6 files changed, 299 insertions, 0 deletions
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
new file mode 100644
index 000000000..b422aeef5
--- /dev/null
+++ b/tools/perf/include/bpf/bpf.h
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _PERF_BPF_H
+#define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
+/*
+ * A helper structure used by eBPF C program to describe map attributes to
+ * elf_bpf loader, taken from tools/testing/selftests/bpf/bpf_helpers.h:
+ */
+struct bpf_map {
+        unsigned int type;
+        unsigned int key_size;
+        unsigned int value_size;
+        unsigned int max_entries;
+        unsigned int map_flags;
+        unsigned int inner_map_idx;
+        unsigned int numa_node;
+};
+
+#define bpf_map(name, _type, type_key, type_val, _max_entries)	\
+struct bpf_map SEC("maps") name = {				\
+	.type	     = BPF_MAP_TYPE_##_type,			\
+	.key_size    = sizeof(type_key),			\
+	.value_size  = sizeof(type_val),			\
+	.max_entries = _max_entries,				\
+};								\
+struct ____btf_map_##name {					\
+	type_key key;						\
+	type_val value;                                 	\
+};								\
+struct ____btf_map_##name __attribute__((section(".maps." #name), used)) \
+	____btf_map_##name = { }
+
+/*
+ * FIXME: this should receive .max_entries as a parameter, as careful
+ *	  tuning of these limits is needed to avoid hitting limits that
+ *	  prevents other BPF constructs, such as tracepoint handlers,
+ *	  to get installed, with cryptic messages from libbpf, etc.
+ *	  For the current need, 'perf trace --filter-pids', 64 should
+ *	  be good enough, but this surely needs to be revisited.
+ */
+#define pid_map(name, value_type) bpf_map(name, HASH, pid_t, value_type, 64)
+
+static int (*bpf_map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags) = (void *)BPF_FUNC_map_update_elem;
+static void *(*bpf_map_lookup_elem)(struct bpf_map *map, void *key) = (void *)BPF_FUNC_map_lookup_elem;
+
+static void (*bpf_tail_call)(void *ctx, void *map, int index) = (void *)BPF_FUNC_tail_call;
+
+#define SEC(NAME) __attribute__((section(NAME),  used))
+
+#define probe(function, vars) \
+	SEC(#function "=" #function " " #vars) function
+
+#define syscall_enter(name) \
+	SEC("syscalls:sys_enter_" #name) syscall_enter_ ## name
+
+#define syscall_exit(name) \
+	SEC("syscalls:sys_exit_" #name) syscall_exit_ ## name
+
+#define license(name) \
+char _license[] SEC("license") = #name; \
+int _version SEC("version") = LINUX_VERSION_CODE;
+
+static int (*probe_read)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read;
+static int (*probe_read_str)(void *dst, int size, const void *unsafe_addr) = (void *)BPF_FUNC_probe_read_str;
+
+static int (*perf_event_output)(void *, struct bpf_map *, int, void *, unsigned long) = (void *)BPF_FUNC_perf_event_output;
+
+#endif /* _PERF_BPF_H */
diff --git a/tools/perf/include/bpf/linux/socket.h b/tools/perf/include/bpf/linux/socket.h
new file mode 100644
index 000000000..7f844568d
--- /dev/null
+++ b/tools/perf/include/bpf/linux/socket.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_SOCKET_H
+#define _UAPI_LINUX_SOCKET_H
+
+/*
+ * Desired design of maximum size and alignment (see RFC2553)
+ */
+#define _K_SS_MAXSIZE	128	/* Implementation specific max size */
+#define _K_SS_ALIGNSIZE	(__alignof__ (struct sockaddr *))
+				/* Implementation specific desired alignment */
+
+typedef unsigned short __kernel_sa_family_t;
+
+struct __kernel_sockaddr_storage {
+	__kernel_sa_family_t	ss_family;		/* address family */
+	/* Following field(s) are implementation specific */
+	char		__data[_K_SS_MAXSIZE - sizeof(unsigned short)];
+				/* space to achieve desired size, */
+				/* _SS_MAXSIZE value minus size of ss_family */
+} __attribute__ ((aligned(_K_SS_ALIGNSIZE)));	/* force desired alignment */
+
+#define sockaddr_storage __kernel_sockaddr_storage
+
+#endif /* _UAPI_LINUX_SOCKET_H */
