perf tools: Support for DWARF CFI unwinding on post processing

This brings the support for DWARF cfi unwinding on perf post
processing. Call frame informations are retrieved and then passed
to libunwind that requests memory and register content from the
applications.

Adding unwind object to handle the user stack backtrace based
on the user register values and user stack dump.

The unwind object access the libunwind via remote interface
and provides to it all the necessary data to unwind the stack.

The unwind interface provides following function:
	unwind__get_entries

And callback (specified in above function) to retrieve
the backtrace entries:
	typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry,
					 void *arg);

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Original-patch-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>
Cc: Arun Sharma <asharma@fb.com>
Cc: Benjamin Redelings <benjamin.redelings@nescent.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Frank Ch. Eigler <fche@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/r/1344345647-11536-12-git-send-email-jolsa@redhat.com
[ Replaced use of perf_session by usage of perf_evsel ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 567 insertions, 0 deletions

diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind.c
new file mode 100644
index 000000000000..00a42aa8d5c1
--- /dev/null
+++ b/tools/perf/util/unwind.c
@@ -0,0 +1,567 @@
+/*
+ * Post mortem Dwarf CFI based unwinding on top of regs and stack dumps.
+ *
+ * Lots of this code have been borrowed or heavily inspired from parts of
+ * the libunwind 0.99 code which are (amongst other contributors I may have
+ * forgotten):
+ *
+ * Copyright (C) 2002-2007 Hewlett-Packard Co
+ *      Contributed by David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * And the bugs have been added by:
+ *
+ * Copyright (C) 2010, Frederic Weisbecker <fweisbec@gmail.com>
+ * Copyright (C) 2012, Jiri Olsa <jolsa@redhat.com>
+ *
+ */
+
+#include <elf.h>
+#include <gelf.h>
+#include <fcntl.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <linux/list.h>
+#include <libunwind.h>
+#include <libunwind-ptrace.h>
+#include "thread.h"
+#include "session.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "util.h"
+
+extern int
+UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
+                                    unw_word_t ip,
+                                    unw_dyn_info_t *di,
+                                    unw_proc_info_t *pi,
+                                    int need_unwind_info, void *arg);
+
+#define dwarf_search_unwind_table UNW_OBJ(dwarf_search_unwind_table)
+
+#define DW_EH_PE_FORMAT_MASK    0x0f    /* format of the encoded value */
+#define DW_EH_PE_APPL_MASK      0x70    /* how the value is to be applied */
+
+/* Pointer-encoding formats: */
+#define DW_EH_PE_omit           0xff
+#define DW_EH_PE_ptr            0x00    /* pointer-sized unsigned value */
+#define DW_EH_PE_udata4         0x03    /* unsigned 32-bit value */
+#define DW_EH_PE_udata8         0x04    /* unsigned 64-bit value */
+#define DW_EH_PE_sdata4         0x0b    /* signed 32-bit value */
+#define DW_EH_PE_sdata8         0x0c    /* signed 64-bit value */
+
+/* Pointer-encoding application: */
+#define DW_EH_PE_absptr         0x00    /* absolute value */
+#define DW_EH_PE_pcrel          0x10    /* rel. to addr. of encoded value */
+
+/*
+ * The following are not documented by LSB v1.3, yet they are used by
+ * GCC, presumably they aren't documented by LSB since they aren't
+ * used on Linux:
+ */
+#define DW_EH_PE_funcrel        0x40    /* start-of-procedure-relative */
+#define DW_EH_PE_aligned        0x50    /* aligned pointer */
+
+/* Flags intentionaly not handled, since they're not needed:
+ * #define DW_EH_PE_indirect      0x80
+ * #define DW_EH_PE_uleb128       0x01
+ * #define DW_EH_PE_udata2        0x02
+ * #define DW_EH_PE_sleb128       0x09
+ * #define DW_EH_PE_sdata2        0x0a
+ * #define DW_EH_PE_textrel       0x20
+ * #define DW_EH_PE_datarel       0x30
+ */
+
+struct unwind_info {
+        struct perf_sample      *sample;
+        struct machine          *machine;
+        struct thread           *thread;
+        u64                     sample_uregs;
+};
+
+#define dw_read(ptr, type, end) ({      \
+        type *__p = (type *) ptr;       \
+        type  __v;                      \
+        if ((__p + 1) > (type *) end)   \
+                return -EINVAL;         \
+        __v = *__p++;                   \
+        ptr = (typeof(ptr)) __p;        \
+        __v;                            \
+        })
+
+static int __dw_read_encoded_value(u8 **p, u8 *end, u64 *val,
+                                   u8 encoding)
