Hi,Liu Thanks your patch. What kind of environment did you test this KASLR problem ? Especialy is it kernel verssion 6.11.8-300.fc41.x86_64 ? Have you checked other versions? Additionally, do you know the version of eppic ? Also, if possible, show this problem results when an error occurs and the results when it is correct. Please tell me. Sincerely On 2025/06/10 18:57, Tao Liu wrote: > There is a bug of not supporting randomized kernel address, this patch fix it. > > Signed-off-by: Tao Liu <ltao(a)redhat.com&gt; > --- > erase_info.c | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > diff --git a/erase_info.c b/erase_info.c > index af6bfae..b67d1d0 100644 > --- a/erase_info.c > +++ b/erase_info.c > @@ -1881,7 +1881,7 @@ get_symbol_addr_all(char *name) { > if (!strcmp(get_dwarf_module_name(), "vmlinux")) { > symbol_addr = get_symbol_addr(name); > if (symbol_addr) > - return symbol_addr; > + return symbol_addr + info->kaslr_offset; > > vmlinux_searched = 1; > } > @@ -1942,9 +1942,9 @@ get_symbol_addr_all(char *name) { > * this function is called with debuginfo set to a particular > * kernel module and we are looking for symbol in vmlinux > */ > - if (!vmlinux_searched) > - return get_symbol_addr(name); > - else > + if (!vmlinux_searched && !!(symbol_addr = get_symbol_addr(name))) { > + return symbol_addr + info->kaslr_offset; > + } else > return NOT_FOUND_SYMBOL; > } >

Hi Tao, On 2025/06/10 18:57, Tao Liu wrote: apologies for my long delay and thank you for the patch. This patch looks good to me and I would like to merge this separately from the series, so Acked-by: Kazuhito Hagio <k-hagio-ab(a)nec.com&gt; Thanks, Kazu > --- > erase_info.c | 8 ++++---- > 1 file changed, 4 insertions(+), 4 deletions(-) > > diff --git a/erase_info.c b/erase_info.c > index af6bfae..b67d1d0 100644 > --- a/erase_info.c > +++ b/erase_info.c > @@ -1881,7 +1881,7 @@ get_symbol_addr_all(char *name) { > if (!strcmp(get_dwarf_module_name(), "vmlinux")) { > symbol_addr = get_symbol_addr(name); > if (symbol_addr) > - return symbol_addr; > + return symbol_addr + info->kaslr_offset; > > vmlinux_searched = 1; > } > @@ -1942,9 +1942,9 @@ get_symbol_addr_all(char *name) { > * this function is called with debuginfo set to a particular > * kernel module and we are looking for symbol in vmlinux > */ > - if (!vmlinux_searched) > - return get_symbol_addr(name); > - else > + if (!vmlinux_searched && !!(symbol_addr = get_symbol_addr(name))) { > + return symbol_addr + info->kaslr_offset; > + } else > return NOT_FOUND_SYMBOL; > } >

On 2025/09/30 9:34, Tao Liu wrote: ah sorry, the ack was for 01/10, I will review 02/10 later. I see. Thanks, Kazu > > Thanks, > Tao Liu > > On Mon, Sep 29, 2025 at 7:30 PM HAGIO KAZUHITO(萩尾　一仁) > <k-hagio-ab(a)nec.com&gt; wrote: >> >> Hi Tao, >> >> On 2025/06/10 18:57, Tao Liu wrote: >>> There is a bug of not supporting randomized kernel address, this patch fix it. >>> >>> Signed-off-by: Tao Liu <ltao(a)redhat.com&gt; >> >> apologies for my long delay and thank you for the patch. >> >> This patch looks good to me and I would like to merge this separately >> from the series, so >> >> Acked-by: Kazuhito Hagio <k-hagio-ab(a)nec.com&gt; >> >> Thanks, >> Kazu >> >>> --- >>> erase_info.c | 8 ++++---- >>> 1 file changed, 4 insertions(+), 4 deletions(-) >>> >>> diff --git a/erase_info.c b/erase_info.c >>> index af6bfae..b67d1d0 100644 >>> --- a/erase_info.c >>> +++ b/erase_info.c >>> @@ -1881,7 +1881,7 @@ get_symbol_addr_all(char *name) { >>> if (!strcmp(get_dwarf_module_name(), "vmlinux")) { >>> symbol_addr = get_symbol_addr(name); >>> if (symbol_addr) >>> - return symbol_addr; >>> + return symbol_addr + info->kaslr_offset; >>> >>> vmlinux_searched = 1; >>> } >>> @@ -1942,9 +1942,9 @@ get_symbol_addr_all(char *name) { >>> * this function is called with debuginfo set to a particular >>> * kernel module and we are looking for symbol in vmlinux >>> */ >>> - if (!vmlinux_searched) >>> - return get_symbol_addr(name); >>> - else >>> + if (!vmlinux_searched && !!(symbol_addr = get_symbol_addr(name))) { >>> + return symbol_addr + info->kaslr_offset; >>> + } else >>> return NOT_FOUND_SYMBOL; >>> } >>>

There is an infinite recursion bug noticed in rust symbols. The root cause is unclear to me. This patch will avoid the bug by skip the recursion of rust symbols, since currently we don't need to deal with those. Signed-off-by: Tao Liu <ltao(a)redhat.com&gt; --- dwarf_info.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/dwarf_info.c b/dwarf_info.c index a3a2fd6..73842ab 100644 --- a/dwarf_info.c +++ b/dwarf_info.c @@ -837,7 +837,7 @@ search_symbol(Dwarf_Die *die, int *found) } static void -search_domain(Dwarf_Die *die, int *found) +search_domain(Dwarf_Die *die, int *found, int lang) { int tag; const char *name; @@ -859,10 +859,11 @@ search_domain(Dwarf_Die *die, int *found) if (is_container(&die_type)) { Dwarf_Die child; - if (dwarf_child(&die_type, &child) != 0) + if (dwarf_child(&die_type, &child) != 0 || + lang == DW_LANG_Rust) continue; - search_domain(&child, found); + search_domain(&child, found, lang); if (*found) return; @@ -924,7 +925,7 @@ search_die(Dwarf_Die *die, int *found) } static void -search_die_tree(Dwarf_Die *die, int *found) +search_die_tree(Dwarf_Die *die, int *found, int lang) { Dwarf_Die child; @@ -932,7 +933,7 @@ search_die_tree(Dwarf_Die *die, int *found) * start by looking at the children */ if (dwarf_child(die, &child) == 0) - search_die_tree(&child, found); + search_die_tree(&child, found, lang); if (*found) return; @@ -950,7 +951,7 @@ search_die_tree(Dwarf_Die *die, int *found) search_typedef(die, found); else if (is_search_domain(dwarf_info.cmd)) - search_domain(die, found); + search_domain(die, found, lang); else if (is_search_die(dwarf_info.cmd)) search_die(die, found); @@ -1007,7 +1008,7 @@ get_debug_info(void) ERRMSG("Can't get CU die.\n"); goto out; } - search_die_tree(&cu_die, &found); + search_die_tree(&cu_die, &found, dwarf_srclang(&cu_die)); if (found) break; off = next_off; -- 2.47.0

Hi YAMAZAKI, On Fri, Oct 3, 2025 at 8:23 PM YAMAZAKI MASAMITSU(山崎　真光) <yamazaki-msmt(a)nec.com&gt; wrote: Sure E.g. using the following eppic program: /tmp/test.c: string test_opt(){return "";} string test_usage(){return "";} static void test_showusage(){printf("");} string test_help(){return "";} int test() { struct task_struct *p; unsigned long offset; p = (struct task_struct *)&init_task; offset = (unsigned long)&(p->tasks) - (unsigned long)p; do { printf("%d\n", (int)(p->pid)); p = (struct task_struct *)((unsigned long)(p->tasks.next) - (unsigned long)p); } while (p != &init_task); return 1; } $ ./makedumpfile --dry-run -d 31 -l /var/crash/127.0.0.1-2025-06-10-18\:03\:12/vmcore /tmp/out -x /lib/debug/lib/modules/6.11.8-300.fc41.x86_64/vmlinux --eppic /tmp/test.c Segmentation fault (core dumped) With the patch, no segfault. The vmcore/vmlinux should contain rust symbols: CONFIG_RUST=y, you can use the following vmcore https://people.redhat.com/~ltao/core/vmcore + https://kojipkgs.fedoraproject.org//packages/kernel/6.11.8/300.fc41/x86_6... for vmlinux and vmcore to test. Thanks, Tao Liu

