Resguardo inicial

linux-7.2.3/tools/perf/arch/powerpc/util/Build

@@ -0,0 +1,9 @@
+perf-util-y += header.o
+perf-util-y += mem-events.o
+perf-util-y += pmu.o
+perf-util-y += sym-handling.o
+perf-util-y += evsel.o
+
+perf-util-$(CONFIG_LIBDW) += skip-callchain-idx.o
+
+perf-util-y += auxtrace.o

linux-7.2.3/tools/perf/arch/powerpc/util/auxtrace.c

@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * VPA support
+ */
+#include <errno.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/zalloc.h>
+
+#include "../../util/evlist.h"
+#include "../../util/debug.h"
+#include "../../util/auxtrace.h"
+#include "../../util/powerpc-vpadtl.h"
+#include "../../util/record.h"
+#include <internal/lib.h> // page_size
+
+#define KiB(x) ((x) * 1024)
+
+static int
+powerpc_vpadtl_recording_options(struct auxtrace_record *ar __maybe_unused,
+			struct evlist *evlist __maybe_unused,
+			struct record_opts *opts)
+{
+	opts->full_auxtrace = true;
+
+	/*
+	 * Set auxtrace_mmap_pages to minimum
+	 * two pages
+	 */
+	if (!opts->auxtrace_mmap_pages) {
+		opts->auxtrace_mmap_pages = KiB(128) / page_size;
+		if (opts->mmap_pages == UINT_MAX)
+			opts->mmap_pages = KiB(256) / page_size;
+	}
+
+	return 0;
+}
+
+static size_t powerpc_vpadtl_info_priv_size(struct auxtrace_record *itr __maybe_unused,
+					struct evlist *evlist __maybe_unused)
+{
+	return VPADTL_AUXTRACE_PRIV_SIZE;
+}
+
+static int
+powerpc_vpadtl_info_fill(struct auxtrace_record *itr __maybe_unused,
+		struct perf_session *session __maybe_unused,
+		struct perf_record_auxtrace_info *auxtrace_info,
+		size_t priv_size __maybe_unused)
+{
+	auxtrace_info->type = PERF_AUXTRACE_VPA_DTL;
+
+	return 0;
+}
+
+static void powerpc_vpadtl_free(struct auxtrace_record *itr)
+{
+	free(itr);
+}
+
+static u64 powerpc_vpadtl_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return 0;
+}
+
+struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
+						int *err)
+{
+	struct auxtrace_record *aux;
+	struct evsel *pos;
+	int found = 0;
+
+	/*
+	 * Set err value to zero here. Any fail later
+	 * will set appropriate return code to err.
+	 */
+	*err = 0;
+
+	evlist__for_each_entry(evlist, pos) {
+		if (strstarts(pos->name, "vpa_dtl")) {
+			found = 1;
+			pos->needs_auxtrace_mmap = true;
+			break;
+		}
+	}
+
+	if (!found)
+		return NULL;
+
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+	 * must come first.
+	 */
+	evlist__to_front(pos->evlist, pos);
+
+	aux = zalloc(sizeof(*aux));
+	if (aux == NULL) {
+		pr_debug("aux record is NULL\n");
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	aux->recording_options = powerpc_vpadtl_recording_options;
+	aux->info_priv_size = powerpc_vpadtl_info_priv_size;
+	aux->info_fill = powerpc_vpadtl_info_fill;
+	aux->free = powerpc_vpadtl_free;
+	aux->reference = powerpc_vpadtl_reference;
+	return aux;
+}

linux-7.2.3/tools/perf/arch/powerpc/util/evsel.c

@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include "util/evsel.h"
+
+void arch_evsel__set_sample_weight(struct evsel *evsel)
+{
+	evsel__set_sample_bit(evsel, WEIGHT_STRUCT);
+}

