From c8b5f2c96d1bf6cefcbe12f67dce0b892fe20512 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 6 Jul 2016 11:56:20 -0300 Subject: tools: Introduce str_error_r() The tools so far have been using the strerror_r() GNU variant, that returns a string, be it the buffer passed or something else. But that, besides being tricky in cases where we expect that the function using strerror_r() returns the error formatted in a provided buffer (we have to check if it returned something else and copy that instead), breaks the build on systems not using glibc, like Alpine Linux, where musl libc is used. So, introduce yet another wrapper, str_error_r(), that has the GNU interface, but uses the portable XSI variant of strerror_r(), so that users rest asured that the provided buffer is used and it is what is returned. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-d4t42fnf48ytlk8rjxs822tf@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/string.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'tools/include') diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index e26223f1f287..b466d0228b57 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -12,4 +12,6 @@ int strtobool(const char *s, bool *res); extern size_t strlcpy(char *dest, const char *src, size_t size); #endif +char *str_error_r(int errnum, char *buf, size_t buflen); + #endif /* _LINUX_STRING_H_ */ -- cgit v1.3-8-gc7d7 From d0761e37fe3fed7810ed8d6e130b79359f0c3e13 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jul 2016 15:42:33 -0300 Subject: perf tools: Uninline scnprintf() and vscnprint() They were in tools/include/linux/kernel.h, requiring that it in turn included stdio.h, which is way too heavy. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-855h8olnkot9v0dajuee1lo3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/kernel.h | 28 +++------------------------- tools/lib/vsprintf.c | 24 ++++++++++++++++++++++++ tools/objtool/builtin-check.c | 1 + tools/perf/MANIFEST | 1 + tools/perf/util/Build | 5 +++++ tools/perf/util/color.c | 2 ++ tools/perf/util/dso.h | 1 + tools/perf/util/help-unknown-cmd.c | 1 + tools/perf/util/python-ext-sources | 1 + 9 files changed, 39 insertions(+), 25 deletions(-) create mode 100644 tools/lib/vsprintf.c (limited to 'tools/include') diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h index 76df53539c2a..28607db02bd3 100644 --- a/tools/include/linux/kernel.h +++ b/tools/include/linux/kernel.h @@ -2,8 +2,7 @@ #define __TOOLS_LINUX_KERNEL_H #include -#include -#include +#include #include #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) @@ -70,29 +69,8 @@ #define cpu_to_le64(x) (x) #define cpu_to_le32(x) (x) -static inline int -vscnprintf(char *buf, size_t size, const char *fmt, va_list args) -{ - int i; - ssize_t ssize = size; - - i = vsnprintf(buf, size, fmt, args); - - return (i >= ssize) ? (ssize - 1) : i; -} - -static inline int scnprintf(char * buf, size_t size, const char * fmt, ...) -{ - va_list args; - ssize_t ssize = size; - int i; - - va_start(args, fmt); - i = vsnprintf(buf, size, fmt, args); - va_end(args); - - return (i >= ssize) ? (ssize - 1) : i; -} +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args); +int scnprintf(char * buf, size_t size, const char * fmt, ...); /* * This looks more complex than it should be. But we need to diff --git a/tools/lib/vsprintf.c b/tools/lib/vsprintf.c new file mode 100644 index 000000000000..45f9a06daa56 --- /dev/null +++ b/tools/lib/vsprintf.c @@ -0,0 +1,24 @@ +#include +#include +#include + +int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) +{ + int i = vsnprintf(buf, size, fmt, args); + ssize_t ssize = size; + + return (i >= ssize) ? (ssize - 1) : i; +} + +int scnprintf(char * buf, size_t size, const char * fmt, ...) +{ + ssize_t ssize = size; + va_list args; + int i; + + va_start(args, fmt); + i = vsnprintf(buf, size, fmt, args); + va_end(args); + + return (i >= ssize) ? (ssize - 1) : i; +} diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index e8a1e69eb92c..92d84b277032 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -26,6 +26,7 @@ */ #include +#include #include #include "builtin.h" diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index f18e781447bc..2bd8c310606c 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -30,6 +30,7 @@ tools/lib/symbol/kallsyms.h tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c +tools/lib/vsprintf.c tools/include/asm/atomic.h tools/include/asm/barrier.h tools/include/asm/bug.h diff --git a/tools/perf/util/Build b/tools/perf/util/Build index a6a805302312..eda68f582884 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -85,6 +85,7 @@ libperf-y += parse-regs-options.o libperf-y += term.o libperf-y += help-unknown-cmd.o libperf-y += mem-events.o +libperf-y += vsprintf.o libperf-$(CONFIG_LIBBPF) += bpf-loader.o libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o @@ -181,3 +182,7 @@ $(OUTPUT)util/str_error_r.o: ../lib/str_error_r.c FORCE $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) + +$(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c index 47a34b561f5d..dbbf89b050a5 100644 --- a/tools/perf/util/color.c +++ b/tools/perf/util/color.c @@ -1,6 +1,8 @@ #include #include "cache.h" #include "config.h" +#include +#include #include "color.h" #include #include diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index a571f24895ca..ecc4bbd3f82e 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c index 776e28562345..2821f8d77e52 100644 --- a/tools/perf/util/help-unknown-cmd.c +++ b/tools/perf/util/help-unknown-cmd.c @@ -1,5 +1,6 @@ #include "cache.h" #include "config.h" +#include #include #include "../builtin.h" #include "levenshtein.h" diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 49210b7a7925..5065ec98049c 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -14,6 +14,7 @@ util/cpumap.c ../lib/find_bit.c ../lib/hweight.c ../lib/str_error_r.c +../lib/vsprintf.c util/thread_map.c util/util.c util/xyarray.c -- cgit v1.3-8-gc7d7 From 61a6445e463a3152590352d8634131955f531c6e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 8 Jul 2016 15:38:51 -0300 Subject: tools lib: Guard the strlcpy() header with __GLIBC__ Better to whitelist it for libraries that require it (glibc) than blacklist it with the ones that don't (uclibc, musl libc, etc). Cc: Adrian Hunter Cc: Alexey Brodkin Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Vineet Gupta Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-52ih0m63a2n63tanpy6yj682@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/string.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/include') diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index b466d0228b57..b96879477311 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -8,7 +8,7 @@ void *memdup(const void *src, size_t len); int strtobool(const char *s, bool *res); -#ifndef __UCLIBC__ +#ifdef __GLIBC__ extern size_t strlcpy(char *dest, const char *src, size_t size); #endif -- cgit v1.3-8-gc7d7 From c4b6014e8bb0c8d47fe5c71ebc604f31091e5d3f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Jul 2016 10:28:48 -0300 Subject: tools: Add copy of perf_event.h to tools/include/linux/ We shouldn't use headers from the kernel sources directly, instead we should use the system's headers or in cases where that isn't possible, like with perf_event.h, where the introduction of kernel features such as perf_event_attr.{write_backwards,sample_max_stack} and PERF_EVENT_IOC_PAUSE_OUTPUT take some time to become available in /usr/include/linux/perf_event.h we need a copy. Do it and check for source code drift, emitting a warning when changes are detected. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-v6aks5un3s5pehory6f42nrl@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/perf_event.h | 983 ++++++++++++++++++++++++++++++++++ tools/perf/MANIFEST | 3 +- tools/perf/Makefile.perf | 3 + tools/perf/config/Makefile | 1 + 4 files changed, 988 insertions(+), 2 deletions(-) create mode 100644 tools/include/uapi/linux/perf_event.h (limited to 'tools/include') diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h new file mode 100644 index 000000000000..c66a485a24ac --- /dev/null +++ b/tools/include/uapi/linux/perf_event.h @@ -0,0 +1,983 @@ +/* + * Performance events: + * + * Copyright (C) 2008-2009, Thomas Gleixner + * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar + * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra + * + * Data type definitions, declarations, prototypes. + * + * Started by: Thomas Gleixner and Ingo Molnar + * + * For licencing details see kernel-base/COPYING + */ +#ifndef _UAPI_LINUX_PERF_EVENT_H +#define _UAPI_LINUX_PERF_EVENT_H + +#include +#include +#include + +/* + * User-space ABI bits: + */ + +/* + * attr.type + */ +enum perf_type_id { + PERF_TYPE_HARDWARE = 0, + PERF_TYPE_SOFTWARE = 1, + PERF_TYPE_TRACEPOINT = 2, + PERF_TYPE_HW_CACHE = 3, + PERF_TYPE_RAW = 4, + PERF_TYPE_BREAKPOINT = 5, + + PERF_TYPE_MAX, /* non-ABI */ +}; + +/* + * Generalized performance event event_id types, used by the + * attr.event_id parameter of the sys_perf_event_open() + * syscall: + */ +enum perf_hw_id { + /* + * Common hardware events, generalized by the kernel: + */ + PERF_COUNT_HW_CPU_CYCLES = 0, + PERF_COUNT_HW_INSTRUCTIONS = 1, + PERF_COUNT_HW_CACHE_REFERENCES = 2, + PERF_COUNT_HW_CACHE_MISSES = 3, + PERF_COUNT_HW_BRANCH_INSTRUCTIONS = 4, + PERF_COUNT_HW_BRANCH_MISSES = 5, + PERF_COUNT_HW_BUS_CYCLES = 6, + PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7, + PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8, + PERF_COUNT_HW_REF_CPU_CYCLES = 9, + + PERF_COUNT_HW_MAX, /* non-ABI */ +}; + +/* + * Generalized hardware cache events: + * + * { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x + * { read, write, prefetch } x + * { accesses, misses } + */ +enum perf_hw_cache_id { + PERF_COUNT_HW_CACHE_L1D = 0, + PERF_COUNT_HW_CACHE_L1I = 1, + PERF_COUNT_HW_CACHE_LL = 2, + PERF_COUNT_HW_CACHE_DTLB = 3, + PERF_COUNT_HW_CACHE_ITLB = 4, + PERF_COUNT_HW_CACHE_BPU = 5, + PERF_COUNT_HW_CACHE_NODE = 6, + + PERF_COUNT_HW_CACHE_MAX, /* non-ABI */ +}; + +enum perf_hw_cache_op_id { + PERF_COUNT_HW_CACHE_OP_READ = 0, + PERF_COUNT_HW_CACHE_OP_WRITE = 1, + PERF_COUNT_HW_CACHE_OP_PREFETCH = 2, + + PERF_COUNT_HW_CACHE_OP_MAX, /* non-ABI */ +}; + +enum perf_hw_cache_op_result_id { + PERF_COUNT_HW_CACHE_RESULT_ACCESS = 0, + PERF_COUNT_HW_CACHE_RESULT_MISS = 1, + + PERF_COUNT_HW_CACHE_RESULT_MAX, /* non-ABI */ +}; + +/* + * Special "software" events provided by the kernel, even if the hardware + * does not support performance events. These events measure various + * physical and sw events of the kernel (and allow the profiling of them as + * well): + */ +enum perf_sw_ids { + PERF_COUNT_SW_CPU_CLOCK = 0, + PERF_COUNT_SW_TASK_CLOCK = 1, + PERF_COUNT_SW_PAGE_FAULTS = 2, + PERF_COUNT_SW_CONTEXT_SWITCHES = 3, + PERF_COUNT_SW_CPU_MIGRATIONS = 4, + PERF_COUNT_SW_PAGE_FAULTS_MIN = 5, + PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6, + PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, + PERF_COUNT_SW_EMULATION_FAULTS = 8, + PERF_COUNT_SW_DUMMY = 9, + PERF_COUNT_SW_BPF_OUTPUT = 10, + + PERF_COUNT_SW_MAX, /* non-ABI */ +}; + +/* + * Bits that can be set in attr.sample_type to request information + * in the overflow packets. + */ +enum perf_event_sample_format { + PERF_SAMPLE_IP = 1U << 0, + PERF_SAMPLE_TID = 1U << 1, + PERF_SAMPLE_TIME = 1U << 2, + PERF_SAMPLE_ADDR = 1U << 3, + PERF_SAMPLE_READ = 1U << 4, + PERF_SAMPLE_CALLCHAIN = 1U << 5, + PERF_SAMPLE_ID = 1U << 6, + PERF_SAMPLE_CPU = 1U << 7, + PERF_SAMPLE_PERIOD = 1U << 8, + PERF_SAMPLE_STREAM_ID = 1U << 9, + PERF_SAMPLE_RAW = 1U << 10, + PERF_SAMPLE_BRANCH_STACK = 1U << 11, + PERF_SAMPLE_REGS_USER = 1U << 12, + PERF_SAMPLE_STACK_USER = 1U << 13, + PERF_SAMPLE_WEIGHT = 1U << 14, + PERF_SAMPLE_DATA_SRC = 1U << 15, + PERF_SAMPLE_IDENTIFIER = 1U << 16, + PERF_SAMPLE_TRANSACTION = 1U << 17, + PERF_SAMPLE_REGS_INTR = 1U << 18, + + PERF_SAMPLE_MAX = 1U << 19, /* non-ABI */ +}; + +/* + * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set + * + * If the user does not pass priv level information via branch_sample_type, + * the kernel uses the event's priv level. Branch and event priv levels do + * not have to match. Branch priv level is checked for permissions. + * + * The branch types can be combined, however BRANCH_ANY covers all types + * of branches and therefore it supersedes all the other types. + */ +enum perf_branch_sample_type_shift { + PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ + PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ + PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ + + PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ + PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ + PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ + PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ + PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ + PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ + PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ + PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ + + PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ + PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ + PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ + + PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT = 14, /* no flags */ + PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT = 15, /* no cycles */ + + PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ +}; + +enum perf_branch_sample_type { + PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, + PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, + PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, + + PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, + PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, + PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, + PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, + PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, + + PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, + PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, + + PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, + PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, +}; + +#define PERF_SAMPLE_BRANCH_PLM_ALL \ + (PERF_SAMPLE_BRANCH_USER|\ + PERF_SAMPLE_BRANCH_KERNEL|\ + PERF_SAMPLE_BRANCH_HV) + +/* + * Values to determine ABI of the registers dump. + */ +enum perf_sample_regs_abi { + PERF_SAMPLE_REGS_ABI_NONE = 0, + PERF_SAMPLE_REGS_ABI_32 = 1, + PERF_SAMPLE_REGS_ABI_64 = 2, +}; + +/* + * Values for the memory transaction event qualifier, mostly for + * abort events. Multiple bits can be set. + */ +enum { + PERF_TXN_ELISION = (1 << 0), /* From elision */ + PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ + PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ + PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */ + PERF_TXN_RETRY = (1 << 4), /* Retry possible */ + PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ + PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ + PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ + + PERF_TXN_MAX = (1 << 8), /* non-ABI */ + + /* bits 32..63 are reserved for the abort code */ + + PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), + PERF_TXN_ABORT_SHIFT = 32, +}; + +/* + * The format of the data returned by read() on a perf event fd, + * as specified by attr.read_format: + * + * struct read_format { + * { u64 value; + * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED + * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING + * { u64 id; } && PERF_FORMAT_ID + * } && !PERF_FORMAT_GROUP + * + * { u64 nr; + * { u64 time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED + * { u64 time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING + * { u64 value; + * { u64 id; } && PERF_FORMAT_ID + * } cntr[nr]; + * } && PERF_FORMAT_GROUP + * }; + */ +enum perf_event_read_format { + PERF_FORMAT_TOTAL_TIME_ENABLED = 1U << 0, + PERF_FORMAT_TOTAL_TIME_RUNNING = 1U << 1, + PERF_FORMAT_ID = 1U << 2, + PERF_FORMAT_GROUP = 1U << 3, + + PERF_FORMAT_MAX = 1U << 4, /* non-ABI */ +}; + +#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ +#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ +#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ +#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */ + /* add: sample_stack_user */ +#define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ +#define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ + +/* + * Hardware event_id to monitor via a performance monitoring event: + * + * @sample_max_stack: Max number of frame pointers in a callchain, + * should be < /proc/sys/kernel/perf_event_max_stack + */ +struct perf_event_attr { + + /* + * Major type: hardware/software/tracepoint/etc. + */ + __u32 type; + + /* + * Size of the attr structure, for fwd/bwd compat. + */ + __u32 size; + + /* + * Type specific configuration information. + */ + __u64 config; + + union { + __u64 sample_period; + __u64 sample_freq; + }; + + __u64 sample_type; + __u64 read_format; + + __u64 disabled : 1, /* off by default */ + inherit : 1, /* children inherit it */ + pinned : 1, /* must always be on PMU */ + exclusive : 1, /* only group on PMU */ + exclude_user : 1, /* don't count user */ + exclude_kernel : 1, /* ditto kernel */ + exclude_hv : 1, /* ditto hypervisor */ + exclude_idle : 1, /* don't count when idle */ + mmap : 1, /* include mmap data */ + comm : 1, /* include comm data */ + freq : 1, /* use freq, not period */ + inherit_stat : 1, /* per task counts */ + enable_on_exec : 1, /* next exec enables */ + task : 1, /* trace fork/exit */ + watermark : 1, /* wakeup_watermark */ + /* + * precise_ip: + * + * 0 - SAMPLE_IP can have arbitrary skid + * 1 - SAMPLE_IP must have constant skid + * 2 - SAMPLE_IP requested to have 0 skid + * 3 - SAMPLE_IP must have 0 skid + * + * See also PERF_RECORD_MISC_EXACT_IP + */ + precise_ip : 2, /* skid constraint */ + mmap_data : 1, /* non-exec mmap data */ + sample_id_all : 1, /* sample_type all events */ + + exclude_host : 1, /* don't count in host */ + exclude_guest : 1, /* don't count in guest */ + + exclude_callchain_kernel : 1, /* exclude kernel callchains */ + exclude_callchain_user : 1, /* exclude user callchains */ + mmap2 : 1, /* include mmap with inode data */ + comm_exec : 1, /* flag comm events that are due to an exec */ + use_clockid : 1, /* use @clockid for time fields */ + context_switch : 1, /* context switch data */ + write_backward : 1, /* Write ring buffer from end to beginning */ + __reserved_1 : 36; + + union { + __u32 wakeup_events; /* wakeup every n events */ + __u32 wakeup_watermark; /* bytes before wakeup */ + }; + + __u32 bp_type; + union { + __u64 bp_addr; + __u64 config1; /* extension of config */ + }; + union { + __u64 bp_len; + __u64 config2; /* extension of config1 */ + }; + __u64 branch_sample_type; /* enum perf_branch_sample_type */ + + /* + * Defines set of user regs to dump on samples. + * See asm/perf_regs.h for details. + */ + __u64 sample_regs_user; + + /* + * Defines size of the user stack to dump on samples. + */ + __u32 sample_stack_user; + + __s32 clockid; + /* + * Defines set of regs to dump for each sample + * state captured on: + * - precise = 0: PMU interrupt + * - precise > 0: sampled instruction + * + * See asm/perf_regs.h for details. + */ + __u64 sample_regs_intr; + + /* + * Wakeup watermark for AUX area + */ + __u32 aux_watermark; + __u16 sample_max_stack; + __u16 __reserved_2; /* align to __u64 */ +}; + +#define perf_flags(attr) (*(&(attr)->read_format + 1)) + +/* + * Ioctls that can be done on a perf event fd: + */ +#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) +#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) +#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) +#define PERF_EVENT_IOC_RESET _IO ('$', 3) +#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64) +#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) +#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) + +enum perf_event_ioc_flags { + PERF_IOC_FLAG_GROUP = 1U << 0, +}; + +/* + * Structure of the page that can be mapped via mmap + */ +struct perf_event_mmap_page { + __u32 version; /* version number of this structure */ + __u32 compat_version; /* lowest version this is compat with */ + + /* + * Bits needed to read the hw events in user-space. + * + * u32 seq, time_mult, time_shift, index, width; + * u64 count, enabled, running; + * u64 cyc, time_offset; + * s64 pmc = 0; + * + * do { + * seq = pc->lock; + * barrier() + * + * enabled = pc->time_enabled; + * running = pc->time_running; + * + * if (pc->cap_usr_time && enabled != running) { + * cyc = rdtsc(); + * time_offset = pc->time_offset; + * time_mult = pc->time_mult; + * time_shift = pc->time_shift; + * } + * + * index = pc->index; + * count = pc->offset; + * if (pc->cap_user_rdpmc && index) { + * width = pc->pmc_width; + * pmc = rdpmc(index - 1); + * } + * + * barrier(); + * } while (pc->lock != seq); + * + * NOTE: for obvious reason this only works on self-monitoring + * processes. + */ + __u32 lock; /* seqlock for synchronization */ + __u32 index; /* hardware event identifier */ + __s64 offset; /* add to hardware event value */ + __u64 time_enabled; /* time event active */ + __u64 time_running; /* time event on cpu */ + union { + __u64 capabilities; + struct { + __u64 cap_bit0 : 1, /* Always 0, deprecated, see commit 860f085b74e9 */ + cap_bit0_is_deprecated : 1, /* Always 1, signals that bit 0 is zero */ + + cap_user_rdpmc : 1, /* The RDPMC instruction can be used to read counts */ + cap_user_time : 1, /* The time_* fields are used */ + cap_user_time_zero : 1, /* The time_zero field is used */ + cap_____res : 59; + }; + }; + + /* + * If cap_user_rdpmc this field provides the bit-width of the value + * read using the rdpmc() or equivalent instruction. This can be used + * to sign extend the result like: + * + * pmc <<= 64 - width; + * pmc >>= 64 - width; // signed shift right + * count += pmc; + */ + __u16 pmc_width; + + /* + * If cap_usr_time the below fields can be used to compute the time + * delta since time_enabled (in ns) using rdtsc or similar. + * + * u64 quot, rem; + * u64 delta; + * + * quot = (cyc >> time_shift); + * rem = cyc & (((u64)1 << time_shift) - 1); + * delta = time_offset + quot * time_mult + + * ((rem * time_mult) >> time_shift); + * + * Where time_offset,time_mult,time_shift and cyc are read in the + * seqcount loop described above. This delta can then be added to + * enabled and possible running (if index), improving the scaling: + * + * enabled += delta; + * if (index) + * running += delta; + * + * quot = count / running; + * rem = count % running; + * count = quot * enabled + (rem * enabled) / running; + */ + __u16 time_shift; + __u32 time_mult; + __u64 time_offset; + /* + * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated + * from sample timestamps. + * + * time = timestamp - time_zero; + * quot = time / time_mult; + * rem = time % time_mult; + * cyc = (quot << time_shift) + (rem << time_shift) / time_mult; + * + * And vice versa: + * + * quot = cyc >> time_shift; + * rem = cyc & (((u64)1 << time_shift) - 1); + * timestamp = time_zero + quot * time_mult + + * ((rem * time_mult) >> time_shift); + */ + __u64 time_zero; + __u32 size; /* Header size up to __reserved[] fields. */ + + /* + * Hole for extension of the self monitor capabilities + */ + + __u8 __reserved[118*8+4]; /* align to 1k. */ + + /* + * Control data for the mmap() data buffer. + * + * User-space reading the @data_head value should issue an smp_rmb(), + * after reading this value. + * + * When the mapping is PROT_WRITE the @data_tail value should be + * written by userspace to reflect the last read data, after issueing + * an smp_mb() to separate the data read from the ->data_tail store. + * In this case the kernel will not over-write unread data. + * + * See perf_output_put_handle() for the data ordering. + * + * data_{offset,size} indicate the location and size of the perf record + * buffer within the mmapped area. + */ + __u64 data_head; /* head in the data section */ + __u64 data_tail; /* user-space written tail */ + __u64 data_offset; /* where the buffer starts */ + __u64 data_size; /* data buffer size */ + + /* + * AUX area is defined by aux_{offset,size} fields that should be set + * by the userspace, so that + * + * aux_offset >= data_offset + data_size + * + * prior to mmap()ing it. Size of the mmap()ed area should be aux_size. + * + * Ring buffer pointers aux_{head,tail} have the same semantics as + * data_{head,tail} and same ordering rules apply. + */ + __u64 aux_head; + __u64 aux_tail; + __u64 aux_offset; + __u64 aux_size; +}; + +#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) +#define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) +#define PERF_RECORD_MISC_KERNEL (1 << 0) +#define PERF_RECORD_MISC_USER (2 << 0) +#define PERF_RECORD_MISC_HYPERVISOR (3 << 0) +#define PERF_RECORD_MISC_GUEST_KERNEL (4 << 0) +#define PERF_RECORD_MISC_GUEST_USER (5 << 0) + +/* + * Indicates that /proc/PID/maps parsing are truncated by time out. + */ +#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT (1 << 12) +/* + * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on + * different events so can reuse the same bit position. + * Ditto PERF_RECORD_MISC_SWITCH_OUT. + */ +#define PERF_RECORD_MISC_MMAP_DATA (1 << 13) +#define PERF_RECORD_MISC_COMM_EXEC (1 << 13) +#define PERF_RECORD_MISC_SWITCH_OUT (1 << 13) +/* + * Indicates that the content of PERF_SAMPLE_IP points to + * the actual instruction that triggered the event. See also + * perf_event_attr::precise_ip. + */ +#define PERF_RECORD_MISC_EXACT_IP (1 << 14) +/* + * Reserve the last bit to indicate some extended misc field + */ +#define PERF_RECORD_MISC_EXT_RESERVED (1 << 15) + +struct perf_event_header { + __u32 type; + __u16 misc; + __u16 size; +}; + +enum perf_event_type { + + /* + * If perf_event_attr.sample_id_all is set then all event types will + * have the sample_type selected fields related to where/when + * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU, + * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed + * just after the perf_event_header and the fields already present for + * the existing fields, i.e. at the end of the payload. That way a newer + * perf.data file will be supported by older perf tools, with these new + * optional fields being ignored. + * + * struct sample_id { + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u64 id; } && PERF_SAMPLE_IDENTIFIER + * } && perf_event_attr::sample_id_all + * + * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. The + * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed + * relative to header.size. + */ + + /* + * The MMAP events record the PROT_EXEC mappings so that we can + * correlate userspace IPs to code. They have the following structure: + * + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * u64 addr; + * u64 len; + * u64 pgoff; + * char filename[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_MMAP = 1, + + /* + * struct { + * struct perf_event_header header; + * u64 id; + * u64 lost; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_LOST = 2, + + /* + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * char comm[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_COMM = 3, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * u64 time; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_EXIT = 4, + + /* + * struct { + * struct perf_event_header header; + * u64 time; + * u64 id; + * u64 stream_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_THROTTLE = 5, + PERF_RECORD_UNTHROTTLE = 6, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, ppid; + * u32 tid, ptid; + * u64 time; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_FORK = 7, + + /* + * struct { + * struct perf_event_header header; + * u32 pid, tid; + * + * struct read_format values; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_READ = 8, + + /* + * struct { + * struct perf_event_header header; + * + * # + * # Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. + * # The advantage of PERF_SAMPLE_IDENTIFIER is that its position + * # is fixed relative to header. + * # + * + * { u64 id; } && PERF_SAMPLE_IDENTIFIER + * { u64 ip; } && PERF_SAMPLE_IP + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 addr; } && PERF_SAMPLE_ADDR + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u64 period; } && PERF_SAMPLE_PERIOD + * + * { struct read_format values; } && PERF_SAMPLE_READ + * + * { u64 nr, + * u64 ips[nr]; } && PERF_SAMPLE_CALLCHAIN + * + * # + * # The RAW record below is opaque data wrt the ABI + * # + * # That is, the ABI doesn't make any promises wrt to + * # the stability of its content, it may vary depending + * # on event, hardware, kernel version and phase of + * # the moon. + * # + * # In other words, PERF_SAMPLE_RAW contents are not an ABI. + * # + * + * { u32 size; + * char data[size];}&& PERF_SAMPLE_RAW + * + * { u64 nr; + * { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK + * + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER + * + * { u64 size; + * char data[size]; + * u64 dyn_size; } && PERF_SAMPLE_STACK_USER + * + * { u64 weight; } && PERF_SAMPLE_WEIGHT + * { u64 data_src; } && PERF_SAMPLE_DATA_SRC + * { u64 transaction; } && PERF_SAMPLE_TRANSACTION + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR + * }; + */ + PERF_RECORD_SAMPLE = 9, + + /* + * The MMAP2 records are an augmented version of MMAP, they add + * maj, min, ino numbers to be used to uniquely identify each mapping + * + * struct { + * struct perf_event_header header; + * + * u32 pid, tid; + * u64 addr; + * u64 len; + * u64 pgoff; + * u32 maj; + * u32 min; + * u64 ino; + * u64 ino_generation; + * u32 prot, flags; + * char filename[]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_MMAP2 = 10, + + /* + * Records that new data landed in the AUX buffer part. + * + * struct { + * struct perf_event_header header; + * + * u64 aux_offset; + * u64 aux_size; + * u64 flags; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX = 11, + + /* + * Indicates that instruction trace has started + * + * struct { + * struct perf_event_header header; + * u32 pid; + * u32 tid; + * }; + */ + PERF_RECORD_ITRACE_START = 12, + + /* + * Records the dropped/lost sample number. + * + * struct { + * struct perf_event_header header; + * + * u64 lost; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_LOST_SAMPLES = 13, + + /* + * Records a context switch in or out (flagged by + * PERF_RECORD_MISC_SWITCH_OUT). See also + * PERF_RECORD_SWITCH_CPU_WIDE. + * + * struct { + * struct perf_event_header header; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_SWITCH = 14, + + /* + * CPU-wide version of PERF_RECORD_SWITCH with next_prev_pid and + * next_prev_tid that are the next (switching out) or previous + * (switching in) pid/tid. + * + * struct { + * struct perf_event_header header; + * u32 next_prev_pid; + * u32 next_prev_tid; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_SWITCH_CPU_WIDE = 15, + + PERF_RECORD_MAX, /* non-ABI */ +}; + +#define PERF_MAX_STACK_DEPTH 127 +#define PERF_MAX_CONTEXTS_PER_STACK 8 + +enum perf_callchain_context { + PERF_CONTEXT_HV = (__u64)-32, + PERF_CONTEXT_KERNEL = (__u64)-128, + PERF_CONTEXT_USER = (__u64)-512, + + PERF_CONTEXT_GUEST = (__u64)-2048, + PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, + PERF_CONTEXT_GUEST_USER = (__u64)-2560, + + PERF_CONTEXT_MAX = (__u64)-4095, +}; + +/** + * PERF_RECORD_AUX::flags bits + */ +#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ + +#define PERF_FLAG_FD_NO_GROUP (1UL << 0) +#define PERF_FLAG_FD_OUTPUT (1UL << 1) +#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ +#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ + +union perf_mem_data_src { + __u64 val; + struct { + __u64 mem_op:5, /* type of opcode */ + mem_lvl:14, /* memory hierarchy level */ + mem_snoop:5, /* snoop mode */ + mem_lock:2, /* lock instr */ + mem_dtlb:7, /* tlb access */ + mem_rsvd:31; + }; +}; + +/* type of opcode (load/store/prefetch,code) */ +#define PERF_MEM_OP_NA 0x01 /* not available */ +#define PERF_MEM_OP_LOAD 0x02 /* load instruction */ +#define PERF_MEM_OP_STORE 0x04 /* store instruction */ +#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */ +#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ +#define PERF_MEM_OP_SHIFT 0 + +/* memory hierarchy (memory level, hit or miss) */ +#define PERF_MEM_LVL_NA 0x01 /* not available */ +#define PERF_MEM_LVL_HIT 0x02 /* hit level */ +#define PERF_MEM_LVL_MISS 0x04 /* miss level */ +#define PERF_MEM_LVL_L1 0x08 /* L1 */ +#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */ +#define PERF_MEM_LVL_L2 0x20 /* L2 */ +#define PERF_MEM_LVL_L3 0x40 /* L3 */ +#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */ +#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */ +#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */ +#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */ +#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */ +#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ +#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ +#define PERF_MEM_LVL_SHIFT 5 + +/* snoop mode */ +#define PERF_MEM_SNOOP_NA 0x01 /* not available */ +#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */ +#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */ +#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */ +#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */ +#define PERF_MEM_SNOOP_SHIFT 19 + +/* locked instruction */ +#define PERF_MEM_LOCK_NA 0x01 /* not available */ +#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */ +#define PERF_MEM_LOCK_SHIFT 24 + +/* TLB access */ +#define PERF_MEM_TLB_NA 0x01 /* not available */ +#define PERF_MEM_TLB_HIT 0x02 /* hit level */ +#define PERF_MEM_TLB_MISS 0x04 /* miss level */ +#define PERF_MEM_TLB_L1 0x08 /* L1 */ +#define PERF_MEM_TLB_L2 0x10 /* L2 */ +#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/ +#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ +#define PERF_MEM_TLB_SHIFT 26 + +#define PERF_MEM_S(a, s) \ + (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) + +/* + * single taken branch record layout: + * + * from: source instruction (may not always be a branch insn) + * to: branch target + * mispred: branch target was mispredicted + * predicted: branch target was predicted + * + * support for mispred, predicted is optional. In case it + * is not supported mispred = predicted = 0. + * + * in_tx: running in a hardware transaction + * abort: aborting a hardware transaction + * cycles: cycles from last branch (or 0 if not supported) + */ +struct perf_branch_entry { + __u64 from; + __u64 to; + __u64 mispred:1, /* target mispredicted */ + predicted:1,/* target predicted */ + in_tx:1, /* in transaction */ + abort:1, /* transaction abort */ + cycles:16, /* cycle count to last branch */ + reserved:44; +}; + +#endif /* _UAPI_LINUX_PERF_EVENT_H */ diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 2bd8c310606c..0b1ebf3c08f6 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -54,6 +54,7 @@ tools/include/linux/hash.h tools/include/linux/kernel.h tools/include/linux/list.h tools/include/linux/log2.h +tools/include/uapi/linux/perf_event.h tools/include/linux/poison.h tools/include/linux/rbtree.h tools/include/linux/rbtree_augmented.h @@ -66,7 +67,6 @@ include/asm-generic/bitops/const_hweight.h include/asm-generic/bitops/fls64.h include/asm-generic/bitops/__fls.h include/asm-generic/bitops/fls.h -include/linux/perf_event.h include/linux/list.h include/linux/hash.h include/linux/stringify.h @@ -79,7 +79,6 @@ arch/*/lib/memset*.S arch/*/include/asm/*features.h include/linux/poison.h include/linux/hw_breakpoint.h -include/uapi/linux/perf_event.h include/uapi/linux/bpf.h include/uapi/linux/bpf_common.h include/uapi/linux/const.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index d0a2cb11296f..5e5f8cb1dd83 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -345,6 +345,9 @@ export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK include $(srctree)/tools/build/Makefile.include $(PERF_IN): prepare FORCE + @(test -f ../../include/uapi/linux/perf_event.h && ( \ + (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \ + || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true $(Q)$(MAKE) $(build)=perf $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST) diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 7d2ea691c11b..bbb22101be2e 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -206,6 +206,7 @@ endif CFLAGS += -I$(src-perf)/util/include CFLAGS += -I$(src-perf)/arch/$(ARCH)/include +CFLAGS += -I$(srctree)/tools/include/uapi CFLAGS += -I$(srctree)/tools/include/ CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi CFLAGS += -I$(srctree)/arch/$(ARCH)/include -- cgit v1.3-8-gc7d7 From 7d7d1bf1d1dabe435ef50efb051724b8664749cb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Jul 2016 12:36:41 -0300 Subject: perf bench: Copy kernel files needed to build mem{cpy,set} x86_64 benchmarks We can't access kernel files directly from tools/, so copy the required bits, and make sure that we detect when the original files, in the kernel, gets modified. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-z7e76274ch5j4nugv048qacb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/x86/include/asm/cpufeatures.h | 316 +++++++++++++++++++++++++ tools/arch/x86/include/asm/disabled-features.h | 60 +++++ tools/arch/x86/include/asm/required-features.h | 103 ++++++++ tools/arch/x86/lib/memcpy_64.S | 297 +++++++++++++++++++++++ tools/arch/x86/lib/memset_64.S | 138 +++++++++++ tools/include/asm/alternative-asm.h | 9 + tools/perf/MANIFEST | 9 +- tools/perf/Makefile.perf | 15 ++ tools/perf/bench/mem-memcpy-x86-64-asm.S | 2 +- tools/perf/bench/mem-memset-x86-64-asm.S | 2 +- tools/perf/util/include/asm/alternative-asm.h | 9 - 11 files changed, 946 insertions(+), 14 deletions(-) create mode 100644 tools/arch/x86/include/asm/cpufeatures.h create mode 100644 tools/arch/x86/include/asm/disabled-features.h create mode 100644 tools/arch/x86/include/asm/required-features.h create mode 100644 tools/arch/x86/lib/memcpy_64.S create mode 100644 tools/arch/x86/lib/memset_64.S create mode 100644 tools/include/asm/alternative-asm.h delete mode 100644 tools/perf/util/include/asm/alternative-asm.h (limited to 'tools/include') diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h new file mode 100644 index 000000000000..4a413485f9eb --- /dev/null +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -0,0 +1,316 @@ +#ifndef _ASM_X86_CPUFEATURES_H +#define _ASM_X86_CPUFEATURES_H + +#ifndef _ASM_X86_REQUIRED_FEATURES_H +#include +#endif + +#ifndef _ASM_X86_DISABLED_FEATURES_H +#include +#endif + +/* + * Defines x86 CPU feature bits + */ +#define NCAPINTS 18 /* N 32-bit words worth of info */ +#define NBUGINTS 1 /* N 32-bit bug flags */ + +/* + * Note: If the comment begins with a quoted string, that string is used + * in /proc/cpuinfo instead of the macro name. If the string is "", + * this feature bit is not displayed in /proc/cpuinfo at all. + */ + +/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* CMOV instructions */ + /* (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* CLFLUSH instruction */ +#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ +#define X86_FEATURE_ACPI ( 0*32+22) /* ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ +#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ +#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ +#define X86_FEATURE_HT ( 0*32+28) /* Hyper-Threading */ +#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ +#define X86_FEATURE_IA64 ( 0*32+30) /* IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* Pending Break Enable */ + +/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ +/* Don't duplicate feature flags which are redundant with Intel! */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* MP Capable. */ +#define X86_FEATURE_NX ( 1*32+20) /* Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* Long Mode (x86-64) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* AMD 3DNow! extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* 3DNow! */ + +/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* LongRun table interface */ + +/* Other features, Linux-defined mapping, word 3 */ +/* This range is used for feature bits which conflict or are synthesized */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ +/* cpu types for specific tunings: */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ +#define X86_FEATURE_K7 ( 3*32+ 5) /* "" Athlon */ +#define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ +#define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ +#define X86_FEATURE_UP ( 3*32+ 9) /* smp kernel running on up */ +#define X86_FEATURE_ART ( 3*32+10) /* Platform has always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in ia32 userspace */ +#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in ia32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* rep microcode works well */ +#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */ +#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* "" Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* cpu topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* TSC does not stop in C states */ +/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* has extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* APERFMPERF */ +#define X86_FEATURE_EAGER_FPU ( 3*32+29) /* "eagerfpu" Non lazy FPU restore */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */ +#define X86_FEATURE_MCE_RECOVERY ( 3*32+31) /* cpu has recoverable machine checks */ + +/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */ +#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* 64-bit Debug Store */ +#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" Monitor/Mwait support */ +#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* Safer mode */ +#define X86_FEATURE_EST ( 4*32+ 7) /* Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* CMPXCHG16B */ +#define X86_FEATURE_XTPR ( 4*32+14) /* Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* Performance Capabilities */ +#define X86_FEATURE_PCID ( 4*32+17) /* Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* Direct Cache Access */ +#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ +#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* x2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* Tsc deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* "" XSAVE enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* 16-bit fp conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* The RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* Running on a hypervisor */ + +/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ +#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ +#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ +#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ +#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* PMM enabled */ + +/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* Secure virtual machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* translation cache extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* trailing bit manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */ +#define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */ + +/* + * Auxiliary flags: Linux defined - For features scattered in various + * CPUID levels like 0x6, 0xA etc, word 7. + * + * Reuse free bits when adding new feature flags! + */ + +#define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ + +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ + +#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ + +/* Virtualization flags: Linux defined, word 8 */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ +#define X86_FEATURE_VNMI ( 8*32+ 1) /* Intel Virtual NMI */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ + +#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ +#define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ + + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* TSC adjustment MSR 0x3b */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ +#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ +#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */ + +/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* XSAVEOPT */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* XSAVEC */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ +#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ +#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ +#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */ + +/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ +#define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+1) /* Instructions Retired Count */ + +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ +#define X86_FEATURE_PKU (16*32+ 3) /* Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* OS Protection Keys Enable */ + +/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+1) /* Uncorrectable error containment and recovery */ +#define X86_FEATURE_SMCA (17*32+3) /* Scalable MCA */ + +/* + * BUG word(s) + */ +#define X86_BUG(x) (NCAPINTS*32 + (x)) + +#define X86_BUG_F00F X86_BUG(0) /* Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* Cyrix 6x86 coma */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ +#define X86_BUG_11AP X86_BUG(5) /* Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ +#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ + + +#ifdef CONFIG_X86_32 +/* + * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional + * to avoid confusion. + */ +#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ +#endif + +#endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h new file mode 100644 index 000000000000..911e9358ceb1 --- /dev/null +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -0,0 +1,60 @@ +#ifndef _ASM_X86_DISABLED_FEATURES_H +#define _ASM_X86_DISABLED_FEATURES_H + +/* These features, although they might be available in a CPU + * will not be used because the compile options to support + * them are not present. + * + * This code allows them to be checked and disabled at + * compile time without an explicit #ifdef. Use + * cpu_feature_enabled(). + */ + +#ifdef CONFIG_X86_INTEL_MPX +# define DISABLE_MPX 0 +#else +# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) +#endif + +#ifdef CONFIG_X86_64 +# define DISABLE_VME (1<<(X86_FEATURE_VME & 31)) +# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31)) +# define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31)) +# define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31)) +#else +# define DISABLE_VME 0 +# define DISABLE_K6_MTRR 0 +# define DISABLE_CYRIX_ARR 0 +# define DISABLE_CENTAUR_MCR 0 +#endif /* CONFIG_X86_64 */ + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +# define DISABLE_PKU 0 +# define DISABLE_OSPKE 0 +#else +# define DISABLE_PKU (1<<(X86_FEATURE_PKU & 31)) +# define DISABLE_OSPKE (1<<(X86_FEATURE_OSPKE & 31)) +#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ + +/* + * Make sure to add features to the correct mask + */ +#define DISABLED_MASK0 (DISABLE_VME) +#define DISABLED_MASK1 0 +#define DISABLED_MASK2 0 +#define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR) +#define DISABLED_MASK4 0 +#define DISABLED_MASK5 0 +#define DISABLED_MASK6 0 +#define DISABLED_MASK7 0 +#define DISABLED_MASK8 0 +#define DISABLED_MASK9 (DISABLE_MPX) +#define DISABLED_MASK10 0 +#define DISABLED_MASK11 0 +#define DISABLED_MASK12 0 +#define DISABLED_MASK13 0 +#define DISABLED_MASK14 0 +#define DISABLED_MASK15 0 +#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) + +#endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h new file mode 100644 index 000000000000..4916144e3c42 --- /dev/null +++ b/tools/arch/x86/include/asm/required-features.h @@ -0,0 +1,103 @@ +#ifndef _ASM_X86_REQUIRED_FEATURES_H +#define _ASM_X86_REQUIRED_FEATURES_H + +/* Define minimum CPUID feature set for kernel These bits are checked + really early to actually display a visible error message before the + kernel dies. Make sure to assign features to the proper mask! + + Some requirements that are not in CPUID yet are also in the + CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too. + + The