Hi Kauz, On Fri, Oct 17, 2025 at 5:21 PM HAGIO KAZUHITO(萩尾　一仁) <k-hagio-ab(a)nec.com&gt; wrote: Agreed. Sure, thanks for your suggestion, I will update it in v2. The following change works for me: /* NOTE: currently Rust is not supported. */ if (dwarf_srclang(&cu_die) == DW_LANG_Rust) { off = next_off; continue; } I'm currently testing and will get it improved in v2 Thanks, Tao Liu

btf data contains symbols' type and size, which is essential to determine a structure/member size & offset. kallsyms contains symbols' address. All the data can provide complete info for symbol resolving. To initialize, we will: 1st) read vmcore info and parse kernel's kallsyms data; 2nd) read kernel data range of "__start/stop_BTF" and parse kernel's btf data, now we have complete type/address info for kernel symbols; 3rd) iterate kernel's module and parse all kernel modules' kallsyms data; 4th) iterate btf_modules and parse all kernel modules' btf data, now we have complete type/address info for kernel and modules symbols. Also to speed up the converting of symbol name to address/type, the parsed btf/kallsyms data are stored in hash tables. Signed-off-by: Tao Liu <ltao(a)redhat.com&gt; --- Makefile | 2 +- btf.c | 919 +++++++++++++++++++++++++++++++++++++++++++++++++ btf.h | 176 ++++++++++ kallsyms.c | 371 ++++++++++++++++++++ kallsyms.h | 42 +++ makedumpfile.c | 3 + makedumpfile.h | 11 + 7 files changed, 1523 insertions(+), 1 deletion(-) create mode 100644 btf.c create mode 100644 btf.h create mode 100644 kallsyms.c create mode 100644 kallsyms.h diff --git a/Makefile b/Makefile index 18d3a17..fbc9f5b 100644 --- a/Makefile +++ b/Makefile @@ -45,7 +45,7 @@ CFLAGS_ARCH += -m32 endif SRC_BASE = makedumpfile.c makedumpfile.h diskdump_mod.h sadump_mod.h sadump_info.h -SRC_PART = print_info.c dwarf_info.c elf_info.c erase_info.c sadump_info.c cache.c tools.c printk.c detect_cycle.c +SRC_PART = print_info.c dwarf_info.c elf_info.c erase_info.c sadump_info.c cache.c tools.c printk.c detect_cycle.c kallsyms.c btf.c OBJ_PART=$(patsubst %.c,%.o,$(SRC_PART)) SRC_ARCH = arch/arm.c arch/arm64.c arch/x86.c arch/x86_64.c arch/ia64.c arch/ppc64.c arch/s390x.c arch/ppc.c arch/sparc64.c arch/mips64.c arch/loongarch64.c arch/riscv64.c OBJ_ARCH=$(patsubst %.c,%.o,$(SRC_ARCH)) diff --git a/btf.c b/btf.c new file mode 100644 index 0000000..c91c841 --- /dev/null +++ b/btf.c @@ -0,0 +1,919 @@ +#include "btf.h" +#include <stdio.h> +#include <assert.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <libelf.h> +#include <gelf.h> +#include <dirent.h> +#include "kallsyms.h" +#include "makedumpfile.h" + +// btf_files_array[0] must be kernel itself +// btf_files_array[1..] are kernel modules +static struct btf_file **btf_files_array = NULL; +static int btf_files_array_index = 0; + +static const char *kind_names[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", + [BTF_KIND_FUNC] = "FUNC", + [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO", + [BTF_KIND_VAR] = "VAR", + [BTF_KIND_DATASEC] = "DATASEC", + [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_DECL_TAG] = "DECL_TAG", + [BTF_KIND_TYPE_TAG] = "TYPE_TAG", + [BTF_KIND_ENUM64] = "ENUM64", +}; + +static inline uint16_t btf_vlen(uint32_t info) +{ + return info & 0xFFFF; +} + +static inline uint32_t btf_kind_flag(uint32_t info) +{ + return info & (1 << 31); +} + +static inline uint32_t btf_member_bit_offset(uint32_t value) +{ + return value & 0xffffff; +} + +static inline uint32_t btf_member_bitfield_size(uint32_t value) +{ + return value >> 24; +} + +static struct btf_type *btf_next(struct btf_type *tp) +{ + uintptr_t next = (uintptr_t)&tp[1]; + + switch (btf_kind(tp->info)) { + case BTF_KIND_INT: + next += sizeof(uint32_t); + break; + + case BTF_KIND_ARRAY: + next += sizeof(struct btf_array); + break; + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + next += btf_vlen(tp->info) * sizeof(struct btf_member); + break; + + case BTF_KIND_ENUM: + next += btf_vlen(tp->info) * sizeof(struct btf_enum); + break; + + case BTF_KIND_FUNC_PROTO: + next += btf_vlen(tp->info) * sizeof(struct btf_param); + break; + + case BTF_KIND_VAR: + next += sizeof(struct btf_var); + break; + + case BTF_KIND_DATASEC: + next += btf_vlen(tp->info) * sizeof(struct btf_var_secinfo); + break; + + case BTF_KIND_DECL_TAG: + next += sizeof(struct btf_decl_tag); + break; + + case BTF_KIND_ENUM64: + next += btf_vlen(tp->info) * sizeof(struct btf_enum64); + break; + + case BTF_KIND_PTR: + case BTF_KIND_FWD: + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + case BTF_KIND_FUNC: + case BTF_KIND_FLOAT: + case BTF_KIND_TYPE_TAG: + break; // no extra data + + default: + __builtin_unreachable(); + } + return (struct btf_type *)next; +} + +#define NAME_HASH 512 +static struct name_entry *name_hash_table[NAME_HASH] = {0}; + +static void *get_name_entry_next(void *entry) +{ + return ((struct name_entry *)entry)->name_hash_next; +} + +static void set_name_entry_next(void *entry, void *next) +{ + ((struct name_entry *)entry)->name_hash_next = next; +} + +static void name_hash_install(struct name_entry *en) +{ + hash_install((void **)name_hash_table, NAME_HASH, en, en->name, + get_name_entry_next, set_name_entry_next); +} + +static unsigned int name_hash_index(char *name) +{ + return hash_index(name, NAME_HASH); +} + +static int read_file_at_offset(char *f, int f_off, int r_size, void *buf) +{ + int got = 0; + int r, fd, ret = -1; + + fd = open(f, O_RDONLY); + if (fd < 0) { + fprintf(stderr, "%s: Failed to open file %s\n", __func__, f); + goto out; + } + + while (got < r_size) { + r = pread(fd, buf + got, r_size - got, f_off + got); + if (r < 0) { + fprintf(stderr, "%s: Failed to read file %s\n", __func__, f); + goto clean_fd; + } + got += r; + } + ret = got; + +clean_fd: + close(fd); +out: + return ret; +} + +static char *get_str_by_name_off(struct btf_file *bf, uint32_t name_off) +{ + struct btf_file *bf_vmlinux = btf_files_array[0]; + + if (bf != bf_vmlinux && name_off >= bf_vmlinux->str_cache_len) + return bf->str_cache + name_off - bf_vmlinux->str_cache_len; + else + return bf_vmlinux->str_cache + name_off; +} + +int get_btf_type_by_type_id(struct btf_file *bf_in, uint32_t id_in, + struct btf_type *bt_out, struct name_entry **en_out) +{ + struct name_entry *en; + struct btf_file *bf_vmlinux = btf_files_array[0]; + + if (bf_in != bf_vmlinux && id_in > bf_vmlinux->array_len) { + en = bf_in->array[id_in - bf_vmlinux->array_len - 1]; + } else { + en = bf_vmlinux->array[id_in - 1]; + } + if (en_out) + *en_out = en; + return read_file_at_offset(en->bf->file_name, + en->btf_type_offset + en->bf->types_data_offset, + sizeof(*bt_out), bt_out); +} + +/* +* Parse the btf data and install elements into hashtable and array for quick +* reference. +*/ +static int parse_btf_data(char *file_path, char *data_start, uint32_t data_len) +{ + struct btf_header *hdr = (struct btf_header *)data_start; + struct btf_file *bf = NULL; + void *type_start; + char *str_start; + struct btf_type *tp; + struct name_entry *en; + int i, j, scale; + + /* We do some check first */ + if (hdr->magic != BTF_MAGIC) { + fprintf(stderr, "%s: Invalid BTF magic in %s\n", + __func__, file_path); + goto out; + } + if (hdr->hdr_len != sizeof(*hdr)) { + fprintf(stderr, "%s: Invalid BTF header length in %s\n", + __func__, file_path); + goto out; + } + if (hdr->hdr_len + hdr->str_off + hdr->str_len > data_len) { + fprintf(stderr, "%s: String section exceeds data length in %s\n", + __func__, file_path); + goto out; + } + if (hdr->hdr_len + hdr->type_off + hdr->type_len > data_len) { + fprintf(stderr, "%s: Type section exceeds data length in %s\n", + __func__, file_path); + goto out; + } + + /* Let's start parsing */ + bf = (struct btf_file *)malloc(sizeof(*bf)); + if (!bf) + goto no_mem; + memset(bf, 0, sizeof(*bf)); + + /* Enlarge array when reach power of 2 */ + btf_files_array[btf_files_array_index++] = bf; + if ((btf_files_array_index & (btf_files_array_index - 1)) == 0) { + struct btf_file **tmp = (struct btf_file **)reallocarray(btf_files_array, + btf_files_array_index << 1, + sizeof(struct btf_file *)); + if (!tmp) + goto no_mem; + btf_files_array = tmp; + } + + type_start = data_start + hdr->hdr_len + hdr->type_off; + str_start = data_start + hdr->hdr_len + hdr->str_off; + + bf->str_cache = malloc(hdr->str_len); + if (!bf->str_cache) + goto no_mem; + memcpy(bf->str_cache, str_start, hdr->str_len); + bf->str_cache_len = hdr->str_len; + + bf->array_len = 64; + bf->array = (struct name_entry **)calloc(bf->array_len, + sizeof(struct name_entry *)); + if (!bf->array) + goto no_mem; + + bf->file_name = strdup(file_path); + if (!bf->file_name) + goto no_mem; + bf->types_data_offset = (char *)type_start - data_start; + + for (tp = (struct btf_type *)type_start, i = 0; + (void *)tp < type_start + hdr->type_len; + tp = btf_next(tp), i++) { + en = (struct name_entry *)malloc(sizeof(struct name_entry)); + if (!en) { + bf->array_len = i; + goto no_mem; + } + memset(en, 0, sizeof(struct name_entry)); + + en->btf_type_offset = (void *)tp - type_start; + en->id = i + 1; + en->bf = bf; + if (tp->name_off) { + en->name = get_str_by_name_off(bf, tp->name_off); + if (en->name[0]) + name_hash_install(en); + } + bf->array[i] = en; + + /* Now deal with sub elements which also have a name */ + if (btf_kind(tp->info) == BTF_KIND_ENUM || + btf_kind(tp->info) == BTF_KIND_ENUM64) { + scale = btf_kind(tp->info) == BTF_KIND_ENUM ? + sizeof(struct btf_enum) : sizeof(struct btf_enum64); + for (j = 0; j < btf_vlen(tp->info); j++) { + en = (struct name_entry *)malloc(sizeof(struct name_entry)); + if (!en) { + bf->array_len = i + 1; + goto no_mem; + } + memset(en, 0, sizeof(struct name_entry)); + en->id = 0; + en->p_id = i + 1; + en->p_id += btf_files_array_index == 1 ? + 0 : btf_files_array[0]->array_len; + en->bf = bf; + en->name = get_str_by_name_off(bf, + *(uint32_t *)((char *)&tp[1] + j * scale)); + // printf("%s\n", en->name); + name_hash_install(en); + } + } + + /* Enlarge array when over 3/4 */ + if (i > (bf->array_len >> 2) * 3) { + struct name_entry **tmp = (struct name_entry **)reallocarray(bf->array, + bf->array_len << 1, sizeof(struct name_entry *)); + if (!tmp) + goto no_mem; + bf->array = tmp; + bf->array_len <<= 1; + } + } + bf->array_len = i; + return 0; +no_mem: + /* All the memory free will be dealed later. */ + fprintf(stderr, "%s: Not enough memory!\n", __func__); +out: + return -1; +} + +/* + * Used by search_name_by_cond() for searching specific type: + * such as struct/union/typedef + */ +static bool is_type(struct name_entry *sp, void *data_in, void *data_out) +{ + struct btf_type *bt = (struct btf_type *)data_out; + int type = *(int *)data_in; + if (sp->id) { + read_file_at_offset(sp->bf->file_name, + sp->btf_type_offset + sp->bf->types_data_offset, + sizeof(*bt), bt); + return btf_kind(bt->info) == type; + } + return false; +} + +static struct name_entry *search_name_by_cond(char *name, + bool (*fn)(struct name_entry *, void *, void *), + void *data_in, void *data_out) +{ + unsigned int index; + struct name_entry *sp; + + index = name_hash_index(name); + for (sp = name_hash_table[index]; sp; sp = sp->name_hash_next) { + if (!strcmp(name, sp->name) && fn(sp, data_in, data_out)) { + return sp; + } + } + return sp; +} + +// caller should prepare bt +void resolve_typedef(struct name_entry *en_in, struct name_entry **en_out, + struct btf_type *bt) +{ + uint32_t id; + struct name_entry *en; + + read_file_at_offset(en_in->bf->file_name, + en_in->btf_type_offset + en_in->bf->types_data_offset, + sizeof(*bt), bt); + if (btf_kind(bt->info) == BTF_KIND_TYPEDEF) { + id = bt->type; + get_btf_type_by_type_id(en_in->bf, id, bt, &en); + return resolve_typedef(en, en_out, bt); + } else { + *en_out = en_in; + } +} + +struct cond_args { + int index; + char *name; +}; + +static bool cond(struct cond_args *c1, struct cond_args *c2) +{ + if (c1->name && c2->name) + /* Check if the member name is what we want */ + return !strcmp(c1->name, c2->name); + else + /* Check if the member index is what we want */ + return c1->index == c2->index; +} + +static bool get_internal_member_info(struct name_entry *en, int base_position, + int *global_index, struct cond_args *tar_arg, + struct member_info *mi, bool initial_dive) +{ + struct btf_type bt, sub_bt; + int member_num; + char *member_array_buf = NULL; + int i; + struct btf_member *bm; + struct btf_array *ba; + int bm_position; + struct name_entry *sub_en; + bool res; + struct cond_args cur_arg = {0}; + + read_file_at_offset(en->bf->file_name, + en->btf_type_offset + en->bf->types_data_offset, + sizeof(bt), &bt); // this struct + if (initial_dive || + ((!en->name || en->name[0] == '\0') && + ((btf_kind(bt.info) == BTF_KIND_STRUCT) || + (btf_kind(bt.info) == BTF_KIND_UNION)))) { + /* anonymous struct/union, dive into */ + member_num = btf_vlen(bt.info); + member_array_buf = calloc(member_num, sizeof(struct btf_member)); + if (!member_array_buf) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + return false; + } + read_file_at_offset(en->bf->file_name, + en->btf_type_offset + en->bf->types_data_offset + sizeof(bt), + member_num *sizeof(struct btf_member), member_array_buf); + for (i = 0, bm = (struct btf_member *)member_array_buf; + i < member_num; i++) { + if (btf_kind_flag(bt.info)) { + bm_position = base_position + + btf_member_bit_offset(bm[i].offset); + mi->bits = btf_member_bitfield_size(bm[i].offset); + } else { + bm_position = base_position + + bm[i].offset; + } + mi->sname = get_str_by_name_off(en->bf, bm[i].name_off); + get_btf_type_by_type_id(en->bf, bm[i].type, + &sub_bt, &sub_en); + // Dive into this member + res = get_internal_member_info(sub_en, bm_position, global_index, + tar_arg, mi, false); + if (res) { + free(member_array_buf); + return res; + } + } + free(member_array_buf); + return false; + } + + cur_arg.index = *global_index; + cur_arg.name = mi->sname; + if (cond(&cur_arg, tar_arg)) { + mi->bit_pos = base_position; + resolve_typedef(en, &sub_en, &bt); + mi->uniq_id = id_to_uniq_id(sub_en->id, sub_en->bf); + if (btf_kind(bt.info) == BTF_KIND_PTR) { + /* + * BUG? No pointer size in btf, + * 32bit btf target on 64bit machine + */ + mi->size = sizeof(void *); + mi->type = "char *"; + } else if (btf_kind(bt.info) == BTF_KIND_ARRAY) { + en = sub_en; + ba = (struct btf_array *)malloc(sizeof(struct btf_array)); + if (!ba) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + return false; + } + read_file_at_offset(en->bf->file_name, + en->btf_type_offset + en->bf->types_data_offset + sizeof(bt), + sizeof(struct btf_array), ba); + mi->size = ba->nelems; // array elements + get_btf_type_by_type_id(en->bf, ba->type, &sub_bt, &sub_en); + resolve_typedef(sub_en, &en, &bt); + free(ba); + mi->size *= bt.size; // element size + mi->type = NULL; // "char [64]? Leave it NULL for now" + } else { + mi->size = bt.size; + mi->type = get_str_by_name_off(sub_en->bf, bt.name_off); + } + return true; + } else { + (*global_index)++; + return false; + } +} + +static bool get_member_info_by_index(struct name_entry *en, int target_index, + struct member_info *mi) +{ + int g_index = 1; + struct cond_args args = {0}; + args.index = target_index; + memset(mi, 0, sizeof(*mi)); + return get_internal_member_info(en, 0, &g_index, &args, mi, true); +} + +static bool get_member_info_by_member_name(struct name_entry *en, char *member_name, + struct member_info *mi) +{ + int g_index = 1; + struct cond_args args = {0}; + args.name = member_name; + memset(mi, 0, sizeof(*mi)); + return get_internal_member_info(en, 0, &g_index, &args, mi, true); +} + +/* + * Entry for query struct members + * Return: struct size, mi_out: member details + */ +uint32_t get_struct_member_by_name(char *struct_name, char *member_name, + struct member_info *mi_out) +{ + struct name_entry *en; + struct btf_type bt = {0}; + int type = BTF_KIND_STRUCT; + + en = search_name_by_cond(struct_name, is_type, (void *)&type, (void *)&bt); + if (!en) + goto out; + if (get_member_info_by_member_name(en, member_name, mi_out)) + return bt.size; +out: + return 0; +} + +/* + * Entry for query type members, similar as above + * Return: found-the-type, mi_out: member details + */ +static uint32_t uniq_id_to_id(uint32_t, struct btf_file **); +bool get_type_member_by_index(uint64_t type_uniq_id, int member_index, + struct member_info *mi_out) +{ + uint32_t id; + struct btf_file *bf; + + id = uniq_id_to_id((uint32_t)type_uniq_id, &bf); + return get_member_info_by_index(bf->array[id - 1], member_index, mi_out); +} + +uint32_t id_to_uniq_id(uint32_t id, struct btf_file *bf) +{ + int i; + uint32_t uniq_id = 0; + for (i = 0; i < btf_files_array_index; i++) { + if (btf_files_array[i] != bf) + uniq_id += btf_files_array[i]->array_len; + else + return id + uniq_id; + } + __builtin_unreachable(); + assert(false); +} + +static uint32_t uniq_id_to_id(uint32_t uid, struct btf_file **bf) +{ + int i; + + for (i = 0; i < btf_files_array_index; i++) { + if (uid > btf_files_array[i]->array_len) { + uid -= btf_files_array[i]->array_len; + } else { + if (bf) + *bf = btf_files_array[i]; + return uid; + } + + } + __builtin_unreachable(); + assert(false); +} + +// api for eppic +uint32_t get_type_size_by_name(char *type_name, int type, uint32_t *uniq_id) +{ + struct name_entry *en; + struct btf_type bt = {0}; + + en = search_name_by_cond(type_name, is_type, (void *)&type, (void *)&bt); + if (!en) + goto out; + if (uniq_id) + *uniq_id = id_to_uniq_id(en->id, en->bf); + return bt.size; +out: + return 0; +} + +// Caller should prepare bt_out +struct name_entry *get_en_by_uniq_id(uint32_t uniq_id, struct btf_type *bt_out) +{ + uint32_t id; + struct btf_file *bf; + struct name_entry *en; + struct name_entry *en_sub; + + id = uniq_id_to_id((uint32_t)uniq_id, &bf); + en = bf->array[id - 1]; + resolve_typedef(en, &en_sub, bt_out); + return en_sub; +} + +/* Deal with btf file */ +static int btf_file_init(int fd) +{ + struct stat f_stat; + char *buf = NULL; + char proc_path[32]; + char real_path[512]; + int ret = -1; + + memset(real_path, 0, sizeof(real_path)); + if (fstat(fd, &f_stat) < 0) { + fprintf(stderr, "%s: fstat fail!\n", __func__); + goto out; + } + buf = malloc(f_stat.st_size); + if (!buf) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + goto out; + } + + snprintf(proc_path, sizeof(proc_path), "/proc/self/fd/%d", fd); + readlink(proc_path, real_path, sizeof(real_path) - 1); + if (read_file_at_offset(real_path, 0, f_stat.st_size, buf) < 0) + goto out; + + ret = parse_btf_data(real_path, buf, f_stat.st_size); +out: + if (buf) + free(buf); + return ret; +} + +/* Deal with elf file which contains .BTF section */ +static int elf_file_init(int fd) +{ + char proc_path[32]; + char real_path[512]; + Elf *elf = NULL; + Elf_Scn *scn = NULL; + size_t shstrndx; + GElf_Shdr shdr; + Elf_Data *data = NULL; + char *str, *databuf = NULL; + int ret = -1; + + snprintf(proc_path, sizeof(proc_path), "/proc/self/fd/%d", fd); + readlink(proc_path, real_path, sizeof(real_path) - 1); + + if (elf_version(EV_CURRENT) == EV_NONE) + goto elf_err; + elf = elf_begin(fd, ELF_C_READ, NULL); + if (!elf || elf_getshdrstrndx(elf, &shstrndx)) + goto elf_err; + while ((scn = elf_nextscn(elf, scn)) != NULL) { + if (!gelf_getshdr(scn, &shdr)) + continue; + str = elf_strptr(elf, shstrndx, shdr.sh_name); + if (!strcmp(str, ".BTF")) + break; + } + if (!scn) { + fprintf(stderr, "%s: No .BTF found in %s!\n", __func__, real_path); + goto out; + } + + data = elf_rawdata(scn, data); + databuf = malloc(data->d_size); + if (!databuf) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + goto out; + } + memcpy(databuf, data->d_buf, data->d_size); + elf_end(elf); + elf = NULL; + ret = parse_btf_data(real_path, databuf, data->d_size); + goto out; + +elf_err: + fprintf(stderr, "%s: elf error in %s!\n", __func__, real_path); +out: + if (databuf) + free(databuf); + if (elf) + elf_end(elf); + return ret; +} + +/* + * Entry for parse btf file and elf file. + */ +static int file_init(char *name) +{ + int fd = 0, ret = -1; + char buf[4] = {0}; + + /* Will be enlarged automatically */ + if (!btf_files_array) { + btf_files_array = calloc(1, sizeof(struct btf_file *)); + if (!btf_files_array) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + goto out; + } + } + + fd = open(name, O_RDONLY); + if (read_file_at_offset(name, 0, sizeof(buf), buf) < 0) + goto out; + if (*(u_int16_t *)&buf == BTF_MAGIC) { + ret = btf_file_init(fd); + } else if (*(u_int32_t *)&buf == (((u_int32_t)ELFMAG0 << 24) | + ((u_int32_t)ELFMAG1 << 16) | + ((u_int32_t)ELFMAG2 << 8) | + ((u_int32_t)ELFMAG3 << 0))) { + ret = elf_file_init(fd); + } else { + __builtin_unreachable(); + } + +out: + if (fd) + close(fd); + return ret; +} + +/* For pure buffer data, wrap it as a file, and handover to file_init() */ +char temp[] = "/tmp/btf_XXXXXX"; +static int init_btf_from_buf(char *mod_name, char *buf, int size) +{ + int fd; + char name_buf[64]; + int w, got = 0; + static char *temp_dir = NULL; + + if (!temp_dir) + temp_dir = mkdtemp(temp); + snprintf(name_buf, sizeof(name_buf), "%s/%s", temp_dir, mod_name); + fd = open(name_buf, O_RDWR | O_CREAT, S_IRUSR | S_IWUSR); + if (fd < 0) { + fprintf(stderr, "%s: open fail in %s!\n", __func__, name_buf); + return -1; + } + + while (got < size) { + w = pwrite(fd, buf + got, size - got, got); + if (w < 0) { + fprintf(stderr, "%s: pwrite fail in %s!