+{
+        u8 *cur = *p;
+        *val = 0;
+
+        switch (encoding) {
+        case DW_EH_PE_omit:
+                *val = 0;
+                goto out;
+        case DW_EH_PE_ptr:
+                *val = dw_read(cur, unsigned long, end);
+                goto out;
+        default:
+                break;
+        }
+
+        switch (encoding & DW_EH_PE_APPL_MASK) {
+        case DW_EH_PE_absptr:
+                break;
+        case DW_EH_PE_pcrel:
+                *val = (unsigned long) cur;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        if ((encoding & 0x07) == 0x00)
+                encoding |= DW_EH_PE_udata4;
+
+        switch (encoding & DW_EH_PE_FORMAT_MASK) {
+        case DW_EH_PE_sdata4:
+                *val += dw_read(cur, s32, end);
+                break;
+        case DW_EH_PE_udata4:
+                *val += dw_read(cur, u32, end);
+                break;
+        case DW_EH_PE_sdata8:
+                *val += dw_read(cur, s64, end);
+                break;
+        case DW_EH_PE_udata8:
+                *val += dw_read(cur, u64, end);
+                break;
+        default:
+                return -EINVAL;
+        }
+
+ out:
+        *p = cur;
+        return 0;
+}
+
+#define dw_read_encoded_value(ptr, end, enc) ({                 \
+        u64 __v;                                                \
+        if (__dw_read_encoded_value(&ptr, end, &__v, enc)) {    \
+                return -EINVAL;                                 \
+        }                                                       \
+        __v;                                                    \
+        })
+
+static Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
+                                    GElf_Shdr *shp, const char *name)
+{
+        Elf_Scn *sec = NULL;
+
+        while ((sec = elf_nextscn(elf, sec)) != NULL) {
+                char *str;
+
+                gelf_getshdr(sec, shp);
+                str = elf_strptr(elf, ep->e_shstrndx, shp->sh_name);
+                if (!strcmp(name, str))
+                        break;
+        }
+
+        return sec;
+}
+
+static u64 elf_section_offset(int fd, const char *name)
+{
+        Elf *elf;
+        GElf_Ehdr ehdr;
+        GElf_Shdr shdr;
+        u64 offset = 0;
+
+        elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+        if (elf == NULL)
+                return 0;
+
+        do {
+                if (gelf_getehdr(elf, &ehdr) == NULL)
+                        break;
+
+                if (!elf_section_by_name(elf, &ehdr, &shdr, name))
+                        break;
+
+                offset = shdr.sh_offset;
+        } while (0);
+
+        elf_end(elf);
+        return offset;
+}
+
+struct table_entry {
+        u32 start_ip_offset;
+        u32 fde_offset;
+};
+
+struct eh_frame_hdr {
+        unsigned char version;
+        unsigned char eh_frame_ptr_enc;
+        unsigned char fde_count_enc;
+        unsigned char table_enc;
+
+        /*
+         * The rest of the header is variable-length and consists of the
+         * following members:
+         *
+         *      encoded_t eh_frame_ptr;
+         *      encoded_t fde_count;
+         */
+
+        /* A single encoded pointer should not be more than 8 bytes. */
+        u64 enc[2];
+
+        /*
+         * struct {
+         *    encoded_t start_ip;
+         *    encoded_t fde_addr;
+         * } binary_search_table[fde_count];
+         */
+        char data[0];
+} __packed;
+
+static int unwind_spec_ehframe(struct dso *dso, struct machine *machine,
+                               u64 offset, u64 *table_data, u64 *segbase,
+                               u64 *fde_count)
+{
+        struct eh_frame_hdr hdr;
+        u8 *enc = (u8 *) &hdr.enc;
+        u8 *end = (u8 *) &hdr.data;
+        ssize_t r;
+
+        r = dso__data_read_offset(dso, machine, offset,
+                                  (u8 *) &hdr, sizeof(hdr));
+        if (r != sizeof(hdr))
+                return -EINVAL;
+
+        /* We dont need eh_frame_ptr, just skip it. */
+        dw_read_encoded_value(enc, end, hdr.eh_frame_ptr_enc);
+
+        *fde_count  = dw_read_encoded_value(enc, end, hdr.fde_count_enc);
+        *segbase    = offset;
+        *table_data = (enc - (u8 *) &hdr) + offset;
+        return 0;
+}
+
+static int read_unwind_spec(struct dso *dso, struct machine *machine,
+                            u64 *table_data, u64 *segbase, u64 *fde_count)
+{
+        int ret = -EINVAL, fd;
+        u64 offset;
+
+        fd = dso__data_fd(dso, machine);
+        if (fd < 0)
+                return -EINVAL;
+
+        offset = elf_section_offset(fd, ".eh_frame_hdr");
+        close(fd);
+
+        if (offset)