real information is in arch/x86/Kconfig.cpu, this just converts + the CONFIGs into a bitmask */ + +#ifndef CONFIG_MATH_EMULATION +# define NEED_FPU (1<<(X86_FEATURE_FPU & 31)) +#else +# define NEED_FPU 0 +#endif + +#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) +# define NEED_PAE (1<<(X86_FEATURE_PAE & 31)) +#else +# define NEED_PAE 0 +#endif + +#ifdef CONFIG_X86_CMPXCHG64 +# define NEED_CX8 (1<<(X86_FEATURE_CX8 & 31)) +#else +# define NEED_CX8 0 +#endif + +#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64) +# define NEED_CMOV (1<<(X86_FEATURE_CMOV & 31)) +#else +# define NEED_CMOV 0 +#endif + +#ifdef CONFIG_X86_USE_3DNOW +# define NEED_3DNOW (1<<(X86_FEATURE_3DNOW & 31)) +#else +# define NEED_3DNOW 0 +#endif + +#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64) +# define NEED_NOPL (1<<(X86_FEATURE_NOPL & 31)) +#else +# define NEED_NOPL 0 +#endif + +#ifdef CONFIG_MATOM +# define NEED_MOVBE (1<<(X86_FEATURE_MOVBE & 31)) +#else +# define NEED_MOVBE 0 +#endif + +#ifdef CONFIG_X86_64 +#ifdef CONFIG_PARAVIRT +/* Paravirtualized systems may not have PSE or PGE available */ +#define NEED_PSE 0 +#define NEED_PGE 0 +#else +#define NEED_PSE (1<<(X86_FEATURE_PSE) & 31) +#define NEED_PGE (1<<(X86_FEATURE_PGE) & 31) +#endif +#define NEED_MSR (1<<(X86_FEATURE_MSR & 31)) +#define NEED_FXSR (1<<(X86_FEATURE_FXSR & 31)) +#define NEED_XMM (1<<(X86_FEATURE_XMM & 31)) +#define NEED_XMM2 (1<<(X86_FEATURE_XMM2 & 31)) +#define NEED_LM (1<<(X86_FEATURE_LM & 31)) +#else +#define NEED_PSE 0 +#define NEED_MSR 0 +#define NEED_PGE 0 +#define NEED_FXSR 0 +#define NEED_XMM 0 +#define NEED_XMM2 0 +#define NEED_LM 0 +#endif + +#define REQUIRED_MASK0 (NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\ + NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\ + NEED_XMM|NEED_XMM2) +#define SSE_MASK (NEED_XMM|NEED_XMM2) + +#define REQUIRED_MASK1 (NEED_LM|NEED_3DNOW) + +#define REQUIRED_MASK2 0 +#define REQUIRED_MASK3 (NEED_NOPL) +#define REQUIRED_MASK4 (NEED_MOVBE) +#define REQUIRED_MASK5 0 +#define REQUIRED_MASK6 0 +#define REQUIRED_MASK7 0 +#define REQUIRED_MASK8 0 +#define REQUIRED_MASK9 0 +#define REQUIRED_MASK10 0 +#define REQUIRED_MASK11 0 +#define REQUIRED_MASK12 0 +#define REQUIRED_MASK13 0 +#define REQUIRED_MASK14 0 +#define REQUIRED_MASK15 0 +#define REQUIRED_MASK16 0 + +#endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S new file mode 100644 index 000000000000..2ec0b0abbfaa --- /dev/null +++ b/tools/arch/x86/lib/memcpy_64.S @@ -0,0 +1,297 @@ +/* Copyright 2002 Andi Kleen */ + +#include +#include +#include +#include + +/* + * We build a jump to memcpy_orig by default which gets NOPped out on + * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which + * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs + * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. + */ + +.weak memcpy + +/* + * memcpy - Copy a memory block. + * + * Input: + * rdi destination + * rsi source + * rdx count + * + * Output: + * rax original destination + */ +ENTRY(__memcpy) +ENTRY(memcpy) + ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ + "jmp memcpy_erms", X86_FEATURE_ERMS + + movq %rdi, %rax + movq %rdx, %rcx + shrq $3, %rcx + andl $7, %edx + rep movsq + movl %edx, %ecx + rep movsb + ret +ENDPROC(memcpy) +ENDPROC(__memcpy) + +/* + * memcpy_erms() - enhanced fast string memcpy. This is faster and + * simpler than memcpy. Use memcpy_erms when possible. + */ +ENTRY(memcpy_erms) + movq %rdi, %rax + movq %rdx, %rcx + rep movsb + ret +ENDPROC(memcpy_erms) + +ENTRY(memcpy_orig) + movq %rdi, %rax + + cmpq $0x20, %rdx + jb .Lhandle_tail + + /* + * We check whether memory false dependence could occur, + * then jump to corresponding copy mode. + */ + cmp %dil, %sil + jl .Lcopy_backward + subq $0x20, %rdx +.Lcopy_forward_loop: + subq $0x20, %rdx + + /* + * Move in blocks of 4x8 bytes: + */ + movq 0*8(%rsi), %r8 + movq 1*8(%rsi), %r9 + movq 2*8(%rsi), %r10 + movq 3*8(%rsi), %r11 + leaq 4*8(%rsi), %rsi + + movq %r8, 0*8(%rdi) + movq %r9, 1*8(%rdi) + movq %r10, 2*8(%rdi) + movq %r11, 3*8(%rdi) + leaq 4*8(%rdi), %rdi + jae .Lcopy_forward_loop + addl $0x20, %edx + jmp .Lhandle_tail + +.Lcopy_backward: + /* + * Calculate copy position to tail. + */ + addq %rdx, %rsi + addq %rdx, %rdi + subq $0x20, %rdx + /* + * At most 3 ALU operations in one cycle, + * so append NOPS in the same 16 bytes trunk. + */ + .p2align 4 +.Lcopy_backward_loop: + subq $0x20, %rdx + movq -1*8(%rsi), %r8 + movq -2*8(%rsi), %r9 + movq -3*8(%rsi), %r10 + movq -4*8(%rsi), %r11 + leaq -4*8(%rsi), %rsi + movq %r8, -1*8(%rdi) + movq %r9, -2*8(%rdi) + movq %r10, -3*8(%rdi) + movq %r11, -4*8(%rdi) + leaq -4*8(%rdi), %rdi + jae .Lcopy_backward_loop + + /* + * Calculate copy position to head. + */ + addl $0x20, %edx + subq %rdx, %rsi + subq %rdx, %rdi +.Lhandle_tail: + cmpl $16, %edx + jb .Lless_16bytes + + /* + * Move data from 16 bytes to 31 bytes. + */ + movq 0*8(%rsi), %r8 + movq 1*8(%rsi), %r9 + movq -2*8(%rsi, %rdx), %r10 + movq -1*8(%rsi, %rdx), %r11 + movq %r8, 0*8(%rdi) + movq %r9, 1*8(%rdi) + movq %r10, -2*8(%rdi, %rdx) + movq %r11, -1*8(%rdi, %rdx) + retq + .p2align 4 +.Lless_16bytes: + cmpl $8, %edx + jb .Lless_8bytes + /* + * Move data from 8 bytes to 15 bytes. + */ + movq 0*8(%rsi), %r8 + movq -1*8(%rsi, %rdx), %r9 + movq %r8, 0*8(%rdi) + movq %r9, -1*8(%rdi, %rdx) + retq + .p2align 4 +.Lless_8bytes: + cmpl $4, %edx + jb .Lless_3bytes + + /* + * Move data from 4 bytes to 7 bytes. + */ + movl (%rsi), %ecx + movl -4(%rsi, %rdx), %r8d + movl %ecx, (%rdi) + movl %r8d, -4(%rdi, %rdx) + retq + .p2align 4 +.Lless_3bytes: + subl $1, %edx + jb .Lend + /* + * Move data from 1 bytes to 3 bytes. + */ + movzbl (%rsi), %ecx + jz .Lstore_1byte + movzbq 1(%rsi), %r8 + movzbq (%rsi, %rdx), %r9 + movb %r8b, 1(%rdi) + movb %r9b, (%rdi, %rdx) +.Lstore_1byte: + movb %cl, (%rdi) + +.Lend: + retq +ENDPROC(memcpy_orig) + +#ifndef CONFIG_UML +/* + * memcpy_mcsafe - memory copy with machine check exception handling + * Note that we only catch machine checks when reading the source addresses. + * Writes to target are posted and don't generate machine checks. + */ +ENTRY(memcpy_mcsafe) + cmpl $8, %edx + /* Less than 8 bytes? Go to byte copy loop */ + jb .L_no_whole_words + + /* Check for bad alignment of source */ + testl $7, %esi + /* Already aligned */ + jz .L_8byte_aligned + + /* Copy one byte at a time until source is 8-byte aligned */ + movl %esi, %ecx + andl $7, %ecx + subl $8, %ecx + negl %ecx + subl %ecx, %edx +.L_copy_leading_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_leading_bytes + +.L_8byte_aligned: + /* Figure out how many whole cache lines (64-bytes) to copy */ + movl %edx, %ecx + andl $63, %edx + shrl $6, %ecx + jz .L_no_whole_cache_lines + + /* Loop copying whole cache lines */ +.L_cache_w0: movq (%rsi), %r8 +.L_cache_w1: movq 1*8(%rsi), %r9 +.L_cache_w2: movq 2*8(%rsi), %r10 +.L_cache_w3: movq 3*8(%rsi), %r11 + movq %r8, (%rdi) + movq %r9, 1*8(%rdi) + movq %r10, 2*8(%rdi) + movq %r11, 3*8(%rdi) +.L_cache_w4: movq 4*8(%rsi), %r8 +.L_cache_w5: movq 5*8(%rsi), %r9 +.L_cache_w6: movq 6*8(%rsi), %r10 +.L_cache_w7: movq 7*8(%rsi), %r11 + movq %r8, 4*8(%rdi) + movq %r9, 5*8(%rdi) + movq %r10, 6*8(%rdi) + movq %r11, 7*8(%rdi) + leaq 64(%rsi), %rsi + leaq 64(%rdi), %rdi + decl %ecx + jnz .L_cache_w0 + + /* Are there any trailing 8-byte words? */ +.L_no_whole_cache_lines: + movl %edx, %ecx + andl $7, %edx + shrl $3, %ecx + jz .L_no_whole_words + + /* Copy trailing words */ +.L_copy_trailing_words: + movq (%rsi), %r8 + mov %r8, (%rdi) + leaq 8(%rsi), %rsi + leaq 8(%rdi), %rdi + decl %ecx + jnz .L_copy_trailing_words + + /* Any trailing bytes? */ +.L_no_whole_words: + andl %edx, %edx + jz .L_done_memcpy_trap + + /* Copy trailing bytes */ + movl %edx, %ecx +.L_copy_trailing_bytes: + movb (%rsi), %al + movb %al, (%rdi) + incq %rsi + incq %rdi + decl %ecx + jnz .L_copy_trailing_bytes + + /* Copy successful. Return zero */ +.L_done_memcpy_trap: + xorq %rax, %rax + ret +ENDPROC(memcpy_mcsafe) + + .section .fixup, "ax" + /* Return -EFAULT for any failure */ +.L_memcpy_mcsafe_fail: + mov $-EFAULT, %rax + ret + + .previous + + _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) +#endif diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S new file mode 100644 index 000000000000..e1229ecd2a82 --- /dev/null +++ b/tools/arch/x86/lib/memset_64.S @@ -0,0 +1,138 @@ +/* Copyright 2002 Andi Kleen, SuSE Labs */ + +#include +#include +#include + +.weak memset + +/* + * ISO C memset - set a memory block to a byte value. This function uses fast + * string to get better performance than the original function. The code is + * simpler and shorter than the original function as well. + * + * rdi destination + * rsi value (char) + * rdx count (bytes) + * + * rax original destination + */ +ENTRY(memset) +ENTRY(__memset) + /* + * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended + * to use it when possible. If not available, use fast string instructions. + * + * Otherwise, use original memset function. + */ + ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \ + "jmp memset_erms", X86_FEATURE_ERMS + + movq %rdi,%r9 + movq %rdx,%rcx + andl $7,%edx + shrq $3,%rcx + /* expand byte value */ + movzbl %sil,%esi + movabs $0x0101010101010101,%rax + imulq %rsi,%rax + rep stosq + movl %edx,%ecx + rep stosb + movq %r9,%rax + ret +ENDPROC(memset) +ENDPROC(__memset) + +/* + * ISO C memset - set a memory block to a byte value. This function uses + * enhanced rep stosb to override the fast string function. + * The code is simpler and shorter than the fast string function as well. + * + * rdi destination + * rsi value (char) + * rdx count (bytes) + * + * rax original destination + */ +ENTRY(memset_erms) + movq %rdi,%r9 + movb %sil,%al + movq %rdx,%rcx + rep stosb + movq %r9,%rax + ret +ENDPROC(memset_erms) + +ENTRY(memset_orig) + movq %rdi,%r10 + + /* expand byte value */ + movzbl %sil,%ecx + movabs $0x0101010101010101,%rax + imulq %rcx,%rax + + /* align dst */ + movl %edi,%r9d + andl $7,%r9d + jnz .Lbad_alignment +.Lafter_bad_alignment: + + movq %rdx,%rcx + shrq $6,%rcx + jz .Lhandle_tail + + .p2align 4 +.Lloop_64: + decq %rcx + movq %rax,(%rdi) + movq %rax,8(%rdi) + movq %rax,16(%rdi) + movq %rax,24(%rdi) + movq %rax,32(%rdi) + movq %rax,40(%rdi) + movq %rax,48(%rdi) + movq %rax,56(%rdi) + leaq 64(%rdi),%rdi + jnz .Lloop_64 + + /* Handle tail in loops. The loops should be faster than hard + to predict jump tables. */ + .p2align 4 +.Lhandle_tail: + movl %edx,%ecx + andl $63&(~7),%ecx + jz .Lhandle_7 + shrl $3,%ecx + .p2align 4 +.Lloop_8: + decl %ecx + movq %rax,(%rdi) + leaq 8(%rdi),%rdi + jnz .Lloop_8 + +.Lhandle_7: + andl $7,%edx + jz .Lende + .p2align 4 +.Lloop_1: + decl %edx + movb %al,(%rdi) + leaq 1(%rdi),%rdi + jnz .Lloop_1 + +.Lende: + movq %r10,%rax + ret + +.Lbad_alignment: + cmpq $7,%rdx + jbe .Lhandle_7 + movq %rax,(%rdi) /* unaligned store */ + movq $8,%r8 + subq %r9,%r8 + addq %r8,%rdi + subq %r8,%rdx + jmp .Lafter_bad_alignment +.Lfinal: +ENDPROC(memset_orig) diff --git a/tools/include/asm/alternative-asm.h b/tools/include/asm/alternative-asm.h new file mode 100644 index 000000000000..2a4d1bfa2988 --- /dev/null +++ b/tools/include/asm/alternative-asm.h @@ -0,0 +1,9 @@ +#ifndef _TOOLS_ASM_ALTERNATIVE_ASM_H +#define _TOOLS_ASM_ALTERNATIVE_ASM_H + +/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ + +#define altinstruction_entry # +#define ALTERNATIVE_2 # + +#endif diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 0b1ebf3c08f6..cf85d1cd1c91 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -12,6 +12,11 @@ tools/arch/sparc/include/asm/barrier_32.h tools/arch/sparc/include/asm/barrier_64.h tools/arch/tile/include/asm/barrier.h tools/arch/x86/include/asm/barrier.h +tools/arch/x86/include/asm/cpufeatures.h +tools/arch/x86/include/asm/disabled-features.h +tools/arch/x86/include/asm/required-features.h +tools/arch/x86/lib/memcpy_64.S +tools/arch/x86/lib/memset_64.S tools/arch/xtensa/include/asm/barrier.h tools/scripts tools/build @@ -31,6 +36,7 @@ tools/lib/find_bit.c tools/lib/bitmap.c tools/lib/str_error_r.c tools/lib/vsprintf.c +tools/include/asm/alternative-asm.h tools/include/asm/atomic.h tools/include/asm/barrier.h tools/include/asm/bug.h @@ -74,9 +80,6 @@ include/linux/swab.h arch/*/include/asm/unistd*.h arch/*/include/uapi/asm/unistd*.h arch/*/include/uapi/asm/perf_regs.h -arch/*/lib/memcpy*.S -arch/*/lib/memset*.S -arch/*/include/asm/*features.h include/linux/poison.h include/linux/hw_breakpoint.h include/uapi/linux/bpf.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 5e5f8cb1dd83..809735c6cb26 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -348,6 +348,21 @@ $(PERF_IN): prepare FORCE @(test -f ../../include/uapi/linux/perf_event.h && ( \ (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \ || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true + @(test -f ../../arch/x86/include/asm/disabled-features.h && ( \ + (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \ + || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true + @(test -f ../../arch/x86/include/asm/required-features.h && ( \ + (diff -B ../arch/x86/include/asm/required-features.h ../../arch/x86/include/asm/required-features.h >/dev/null) \ + || echo "Warning: tools/arch/x86/include/asm/required-features.h differs from kernel" >&2 )) || true + @(test -f ../../arch/x86/include/asm/cpufeatures.h && ( \ + (diff -B ../arch/x86/include/asm/cpufeatures.h ../../arch/x86/include/asm/cpufeatures.h >/dev/null) \ + || echo "Warning: tools/arch/x86/include/asm/cpufeatures.h differs from kernel" >&2 )) || true + @(test -f ../../arch/x86/lib/memcpy_64.S && ( \ + (diff -B ../arch/x86/lib/memcpy_64.S ../../arch/x86/lib/memcpy_64.S >/dev/null) \ + || echo "Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel" >&2 )) || true + @(test -f ../../arch/x86/lib/memset_64.S && ( \ + (diff -B ../arch/x86/lib/memset_64.S ../../arch/x86/lib/memset_64.S >/dev/null) \ + || echo "Warning: tools/arch/x86/lib/memset_64.S differs from kernel" >&2 )) || true $(Q)$(MAKE) $(build)=perf $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST) diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index 5c3cce082cb8..f700369bb0f6 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -6,7 +6,7 @@ #define globl p2align 4; .globl #define _ASM_EXTABLE_FAULT(x, y) -#include "../../../arch/x86/lib/memcpy_64.S" +#include "../../arch/x86/lib/memcpy_64.S" /* * We need to provide note.GNU-stack section, saying that we want * NOT executable stack. Otherwise the final linking will assume that diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S index de278784c866..58407aa24c1b 100644 --- a/tools/perf/bench/mem-memset-x86-64-asm.S +++ b/tools/perf/bench/mem-memset-x86-64-asm.S @@ -1,7 +1,7 @@ #define memset MEMSET /* don't hide glibc's memset() */ #define altinstr_replacement text #define globl p2align 4; .globl -#include "../../../arch/x86/lib/memset_64.S" +#include "../../arch/x86/lib/memset_64.S" /* * We need to provide note.GNU-stack section, saying that we want diff --git a/tools/perf/util/include/asm/alternative-asm.h b/tools/perf/util/include/asm/alternative-asm.h deleted file mode 100644 index 3a3a0f16456a..000000000000 --- a/tools/perf/util/include/asm/alternative-asm.h +++ /dev/null @@ -1,9 +0,0 @@ -#ifndef _PERF_ASM_ALTERNATIVE_ASM_H -#define _PERF_ASM_ALTERNATIVE_ASM_H - -/* Just disable it so we can build arch/x86/lib/memcpy_64.S for perf bench: */ - -#define altinstruction_entry # -#define ALTERNATIVE_2 # - -#endif -- cgit v1.3-8-gc7d7 From 971e827bffef781dd089a402fe602ff20c1f1819 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Jul 2016 16:38:05 -0300 Subject: tools lib bpf: Copy bpf.h and bpf_common.h from the kernel To allow the build to complete on older systems, where those files are either not uptodate, lacking some recent additions or not present at all. And check if the copy drifts from the kernel, as in this synthetic test: BUILD: Doing 'make -j4' parallel build Warning: tools/include/linux/bpf.h differs from kernel Warning: tools/include/linux/bpf_common.h differs from