\n", __func__, name_buf); + return -1; + } + got += w; + } + close(fd); + return file_init(name_buf); +} + +int init_kernel_btf(void) +{ + uint64_t size; + char *buf; + int ret; + + uint64_t start_btf = get_kallsyms_value_by_name("__start_BTF"); + uint64_t stop_btf = get_kallsyms_value_by_name("__stop_BTF"); + if (!start_btf || !stop_btf) { + fprintf(stderr, "%s: symbol __start/stop_BTF not found!\n", __func__); + return -1; + } + + size = stop_btf - start_btf; + buf = (char *)malloc(size); + if (!buf) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + return -1; + } + readmem(VADDR, start_btf, buf, size); + ret = init_btf_from_buf("vmlinux", buf, size); + free(buf); + + return ret; +} + +int init_module_btf(void) +{ + uint64_t btf_modules, list; + struct member_info mi; + uint64_t btf = 0, data = 0, module = 0; + int data_size = 0; + char *btf_buf = NULL; + char *modname = NULL; + + btf_modules = get_kallsyms_value_by_name("btf_modules"); + if (!btf_modules) + /* Maybe module is not enabled, this is not an error */ + return 0; + + INIT_MEMBER_OFF_SIZE(btf_module, list); + INIT_MEMBER_OFF_SIZE(btf_module, btf); + INIT_MEMBER_OFF_SIZE(btf_module, module); + INIT_MEMBER_OFF_SIZE(module, name); + INIT_MEMBER_OFF_SIZE(btf, data); + INIT_MEMBER_OFF_SIZE(btf, data_size); + modname = (char *)malloc(GET_MEMBER_SIZE(module, name)); + if (!modname) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + goto out; + } + + for (list = next_list(btf_modules); list != btf_modules; list = next_list(list)) { + readmem(VADDR, list - GET_MEMBER_OFF(btf_module, list) + + GET_MEMBER_OFF(btf_module, btf), + &btf, GET_MEMBER_SIZE(btf_module, btf)); + readmem(VADDR, list - GET_MEMBER_OFF(btf_module, list) + + GET_MEMBER_OFF(btf_module, module), + &module, GET_MEMBER_SIZE(btf_module, module)); + readmem(VADDR, module + GET_MEMBER_OFF(module, name), + modname, GET_MEMBER_SIZE(module, name)); + readmem(VADDR, btf + GET_MEMBER_OFF(btf, data), + &data, GET_MEMBER_SIZE(btf, data)); + readmem(VADDR, btf + GET_MEMBER_OFF(btf, data_size), + &data_size, GET_MEMBER_SIZE(btf, data_size)); + btf_buf = (char *)malloc(data_size); + if (!btf_buf) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + goto out; + } + readmem(VADDR, data, btf_buf, data_size); + if (init_btf_from_buf(modname, btf_buf, data_size)) + goto out; + free(btf_buf); + } + return 0; +out: + if (modname) + free(modname); + if (btf_buf) + free(btf_buf); + return -1; +} + +void cleanup_btf(void) +{ + int bf_index, i; + struct btf_file *bf; + struct name_entry *en, *en_tmp; + DIR *temp_dir; + struct dirent *entry; + char path[512]; + + /* Free no-hashtable-installed elements */ + for (bf_index = 0; bf_index < btf_files_array_index; bf_index++) { + bf = btf_files_array[bf_index]; + if (bf && bf->array) { + for (i = 0; i < bf->array_len; i++) { + if (!bf->array[i]->name || !bf->array[i]->name[0]) + free(bf->array[i]); + } + } + } + + /* Free the hashtable-installed elements */ + for (i = 0; i < NAME_HASH; i++) { + for (en = name_hash_table[i]; en;) { + en_tmp = en; + en = en->name_hash_next; + free(en_tmp); + } + } + + /* Cleanup anything else */ + for (bf_index = 0; bf_index < btf_files_array_index; bf_index++) { + bf = btf_files_array[bf_index]; + if (bf && bf->array) { + free(bf->array); + } + if (bf && bf->file_name) + free(bf->file_name); + if (bf && bf->str_cache) + free(bf->str_cache); + if (bf) + free(bf); + } + + if (btf_files_array) + free(btf_files_array); + + /* Cleanup the dir /tmp/btf_XXXXXX */ + temp_dir = opendir(temp); + if (!temp_dir) + return; + while ((entry = readdir(temp_dir)) != NULL) { + if (!strcmp(entry->d_name, ".") || !strcmp(entry->d_name, "..")) + continue; + snprintf(path, sizeof(path), "%s/%s", temp, entry->d_name); + if (remove(path)) { + fprintf(stderr, "%s: fail del %s!\n", __func__, path); + /* In case too many fail messages of files in the dir */ + return; + } + } + closedir(temp_dir); + rmdir(temp); +} diff --git a/btf.h b/btf.h new file mode 100644 index 0000000..a0d13e6 --- /dev/null +++ b/btf.h @@ -0,0 +1,176 @@ +#ifndef _BTF_H +#define _BTF_H +#include <stdint.h> +#include <stdbool.h> + +typedef uint8_t __u8; +typedef uint16_t __u16; +typedef uint32_t __u32; +typedef int32_t __s32; + +#define BTF_MAGIC 0xeb9f + +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ + BTF_KIND_TYPE_TAG = 18, /* Type Tag */ + BTF_KIND_ENUM64 = 19, /* Enumeration up to 64-bit values */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; + +struct btf_type { + __u32 name_off; + + /* "info" bits arrangement + * bits 0-15: vlen (e.g. # of struct's members) + * bits 16-23: unused + * bits 24-27: kind (e.g. int, ptr, array...etc) + * bits 28-30: unused + * bit 31: kind_flag, currently used by + * struct, union and fwd + */ + __u32 info; + + /* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, + * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + __u32 hdr_len; + + /* All offsets are in bytes relative to the end of this header */ + __u32 type_off; /* offset of type section */ + __u32 type_len; /* length of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ +}; + +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +struct btf_member { + __u32 name_off; + __u32 type; + /* If the type info kind_flag is set, the btf_member offset + * contains both member bitfield size and bit offset. The + * bitfield size is set for bitfield members. If the type + * info kind_flag is not set, the offset contains only bit + * offset. + */ + __u32 offset; +}; + +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +struct btf_enum64 { + __u32 name_off; + __u32 val_lo32; + __u32 val_hi32; +}; + +struct btf_param { + __u32 name_off; + __u32 type; +}; + +struct btf_var { + __u32 linkage; +}; + +struct btf_var_secinfo { + __u32 type; + __u32 offset; + __u32 size; +}; + +struct btf_decl_tag { + __s32 component_idx; +}; + +/*************************************/ +struct btf_file { + char *file_name; + char *str_cache; + uint32_t str_cache_len; + uint32_t types_data_offset; + uint32_t array_len; + struct name_entry **array; +}; + +struct name_entry { + union { + uint32_t btf_type_offset; + uint32_t p_id; + }; + + uint32_t id; + char *name; + struct btf_file *bf; + struct name_entry *name_hash_next; +}; + +struct member_info { + char *sname; // member name + char *type; // member type: int, long etc + uint32_t bit_pos; // member position in bits + uint32_t bits; // member width in bits + uint32_t size; // member size in bytes + int uniq_id; // uniq_id of btf +}; + +/*************************************/ + +int init_kernel_btf(void); +uint32_t get_struct_member_by_name(char *, char *, struct member_info *); +bool get_type_member_by_index(uint64_t, int, struct member_info *); +uint32_t get_type_size_by_name(char *, int, uint32_t *); +struct name_entry *get_en_by_uniq_id(uint32_t, struct btf_type *); +void resolve_typedef(struct name_entry *, struct name_entry **, struct btf_type *); +int get_btf_type_by_type_id(struct btf_file *, uint32_t, + struct btf_type *, struct name_entry **); +uint32_t id_to_uniq_id(uint32_t, struct