+                ret = unwind_spec_ehframe(dso, machine, offset,
+                                          table_data, segbase,
+                                          fde_count);
+
+        /* TODO .debug_frame check if eh_frame_hdr fails */
+        return ret;
+}
+
+static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
+{
+        struct addr_location al;
+
+        thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+                              MAP__FUNCTION, ip, &al);
+        return al.map;
+}
+
+static int
+find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+               int need_unwind_info, void *arg)
+{
+        struct unwind_info *ui = arg;
+        struct map *map;
+        unw_dyn_info_t di;
+        u64 table_data, segbase, fde_count;
+
+        map = find_map(ip, ui);
+        if (!map || !map->dso)
+                return -EINVAL;
+
+        pr_debug("unwind: find_proc_info dso %s\n", map->dso->name);
+
+        if (read_unwind_spec(map->dso, ui->machine,
+                             &table_data, &segbase, &fde_count))
+                return -EINVAL;
+
+        memset(&di, 0, sizeof(di));
+        di.format   = UNW_INFO_FORMAT_REMOTE_TABLE;
+        di.start_ip = map->start;
+        di.end_ip   = map->end;
+        di.u.rti.segbase    = map->start + segbase;
+        di.u.rti.table_data = map->start + table_data;
+        di.u.rti.table_len  = fde_count * sizeof(struct table_entry)
+                              / sizeof(unw_word_t);
+        return dwarf_search_unwind_table(as, ip, &di, pi,
+                                         need_unwind_info, arg);
+}
+
+static int access_fpreg(unw_addr_space_t __used as, unw_regnum_t __used num,
+                        unw_fpreg_t __used *val, int __used __write,
+                        void __used *arg)
+{
+        pr_err("unwind: access_fpreg unsupported\n");
+        return -UNW_EINVAL;
+}
+
+static int get_dyn_info_list_addr(unw_addr_space_t __used as,
+                                  unw_word_t __used *dil_addr,
+                                  void __used *arg)
+{
+        return -UNW_ENOINFO;
+}
+
+static int resume(unw_addr_space_t __used as, unw_cursor_t __used *cu,
+                  void __used *arg)
+{
+        pr_err("unwind: resume unsupported\n");
+        return -UNW_EINVAL;
+}
+
+static int
+get_proc_name(unw_addr_space_t __used as, unw_word_t __used addr,
+                char __used *bufp, size_t __used buf_len,
+                unw_word_t __used *offp, void __used *arg)
+{
+        pr_err("unwind: get_proc_name unsupported\n");
+        return -UNW_EINVAL;
+}
+
+static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
+                          unw_word_t *data)
+{
+        struct addr_location al;
+        ssize_t size;
+
+        thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+                              MAP__FUNCTION, addr, &al);
+        if (!al.map) {
+                pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+                return -1;
+        }
+
+        if (!al.map->dso)
+                return -1;
+
+        size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+                                   addr, (u8 *) data, sizeof(*data));
+
+        return !(size == sizeof(*data));
+}
+
+static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
+                     u64 sample_regs)
+{
+        int i, idx = 0;
+
+        if (!(sample_regs & (1 << id)))
+                return -EINVAL;
+
+        for (i = 0; i < id; i++) {
+                if (sample_regs & (1 << i))
+                        idx++;
+        }
+
+        *valp = regs->regs[idx];
+        return 0;
+}
+
+static int access_mem(unw_addr_space_t __used as,
+                      unw_word_t addr, unw_word_t *valp,
+                      int __write, void *arg)
+{
+        struct unwind_info *ui = arg;
+        struct stack_dump *stack = &ui->sample->user_stack;
+        unw_word_t start, end;
+        int offset;
+        int ret;
+
+        /* Don't support write, probably not needed. */
+        if (__write || !stack || !ui->sample->user_regs.regs) {
+                *valp = 0;
+                return 0;
+        }
+
+        ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP,
+                        ui->sample_uregs);
+        if (ret)
+                return ret;
+
+        end = start + stack->size;
+
+        /* Check overflow. */
+        if (addr + sizeof(unw_word_t) < addr)
+                return -EINVAL;
+
+        if (addr < start || addr + sizeof(unw_word_t) >= end) {
+                ret = access_dso_mem(ui, addr, valp);
+                if (ret) {
+                        pr_debug("unwind: access_mem %p not inside range %p-%p\n",