kernel Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-5plvi2gq4x469dcyybiu226q@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/bpf.h | 389 ++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf_common.h | 55 +++++ tools/lib/bpf/Makefile | 8 +- tools/perf/MANIFEST | 5 +- tools/perf/config/Makefile | 5 +- 5 files changed, 456 insertions(+), 6 deletions(-) create mode 100644 tools/include/uapi/linux/bpf.h create mode 100644 tools/include/uapi/linux/bpf_common.h (limited to 'tools/include') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h new file mode 100644 index 000000000000..406459b935a2 --- /dev/null +++ b/tools/include/uapi/linux/bpf.h @@ -0,0 +1,389 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#ifndef _UAPI__LINUX_BPF_H__ +#define _UAPI__LINUX_BPF_H__ + +#include +#include + +/* Extended instruction set based on top of classic BPF */ + +/* instruction classes */ +#define BPF_ALU64 0x07 /* alu mode in double word width */ + +/* ld/ldx fields */ +#define BPF_DW 0x18 /* double word */ +#define BPF_XADD 0xc0 /* exclusive add */ + +/* alu/jmp fields */ +#define BPF_MOV 0xb0 /* mov reg to reg */ +#define BPF_ARSH 0xc0 /* sign extending arithmetic shift right */ + +/* change endianness of a register */ +#define BPF_END 0xd0 /* flags for endianness conversion: */ +#define BPF_TO_LE 0x00 /* convert to little-endian */ +#define BPF_TO_BE 0x08 /* convert to big-endian */ +#define BPF_FROM_LE BPF_TO_LE +#define BPF_FROM_BE BPF_TO_BE + +#define BPF_JNE 0x50 /* jump != */ +#define BPF_JSGT 0x60 /* SGT is signed '>', GT in x86 */ +#define BPF_JSGE 0x70 /* SGE is signed '>=', GE in x86 */ +#define BPF_CALL 0x80 /* function call */ +#define BPF_EXIT 0x90 /* function return */ + +/* Register numbers */ +enum { + BPF_REG_0 = 0, + BPF_REG_1, + BPF_REG_2, + BPF_REG_3, + BPF_REG_4, + BPF_REG_5, + BPF_REG_6, + BPF_REG_7, + BPF_REG_8, + BPF_REG_9, + BPF_REG_10, + __MAX_BPF_REG, +}; + +/* BPF has 10 general purpose 64-bit registers and stack frame. */ +#define MAX_BPF_REG __MAX_BPF_REG + +struct bpf_insn { + __u8 code; /* opcode */ + __u8 dst_reg:4; /* dest register */ + __u8 src_reg:4; /* source register */ + __s16 off; /* signed offset */ + __s32 imm; /* signed immediate constant */ +}; + +/* BPF syscall commands, see bpf(2) man-page for details. */ +enum bpf_cmd { + BPF_MAP_CREATE, + BPF_MAP_LOOKUP_ELEM, + BPF_MAP_UPDATE_ELEM, + BPF_MAP_DELETE_ELEM, + BPF_MAP_GET_NEXT_KEY, + BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, +}; + +enum bpf_map_type { + BPF_MAP_TYPE_UNSPEC, + BPF_MAP_TYPE_HASH, + BPF_MAP_TYPE_ARRAY, + BPF_MAP_TYPE_PROG_ARRAY, + BPF_MAP_TYPE_PERF_EVENT_ARRAY, + BPF_MAP_TYPE_PERCPU_HASH, + BPF_MAP_TYPE_PERCPU_ARRAY, + BPF_MAP_TYPE_STACK_TRACE, +}; + +enum bpf_prog_type { + BPF_PROG_TYPE_UNSPEC, + BPF_PROG_TYPE_SOCKET_FILTER, + BPF_PROG_TYPE_KPROBE, + BPF_PROG_TYPE_SCHED_CLS, + BPF_PROG_TYPE_SCHED_ACT, + BPF_PROG_TYPE_TRACEPOINT, +}; + +#define BPF_PSEUDO_MAP_FD 1 + +/* flags for BPF_MAP_UPDATE_ELEM command */ +#define BPF_ANY 0 /* create new element or update existing */ +#define BPF_NOEXIST 1 /* create new element if it didn't exist */ +#define BPF_EXIST 2 /* update existing element */ + +#define BPF_F_NO_PREALLOC (1U << 0) + +union bpf_attr { + struct { /* anonymous struct used by BPF_MAP_CREATE command */ + __u32 map_type; /* one of enum bpf_map_type */ + __u32 key_size; /* size of key in bytes */ + __u32 value_size; /* size of value in bytes */ + __u32 max_entries; /* max number of entries in a map */ + __u32 map_flags; /* prealloc or not */ + }; + + struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ + __u32 map_fd; + __aligned_u64 key; + union { + __aligned_u64 value; + __aligned_u64 next_key; + }; + __u64 flags; + }; + + struct { /* anonymous struct used by BPF_PROG_LOAD command */ + __u32 prog_type; /* one of enum bpf_prog_type */ + __u32 insn_cnt; + __aligned_u64 insns; + __aligned_u64 license; + __u32 log_level; /* verbosity level of verifier */ + __u32 log_size; /* size of user buffer */ + __aligned_u64 log_buf; /* user supplied buffer */ + __u32 kern_version; /* checked when prog_type=kprobe */ + }; + + struct { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + }; +} __attribute__((aligned(8))); + +/* integer value in 'imm' field of BPF_CALL instruction selects which helper + * function eBPF program intends to call + */ +enum bpf_func_id { + BPF_FUNC_unspec, + BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */ + BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */ + BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ + BPF_FUNC_probe_read, /* int bpf_probe_read(void *dst, int size, void *src) */ + BPF_FUNC_ktime_get_ns, /* u64 bpf_ktime_get_ns(void) */ + BPF_FUNC_trace_printk, /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */ + BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ + BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ + + /** + * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet + * @skb: pointer to skb + * @offset: offset within packet from skb->mac_header + * @from: pointer where to copy bytes from + * @len: number of bytes to store into packet + * @flags: bit 0 - if true, recompute skb->csum + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_skb_store_bytes, + + /** + * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum + * @skb: pointer to skb + * @offset: offset within packet where IP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_l3_csum_replace, + + /** + * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum + * @skb: pointer to skb + * @offset: offset within packet where TCP/UDP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * bit 4 - is pseudo header + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_l4_csum_replace, + + /** + * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program + * @ctx: context pointer passed to next program + * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY + * @index: index inside array that selects specific program to run + * Return: 0 on success + */ + BPF_FUNC_tail_call, + + /** + * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev + * @skb: pointer to skb + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: 0 on success + */ + BPF_FUNC_clone_redirect, + + /** + * u64 bpf_get_current_pid_tgid(void) + * Return: current->tgid << 32 | current->pid + */ + BPF_FUNC_get_current_pid_tgid, + + /** + * u64 bpf_get_current_uid_gid(void) + * Return: current_gid << 32 | current_uid + */ + BPF_FUNC_get_current_uid_gid, + + /** + * bpf_get_current_comm(char *buf, int size_of_buf) + * stores current->comm into buf + * Return: 0 on success + */ + BPF_FUNC_get_current_comm, + + /** + * bpf_get_cgroup_classid(skb) - retrieve a proc's classid + * @skb: pointer to skb + * Return: classid if != 0 + */ + BPF_FUNC_get_cgroup_classid, + BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */ + BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */ + + /** + * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags) + * retrieve or populate tunnel metadata + * @skb: pointer to skb + * @key: pointer to 'struct bpf_tunnel_key' + * @size: size of 'struct bpf_tunnel_key' + * @flags: room for future extensions + * Retrun: 0 on success + */ + BPF_FUNC_skb_get_tunnel_key, + BPF_FUNC_skb_set_tunnel_key, + BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ + /** + * bpf_redirect(ifindex, flags) - redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: TC_ACT_REDIRECT + */ + BPF_FUNC_redirect, + + /** + * bpf_get_route_realm(skb) - retrieve a dst's tclassid + * @skb: pointer to skb + * Return: realm if != 0 + */ + BPF_FUNC_get_route_realm, + + /** + * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample + * @ctx: struct pt_regs* + * @map: pointer to perf_event_array map + * @index: index of event in the map + * @data: data on stack to be output as raw data + * @size: size of data + * Return: 0 on success + */ + BPF_FUNC_perf_event_output, + BPF_FUNC_skb_load_bytes, + + /** + * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + */ + BPF_FUNC_get_stackid, + + /** + * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff + * @from: raw from buffer + * @from_size: length of from buffer + * @to: raw to buffer + * @to_size: length of to buffer + * @seed: optional seed + * Return: csum result + */ + BPF_FUNC_csum_diff, + + /** + * bpf_skb_[gs]et_tunnel_opt(skb, opt, size) + * retrieve or populate tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: 0 on success for set, option size for get + */ + BPF_FUNC_skb_get_tunnel_opt, + BPF_FUNC_skb_set_tunnel_opt, + __BPF_FUNC_MAX_ID, +}; + +/* All flags used by eBPF helper functions, placed here. */ + +/* BPF_FUNC_skb_store_bytes flags. */ +#define BPF_F_RECOMPUTE_CSUM (1ULL << 0) +#define BPF_F_INVALIDATE_HASH (1ULL << 1) + +/* BPF_FUNC_l3_csum_replace and BPF_FUNC_l4_csum_replace flags. + * First 4 bits are for passing the header field size. + */ +#define BPF_F_HDR_FIELD_MASK 0xfULL + +/* BPF_FUNC_l4_csum_replace flags. */ +#define BPF_F_PSEUDO_HDR (1ULL << 4) +#define BPF_F_MARK_MANGLED_0 (1ULL << 5) + +/* BPF_FUNC_clone_redirect and BPF_FUNC_redirect flags. */ +#define BPF_F_INGRESS (1ULL << 0) + +/* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ +#define BPF_F_TUNINFO_IPV6 (1ULL << 0) + +/* BPF_FUNC_get_stackid flags. */ +#define BPF_F_SKIP_FIELD_MASK 0xffULL +#define BPF_F_USER_STACK (1ULL << 8) +#define BPF_F_FAST_STACK_CMP (1ULL << 9) +#define BPF_F_REUSE_STACKID (1ULL << 10) + +/* BPF_FUNC_skb_set_tunnel_key flags. */ +#define BPF_F_ZERO_CSUM_TX (1ULL << 1) +#define BPF_F_DONT_FRAGMENT (1ULL << 2) + +/* BPF_FUNC_perf_event_output flags. */ +#define BPF_F_INDEX_MASK 0xffffffffULL +#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK + +/* user accessible mirror of in-kernel sk_buff. + * new fields can only be added to the end of this structure + */ +struct __sk_buff { + __u32 len; + __u32 pkt_type; + __u32 mark; + __u32 queue_mapping; + __u32 protocol; + __u32 vlan_present; + __u32 vlan_tci; + __u32 vlan_proto; + __u32 priority; + __u32 ingress_ifindex; + __u32 ifindex; + __u32 tc_index; + __u32 cb[5]; + __u32 hash; + __u32 tc_classid; + __u32 data; + __u32 data_end; +}; + +struct bpf_tunnel_key { + __u32 tunnel_id; + union { + __u32 remote_ipv4; + __u32 remote_ipv6[4]; + }; + __u8 tunnel_tos; + __u8 tunnel_ttl; + __u16 tunnel_ext; + __u32 tunnel_label; +}; + +#endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/bpf_common.h b/tools/include/uapi/linux/bpf_common.h new file mode 100644 index 000000000000..a5c220e0828f --- /dev/null +++ b/tools/include/uapi/linux/bpf_common.h @@ -0,0 +1,55 @@ +#ifndef _UAPI__LINUX_BPF_COMMON_H__ +#define _UAPI__LINUX_BPF_COMMON_H__ + +/* Instruction classes */ +#define BPF_CLASS(code) ((code) & 0x07) +#define BPF_LD 0x00 +#define BPF_LDX 0x01 +#define BPF_ST 0x02 +#define BPF_STX 0x03 +#define BPF_ALU 0x04 +#define BPF_JMP 0x05 +#define BPF_RET 0x06 +#define BPF_MISC 0x07 + +/* ld/ldx fields */ +#define BPF_SIZE(code) ((code) & 0x18) +#define BPF_W 0x00 +#define BPF_H 0x08 +#define BPF_B 0x10 +#define BPF_MODE(code) ((code) & 0xe0) +#define BPF_IMM 0x00 +#define BPF_ABS 0x20 +#define BPF_IND 0x40 +#define BPF_MEM 0x60 +#define BPF_LEN 0x80 +#define BPF_MSH 0xa0 + +/* alu/jmp fields */ +#define BPF_OP(code) ((code) & 0xf0) +#define BPF_ADD 0x00 +#define BPF_SUB 0x10 +#define BPF_MUL 0x20 +#define BPF_DIV 0x30 +#define BPF_OR 0x40 +#define BPF_AND 0x50 +#define BPF_LSH 0x60 +#define BPF_RSH 0x70 +#define BPF_NEG 0x80 +#define BPF_MOD 0x90 +#define BPF_XOR 0xa0 + +#define BPF_JA 0x00 +#define BPF_JEQ 0x10 +#define BPF_JGT 0x20 +#define BPF_JGE 0x30 +#define BPF_JSET 0x40 +#define BPF_SRC(code) ((code) & 0x08) +#define BPF_K 0x00 +#define BPF_X 0x08 + +#ifndef BPF_MAXINSNS +#define BPF_MAXINSNS 4096 +#endif + +#endif /* _UAPI__LINUX_BPF_COMMON_H__ */ diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index fc1bc75ae56d..62d89d50fcbd 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -68,7 +68,7 @@ FEATURE_USER = .libbpf FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf FEATURE_DISPLAY = libelf bpf -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi +INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) check_feat := 1 @@ -154,6 +154,12 @@ all: fixdep $(VERSION_FILES) all_cmd all_cmd: $(CMD_TARGETS) $(BPF_IN): force elfdep bpfdep + @(test -f ../../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ + (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ + echo "Warning: tools/include/uapi/linux/bpf.h differs from kernel" >&2 )) || true + @(test -f ../../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \ + (diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \ + echo "Warning: tools/include/uapi/linux/bpf_common.h differs from kernel" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf $(OUTPUT)libbpf.so: $(BPF_IN) diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index cf85d1cd1c91..a300cbb13541 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -23,7 +23,6 @@ tools/build tools/arch/x86/include/asm/atomic.h tools/arch/x86/include/asm/rmwcc.h tools/lib/traceevent -tools/lib/bpf tools/lib/api tools/lib/bpf tools/lib/subcmd @@ -60,6 +59,8 @@ tools/include/linux/hash.h tools/include/linux/kernel.h tools/include/linux/list.h tools/include/linux/log2.h +tools/include/uapi/linux/bpf.h +tools/include/uapi/linux/bpf_common.h tools/include/uapi/linux/perf_event.h tools/include/linux/poison.h tools/include/linux/rbtree.h @@ -82,8 +83,6 @@ arch/*/include/uapi/asm/unistd*.h arch/*/include/uapi/asm/perf_regs.h include/linux/poison.h include/linux/hw_breakpoint.h -include/uapi/linux/bpf.h -include/uapi/linux/bpf_common.h include/uapi/linux/const.h include/uapi/linux/swab.h include/uapi/linux/hw_breakpoint.h diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index bbb22101be2e..d629e5f5abdc 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -115,7 +115,7 @@ endif FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS) FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf -FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/arch/$(ARCH)/include/uapi -I$(srctree)/include/uapi +FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi # include ARCH specific config -include $(src-perf)/arch/$(ARCH)/Makefile @@ -210,7 +210,8 @@ CFLAGS += -I$(srctree)/tools/include/uapi CFLAGS += -I$(srctree)/tools/include/ CFLAGS += -I$(srctree)/arch/$(ARCH)/include/uapi CFLAGS += -I$(srctree)/arch/$(ARCH)/include -CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include +CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/include/uapi +CFLAGS += -I$(srctree)/tools/arch/$(ARCH)/ CFLAGS += -I$(srctree)/include/uapi CFLAGS += -I$(srctree)/include -- cgit v1.3-8-gc7d7 From 4998a1224686d74ab7f7789787f7f7f904c75dfc Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 11 Jul 2016 23:37:18 -0300 Subject: tools: Copy uapi/linux/hw_breakpoint.h from the kernel To allow the build to complete on older systems, where those files are either not uptodate, lacking some recent additions or not present at all. And check if the copy drifts from the kernel. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-3jz31pz4nw526uko5da9e7o3@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/hw_breakpoint.h | 30 ++++++++++++++++++++++++++++++ tools/perf/MANIFEST | 3 +-- tools/perf/Makefile.perf | 3 +++ 3 files changed, 34 insertions(+), 2 deletions(-) create mode 100644 tools/include/uapi/linux/hw_breakpoint.h (limited to 'tools/include') diff --git a/tools/include/uapi/linux/hw_breakpoint.h b/tools/include/uapi/linux/hw_breakpoint.h new file mode 100644 index 000000000000..b04000a2296a --- /dev/null +++ b/tools/include/uapi/linux/hw_breakpoint.h @@ -0,0 +1,30 @@ +#ifndef _UAPI_LINUX_HW_BREAKPOINT_H +#define _UAPI_LINUX_HW_BREAKPOINT_H + +enum { + HW_BREAKPOINT_LEN_1 = 1, + HW_BREAKPOINT_LEN_2 = 2, + HW_BREAKPOINT_LEN_4 = 4, + HW_BREAKPOINT_LEN_8 = 8, +}; + +enum { + HW_BREAKPOINT_EMPTY = 0, + HW_BREAKPOINT_R = 1, + HW_BREAKPOINT_W = 2, + HW_BREAKPOINT_RW = HW_BREAKPOINT_R | HW_BREAKPOINT_W, + HW_BREAKPOINT_X = 4, + HW_BREAKPOINT_INVALID = HW_BREAKPOINT_RW | HW_BREAKPOINT_X, +}; + +enum bp_type_idx { + TYPE_INST = 0, +#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS + TYPE_DATA = 0, +#else + TYPE_DATA = 1, +#endif + TYPE_MAX +}; + +#endif /* _UAPI_LINUX_HW_BREAKPOINT_H */ diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index d15c052ccb7b..a4aefaeff355 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -61,6 +61,7 @@ tools/include/linux/list.h tools/include/linux/log2.h tools/include/uapi/linux/bpf.h tools/include/uapi/linux/bpf_common.h +tools/include/uapi/linux/hw_breakpoint.h tools/include/uapi/linux/perf_event.h tools/include/linux/poison.h tools/include/linux/rbtree.h @@ -82,10 +83,8 @@ arch/*/include/asm/unistd*.h arch/*/include/uapi/asm/unistd*.h tools/arch/*/include/uapi/asm/perf_regs.h include/linux/poison.h -include/linux/hw_breakpoint.h include/uapi/linux/const.h include/uapi/linux/swab.h -include/uapi/linux/hw_breakpoint.h arch/x86/include/asm/svm.h arch/x86/include/asm/vmx.h arch/x86/include/asm/kvm_host.