linux-7.2.3/tools/perf/arch/powerpc/util/header.c

@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <sys/types.h>
+#include <errno.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/stringify.h>
+#include "header.h"
+#include "utils_header.h"
+#include "metricgroup.h"
+#include <api/fs/fs.h>
+#include <sys/auxv.h>
+
+static bool is_compat_mode(void)
+{
+	unsigned long base_platform = getauxval(AT_BASE_PLATFORM);
+	unsigned long platform = getauxval(AT_PLATFORM);
+
+	if (!strcmp((char *)platform, (char *)base_platform))
+		return false;
+
+	return true;
+}
+
+int
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
+{
+	unsigned long pvr;
+	int nb;
+
+	pvr = mfspr(SPRN_PVR);
+
+	nb = scnprintf(buffer, sz, "%lu,%lu$", PVR_VER(pvr), PVR_REV(pvr));
+
+	/* look for end marker to ensure the entire data fit */
+	if (strchr(buffer, '$')) {
+		buffer[nb-1] = '\0';
+		return 0;
+	}
+	return ENOBUFS;
+}
+
+char *
+get_cpuid_str(struct perf_cpu cpu __maybe_unused)
+{
+	char *bufp;
+	unsigned long pvr;
+
+	/*
+	 * IBM Power System supports compatible mode. That is
+	 * Nth generation platform can support previous generation
+	 * OS in a mode called compatibile mode. For ex. LPAR can be
+	 * booted in a Power9 mode when the system is a Power10.
+	 *
+	 * In the compatible mode, care must be taken when generating
+	 * PVR value. When read, PVR will be of the AT_BASE_PLATFORM
+	 * To support generic events, return 0x00ffffff as pvr when
+	 * booted in compat mode. Based on this pvr value, json will
+	 * pick events from pmu-events/arch/powerpc/compat
+	 */
+	if (!is_compat_mode())
+		pvr = mfspr(SPRN_PVR);
+	else
+		pvr = 0x00ffffff;
+
+	if (asprintf(&bufp, "0x%.8lx", pvr) < 0)
+		bufp = NULL;
+
+	return bufp;
+}
+
+int arch_get_runtimeparam(const struct pmu_metric *pm)
+{
+	int count;
+	char path[PATH_MAX] = "/devices/hv_24x7/interface/";
+
+	strcat(path, pm->aggr_mode == PerChip ? "sockets" : "coresperchip");
+	return sysfs__read_int(path, &count) < 0 ? 1 : count;
+}

linux-7.2.3/tools/perf/arch/powerpc/util/mem-events.c

@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "util/map_symbol.h"
+#include "util/mem-events.h"
+#include "mem-events.h"
+
+#define E(t, n, s, l, a) { .tag = t, .name = n, .event_name = s, .ldlat = l, .aux_event = a }
+
+struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"%s/mem-loads/",	"mem-loads",	false,	0),
+	E("ldlat-stores",	"%s/mem-stores/",	"mem-stores",	false,	0),
+	E(NULL,			NULL,			NULL,		false,	0),
+};

linux-7.2.3/tools/perf/arch/powerpc/util/mem-events.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _POWER_MEM_EVENTS_H
+#define _POWER_MEM_EVENTS_H
+
+extern struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX];
+
+#endif /* _POWER_MEM_EVENTS_H */

linux-7.2.3/tools/perf/arch/powerpc/util/pmu.c

@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include "../../../util/pmu.h"
+#include "mem-events.h"
+
+void perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	if (pmu->is_core)
+		pmu->mem_events = perf_mem_events_power;
+}