diff --git a/tools/perf/include/bpf/pid_filter.h b/tools/perf/include/bpf/pid_filter.h
new file mode 100644
index 000000000..6e61c4bdf
--- /dev/null
+++ b/tools/perf/include/bpf/pid_filter.h
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+#ifndef _PERF_BPF_PID_FILTER_
+#define _PERF_BPF_PID_FILTER_
+
+#include <bpf.h>
+
+#define pid_filter(name) pid_map(name, bool)
+
+static int pid_filter__add(struct bpf_map *pids, pid_t pid)
+{
+	bool value = true;
+	return bpf_map_update_elem(pids, &pid, &value, BPF_NOEXIST);
+}
+
+static bool pid_filter__has(struct bpf_map *pids, pid_t pid)
+{
+	return bpf_map_lookup_elem(pids, &pid) != NULL;
+}
+
+#endif // _PERF_BPF_PID_FILTER_
diff --git a/tools/perf/include/bpf/stdio.h b/tools/perf/include/bpf/stdio.h
new file mode 100644
index 000000000..316af5b2f
--- /dev/null
+++ b/tools/perf/include/bpf/stdio.h
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <bpf.h>
+
+struct bpf_map SEC("maps") __bpf_stdout__ = {
+       .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+       .key_size = sizeof(int),
+       .value_size = sizeof(u32),
+       .max_entries = __NR_CPUS__,
+};
+
+#define puts(from) \
+	({ const int __len = sizeof(from); \
+	   char __from[__len] = from; \
+	   perf_event_output(args, &__bpf_stdout__, BPF_F_CURRENT_CPU, \
+			  &__from, __len & (sizeof(from) - 1)); })
diff --git a/tools/perf/include/bpf/unistd.h b/tools/perf/include/bpf/unistd.h
new file mode 100644
index 000000000..ca7877f9a
--- /dev/null
+++ b/tools/perf/include/bpf/unistd.h
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+#include <bpf.h>
+
+static int (*bpf_get_current_pid_tgid)(void) = (void *)BPF_FUNC_get_current_pid_tgid;
+
+static pid_t getpid(void)
+{
+	return bpf_get_current_pid_tgid();
+}
diff --git a/tools/perf/include/perf/perf_dlfilter.h b/tools/perf/include/perf/perf_dlfilter.h
new file mode 100644
index 000000000..a26e2f129
--- /dev/null
+++ b/tools/perf/include/perf/perf_dlfilter.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * perf_dlfilter.h: API for perf --dlfilter shared object
+ * Copyright (c) 2021, Intel Corporation.
+ */
+#ifndef _LINUX_PERF_DLFILTER_H
+#define _LINUX_PERF_DLFILTER_H
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+/*
+ * The following macro can be used to determine if this header defines
+ * perf_dlfilter_sample machine_pid and vcpu.
+ */
+#define PERF_DLFILTER_HAS_MACHINE_PID
+
+/* Definitions for perf_dlfilter_sample flags */
+enum {
+	PERF_DLFILTER_FLAG_BRANCH	= 1ULL << 0,
+	PERF_DLFILTER_FLAG_CALL		= 1ULL << 1,
+	PERF_DLFILTER_FLAG_RETURN	= 1ULL << 2,
+	PERF_DLFILTER_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_DLFILTER_FLAG_SYSCALLRET	= 1ULL << 4,
+	PERF_DLFILTER_FLAG_ASYNC	= 1ULL << 5,
+	PERF_DLFILTER_FLAG_INTERRUPT	= 1ULL << 6,
+	PERF_DLFILTER_FLAG_TX_ABORT	= 1ULL << 7,
+	PERF_DLFILTER_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_DLFILTER_FLAG_TRACE_END	= 1ULL << 9,
+	PERF_DLFILTER_FLAG_IN_TX	= 1ULL << 10,
+	PERF_DLFILTER_FLAG_VMENTRY	= 1ULL << 11,
+	PERF_DLFILTER_FLAG_VMEXIT	= 1ULL << 12,
+};
+
+/*
+ * perf sample event information (as per perf script and <linux/perf_event.h>)
+ */
+struct perf_dlfilter_sample {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u16 ins_lat;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u16 p_stage_cyc;	/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 ip;
+	__s32 pid;
+	__s32 tid;
+	__u64 time;
+	__u64 addr;
+	__u64 id;
+	__u64 stream_id;
+	__u64 period;
+	__u64 weight;		/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+	__u64 transaction;	/* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */
+	__u64 insn_cnt;	/* For instructions-per-cycle (IPC) */
+	__u64 cyc_cnt;		/* For instructions-per-cycle (IPC) */
+	__s32 cpu;
+	__u32 flags;		/* Refer PERF_DLFILTER_FLAG_* above */
+	__u64 data_src;		/* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */
+	__u64 phys_addr;	/* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */
+	__u64 data_page_size;	/* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 code_page_size;	/* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */
+	__u64 cgroup;		/* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */
+	__u8  cpumode;		/* Refer CPUMODE_MASK etc in <linux/perf_event.h> */
+	__u8  addr_correlates_sym; /* True => resolve_addr() can be called */
+	__u16 misc;		/* Refer perf_event_header in <linux/perf_event.h> */
+	__u32 raw_size;		/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	const void *raw_data;	/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+	__u64 brstack_nr;	/* Number of brstack entries */
+	const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */
+	__u64 raw_callchain_nr;	/* Number of raw_callchain entries */
+	const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */
+	const char *event;
+	__s32 machine_pid;
+	__s32 vcpu;
+};
+
+/*
+ * Address location (as per perf script)
+ */
+struct perf_dlfilter_al {
+	__u32 size; /* Size of this structure (for compatibility checking) */
+	__u32 symoff;
+	const char *sym;
+	__u64 addr; /* Mapped address (from dso) */
+	__u64 sym_start;
+	__u64 sym_end;
+	const char *dso;
+	__u8  sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */
+	__u8  is_64_bit; /* Only valid if dso is not NULL */
+	__u8  is_kernel_ip; /* True if in kernel space */
+	__u32 buildid_size;
+	__u8 *buildid;
+	/* Below members are only populated by resolve_ip() */
+	__u8 filtered; /* True if this sample event will be filtered out */
+	const char *comm;
+};
+
+struct perf_dlfilter_fns {
+	/* Return information about ip */
+	const struct perf_dlfilter_al *(*resolve_ip)(void *ctx);
+	/* Return information about addr (if addr_correlates_sym) */
+	const struct perf_dlfilter_al *(*resolve_addr)(void *ctx);
+	/* Return arguments from --dlarg option */
+	char **(*args)(void *ctx, int *dlargc);
+	/*
+	 * Return information about address (al->size must be set before
+	 * calling). Returns 0 on success, -1 otherwise.
+	 */
+	__s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al);
+	/* Return instruction bytes and length */
+	const __u8 *(*insn)(void *ctx, __u32 *length);
+	/* Return source file name and line number */
+	const char *(*srcline)(void *ctx, __u32 *line_number);
+	/* Return perf_event_attr, refer <linux/perf_event.h> */
+	struct perf_event_attr *(*attr)(void *ctx);
+	/* Read object code, return numbers of bytes read */
+	__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
+	/* Reserved */
+	void *(*reserved[120])(void *);
+};
+
+/*
+ * If implemented, 'start' will be called at the beginning,
+ * before any calls to 'filter_event'. Return 0 to indicate success,
+ * or return a negative error code. '*data' can be assigned for use
+ * by other functions. 'ctx' is needed for calls to perf_dlfilter_fns,
+ * but most perf_dlfilter_fns are not valid when called from 'start'.
+ */
+int start(void **data, void *ctx);
+
+/*
+ * If implemented, 'stop' will be called at the end,
+ * after any calls to 'filter_event'. Return 0 to indicate success, or
+ * return a negative error code. 'data' is set by start(). 'ctx' is
+ * needed for calls to perf_dlfilter_fns, but most perf_dlfilter_fns
+ * are not valid when called from 'stop'.
+ */
+int stop(void *data, void *ctx);
+
+/*
+ * If implemented, 'filter_event' will be called for each sample
+ * event. Return 0 to keep the sample event, 1 to filter it out, or
+ * return a negative error code. 'data' is set by start(). 'ctx' is
+ * needed for calls to perf_dlfilter_fns.
+ */
+int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx);
+
+/*
+ * The same as 'filter_event' except it is called before internal
+ * filtering.
+ */
+int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx);
+
+/*
+ * If implemented, return a one-line description of the filter, and optionally
+ * a longer description.
+ */
+const char *filter_description(const char **long_description);
+
+#endif