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 34b91ba8b425..0d07672c3af7 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -348,6 +348,9 @@ $(PERF_IN): prepare FORCE @(test -f ../../include/uapi/linux/perf_event.h && ( \ (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \ || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true + @(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \ + (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \ + || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true @(test -f ../../arch/x86/include/asm/disabled-features.h && ( \ (diff -B ../arch/x86/include/asm/disabled-features.h ../../arch/x86/include/asm/disabled-features.h >/dev/null) \ || echo "Warning: tools/arch/x86/include/asm/disabled-features.h differs from kernel" >&2 )) || true -- cgit v1.3-8-gc7d7 From bb9707077b4ee5f77bc9939b057ff8a0d410296f Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 12 Jul 2016 11:12:18 -0300 Subject: tools: Copy the bitsperlong.h files from the kernel We use it in bitops/__ffs.h and bitops/atomic.h, that we also got from the kernel, but were getting it from either newer systems that carry it in /usr/include, or from the kernel sources, that we decided not to touch from tools/ code. Fix it. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-lwqvgbuitjmrdpjmjp6zqnyx@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/arch/alpha/include/uapi/asm/bitsperlong.h | 8 +++++++ tools/arch/arm64/include/uapi/asm/bitsperlong.h | 23 +++++++++++++++++++ tools/arch/frv/include/uapi/asm/bitsperlong.h | 1 + tools/arch/h8300/include/asm/bitsperlong.h | 14 ++++++++++++ tools/arch/hexagon/include/uapi/asm/bitsperlong.h | 26 ++++++++++++++++++++++ tools/arch/ia64/include/uapi/asm/bitsperlong.h | 8 +++++++ tools/arch/m32r/include/uapi/asm/bitsperlong.h | 1 + .../arch/microblaze/include/uapi/asm/bitsperlong.h | 1 + tools/arch/mips/include/uapi/asm/bitsperlong.h | 8 +++++++ tools/arch/mn10300/include/uapi/asm/bitsperlong.h | 1 + tools/arch/parisc/include/uapi/asm/bitsperlong.h | 14 ++++++++++++ tools/arch/powerpc/include/uapi/asm/bitsperlong.h | 12 ++++++++++ tools/arch/s390/include/uapi/asm/bitsperlong.h | 12 ++++++++++ tools/arch/score/include/uapi/asm/bitsperlong.h | 6 +++++ tools/arch/sparc/include/uapi/asm/bitsperlong.h | 12 ++++++++++ tools/arch/tile/include/uapi/asm/bitsperlong.h | 26 ++++++++++++++++++++++ tools/arch/x86/include/uapi/asm/bitsperlong.h | 12 ++++++++++ tools/include/asm-generic/bitops/__ffs.h | 1 + tools/include/asm-generic/bitops/atomic.h | 1 + tools/include/asm-generic/bitsperlong.h | 25 +++++++++++++++++++++ tools/include/uapi/asm-generic/bitsperlong.h | 15 +++++++++++++ 21 files changed, 227 insertions(+) create mode 100644 tools/arch/alpha/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/arm64/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/frv/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/h8300/include/asm/bitsperlong.h create mode 100644 tools/arch/hexagon/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/ia64/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/m32r/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/microblaze/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/mips/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/mn10300/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/parisc/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/powerpc/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/s390/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/score/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/sparc/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/tile/include/uapi/asm/bitsperlong.h create mode 100644 tools/arch/x86/include/uapi/asm/bitsperlong.h create mode 100644 tools/include/asm-generic/bitsperlong.h create mode 100644 tools/include/uapi/asm-generic/bitsperlong.h (limited to 'tools/include') diff --git a/tools/arch/alpha/include/uapi/asm/bitsperlong.h b/tools/arch/alpha/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..ad57f7868203 --- /dev/null +++ b/tools/arch/alpha/include/uapi/asm/bitsperlong.h @@ -0,0 +1,8 @@ +#ifndef __ASM_ALPHA_BITSPERLONG_H +#define __ASM_ALPHA_BITSPERLONG_H + +#define __BITS_PER_LONG 64 + +#include + +#endif /* __ASM_ALPHA_BITSPERLONG_H */ diff --git a/tools/arch/arm64/include/uapi/asm/bitsperlong.h b/tools/arch/arm64/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..fce9c2924fa3 --- /dev/null +++ b/tools/arch/arm64/include/uapi/asm/bitsperlong.h @@ -0,0 +1,23 @@ +/* + * Copyright (C) 2012 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#ifndef __ASM_BITSPERLONG_H +#define __ASM_BITSPERLONG_H + +#define __BITS_PER_LONG 64 + +#include + +#endif /* __ASM_BITSPERLONG_H */ diff --git a/tools/arch/frv/include/uapi/asm/bitsperlong.h b/tools/arch/frv/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..6dc0bb0c13b2 --- /dev/null +++ b/tools/arch/frv/include/uapi/asm/bitsperlong.h @@ -0,0 +1 @@ +#include diff --git a/tools/arch/h8300/include/asm/bitsperlong.h b/tools/arch/h8300/include/asm/bitsperlong.h new file mode 100644 index 000000000000..e140e46729ac --- /dev/null +++ b/tools/arch/h8300/include/asm/bitsperlong.h @@ -0,0 +1,14 @@ +#ifndef __ASM_H8300_BITS_PER_LONG +#define __ASM_H8300_BITS_PER_LONG + +#include + +#if !defined(__ASSEMBLY__) +/* h8300-unknown-linux required long */ +#define __kernel_size_t __kernel_size_t +typedef unsigned long __kernel_size_t; +typedef long __kernel_ssize_t; +typedef long __kernel_ptrdiff_t; +#endif + +#endif /* __ASM_H8300_BITS_PER_LONG */ diff --git a/tools/arch/hexagon/include/uapi/asm/bitsperlong.h b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..4a658151383d --- /dev/null +++ b/tools/arch/hexagon/include/uapi/asm/bitsperlong.h @@ -0,0 +1,26 @@ +/* + * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA + * 02110-1301, USA. + */ + +#ifndef __ASM_HEXAGON_BITSPERLONG_H +#define __ASM_HEXAGON_BITSPERLONG_H + +#define __BITS_PER_LONG 32 + +#include + +#endif diff --git a/tools/arch/ia64/include/uapi/asm/bitsperlong.h b/tools/arch/ia64/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..ec4db3c970b7 --- /dev/null +++ b/tools/arch/ia64/include/uapi/asm/bitsperlong.h @@ -0,0 +1,8 @@ +#ifndef __ASM_IA64_BITSPERLONG_H +#define __ASM_IA64_BITSPERLONG_H + +#define __BITS_PER_LONG 64 + +#include + +#endif /* __ASM_IA64_BITSPERLONG_H */ diff --git a/tools/arch/m32r/include/uapi/asm/bitsperlong.h b/tools/arch/m32r/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..6dc0bb0c13b2 --- /dev/null +++ b/tools/arch/m32r/include/uapi/asm/bitsperlong.h @@ -0,0 +1 @@ +#include diff --git a/tools/arch/microblaze/include/uapi/asm/bitsperlong.h b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..6dc0bb0c13b2 --- /dev/null +++ b/tools/arch/microblaze/include/uapi/asm/bitsperlong.h @@ -0,0 +1 @@ +#include diff --git a/tools/arch/mips/include/uapi/asm/bitsperlong.h b/tools/arch/mips/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..3e4c10a8e787 --- /dev/null +++ b/tools/arch/mips/include/uapi/asm/bitsperlong.h @@ -0,0 +1,8 @@ +#ifndef __ASM_MIPS_BITSPERLONG_H +#define __ASM_MIPS_BITSPERLONG_H + +#define __BITS_PER_LONG _MIPS_SZLONG + +#include + +#endif /* __ASM_MIPS_BITSPERLONG_H */ diff --git a/tools/arch/mn10300/include/uapi/asm/bitsperlong.h b/tools/arch/mn10300/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..6dc0bb0c13b2 --- /dev/null +++ b/tools/arch/mn10300/include/uapi/asm/bitsperlong.h @@ -0,0 +1 @@ +#include diff --git a/tools/arch/parisc/include/uapi/asm/bitsperlong.h b/tools/arch/parisc/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..e0a23c7bdd43 --- /dev/null +++ b/tools/arch/parisc/include/uapi/asm/bitsperlong.h @@ -0,0 +1,14 @@ +#ifndef __ASM_PARISC_BITSPERLONG_H +#define __ASM_PARISC_BITSPERLONG_H + +#if defined(__LP64__) +#define __BITS_PER_LONG 64 +#define SHIFT_PER_LONG 6 +#else +#define __BITS_PER_LONG 32 +#define SHIFT_PER_LONG 5 +#endif + +#include + +#endif /* __ASM_PARISC_BITSPERLONG_H */ diff --git a/tools/arch/powerpc/include/uapi/asm/bitsperlong.h b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..5f1659032c40 --- /dev/null +++ b/tools/arch/powerpc/include/uapi/asm/bitsperlong.h @@ -0,0 +1,12 @@ +#ifndef __ASM_POWERPC_BITSPERLONG_H +#define __ASM_POWERPC_BITSPERLONG_H + +#if defined(__powerpc64__) +# define __BITS_PER_LONG 64 +#else +# define __BITS_PER_LONG 32 +#endif + +#include + +#endif /* __ASM_POWERPC_BITSPERLONG_H */ diff --git a/tools/arch/s390/include/uapi/asm/bitsperlong.h b/tools/arch/s390/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..e351ea2ad43e --- /dev/null +++ b/tools/arch/s390/include/uapi/asm/bitsperlong.h @@ -0,0 +1,12 @@ +#ifndef __ASM_S390_BITSPERLONG_H +#define __ASM_S390_BITSPERLONG_H + +#ifndef __s390x__ +#define __BITS_PER_LONG 32 +#else +#define __BITS_PER_LONG 64 +#endif + +#include + +#endif /* __ASM_S390_BITSPERLONG_H */ diff --git a/tools/arch/score/include/uapi/asm/bitsperlong.h b/tools/arch/score/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..86ff337aa459 --- /dev/null +++ b/tools/arch/score/include/uapi/asm/bitsperlong.h @@ -0,0 +1,6 @@ +#ifndef _ASM_SCORE_BITSPERLONG_H +#define _ASM_SCORE_BITSPERLONG_H + +#include + +#endif /* _ASM_SCORE_BITSPERLONG_H */ diff --git a/tools/arch/sparc/include/uapi/asm/bitsperlong.h b/tools/arch/sparc/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..b62dd907d7c3 --- /dev/null +++ b/tools/arch/sparc/include/uapi/asm/bitsperlong.h @@ -0,0 +1,12 @@ +#ifndef __ASM_ALPHA_BITSPERLONG_H +#define __ASM_ALPHA_BITSPERLONG_H + +#if defined(__sparc__) && defined(__arch64__) +#define __BITS_PER_LONG 64 +#else +#define __BITS_PER_LONG 32 +#endif + +#include + +#endif /* __ASM_ALPHA_BITSPERLONG_H */ diff --git a/tools/arch/tile/include/uapi/asm/bitsperlong.h b/tools/arch/tile/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..58c771f2af2f --- /dev/null +++ b/tools/arch/tile/include/uapi/asm/bitsperlong.h @@ -0,0 +1,26 @@ +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#ifndef _ASM_TILE_BITSPERLONG_H +#define _ASM_TILE_BITSPERLONG_H + +#ifdef __LP64__ +# define __BITS_PER_LONG 64 +#else +# define __BITS_PER_LONG 32 +#endif + +#include + +#endif /* _ASM_TILE_BITSPERLONG_H */ diff --git a/tools/arch/x86/include/uapi/asm/bitsperlong.h b/tools/arch/x86/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000000..6e23c543cd80 --- /dev/null +++ b/tools/arch/x86/include/uapi/asm/bitsperlong.h @@ -0,0 +1,12 @@ +#ifndef __ASM_X86_BITSPERLONG_H +#define __ASM_X86_BITSPERLONG_H + +#if defined(__x86_64__) && !defined(__ILP32__) +# define __BITS_PER_LONG 64 +#else +# define __BITS_PER_LONG 32 +#endif + +#include + +#endif /* __ASM_X86_BITSPERLONG_H */ diff --git a/tools/include/asm-generic/bitops/__ffs.h b/tools/include/asm-generic/bitops/__ffs.h index c94175015a82..b3accfdf24b9 100644 --- a/tools/include/asm-generic/bitops/__ffs.h +++ b/tools/include/asm-generic/bitops/__ffs.h @@ -2,6 +2,7 @@ #define _TOOLS_LINUX_ASM_GENERIC_BITOPS___FFS_H_ #include +#include /** * __ffs - find first bit in word. diff --git a/tools/include/asm-generic/bitops/atomic.h b/tools/include/asm-generic/bitops/atomic.h index 4bccd7c3d5d6..18663f59d72f 100644 --- a/tools/include/asm-generic/bitops/atomic.h +++ b/tools/include/asm-generic/bitops/atomic.h @@ -2,6 +2,7 @@ #define _TOOLS_LINUX_ASM_GENERIC_BITOPS_ATOMIC_H_ #include +#include static inline void set_bit(int nr, unsigned long *addr) { diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h new file mode 100644 index 000000000000..d1d70aa19021 --- /dev/null +++ b/tools/include/asm-generic/bitsperlong.h @@ -0,0 +1,25 @@ +#ifndef __ASM_GENERIC_BITS_PER_LONG +#define __ASM_GENERIC_BITS_PER_LONG + +#include + + +#ifdef CONFIG_64BIT +#define BITS_PER_LONG 64 +#else +#define BITS_PER_LONG 32 +#endif /* CONFIG_64BIT */ + +/* + * FIXME: The check currently breaks x86-64 build, so it's + * temporarily disabled. Please fix x86-64 and reenable + */ +#if 0 && BITS_PER_LONG != __BITS_PER_LONG +#error Inconsistent word size. Check asm/bitsperlong.h +#endif + +#ifndef BITS_PER_LONG_LONG +#define BITS_PER_LONG_LONG 64 +#endif + +#endif /* __ASM_GENERIC_BITS_PER_LONG */ diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h new file mode 100644 index 000000000000..23e6c416b85f --- /dev/null +++ b/tools/include/uapi/asm-generic/bitsperlong.h @@ -0,0 +1,15 @@ +#ifndef _UAPI__ASM_GENERIC_BITS_PER_LONG +#define _UAPI__ASM_GENERIC_BITS_PER_LONG + +/* + * There seems to be no way of detecting this automatically from user + * space, so 64 bit architectures should override this in their + * bitsperlong.h. In particular, an architecture that supports + * both 32 and 64 bit user space must not rely on CONFIG_64BIT + * to decide it, but rather check a compiler provided macro. + */ +#ifndef __BITS_PER_LONG +#define __BITS_PER_LONG 32 +#endif + +#endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */ -- cgit v1.3-8-gc7d7 From 7b39cafb7aa68ef8e32a9f51fbe737d96084ca74 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Wed, 13 Jul 2016 09:37:43 +0200 Subject: tools: Work around BITS_PER_LONG related build failure in objtool The objtool build fails with the recent changes to the bits-per-long headers: tools/include/linux/bitops.h:12:0: error: "BITS_PER_LONG" redefined [-Werror] Which got introduced by: bb9707077b4e tools: Copy the bitsperlong.h files from the kernel Work it around for the time being. Cc: Arnaldo Carvalho de Melo Cc: Josh Poimboeuf Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- tools/include/linux/bitops.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'tools/include') diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 5ad9ee1dd7f6..49c929a104ee 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -9,7 +9,9 @@ #define __WORDSIZE (__SIZEOF_LONG__ * 8) #endif -#define BITS_PER_LONG __WORDSIZE +#ifndef BITS_PER_LONG +# define BITS_PER_LONG __WORDSIZE +#endif #define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / BITS_PER_LONG) -- cgit v1.3-8-gc7d7 From 2a00f026a15d161b47ba3d3417d0fec5193468c3 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 13 Jul 2016 15:04:04 -0300 Subject: tools: Fix up BITS_PER_LONG setting It was set based on CONFIG_64BIT, that is available only when using Kconfig, which we're working towards but not to the point of having this CONFIG variable set, so synthesize it from available compiler defined defines, __SIZEOF_LONG__ or, lacking that, __WORDSIZE. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-og5fmkr17856lhupacihwxvb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/asm-generic/bitsperlong.h | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'tools/include') diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h index d1d70aa19021..cfd661c6fc17 100644 --- a/tools/include/asm-generic/bitsperlong.h +++ b/tools/include/asm-generic/bitsperlong.h @@ -3,6 +3,24 @@ #include +/* + * In the kernel, where this file comes from, we can rely on CONFIG_64BIT, + * here we have to make amends with what the various compilers provides us + * to figure out if we're on a 64-bit machine... + */ +#ifdef __SIZEOF_LONG__ +# if __SIZEOF_LONG__ == 8 +# define CONFIG_64BIT +# endif +#else +# ifdef __WORDSIZE +# if __WORDSIZE == 64 +# define CONFIG_64BIT +# endif +# else +# error Failed to determine BITS_PER_LONG value +# endif +#endif #ifdef CONFIG_64BIT #define BITS_PER_LONG 64 @@ -10,11 +28,7 @@ #define BITS_PER_LONG 32 #endif /* CONFIG_64BIT */ -/* - * FIXME: The check currently breaks x86-64 build, so it's - * temporarily disabled. Please fix x86-64 and reenable - */ -#if 0 && BITS_PER_LONG != __BITS_PER_LONG +#if BITS_PER_LONG != __BITS_PER_LONG #error Inconsistent word size. Check asm/bitsperlong.h #endif -- cgit v1.3-8-gc7d7 From 8c98abff43616a2a9c208189f86d32cefafbe708 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 14 Jul 2016 12:03:04 -0300 Subject: tools: Make "__always_inline" just "inline" on Android As the gcc there is producing tons of: "warning: always_inline function might not be inlinable" At least on android-ndk-r12/platforms/android-24/arch-arm, so, for the time being, use this big hammer. Cc: Adrian Hunter Cc: Chris Phlipot Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-97l3eg3fnk5shmo4rsyyvj2t@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/compiler.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'tools/include') diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h index fa7208a32d76..e33fc1df3935 100644 --- a/tools/include/linux/compiler.h +++ b/tools/include/linux/compiler.h @@ -9,6 +9,17 @@ # define __always_inline inline __attribute__((always_inline)) #endif +#ifdef __ANDROID__ +/* + * FIXME: Big hammer to get rid of tons of: + * "warning: always_inline function might not be inlinable" + * + * At least on android-ndk-r12/platforms/android-24/arch-arm + */ +#undef __always_inline +#define __always_inline inline +#endif + #define __user #ifndef __attribute_const__ -- cgit v1.3-8-gc7d7 From e81fcd43723d32e9c9dbb8e8d66f147b5b84256b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 15 Jul 2016 12:38:18 -0300 Subject: tools: Simplify BITS_PER_LONG define Do it using (__CHAR_BIT__ * __SIZEOF_LONG__), simpler, works everywhere, reduces the complexity by ditching CONFIG_64BIT, that was being synthesized from yet another set of defines, which proved fragile, breaking the build on linux-next for no obvious reasons. Committer Note: Except on: gcc version 4.1.2 20080704 (Red Hat 4.1.2-55) Fallback to __WORDSIZE in that case... Reported-by: Stephen Rothwell Signed-off-by: Peter Zijlstra Tested-by: Arnaldo Carvalho de Melo Cc: Andy Lutomirski Cc: H. Peter Anvin Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160715072243.GP30154@twins.programming.kicks-ass.net Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/asm-generic/bitsperlong.h | 23 ++--------------------- 1 file changed, 2 insertions(+), 21 deletions(-) (limited to 'tools/include') diff --git a/tools/include/asm-generic/bitsperlong.h b/tools/include/asm-generic/bitsperlong.h index cfd661c6fc17..45eca517efb3 100644 --- a/tools/include/asm-generic/bitsperlong.h +++ b/tools/include/asm-generic/bitsperlong.h @@ -3,31 +3,12 @@ #include -/* - * In the kernel, where this file comes from, we can rely on CONFIG_64BIT, - * here we have to make amends with what the various compilers provides us - * to figure out if we're on a 64-bit machine... - */ #ifdef __SIZEOF_LONG__ -# if __SIZEOF_LONG__ == 8 -# define CONFIG_64BIT -# endif +#define BITS_PER_LONG (__CHAR_BIT__ * __SIZEOF_LONG__) #else -# ifdef __WORDSIZE -# if __WORDSIZE == 64 -# define CONFIG_64BIT -# endif -# else -# error Failed to determine BITS_PER_LONG value -# endif +#define BITS_PER_LONG __WORDSIZE #endif -#ifdef CONFIG_64BIT -#define BITS_PER_LONG 64 -#else -#define BITS_PER_LONG 32 -#endif /* CONFIG_64BIT */ - #if BITS_PER_LONG != __BITS_PER_LONG #error Inconsistent word size. Check asm/bitsperlong.h #endif -- cgit v1.3-8-gc7d7 From de1e17b1d0c81be472039798698b517c8a68b516 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 18 Jul 2016 18:13:22 -0300 Subject: tools: Copy the bitops files accessed from the kernel and check for drift copy some more kernel files accessed from tools/, check for drift. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-omz8xdyvvxgjiuqzwj6ecm6j@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/asm-generic/bitops/__fls.h | 44 +++++++++++++++++++++++- tools/include/asm-generic/bitops/arch_hweight.h | 26 +++++++++++++- tools/include/asm-generic/bitops/const_hweight.h | 44 +++++++++++++++++++++++- tools/include/asm-generic/bitops/fls.h | 42 +++++++++++++++++++++- tools/include/asm-generic/bitops/fls64.h | 37 +++++++++++++++++++- tools/perf/MANIFEST | 5 --- tools/perf/Makefile.perf | 15 ++++++++ 7 files changed, 203 insertions(+), 10 deletions(-) (limited to 'tools/include') diff --git a/tools/include/asm-generic/bitops/__fls.h b/tools/include/asm-generic/bitops/__fls.h index 494c9c615d1c..a60a7ccb6782 100644 --- a/tools/include/asm-generic/bitops/__fls.h +++ b/tools/include/asm-generic/bitops/__fls.h @@ -1 +1,43 @@ -#include "../../../../include/asm-generic/bitops/__fls.h" +#ifndef _ASM_GENERIC_BITOPS___FLS_H_ +#define _ASM_GENERIC_BITOPS___FLS_H_ + +#include + +/** + * __fls - find last (most-significant) set bit in a long word + * @word: the word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +static __always_inline unsigned long __fls(unsigned long word) +{ + int num = BITS_PER_LONG - 1; + +#if BITS_PER_LONG == 64 + if (!(word & (~0ul << 32))) { + num -= 32; + word <<= 32; + } +#endif + if (!(word & (~0ul << (BITS_PER_LONG-16)))) { + num -= 16; + word <<= 16; + } + if (!(word & (~0ul << (BITS_PER_LONG-8)))) { + num -= 8; + word <<= 8; + } + if (!(word & (~0ul << (BITS_PER_LONG-4)))) { + num -= 4; + word <<= 4; + } + if (!(word & (~0ul << (BITS_PER_LONG-2)))) { + num -= 2; + word <<= 2; + } + if (!(word & (~0ul << (BITS_PER_LONG-1)))) + num -= 1; + return num; +} + +#endif /* _ASM_GENERIC_BITOPS___FLS_H_ */ diff --git a/tools/include/asm-generic/bitops/arch_hweight.h b/tools/include/asm-generic/bitops/arch_hweight.h index 318bb2b202b0..6a211f40665c 100644 --- a/tools/include/asm-generic/bitops/arch_hweight.h +++ b/tools/include/asm-generic/bitops/arch_hweight.h @@ -1 +1,25 @@ -#include "../../../../include/asm-generic/bitops/arch_hweight.h" +#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_ + +#include + +static inline unsigned int __arch_hweight32(unsigned int w) +{ + return __sw_hweight32(w); +} + +static inline unsigned int __arch_hweight16(unsigned int w) +{ + return __sw_hweight16(w); +} + +static inline unsigned int __arch_hweight8(unsigned int w) +{ + return __sw_hweight8(w); +} + +static inline unsigned long __arch_hweight64(__u64 w) +{ + return __sw_hweight64(w); +} +#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */ diff --git a/tools/include/asm-generic/bitops/const_hweight.h b/tools/include/asm-generic/bitops/const_hweight.h index 0afd644aff83..0a7e06623470 100644 --- a/tools/include/asm-generic/bitops/const_hweight.h +++ b/tools/include/asm-generic/bitops/const_hweight.h @@ -1 +1,43 @@ -#include "../../../../include/asm-generic/bitops/const_hweight.h" +#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ +#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ + +/* + * Compile time versions of __arch_hweightN() + */ +#define __const_hweight8(w) \ + ((unsigned int) \ + ((!!((w) & (1ULL << 0))) + \ + (!!((w) & (1ULL << 1))) + \ + (!!((w) & (1ULL << 2))) + \ + (!!((w) & (1ULL << 3))) + \ + (!!((w) & (1ULL << 4))) + \ + (!!((w) & (1ULL << 5))) + \ + (!!((w) & (1ULL << 6))) + \ + (!!((w) & (1ULL << 7))))) + +#define __const_hweight16(w) (__const_hweight8(w) + __const_hweight8((w) >> 8 )) +#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16)) +#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32)) + +/* + * Generic interface. + */ +#define hweight8(w) (__builtin_constant_p(w) ? __const_hweight8(w) : __arch_hweight8(w)) +#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w)) +#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w)) +#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w)) + +/* + * Interface for known constant arguments + */ +#define HWEIGHT8(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w)) +#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w)) +#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w)) +#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w)) + +/* + * Type invariant interface to the compile time constant hweight functions. + */ +#define HWEIGHT(w) HWEIGHT64((u64)w) + +#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */ diff --git a/tools/include/asm-generic/bitops/fls.h b/tools/include/asm-generic/bitops/fls.h index 0e4995fa0248..0576d1f42f43 100644 --- a/tools/include/asm-generic/bitops/fls.h +++ b/tools/include/asm-generic/bitops/fls.h @@ -1 +1,41 @@ -#include "../../../../include/asm-generic/bitops/fls.h" +#ifndef _ASM_GENERIC_BITOPS_FLS_H_ +#define _ASM_GENERIC_BITOPS_FLS_H_ + +/** + * fls - find last (most-significant) bit set + * @x: the word to search + * + * This is defined the same way as ffs. + * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. + */ + +static __always_inline int fls(int x) +{ + int r = 32; + + if (!x) + return 0; + if (!(x & 0xffff0000u)) { + x <<= 16; + r -= 16; + } + if (!(x & 0xff000000u)) { + x <<= 8; + r -= 8; + } + if (!(x & 0xf0000000u)) { + x <<= 4; + r -= 4; + } + if (!(x & 0xc0000000u)) { + x <<= 2; + r -= 2; + } + if (!(x & 0x80000000u)) { + x <<= 1; + r -= 1; + } + return r; +} + +#endif /* _ASM_GENERIC_BITOPS_FLS_H_ */ diff --git a/tools/include/asm-generic/bitops/fls64.h b/tools/include/asm-generic/bitops/fls64.h index 35bee0071e78..b097cf8444e3 100644 --- a/tools/include/asm-generic/bitops/fls64.h +++ b/tools/include/asm-generic/bitops/fls64.h @@ -1 +1,36 @@ -#include "../../../../include/asm-generic/bitops/fls64.h" +#ifndef _ASM_GENERIC_BITOPS_FLS64_H_ +#define _ASM_GENERIC_BITOPS_FLS64_H_ + +#include + +/** + * fls64 - find last set bit in a 64-bit word + * @x: the word to search + * + * This is defined in a similar way as the libc and compiler builtin + * ffsll, but returns the position of the most significant set bit. + * + * fls64(value) returns 0 if value is 0 or the position of the last + * set bit if value is nonzero. The last (most significant) bit is + * at position 64. + */ +#if BITS_PER_LONG == 32 +static __always_inline int fls64(__u64 x) +{ + __u32 h = x >> 32; + if (h) + return fls(h) + 32; + return fls(x); +} +#elif BITS_PER_LONG == 64 +static __always_inline int fls64(__u64 x) +{ + if (x == 0) + return 0; + return __fls(x) + 1; +} +#else +#error BITS_PER_LONG not 32 or 64 +#endif + +#endif /* _ASM_GENERIC_BITOPS_FLS64_H_ */ diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index e18df995bd3c..eeb2fdc3392f 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -77,11 +77,6 @@ tools/include/linux/stringify.h tools/include/linux/types.h tools/include/linux/err.h tools/include/linux/bitmap.h -include/asm-generic/bitops/arch_hweight.h -include/asm-generic/bitops/const_hweight.h -include/asm-generic/bitops/fls64.h -include/asm-generic/bitops/__fls.h -include/asm-generic/bitops/fls.h include/linux/list.h include/linux/hash.h tools/arch/*/include/uapi/asm/perf_regs.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index a129fbc1ed37..580f4e208c7a 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -411,6 +411,21 @@ $(PERF_IN): prepare FORCE @(test -f ../../arch/arm64/include/uapi/asm/kvm.h && ( \ (diff -B ../arch/arm64/include/uapi/asm/kvm.h ../../arch/arm64/include/uapi/asm/kvm.h >/dev/null) \ || echo "Warning: tools/arch/arm64/include/uapi/asm/kvm.h differs from kernel" >&2 )) || true + @(test -f ../../include/asm-generic/bitops/arch_hweight.h && ( \ + (diff -B ../include/asm-generic/bitops/arch_hweight.h ../../include/asm-generic/bitops/arch_hweight.h >/dev/null) \ + || echo "Warning: tools/include/asm-generic/bitops/arch_hweight.h differs from kernel" >&2 )) || true + @(test -f ../../include/asm-generic/bitops/const_hweight.h && ( \ + (diff -B ../include/asm-generic/bitops/const_hweight.h ../../include/asm-generic/bitops/const_hweight.h >/dev/null) \ + || echo "Warning: tools/include/asm-generic/bitops/const_hweight.h differs from kernel" >&2 )) || true + @(test -f ../../include/asm-generic/bitops/__fls.h && ( \ + (diff -B ../include/asm-generic/bitops/__fls.h ../../include/asm-generic/bitops/__fls.h >/dev/null) \ + || echo "Warning: tools/include/asm-generic/bitops/__fls.h differs from kernel" >&2 )) || true + @(test -f ../../include/asm-generic/bitops/fls.h && ( \ + (diff -B ../include/asm-generic/bitops/fls.h ../../include/asm-generic/bitops/fls.h >/dev/null) \ + || echo "Warning: tools/include/asm-generic/bitops/fls.h differs from kernel" >&2 )) || true + @(test -f ../../include/asm-generic/bitops/fls64.h && ( \ + (diff -B ../include/asm-generic/bitops/fls64.h ../../include/asm-generic/bitops/fls64.h >/dev/null) \ + || echo "Warning: tools/include/asm-generic/bitops/fls64.h differs from kernel" >&2 )) || true $(Q)$(MAKE) $(build)=perf $(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST) -- cgit v1.3-8-gc7d7 From ae3c14a028ed10552803b68276b6833295ba18cf Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 18 Jul 2016 18:39:36 -0300 Subject: tools: Copy linux/{hash,poison}.h and check for drift We were also using this directly from the kernel sources, the two last cases, fix it. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-7o14xvacqcjc5llc7gvjjyl8@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/hash.h | 105 +++++++++++++++++++++++++++++++++++++++++-- tools/include/linux/poison.h | 91 ++++++++++++++++++++++++++++++++++++- tools/perf/MANIFEST | 2 - tools/perf/Makefile.perf | 3 ++ 4 files changed, 195 insertions(+), 6 deletions(-) (limited to 'tools/include') diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h index d026c6573018..ad6fa21d977b 100644 --- a/tools/include/linux/hash.h +++ b/tools/include/linux/hash.h @@ -1,5 +1,104 @@ -#include "../../../include/linux/hash.h" +#ifndef _LINUX_HASH_H +#define _LINUX_HASH_H +/* Fast hashing routine for ints, longs and pointers. + (C) 2002 Nadia Yvette Chambers, IBM */ -#ifndef _TOOLS_LINUX_HASH_H -#define _TOOLS_LINUX_HASH_H +#include +#include + +/* + * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and + * fs/inode.c. It's not actually prime any more (the previous primes + * were actively bad for hashing), but the name remains. + */ +#if BITS_PER_LONG == 32 +#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32 +#define hash_long(val, bits) hash_32(val, bits) +#elif BITS_PER_LONG == 64 +#define hash_long(val, bits) hash_64(val, bits) +#define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64 +#else +#error Wordsize not 32 or 64 +#endif + +/* + * This hash multiplies the input by a large odd number and takes the + * high bits. Since multiplication propagates changes to the most + * significant end only, it is essential that the high bits of the + * product be used for the hash value. + * + * Chuck Lever verified the effectiveness of this technique: + * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf + * + * Although a random odd number will do, it turns out that the golden + * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice + * properties. (See Knuth vol 3, section 6.4, exercise 9.) + * + * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2, + * which is very slightly easier to multiply by and makes no + * difference to the hash distribution. + */ +#define GOLDEN_RATIO_32 0x61C88647 +#define GOLDEN_RATIO_64 0x61C8864680B583EBull + +#ifdef CONFIG_HAVE_ARCH_HASH +/* This header may use the GOLDEN_RATIO_xx constants */ +#include +#endif + +/* + * The _generic versions exist only so lib/test_hash.c can compare + * the arch-optimized versions with the generic. + * + * Note that if you change these, any that aren't updated + * to match need to have their HAVE_ARCH_* define values updated so the + * self-test will not false-positive. + */ +#ifndef HAVE_ARCH__HASH_32 +#define __hash_32 __hash_32_generic +#endif +static inline u32 __hash_32_generic(u32 val) +{ + return val * GOLDEN_RATIO_32; +} + +#ifndef HAVE_ARCH_HASH_32 +#define hash_32 hash_32_generic #endif +static inline u32 hash_32_generic(u32 val, unsigned int bits) +{ + /* High bits are more random, so use them. */ + return __hash_32(val) >> (32 - bits); +} + +#ifndef HAVE_ARCH_HASH_64 +#define hash_64 