linux-7.2.3/tools/perf/arch/powerpc/util/skip-callchain-idx.c

@@ -0,0 +1,257 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Use DWARF Debug information to skip unnecessary callchain entries.
+ *
+ * Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation.
+ * Copyright (C) 2014 Ulrich Weigand, IBM Corporation.
+ */
+#include <inttypes.h>
+#include <dwarf.h>
+#include <elfutils/libdwfl.h>
+
+#include "util/thread.h"
+#include "util/callchain.h"
+#include "util/debug.h"
+#include "util/dso.h"
+#include "util/event.h" // struct ip_callchain
+#include "util/map.h"
+#include "util/symbol.h"
+
+/*
+ * When saving the callchain on Power, the kernel conservatively saves
+ * excess entries in the callchain. A few of these entries are needed
+ * in some cases but not others. If the unnecessary entries are not
+ * ignored, we end up with duplicate arcs in the call-graphs. Use
+ * DWARF debug information to skip over any unnecessary callchain
+ * entries.
+ *
+ * See function header for arch_adjust_callchain() below for more details.
+ *
+ * The libdwfl code in this file is based on code from elfutils
+ * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc).
+ */
+
+/*
+ * Use the DWARF expression for the Call-frame-address and determine
+ * if return address is in LR and if a new frame was allocated.
+ */
+static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
+{
+	Dwarf_Op ops_mem[3];
+	Dwarf_Op dummy;
+	Dwarf_Op *ops = &dummy;
+	size_t nops;
+	int result;
+
+	result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops);
+	if (result < 0) {
+		pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1));
+		return -1;
+	}
+
+	/*
+	 * Check if return address is on the stack. If return address
+	 * is in a register (typically R0), it is yet to be saved on
+	 * the stack.
+	 */
+	if ((nops != 0 || ops != NULL) &&
+		!(nops == 1 && ops[0].atom == DW_OP_regx &&
+			ops[0].number2 == 0 && ops[0].offset == 0))
+		return 0;
+
+	/*
+	 * Return address is in LR. Check if a frame was allocated
+	 * but not-yet used.
+	 */
+	result = dwarf_frame_cfa(frame, &ops, &nops);
+	if (result < 0) {
+		pr_debug("dwarf_frame_cfa() returns %d, %s\n", result,
+					dwarf_errmsg(-1));
+		return -1;
+	}
+
+	/*
+	 * If call frame address is in r1, no new frame was allocated.
+	 */
+	if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 &&
+				ops[0].number2 == 0)
+		return 1;
+
+	/*
+	 * A new frame was allocated but has not yet been used.
+	 */
+	return 2;
+}
+
+/*
+ * Get the DWARF frame from the .eh_frame section.
+ */
+static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+	int		result;
+	Dwarf_Addr	bias;
+	Dwarf_CFI	*cfi;
+	Dwarf_Frame	*frame;
+
+	cfi = dwfl_module_eh_cfi(mod, &bias);
+	if (!cfi) {
+		pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
+	if (result) {
+		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	return frame;
+}
+
+/*
+ * Get the DWARF frame from the .debug_frame section.
+ */
+static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+	Dwarf_CFI       *cfi;
+	Dwarf_Addr      bias;
+	Dwarf_Frame     *frame;
+	int             result;
+
+	cfi = dwfl_module_dwarf_cfi(mod, &bias);
+	if (!cfi) {
+		pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	result = dwarf_cfi_addrframe(cfi, pc-bias, &frame);
+	if (result) {
+		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	return frame;
+}
+
+/*
+ * Return:
+ *	0 if return address for the program counter @pc is on stack
+ *	1 if return address is in LR and no new stack frame was allocated
+ *	2 if return address is in LR and a new frame was allocated (but not
+ *		yet used)
+ *	-1 in case of errors
+ */
+static int check_return_addr(struct dso *dso, Dwarf_Addr mapped_pc)
+{
+	int		rc = -1;
+	Dwfl		*dwfl;
+	Dwfl_Module	*mod;
+	Dwarf_Frame	*frame;
+	int		ra_regno;
+	Dwarf_Addr	start = mapped_pc;
+	Dwarf_Addr	end = mapped_pc;
+	bool		signalp;
+
+	dwfl = dso__libdw_dwfl(dso);
+	if (!dwfl)
+		return -1;
+
+	mod = dwfl_addrmodule(dwfl, mapped_pc);
+	if (!mod) {
+		pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1));
+		goto out;
+	}
+
+	/*
+	 * To work with split debug info files (eg: glibc), check both
+	 * .eh_frame and .debug_frame sections of the ELF header.
+	 */
+	frame = get_eh_frame(mod, mapped_pc);
+	if (!frame) {
+		frame = get_dwarf_frame(mod, mapped_pc);
+		if (!frame)
+			goto out;
+	}
+
+	ra_regno = dwarf_frame_info(frame, &start, &end, &signalp);
+	if (ra_regno < 0) {
+		pr_debug("Return address register unavailable: %s\n",
+				dwarf_errmsg(-1));
+		goto out;
+	}
+
+	rc = check_return_reg(ra_regno, frame);
+
+out:
+	return rc;
+}
+
+/*
+ * The callchain saved by the kernel always includes the link register (LR).
+ *
+ *	0:	PERF_CONTEXT_USER
+ *	1:	Program counter (Next instruction pointer)
+ *	2:	LR value
+ *	3:	Caller's caller
+ *	4:	...
+ *
+ * The value in LR is only needed when it holds a return address. If the
+ * return address is on the stack, we should ignore the LR value.
+ *
+ * Further, when the return address is in the LR, if a new frame was just
+ * allocated but the LR was not saved into it, then the LR contains the
+ * caller, slot 4: contains the caller's caller and the contents of slot 3:
+ * (chain->ips[3]) is undefined and must be ignored.
+ *
+ * Use DWARF debug information to determine if any entries need to be skipped.
+ *
+ * Return:
+ *	index:	of callchain entry that needs to be ignored (if any)
+ *	-1	if no entry needs to be ignored or in case of errors
+ */
+int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
+{
+	struct addr_location al;
+	struct dso *dso = NULL;
+	int rc;
+	u64 ip;
+	u64 skip_slot = -1;
+
+	if (!chain || chain->nr < 3)
+		return skip_slot;
+
+	addr_location__init(&al);
+	ip = chain->ips[1];
+
+	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
+
+	if (al.map)
+		dso = map__dso(al.map);
+
+	if (!dso) {
+		pr_debug("%" PRIx64 " dso is NULL\n", ip);
+		addr_location__exit(&al);
+		return skip_slot;
+	}
+
+	rc = check_return_addr(dso, map__map_ip(al.map, ip));
+
+	pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
+		dso__long_name(dso), al.sym->name, ip, rc);
+
+	if (rc == 0) {
+		/*
+		 * Return address on stack. Ignore LR value in callchain
+		 */
+		skip_slot = 2;
+	} else if (rc == 2) {
+		/*
+		 * New frame allocated but return address still in LR.
+		 * Ignore the caller's caller entry in callchain.
+		 */
+		skip_slot = 3;
+	}
+
+	addr_location__exit(&al);
+	return skip_slot;
+}

