ending at + * position @h. For example + * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000. + */ +#define GENMASK(h, l) \ + (((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h)))) + +#define GENMASK_ULL(h, l) \ + (((~0ULL) - (1ULL << (l)) + 1) & \ + (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* __LINUX_BITS_H */ diff --git a/tools/include/linux/err.h b/tools/include/linux/err.h index 7a8b61ad44cb..094649667bae 100644 --- a/tools/include/linux/err.h +++ b/tools/include/linux/err.h @@ -52,4 +52,11 @@ static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr) return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr); } +static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr) +{ + if (IS_ERR(ptr)) + return PTR_ERR(ptr); + else + return 0; +} #endif /* _LINUX_ERR_H */ diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h index 6b0c36a58fcb..e56997288f2b 100644 --- a/tools/include/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -30,9 +30,12 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; gfp_t lockdep_reclaim_gfp; int pid; + int state; char comm[17]; }; +#define TASK_RUNNING 0 + extern struct task_struct *__curr(void); #define current (__curr()) diff --git a/tools/include/linux/nmi.h b/tools/include/linux/nmi.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/linux/nmi.h diff --git a/tools/include/linux/ring_buffer.h b/tools/include/linux/ring_buffer.h new file mode 100644 index 000000000000..9a083ae60473 --- /dev/null +++ b/tools/include/linux/ring_buffer.h @@ -0,0 +1,73 @@ +#ifndef _TOOLS_LINUX_RING_BUFFER_H_ +#define _TOOLS_LINUX_RING_BUFFER_H_ + +#include <asm/barrier.h> + +/* + * Contract with kernel for walking the perf ring buffer from + * user space requires the following barrier pairing (quote + * from kernel/events/ring_buffer.c): + * + * Since the mmap() consumer (userspace) can run on a + * different CPU: + * + * kernel user + * + * if (LOAD ->data_tail) { LOAD ->data_head + * (A) smp_rmb() (C) + * STORE $data LOAD $data + * smp_wmb() (B) smp_mb() (D) + * STORE ->data_head STORE ->data_tail + * } + * + * Where A pairs with D, and B pairs with C. + * + * In our case A is a control dependency that separates the + * load of the ->data_tail and the stores of $data. In case + * ->data_tail indicates there is no room in the buffer to + * store $data we do not. + * + * D needs to be a full barrier since it separates the data + * READ from the tail WRITE. + * + * For B a WMB is sufficient since it separates two WRITEs, + * and for C an RMB is sufficient since it separates two READs. + * + * Note, instead of B, C, D we could also use smp_store_release() + * in B and D as well as smp_load_acquire() in C. + * + * However, this optimization does not make sense for all kernel + * supported architectures since for a fair number it would + * resolve into READ_ONCE() + smp_mb() pair for smp_load_acquire(), + * and smp_mb() + WRITE_ONCE() pair for smp_store_release(). + * + * Thus for those smp_wmb() in B and smp_rmb() in C would still + * be less expensive. For the case of D this has either the same + * cost or is less expensive, for example, due to TSO x86 can + * avoid the CPU barrier entirely. + */ + +static inline u64 ring_buffer_read_head(struct perf_event_mmap_page *base) +{ +/* + * Architectures where smp_load_acquire() does not fallback to + * READ_ONCE() + smp_mb() pair. + */ +#if defined(__x86_64__) || defined(__aarch64__) || defined(__powerpc64__) || \ + defined(__ia64__) || defined(__sparc__) && defined(__arch64__) + return smp_load_acquire(&base->data_head); +#else + u64 head = READ_ONCE(base->data_head); + + smp_rmb(); + return head; +#endif +} + +static inline void ring_buffer_write_tail(struct perf_event_mmap_page *base, + u64 tail) +{ + smp_store_release(&base->data_tail, tail); +} + +#endif /* _TOOLS_LINUX_RING_BUFFER_H_ */ |