+                                (void *)addr, (void *)start, (void *)end);
+                        *valp = 0;
+                        return ret;
+                }
+                return 0;
+        }
+
+        offset = addr - start;
+        *valp  = *(unw_word_t *)&stack->data[offset];
+        pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n",
+                 (void *)addr, (unsigned long)*valp, offset);
+        return 0;
+}
+
+static int access_reg(unw_addr_space_t __used as,
+                      unw_regnum_t regnum, unw_word_t *valp,
+                      int __write, void *arg)
+{
+        struct unwind_info *ui = arg;
+        int id, ret;
+
+        /* Don't support write, I suspect we don't need it. */
+        if (__write) {
+                pr_err("unwind: access_reg w %d\n", regnum);
+                return 0;
+        }
+
+        if (!ui->sample->user_regs.regs) {
+                *valp = 0;
+                return 0;
+        }
+
+        id = unwind__arch_reg_id(regnum);
+        if (id < 0)
+                return -EINVAL;
+
+        ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs);
+        if (ret) {
+                pr_err("unwind: can't read reg %d\n", regnum);
+                return ret;
+        }
+
+        pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
+        return 0;
+}
+
+static void put_unwind_info(unw_addr_space_t __used as,
+                            unw_proc_info_t *pi __used,
+                            void *arg __used)
+{
+        pr_debug("unwind: put_unwind_info called\n");
+}
+
+static int entry(u64 ip, struct thread *thread, struct machine *machine,
+                 unwind_entry_cb_t cb, void *arg)
+{
+        struct unwind_entry e;
+        struct addr_location al;
+
+        thread__find_addr_location(thread, machine,
+                                   PERF_RECORD_MISC_USER,
+                                   MAP__FUNCTION, ip, &al, NULL);
+
+        e.ip = ip;
+        e.map = al.map;
+        e.sym = al.sym;
+
+        pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+                 al.sym ? al.sym->name : "''",
+                 ip,
+                 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+        return cb(&e, arg);
+}
+
+static void display_error(int err)
+{
+        switch (err) {
+        case UNW_EINVAL:
+                pr_err("unwind: Only supports local.\n");
+                break;
+        case UNW_EUNSPEC:
+                pr_err("unwind: Unspecified error.\n");
+                break;
+        case UNW_EBADREG:
+                pr_err("unwind: Register unavailable.\n");
+                break;
+        default:
+                break;
+        }
+}
+
+static unw_accessors_t accessors = {
+        .find_proc_info         = find_proc_info,
+        .put_unwind_info        = put_unwind_info,
+        .get_dyn_info_list_addr = get_dyn_info_list_addr,
+        .access_mem             = access_mem,
+        .access_reg             = access_reg,
+        .access_fpreg           = access_fpreg,
+        .resume                 = resume,
+        .get_proc_name          = get_proc_name,
+};
+
+static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
+                       void *arg)
+{
+        unw_addr_space_t addr_space;
+        unw_cursor_t c;
+        int ret;
+
+        addr_space = unw_create_addr_space(&accessors, 0);
+        if (!addr_space) {
+                pr_err("unwind: Can't create unwind address space.\n");
+                return -ENOMEM;
+        }
+
+        ret = unw_init_remote(&c, addr_space, ui);
+        if (ret)
+                display_error(ret);
+
+        while (!ret && (unw_step(&c) > 0)) {
+                unw_word_t ip;
+
+                unw_get_reg(&c, UNW_REG_IP, &ip);
+                ret = entry(ip, ui->thread, ui->machine, cb, arg);
+        }
+
+        unw_destroy_addr_space(addr_space);
+        return ret;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+                        struct machine *machine, struct thread *thread,
+                        u64 sample_uregs, struct perf_sample *data)
+{
+        unw_word_t ip;
+        struct unwind_info ui = {
+                .sample       = data,
+                .sample_uregs = sample_uregs,
+                .thread       = thread,
+                .machine      = machine,
+        };
+        int ret;
+
+        if (!data->user_regs.regs)
+                return -EINVAL;
+
+        ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs);
+        if (ret)
+                return ret;
+
+        ret = entry(ip, thread, machine, cb, arg);
+        if (ret)
+                return -ENOMEM;
+
+        return get_entries(&ui, cb, arg);
+}