linux-7.2.3/tools/perf/arch/powerpc/util/sym-handling.c

@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "dso.h"
+#include "symbol.h"
+#include "map.h"
+#include "probe-event.h"
+#include "probe-file.h"
+
+int arch__choose_best_symbol(struct symbol *syma,
+			     struct symbol *symb __maybe_unused)
+{
+	char *sym = syma->name;
+
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+	/* Skip over any initial dot */
+	if (*sym == '.')
+		sym++;
+#endif
+
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(sym) >= 10 && !strncmp(sym, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
+
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+/* Allow matching against dot variants */
+int arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	/* Skip over initial dot */
+	if (*namea == '.')
+		namea++;
+	if (*nameb == '.')
+		nameb++;
+
+	return strcmp(namea, nameb);
+}
+
+int arch__compare_symbol_names_n(const char *namea, const char *nameb,
+				 unsigned int n)
+{
+	/* Skip over initial dot */
+	if (*namea == '.')
+		namea++;
+	if (*nameb == '.')
+		nameb++;
+
+	return strncmp(namea, nameb, n);
+}
+
+const char *arch__normalize_symbol_name(const char *name)
+{
+	/* Skip over initial dot */
+	if (name && *name == '.')
+		name++;
+	return name;
+}
+#endif
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+
+#ifdef HAVE_LIBELF_SUPPORT
+void arch__sym_update(struct symbol *s, GElf_Sym *sym)
+{
+	s->arch_sym = sym->st_other;
+}
+#endif
+
+#define PPC64LE_LEP_OFFSET	8
+
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map,
+			     struct symbol *sym)
+{
+	int lep_offset;
+
+	/*
+	 * When probing at a function entry point, we normally always want the
+	 * LEP since that catches calls to the function through both the GEP and
+	 * the LEP. Hence, we would like to probe at an offset of 8 bytes if
+	 * the user only specified the function entry.
+	 *
+	 * However, if the user specifies an offset, we fall back to using the
+	 * GEP since all userspace applications (objdump/readelf) show function
+	 * disassembly with offsets from the GEP.
+	 */
+	if (pev->point.offset || !map || !sym)
+		return;
+
+	/* For kretprobes, add an offset only if the kernel supports it */
+	if (!pev->uprobes && pev->point.retprobe) {
+#ifdef HAVE_LIBELF_SUPPORT
+		if (!kretprobe_offset_is_supported())
+#endif
+			return;
+	}
+
+	lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
+
+	if (map__dso(map)->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
+		tev->point.offset += PPC64LE_LEP_OFFSET;
+	else if (lep_offset) {
+		if (pev->uprobes)
+			tev->point.address += lep_offset;
+		else
+			tev->point.offset += lep_offset;
+	}
+}
+
+#ifdef HAVE_LIBELF_SUPPORT
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+					   int ntevs)
+{
+	struct probe_trace_event *tev;
+	struct map *map;
+	struct symbol *sym = NULL;
+	struct rb_node *tmp;
+	int i = 0;
+
+	map = get_target_map(pev->target, pev->nsi, pev->uprobes);
+	if (!map || map__load(map) < 0)
+		return;
+
+	for (i = 0; i < ntevs; i++) {
+		tev = &pev->tevs[i];
+		map__for_each_symbol(map, sym, tmp) {
+			if (map__unmap_ip(map, sym->start) == tev->point.address) {
+				arch__fix_tev_from_maps(pev, tev, map, sym);
+				break;
+			}
+		}
+	}
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
+#endif

linux-7.2.3/tools/perf/arch/powerpc/util/utils_header.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_UTIL_HEADER_H
+#define __PERF_UTIL_HEADER_H
+
+#include <linux/stringify.h>
+
+#define mfspr(rn)       ({unsigned long rval; \
+			asm volatile("mfspr %0," __stringify(rn) \
+				: "=r" (rval)); rval; })
+
+#define SPRN_PVR        0x11F   /* Processor Version Register */
+#define PVR_VER(pvr)    (((pvr) >>  16) & 0xFFFF) /* Version field */
+#define PVR_REV(pvr)    (((pvr) >>   0) & 0xFFFF) /* Revision field */
+
+#endif /* __PERF_UTIL_HEADER_H */