hash_64_generic +#endif +static __always_inline u32 hash_64_generic(u64 val, unsigned int bits) +{ +#if BITS_PER_LONG == 64 + /* 64x64-bit multiply is efficient on all 64-bit processors */ + return val * GOLDEN_RATIO_64 >> (64 - bits); +#else + /* Hash 64 bits using only 32x32-bit multiply. */ + return hash_32((u32)val ^ __hash_32(val >> 32), bits); +#endif +} + +static inline u32 hash_ptr(const void *ptr, unsigned int bits) +{ + return hash_long((unsigned long)ptr, bits); +} + +/* This really should be called fold32_ptr; it does no hashing to speak of. */ +static inline u32 hash32_ptr(const void *ptr) +{ + unsigned long val = (unsigned long)ptr; + +#if BITS_PER_LONG == 64 + val ^= (val >> 32); +#endif + return (u32)val; +} + +#endif /* _LINUX_HASH_H */ diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h index 0c27bdf14233..51334edec506 100644 --- a/tools/include/linux/poison.h +++ b/tools/include/linux/poison.h @@ -1 +1,90 @@ -#include "../../../include/linux/poison.h" +#ifndef _LINUX_POISON_H +#define _LINUX_POISON_H + +/********** include/linux/list.h **********/ + +/* + * Architectures might want to move the poison pointer offset + * into some well-recognized area such as 0xdead000000000000, + * that is also not mappable by user-space exploits: + */ +#ifdef CONFIG_ILLEGAL_POINTER_VALUE +# define POISON_POINTER_DELTA _AC(CONFIG_ILLEGAL_POINTER_VALUE, UL) +#else +# define POISON_POINTER_DELTA 0 +#endif + +/* + * These are non-NULL pointers that will result in page faults + * under normal circumstances, used to verify that nobody uses + * non-initialized list entries. + */ +#define LIST_POISON1 ((void *) 0x100 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x200 + POISON_POINTER_DELTA) + +/********** include/linux/timer.h **********/ +/* + * Magic number "tsta" to indicate a static timer initializer + * for the object debugging code. + */ +#define TIMER_ENTRY_STATIC ((void *) 0x300 + POISON_POINTER_DELTA) + +/********** mm/debug-pagealloc.c **********/ +#ifdef CONFIG_PAGE_POISONING_ZERO +#define PAGE_POISON 0x00 +#else +#define PAGE_POISON 0xaa +#endif + +/********** mm/page_alloc.c ************/ + +#define TAIL_MAPPING ((void *) 0x400 + POISON_POINTER_DELTA) + +/********** mm/slab.c **********/ +/* + * Magic nums for obj red zoning. + * Placed in the first word before and the first word after an obj. + */ +#define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */ +#define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */ + +#define SLUB_RED_INACTIVE 0xbb +#define SLUB_RED_ACTIVE 0xcc + +/* ...and for poisoning */ +#define POISON_INUSE 0x5a /* for use-uninitialised poisoning */ +#define POISON_FREE 0x6b /* for use-after-free poisoning */ +#define POISON_END 0xa5 /* end-byte of poisoning */ + +/********** arch/$ARCH/mm/init.c **********/ +#define POISON_FREE_INITMEM 0xcc + +/********** arch/ia64/hp/common/sba_iommu.c **********/ +/* + * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a + * value of "SBAIOMMU POISON\0" for spill-over poisoning. + */ + +/********** fs/jbd/journal.c **********/ +#define JBD_POISON_FREE 0x5b +#define JBD2_POISON_FREE 0x5c + +/********** drivers/base/dmapool.c **********/ +#define POOL_POISON_FREED 0xa7 /* !inuse */ +#define POOL_POISON_ALLOCATED 0xa9 /* !initted */ + +/********** drivers/atm/ **********/ +#define ATM_POISON_FREE 0x12 +#define ATM_POISON 0xdeadbeef + +/********** kernel/mutexes **********/ +#define MUTEX_DEBUG_INIT 0x11 +#define MUTEX_DEBUG_FREE 0x22 + +/********** lib/flex_array.c **********/ +#define FLEX_ARRAY_FREE 0x6c /* for use-after-free poisoning */ + +/********** security/ **********/ +#define KEY_DESTROY 0xbd + +#endif diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index 3ac7f8dff47f..ad2534df4ba6 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -77,6 +77,4 @@ tools/include/linux/stringify.h tools/include/linux/types.h tools/include/linux/err.h tools/include/linux/bitmap.h -include/linux/hash.h tools/arch/*/include/uapi/asm/perf_regs.h -include/linux/poison.h diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 580f4e208c7a..6641abb97f0a 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -351,6 +351,9 @@ $(PERF_IN): prepare FORCE @(test -f ../../include/uapi/linux/perf_event.h && ( \ (diff -B ../include/uapi/linux/perf_event.h ../../include/uapi/linux/perf_event.h >/dev/null) \ || echo "Warning: tools/include/uapi/linux/perf_event.h differs from kernel" >&2 )) || true + @(test -f ../../include/linux/hash.h && ( \ + (diff -B ../include/linux/hash.h ../../include/linux/hash.h >/dev/null) \ + || echo "Warning: tools/include/linux/hash.h differs from kernel" >&2 )) || true @(test -f ../../include/uapi/linux/hw_breakpoint.h && ( \ (diff -B ../include/uapi/linux/hw_breakpoint.h ../../include/uapi/linux/hw_breakpoint.h >/dev/null) \ || echo "Warning: tools/include/uapi/linux/hw_breakpoint.h differs from kernel" >&2 )) || true -- cgit v1.3-8-gc7d7 From 98c032967a299ee4bf14ef19eded02b65df32e6f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 2 Aug 2016 13:33:02 +0200 Subject: tools lib: Add bitmap_alloc function Adding bitmap_alloc function to dynamically allocate bitmap. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20160802113302.GA7479@krava Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/bitmap.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'tools/include') diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 28f5493da491..60c44b615902 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -3,6 +3,7 @@ #include #include +#include #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] @@ -65,4 +66,13 @@ static inline int test_and_set_bit(int nr, unsigned long *addr) return (old & mask) != 0; } +/** + * bitmap_alloc - Allocate bitmap + * @nr: Bit to set + */ +static inline unsigned long *bitmap_alloc(int nbits) +{ + return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); +} + #endif /* _PERF_BITOPS_H */ -- cgit v1.3-8-gc7d7 From 820d12b70f91a19eb4a3152b9dd4ea9aee194a36 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 1 Aug 2016 20:02:30 +0200 Subject: tools lib: Add bitmap_scnprintf function Add support to print bitmap list. Code mostly taken from kernel's bitmap_list_string. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1470074555-24889-3-git-send-email-jolsa@kernel.org [ s/bitmap_snprintf/bitmap_scnprintf/g as it is a scnprintf wrapper, having the same semantics wrt return value ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/bitmap.h | 10 ++++++++++ tools/lib/bitmap.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) (limited to 'tools/include') diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 60c44b615902..1cdded0041a8 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -75,4 +75,14 @@ static inline unsigned long *bitmap_alloc(int nbits) return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); } +/* + * bitmap_scnprintf - print bitmap list into buffer + * @bitmap: bitmap + * @nbits: size of bitmap + * @buf: buffer to store output + * @size: size of @buf + */ +size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, + char *buf, size_t size); + #endif /* _PERF_BITOPS_H */ diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 0a1adc1111fd..5c7e3185507c 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -29,3 +29,32 @@ void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } + +size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, + char *buf, size_t size) +{ + /* current bit is 'cur', most recently seen range is [rbot, rtop] */ + int cur, rbot, rtop; + bool first = true; + size_t ret = 0; + + rbot = cur = find_first_bit(bitmap, nbits); + while (cur < nbits) { + rtop = cur; + cur = find_next_bit(bitmap, nbits, cur + 1); + if (cur < nbits && cur <= rtop + 1) + continue; + + if (!first) + ret += scnprintf(buf + ret, size - ret, ","); + + first = false; + + ret += scnprintf(buf + ret, size - ret, "%d", rbot); + if (rbot < rtop) + ret += scnprintf(buf + ret, size - ret, "-%d", rtop); + + rbot = cur; + } + return ret; +} -- cgit v1.3-8-gc7d7 From 741c74f55e8a66f3bc5bbc29dc162c952759e47b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 1 Aug 2016 20:02:31 +0200 Subject: tools lib: Add bitmap_and function Add support to perform logical and on bitmaps. Code taken from kernel's include/linux/bitmap.h. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1470074555-24889-4-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/bitmap.h | 17 +++++++++++++++++ tools/lib/bitmap.c | 15 +++++++++++++++ 2 files changed, 32 insertions(+) (limited to 'tools/include') diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 1cdded0041a8..43c1c5021e4b 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -11,6 +11,8 @@ int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); +int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits); #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) @@ -85,4 +87,19 @@ static inline unsigned long *bitmap_alloc(int nbits) size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, char *buf, size_t size); +/** + * bitmap_and - Do logical and on bitmaps + * @dst: resulting bitmap + * @src1: operand 1 + * @src2: operand 2 + * @nbits: size of bitmap + */ +static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) + return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; + return __bitmap_and(dst, src1, src2, nbits); +} + #endif /* _PERF_BITOPS_H */ diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 5c7e3185507c..38748b0e342f 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -58,3 +58,18 @@ size_t bitmap_scnprintf(unsigned long *bitmap, int nbits, } return ret; } + +int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int bits) +{ + unsigned int k; + unsigned int lim = bits/BITS_PER_LONG; + unsigned long result = 0; + + for (k = 0; k < lim; k++) + result |= (dst[k] = bitmap1[k] & bitmap2[k]); + if (bits % BITS_PER_LONG) + result |= (dst[k] = bitmap1[k] & bitmap2[k] & + BITMAP_LAST_WORD_MASK(bits)); + return result != 0; +} -- cgit v1.3-8-gc7d7 From 791cceb89f7987c0375ff2e8971928a47f62ccae Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 9 Aug 2016 11:48:07 -0300 Subject: toops: Sync tools/include/uapi/linux/bpf.h with the kernel The way we're using kernel headers in tools/ now, with a copy that is made to the same path prefixed by "tools/" plus checking if that copy got stale, i.e. if the kernel counterpart changed, helps in keeping track with new features that may be useful for tools to exploit. For instance, looking at all the changes to bpf.h since it was last copied to tools/include brings this to toolers' attention: Need to investigate this one to check how to run a program via perf, setting up a BPF event, that will take advantage of the way perf already calls clang/LLVM, sets up the event and runs the workload in a single command line, helping in debugging such semi cooperative programs: 96ae52279594 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers") This one needs further investigation about using the feature it improves in 'perf trace' to do some tcpdumpin' mixed with syscalls, tracepoints, probe points, callgraphs, etc: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Add tracing just packets that are related to some container to that mix: 4a482f34afcc ("cgroup: bpf: Add bpf_skb_in_cgroup_proto") 4ed8ec521ed5 ("cgroup: bpf: Add BPF_MAP_TYPE_CGROUP_ARRAY") Definetely needs to have example programs accessing task_struct from a bpf proggie started from 'perf trace': 606274c5abd8 ("bpf: introduce bpf_get_current_task() helper") Core networking related, XDP: 6ce96ca348a9 ("bpf: add XDP_TX xdp_action for direct forwarding") 6a773a15a1e8 ("bpf: add XDP prog type for early driver filter") 13c5c240f789 ("bpf: add bpf_get_hash_recalc helper") d2485c4242a8 ("bpf: add bpf_skb_change_type helper") 6578171a7ff0 ("bpf: add bpf_skb_change_proto helper") Changes detected by the tools build system: $ make -C tools/perf O=/tmp/build/perf install-bin make: Entering directory '/home/acme/git/linux/tools/perf' BUILD: Doing 'make -j4' parallel build Warning: tools/include/uapi/linux/bpf.h differs from kernel INSTALL GTK UI CC /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o $ Cc: Adrian Hunter Cc: Alexei Starovoitov Cc: Brenden Blanco Cc: Daniel Borkmann Cc: David Ahern Cc: David S. Miller Cc: Jiri Olsa Cc: Martin KaFai Lau Cc: Namhyung Kim Cc: Sargun Dhillon Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-difq4ts1xvww6eyfs9e7zlft@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/uapi/linux/bpf.h | 86 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 85 insertions(+), 1 deletion(-) (limited to 'tools/include') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 406459b935a2..da218fec6056 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -84,6 +84,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, }; enum bpf_prog_type { @@ -93,6 +94,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, }; #define BPF_PSEUDO_MAP_FD 1 @@ -313,6 +315,66 @@ enum bpf_func_id { */ BPF_FUNC_skb_get_tunnel_opt, BPF_FUNC_skb_set_tunnel_opt, + + /** + * bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is + * v4 -> v6, v6 -> v4 transitions. The helper will also + * resize the skb. eBPF program is expected to fill the + * new headers via skb_store_bytes and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_proto, + + /** + * bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_type, + + /** + * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + */ + BPF_FUNC_skb_in_cgroup, + + /** + * bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + */ + BPF_FUNC_get_hash_recalc, + + /** + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + */ + BPF_FUNC_get_current_task, + + /** + * bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + */ + BPF_FUNC_probe_write_user, + __BPF_FUNC_MAX_ID, }; @@ -347,9 +409,11 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output flags. */ +/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure @@ -386,4 +450,24 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will result + * in packet drop. + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.3-8-gc7d7 From 0215d59b154ab90c56c4fe49bc1deefe8bca18f1 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 18 Aug 2016 09:28:23 -0700 Subject: tools lib: Reinstate strlcpy() header guard with __UCLIBC__ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit perf tools build in recent kernels spews splat when cross compiling with uClibc: | CC util/alias.o | In file included from tools/perf/util/../ui/../util/cache.h:8:0, | from tools/perf/util/../ui/helpline.h:7, | from tools/perf/util/debug.h:8, | from arch/../util/cpumap.h:9, | from arch/../util/env.h:5, | from arch/common.h:4, | from arch/common.c:3: | tools/include/linux/string.h:12:15: warning: redundant redeclaration of ‘strlcpy’ [-Wredundant-decls] | extern size_t strlcpy(char *dest, const char *src, size_t size); ^ This is after commit 61a6445e463a31 ("tools lib: Guard the strlcpy() header with __GLIBC__"). The problem is uClibc also defines __GLIBC__ for exported headers for applications. So add that specific check to not trip for uClibc. Signed-off-by: Vineet Gupta Cc: Adrian Hunter Cc: Alexey Brodkin Cc: David Ahern Cc: Jiri Olsa Cc: Josh Poimboeuf Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Petri Gynther Cc: Wang Nan Cc: linux-snps-arc@lists.infradead.org Link: http://lkml.kernel.org/r/1471537703-16439-1-git-send-email-vgupta@synopsys.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/include/linux/string.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'tools/include') diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index b96879477311..f436d2420a18 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -8,7 +8,11 @@ void *memdup(const void *src, size_t len); int strtobool(const char *s, bool *res); -#ifdef __GLIBC__ +/* + * glibc based builds needs the extern while uClibc doesn't. + * However uClibc headers also define __GLIBC__ hence the hack below + */ +#if defined(__GLIBC__) && !defined(__UCLIBC__) extern size_t strlcpy(char *dest, const char *src, size_t size); #endif -- cgit v1.3-8-gc7d7