btf_file *); +int init_module_btf(void); +void cleanup_btf(void); + +static inline uint32_t btf_kind(uint32_t info) +{ + return (info & 0x1F000000) >> 24; +} + +#endif /* _BTF_H */ diff --git a/kallsyms.c b/kallsyms.c new file mode 100644 index 0000000..89f6bfa --- /dev/null +++ b/kallsyms.c @@ -0,0 +1,371 @@ +#include <stdint.h> +#include <stdbool.h> +#include <string.h> +#include <assert.h> +#include "makedumpfile.h" +#include "kallsyms.h" +#include "btf.h" + +static uint32_t *kallsyms_offsets = NULL; +static uint16_t *kallsyms_token_index = NULL; +static uint8_t *kallsyms_token_table = NULL; +static uint8_t *kallsyms_names = NULL; +static unsigned long kallsyms_relative_base = 0; +static unsigned int kallsyms_num_syms = 0; + +#define NAME_HASH 512 +static struct syment *symtable = NULL; +static struct syment *name_hash_table[NAME_HASH] = {0}; + +static uint64_t absolute_percpu(uint64_t base, int32_t val) +{ + if (val >= 0) + return (uint64_t)val; + else + return base - 1 - val; +} + +static void *get_syment_next(void *entry) +{ + return ((struct syment *)entry)->name_hash_next; +} + +static void set_syment_next(void *entry, void *next) +{ + ((struct syment *)entry)->name_hash_next = next; +} + +static unsigned int name_hash_index(char *name) +{ + return hash_index(name, NAME_HASH); +} + +static void name_hash_install(struct syment *en) +{ + hash_install((void **)name_hash_table, NAME_HASH, en, en->name, + get_syment_next, set_syment_next); +} + +struct syment *search_kallsyms_by_name(char *name) +{ + unsigned int index; + struct syment *sp; + + index = name_hash_index(name); + for (sp = name_hash_table[index]; sp; sp = sp->name_hash_next) { + if (!strcmp(name, sp->name)) { + return sp; + } + } + return sp; +} + +uint64_t get_kallsyms_value_by_name(char *name) +{ + struct syment *sp; + + sp = search_kallsyms_by_name(name); + if (!sp) + return 0; + return sp->value; +} + +#define BUFLEN 512 +int parse_kernel_kallsyms(void) +{ + char buf[BUFLEN]; + int len = 0; + int index = 0, i; + uint8_t *compressd_data; + uint8_t *uncompressd_data; + uint64_t stext; + + symtable = calloc(kallsyms_num_syms, sizeof(struct syment)); + if (!symtable) + goto no_mem; + + for (i = 0; i < kallsyms_num_syms; i++) { + memset(buf, 0, BUFLEN); + len = kallsyms_names[index++]; + compressd_data = &kallsyms_names[index]; + index += len; + while (len--) { + uncompressd_data = &kallsyms_token_table[kallsyms_token_index[*compressd_data]]; + assert(strlen(buf) + strlen((char *)uncompressd_data) < BUFLEN); + strcat(buf, (char *)uncompressd_data); + compressd_data++; + } + symtable[i].value = kallsyms_offsets[i]; + symtable[i].type = buf[0]; + symtable[i].name = strdup(&buf[1]); + if (!symtable[i].name) + goto no_mem; + name_hash_install(&symtable[i]); + } + + /* Now refresh the absolute each kallsyms address */ + stext = get_kallsyms_value_by_name("_stext"); + if (SYMBOL(_stext) == absolute_percpu(kallsyms_relative_base, stext)) { + for (i = 0; i < kallsyms_num_syms; i++) { + symtable[i].value = absolute_percpu(kallsyms_relative_base, + symtable[i].value); + } + } else if (SYMBOL(_stext) == kallsyms_relative_base + stext) { + for (i = 0; i < kallsyms_num_syms; i++) { + symtable[i].value += kallsyms_relative_base; + } + } else { + fprintf(stderr, "%s: Wrong calculate kallsyms symbol value!\n", __func__); + goto out; + } + + return 0; +no_mem: + fprintf(stderr, "%s: Not enough memory!\n", __func__); +out: + return -1; +} + +static bool vmcore_info_ready = false; + +int read_vmcoreinfo_kallsyms(void) +{ + READ_SYMBOL("kallsyms_names", kallsyms_names); + READ_SYMBOL("kallsyms_num_syms", kallsyms_num_syms); + READ_SYMBOL("kallsyms_token_table", kallsyms_token_table); + READ_SYMBOL("kallsyms_token_index", kallsyms_token_index); + READ_SYMBOL("kallsyms_offsets", kallsyms_offsets); + READ_SYMBOL("kallsyms_relative_base", kallsyms_relative_base); + vmcore_info_ready = true; + return true; +} + +int init_kernel_kallsyms(void) +{ + const int token_index_size = (UINT8_MAX + 1) * sizeof(uint16_t); + uint64_t last_token, len; + char data; + int i; + int ret = -1; + + if (vmcore_info_ready == false) { + fprintf(stderr, "%s: vmcoreinfo not ready for kallsyms!\n", + __func__); + return ret; + } + + readmem(VADDR, SYMBOL(kallsyms_num_syms), &kallsyms_num_syms, + sizeof(kallsyms_num_syms)); + readmem(VADDR, SYMBOL(kallsyms_relative_base), &kallsyms_relative_base, + sizeof(kallsyms_relative_base)); + + kallsyms_offsets = malloc(sizeof(uint32_t) * kallsyms_num_syms); + if (!kallsyms_offsets) + goto no_mem; + readmem(VADDR, SYMBOL(kallsyms_offsets), kallsyms_offsets, + kallsyms_num_syms * sizeof(uint32_t)); + + kallsyms_token_index = malloc(token_index_size); + if (!kallsyms_token_index) + goto no_mem; + readmem(VADDR, SYMBOL(kallsyms_token_index), kallsyms_token_index, + token_index_size); + + last_token = SYMBOL(kallsyms_token_table) + kallsyms_token_index[UINT8_MAX]; + do { + readmem(VADDR, last_token++, &data, 1); + } while(data); + len = last_token - SYMBOL(kallsyms_token_table); + kallsyms_token_table = malloc(len); + if (!kallsyms_token_table) + goto no_mem; + readmem(VADDR, SYMBOL(kallsyms_token_table), kallsyms_token_table, len); + + for (len = 0, i = 0; i < kallsyms_num_syms; i++) { + readmem(VADDR, SYMBOL(kallsyms_names) + len, &data, 1); + if (data & 0x80) { + printf("BUG! long sym name"); + goto out; + } + len += data + 1; + } + kallsyms_names = malloc(len); + if (!kallsyms_names) + goto no_mem; + readmem(VADDR, SYMBOL(kallsyms_names), kallsyms_names, len); + + ret = parse_kernel_kallsyms(); + goto out; + +no_mem: + fprintf(stderr, "%s: Not enough memory!\n", __func__); +out: + if (kallsyms_offsets) + free(kallsyms_offsets); + if (kallsyms_token_index) + free(kallsyms_token_index); + if (kallsyms_token_table) + free(kallsyms_token_table); + if (kallsyms_names) + free(kallsyms_names); + return ret; +} + +uint64_t next_list(uint64_t list) +{ + static int list_head_next_offset = 0; + static int list_head_next_size = 0; + + struct member_info mi; + uint64_t next = 0; + + if (!list_head_next_size) { + get_struct_member_by_name("list_head", "next", &mi); + list_head_next_size = mi.size; + list_head_next_offset = mi.bit_pos / 8; + } + readmem(VADDR, list + list_head_next_offset, &next, list_head_next_size); + return next; +} + +int init_module_kallsyms(void) +{ + struct member_info mi; + uint64_t modules, list, value = 0, symtab = 0, + strtab = 0, typetab = 0; + uint32_t st_name = 0; + int num_symtab, i, j; + struct syment *mod_syment; + char symname[512], ch; + int ret = -1; + + modules = get_kallsyms_value_by_name("modules"); + if (!modules) { + /* Not a failure if no module enabled */ + ret = 0; + goto out; + } + + INIT_MEMBER_OFF_SIZE(module, list); + INIT_MEMBER_OFF_SIZE(module, core_kallsyms); + INIT_MEMBER_OFF_SIZE(mod_kallsyms, symtab); + INIT_MEMBER_OFF_SIZE(mod_kallsyms, num_symtab); + INIT_MEMBER_OFF_SIZE(mod_kallsyms, strtab); + INIT_MEMBER_OFF_SIZE(mod_kallsyms, typetab); + INIT_MEMBER_OFF_SIZE(elf64_sym, st_name); + INIT_MEMBER_OFF_SIZE(elf64_sym, st_value); + + for (list = next_list(modules); list != modules; list = next_list(list)) { + readmem(VADDR, list - GET_MEMBER_OFF(module, list) + + GET_MEMBER_OFF(module, core_kallsyms) + + GET_MEMBER_OFF(mod_kallsyms, num_symtab), + &num_symtab, GET_MEMBER_SIZE(mod_kallsyms, num_symtab)); + readmem(VADDR, list - GET_MEMBER_OFF(module, list) + + GET_MEMBER_OFF(module, core_kallsyms) + + GET_MEMBER_OFF(mod_kallsyms, symtab), + &symtab, GET_MEMBER_SIZE(mod_kallsyms, symtab)); + readmem(VADDR, list - GET_MEMBER_OFF(module, list) + + GET_MEMBER_OFF(module, core_kallsyms) + + GET_MEMBER_OFF(mod_kallsyms, strtab), + &strtab, GET_MEMBER_SIZE(mod_kallsyms, strtab)); + readmem(VADDR, list - GET_MEMBER_OFF(module, list) + + GET_MEMBER_OFF(module, core_kallsyms) + + GET_MEMBER_OFF(mod_kallsyms, typetab), + &typetab, GET_MEMBER_SIZE(mod_kallsyms, typetab)); + for (i = 0; i < num_symtab; i++) { + j = 0; + readmem(VADDR, symtab + i * GET_STRUCT_SIZE(elf64_sym, st_value) + + GET_MEMBER_OFF(elf64_sym, st_value), + &value, GET_MEMBER_SIZE(elf64_sym, st_value)); + readmem(VADDR, symtab + i * GET_STRUCT_SIZE(elf64_sym, st_name) + + GET_MEMBER_OFF(elf64_sym, st_name), + &st_name, GET_MEMBER_SIZE(elf64_sym, st_name)); + do { + readmem(VADDR, strtab + st_name + j++, &ch, 1); + } while (ch != '\0'); + if (j == 1) + /* Skip empty string */ + continue; + assert(j <= sizeof(symname)); + mod_syment = (struct syment *)calloc(1, sizeof(struct syment)); + if (!mod_syment) + goto no_mem; + readmem(VADDR, strtab + st_name, symname, j); + mod_syment->name = strdup(symname); + if (!mod_syment->name) { + free(mod_syment); + goto no_mem; + } + mod_syment->value = value; + readmem(VADDR, typetab + i, &mod_syment->type, 1); + name_hash_install(mod_syment); + } + } + ret = 0; + goto out; +no_mem: + /* Hashtable will be cleaned later */ + fprintf(stderr, "%s: Not enough memory!\n", __func__); +out: + return ret; +} + +void cleanup_kallsyms(void) +{ + struct syment *en, *en_tmp; + int i; + + /* Free the module's kallsyms first */ + for (i = 0; i < NAME_HASH; i++) { + for (en = name_hash_table[i]; en;) { + en_tmp = en; + en = en->name_hash_next; + if (en_tmp <= &symtable[kallsyms_num_syms - 1] && + en_tmp >= &symtable[0]) + continue; + free(en_tmp->name); + free(en_tmp); + } + } + + /* Free the kernel ones */ + for (i = 0; i < kallsyms_num_syms; i++) { + if (symtable[i].name) + free(symtable[i].name); + } + free(symtable); +} + +/* Hash table utils */ +unsigned int hash_index(const char *name, unsigned int hash_size) +{ + unsigned int len, value; + + len = strlen(name); + value = name[len - 1] * name[len / 2]; + + return (name[0] ^ value) % hash_size; +} + +void hash_install(void **hash_table, unsigned int hash_size, + void *entry, const char *name, + void *(*get_next)(void *), + void (*set_next)(void *, void *)) +{ + unsigned int index = hash_index(name, hash_size); + void *sp = hash_table[index]; + + assert(index < hash_size); + if (sp == NULL) { + hash_table[index] = entry; + } else { + while (sp) { + if (get_next(sp)) { + sp = get_next(sp); + } else { + set_next(sp, entry); + break; + } + } + } +} \ No newline at end of file diff --git a/kallsyms.h b/kallsyms.h new file mode 100644 index 0000000..96ea970 --- /dev/null +++ b/kallsyms.h @@ -0,0 +1,42 @@ +#ifndef _KALLSYMS_H +#define _KALLSYMS_H + +#include <stdint.h> + +struct syment { + uint64_t value; + char *name; + struct syment *name_hash_next; + char type; +}; + +int init_kernel_kallsyms(void); +int read_vmcoreinfo_kallsyms(void); +int parse_kernel_kallsyms(void); +struct syment *search_kallsyms_by_name(char *); +uint64_t next_list(uint64_t); +uint64_t get_kallsyms_value_by_name(char *); +int init_module_kallsyms(void); +void cleanup_kallsyms(void); +int read_vmcoreinfo_kallsyms(void); + +struct member_off_size { + int m_off; + int m_size; + int s_size; +}; +#define QUATE(x) #x +#define INIT_MEMBER_OFF_SIZE(S, M) \ + struct member_off_size S##_##M; \ + S##_##M.s_size = get_struct_member_by_name(QUATE(S), QUATE(M), &mi); \ + S##_##M.m_off = mi.bit_pos / 8; \ + S##_##M.m_size = mi.size; +#define GET_MEMBER_OFF(S, M) (S##_##M.m_off) +#define GET_MEMBER_SIZE(S, M) (S##_##M.m_size) +#define GET_STRUCT_SIZE(S, M) (S##_##M.s_size) + +unsigned int hash_index(const char *, unsigned int); +void hash_install(void **, unsigned int, void *, const char *, + void *(*)(void *), void (*)(void *, void *)); + +#endif /* _KALLSYMS_H */ \ No newline at end of file diff --git a/makedumpfile.c b/makedumpfile.c index 33fad32..cdfcfeb 100644 --- a/makedumpfile.c +++ b/makedumpfile.c @@ -27,6 +27,7 @@ #include <limits.h> #include <assert.h> #include <zlib.h> +#include "kallsyms.h" struct symbol_table symbol_table; struct size_table size_table; @@ -3103,6 +3104,8 @@ read_vmcoreinfo_from_vmcore(off_t offset, unsigned long size, int flag_xen_hv) if (!read_vmcoreinfo()) goto out; } + read_vmcoreinfo_kallsyms(); + close_vmcoreinfo(); ret = TRUE; diff --git a/makedumpfile.h b/makedumpfile.h index 944397a..cc474ad 100644 --- a/makedumpfile.h +++ b/makedumpfile.h @@ -257,6 +257,7 @@ static inline int string_exists(char *s) { return (s ? TRUE : FALSE); } #define UINT(ADDR) *((unsigned int *)(ADDR)) #define ULONG(ADDR) *((unsigned long *)(ADDR)) #define ULONGLONG(ADDR) *((unsigned long long *)(ADDR)) +#define VOID_PTR(ADDR) *((void **)(ADDR)) /* @@ -1917,6 +1918,16 @@ struct symbol_table { * symbols on sparc64 arch */ unsigned long long vmemmap_table; + + /* + * kallsyms related + */ + unsigned long long kallsyms_names; + unsigned long long kallsyms_num_syms; + unsigned long long kallsyms_token_table; + unsigned long long kallsyms_token_index; + unsigned long long kallsyms_offsets; + unsigned long long kallsyms_relative_base; }; struct size_table { -- 2.47.0

The majority of maple tree code is copied from crash utility. Since currenty it is not needed by makedumpfile, maple tree is integrated with eppic extension only. The minor change of maple tree code are: 1) a cache buffer for maple tree data because eppic script cannot allocate a buffer currently; 2) an interface for eppic script. Signed-off-by: Tao Liu <ltao(a)redhat.com&gt; --- Makefile | 4 +- eppic_maple.c | 431 ++++++++++++++++++++++++++++++++++++++++++++++++++ eppic_maple.h | 8 + 3 files changed, 441 insertions(+), 2 deletions(-) create mode 100644 eppic_maple.c create mode 100644 eppic_maple.h diff --git a/Makefile b/Makefile index fbc9f5b..216749f 100644 --- a/Makefile +++ b/Makefile @@ -121,8 +121,8 @@ makedumpfile: $(SRC_BASE) $(OBJ_PART) $(OBJ_ARCH) -e "s/@VERSION@/$(VERSION)/" \ $(VPATH)makedumpfile.conf.5.in > $(VPATH)makedumpfile.conf.5 -eppic_makedumpfile.so: extension_eppic.c - $(CC) $(CFLAGS) $(LDFLAGS) -shared -rdynamic -o $@ extension_eppic.c -fPIC -leppic -ltinfo +eppic_makedumpfile.so: extension_eppic.c eppic_maple.c + $(CC) $(CFLAGS) $(LDFLAGS) -shared -rdynamic -o $@ $^ -fPIC -leppic -ltinfo clean: rm -f $(OBJ) $(OBJ_PART) $(OBJ_ARCH) makedumpfile makedumpfile.8 makedumpfile.conf.5 diff --git a/eppic_maple.c b/eppic_maple.c new file mode 100644 index 0000000..ee8d23d --- /dev/null +++ b/eppic_maple.c @@ -0,0 +1,431 @@ + +#include <stdbool.h> +#include <limits.h> +#include <sys/types.h> +#include <assert.h> +#include "makedumpfile.h" +#include "extension_eppic.h" +#include "btf.h" +#include "kallsyms.h" +#include "erase_info.h" + +enum maple_type { + maple_dense, + maple_leaf_64, + maple_range_64, + maple_arange_64, +}; + +#define MAPLE_TREE_COUNT (1) +#define MAPLE_TREE_SEARCH (2) +#define MAPLE_TREE_DUMP (3) +#define MAPLE_TREE_GATHER (4) +#define MAPLE_TREE_DUMP_CB (5) + +#define MAPLE_NODE_MASK 255UL +#define MT_FLAGS_HEIGHT_OFFSET 0x02 +#define MT_FLAGS_HEIGHT_MASK 0x7C +#define MAPLE_NODE_TYPE_MASK 0x0F +#define MAPLE_NODE_TYPE_SHIFT 0x03 +#define MAPLE_BUFSIZE 512 + +static unsigned char *mt_slots = NULL; + +static ulong mt_max[4] = {0}; + +static long g_maple_tree; +static long g_maple_node; +static long g_maple_tree_ma_root; +static long g_maple_node_ma64; +static long g_maple_node_mr64; +static long g_maple_node_slot; +static long g_maple_arange_64_pivot; +static long g_maple_arange_64_slot; +static long g_maple_range_64_pivot; +static long g_maple_range_64_slot; + +/********************maple tree internal**************************/ + +static inline bool xa_is_internal(ulong entry) +{ + return (entry & 3) == 2; +} + +static inline bool xa_is_node(ulong entry) +{ + return xa_is_internal(entry) && entry > 4096; +} + +static inline ulong mte_to_node(ulong maple_enode_entry) +{ + return maple_enode_entry & ~MAPLE_NODE_MASK; +} + +static inline enum maple_type mte_node_type(ulong maple_enode_entry) +{ + return (maple_enode_entry >> MAPLE_NODE_TYPE_SHIFT) & + MAPLE_NODE_TYPE_MASK; +} + +static inline ulong mt_slot(void **slots, unsigned char offset) +{ + return (ulong)slots[offset]; +} + +static inline bool ma_is_leaf(const enum maple_type type) +{ + return type < maple_range_64; +} + +struct do_maple_tree_info { + ulong count; + void *data; +}; + +struct maple_tree_ops { + void (*entry)(ulong node, void *private); + void *private; +}; + +static void do_mt_range64(ulong, ulong, ulong, + struct maple_tree_ops *); +static void do_mt_arange64(ulong, ulong, ulong, + struct maple_tree_ops *); +static void do_mt_entry(ulong, struct maple_tree_ops *); +static void do_mt_node(ulong, ulong, ulong, + struct maple_tree_ops *); + +static inline bool mte_is_leaf(ulong maple_enode_entry) +{ + return ma_is_leaf(mte_node_type(maple_enode_entry)); +} + +static void do_mt_range64(ulong entry, ulong min, ulong max, + struct maple_tree_ops *ops) +{ + ulong maple_node_m_node = mte_to_node(entry); + char node_buf[MAPLE_BUFSIZE]; + bool leaf = mte_is_leaf(entry); + ulong first = min, last; + int i; + char *mr64_buf; + + READMEM(VADDR, maple_node_m_node, node_buf, g_maple_node); + + mr64_buf = node_buf + g_maple_node_mr64; + + for (i = 0; i < mt_slots[maple_range_64]; i++) { + last = max; + + if (i < (mt_slots[maple_range_64] - 1)) + last = ULONG(mr64_buf + g_maple_range_64_pivot + + sizeof(ulong) * i); + + else if (!VOID_PTR(mr64_buf + g_maple_range_64_slot + + sizeof(void *) * i) && + max != mt_max[mte_node_type(entry)]) + break; + if (last == 0 && i > 0) + break; + if (leaf) + do_mt_entry(mt_slot((void **)(mr64_buf + + g_maple_range_64_slot), i), + ops); + else if (VOID_PTR(mr64_buf + g_maple_range_64_slot + + sizeof(void *) * i)) { + do_mt_node(mt_slot((void **)(mr64_buf + + g_maple_range_64_slot), i), + first, last, ops); + } + + if (last == max) + break; + if (last > max) { + printf("node %p last (%lu) > max (%lu) at pivot %d!\n", + mr64_buf, last, max, i); + break; + } + first = last + 1; + } +} + +static void do_mt_arange64(ulong entry, ulong min, ulong max, + struct maple_tree_ops *ops) +{ + ulong maple_node_m_node = mte_to_node(entry); + char node_buf[MAPLE_BUFSIZE]; + bool leaf = mte_is_leaf(entry); + ulong first = min, last; + int i; + char *ma64_buf; + + READMEM(VADDR, maple_node_m_node, node_buf, g_maple_node); + + ma64_buf = node_buf + g_maple_node_ma64; + + for (i = 0; i < mt_slots[maple_arange_64]; i++) { + last = max; + + if (i < (mt_slots[maple_arange_64] - 1)) + last = ULONG(ma64_buf + g_maple_arange_64_pivot + + sizeof(ulong) * i); + else if (!VOID_PTR(ma64_buf + g_maple_arange_64_slot + + sizeof(void *) * i)) + break; + if (last == 0 && i > 0) + break; + + if (leaf) + do_mt_entry(mt_slot((void **)(ma64_buf + + g_maple_arange_64_slot), i), + ops); + else if (VOID_PTR(ma64_buf + g_maple_arange_64_slot + + sizeof(void *) * i)) { + do_mt_node(mt_slot((void **)(ma64_buf + + g_maple_arange_64_slot), i), + first, last, ops); + } + + if (last == max) + break; + if (last > max) { + printf("node %p last (%lu) > max (%lu) at pivot %d!\n", + ma64_buf, last, max, i); + break; + } + first = last + 1; + } +} + +static void do_mt_entry(ulong entry, struct maple_tree_ops *ops) +{ + if (ops->entry && entry) + ops->entry(entry, ops->private); +} + +static void do_mt_node(ulong entry, ulong min, ulong max, + struct maple_tree_ops *ops) +{ + ulong maple_node = mte_to_node(entry); + int i, type = mte_node_type(entry); + char node_buf[MAPLE_BUFSIZE]; + + READMEM(VADDR, maple_node, node_buf, g_maple_node); + + switch (type) { + case maple_dense: + for (i = 0; i < mt_slots[maple_dense]; i++) { + if (min + i > max) + printf("OUT OF RANGE: "); + do_mt_entry(mt_slot((void **)(node_buf + + g_maple_node_slot), i), ops); + } + break; + case maple_leaf_64: + case maple_range_64: + do_mt_range64(entry, min, max, ops); + break; + case maple_arange_64: + do_mt_arange64(entry, min, max, ops); + break; + default: + printf(" UNKNOWN TYPE\n"); + } +} + +static int do_maple_tree_traverse(ulong ptr, struct maple_tree_ops *ops) +{ + char tree_buf[MAPLE_BUFSIZE]; + ulong entry; + + assert(MAPLE_BUFSIZE >= g_maple_tree); + + READMEM(VADDR, ptr, tree_buf, g_maple_tree); + entry = ULONG(tree_buf + g_maple_tree_ma_root); + + if (!xa_is_node(entry)) + do_mt_entry(entry, ops); + else if (entry) { + do_mt_node(entry, 0, mt_max[mte_node_type(entry)], ops); + } + + return 0; +} + +static void do_maple_tree_count(ulong node, void *private) +{ + struct do_maple_tree_info *info = private; + info->count++; +} + +static void do_maple_tree_gather(ulong node, void *private) +{ + struct do_maple_tree_info *info = private; + ulong *buf = info->data; + + buf[info->count] = node; + info->count++; +} + +static ulong do_maple_tree(ulong root, int flag, ulong *buf) +{ + struct do_maple_tree_info info = { + .count = 0, + .data = buf, + }; + struct maple_tree_ops ops = { + .private = &info, + }; + + switch (flag) + { + case MAPLE_TREE_COUNT: + ops.entry = do_maple_tree_count; + break; + + case MAPLE_TREE_GATHER: + ops.entry = do_maple_tree_gather; + break; + + default: + fprintf(stderr, "do_maple_tree: invalid flag: %x\n", flag); + return 0; + } + + do_maple_tree_traverse(root, &ops); + return info.count; +} + +#define MAPLE_SIZE_INIT(X, Y) \ +do { \ + if (is_btf) { \ + if ((X = cb->get_type_size_by_name(Y, BTF_KIND_STRUCT, NULL)) \ + == 0) \ + return FALSE; \ + } else { \ + if ((X = cb->get_structure_size(Y, DWARF_INFO_GET_STRUCT_SIZE)) \ + == FAILED_DWARFINFO) \ + return FALSE; \ + } \ +} while (0) + +#define MAPLE_OFFSET_INIT(X, Y, Z) \ +do { \ + if (is_btf) { \ + struct member_info mi; \ + memset(&mi, 0, sizeof(mi)); \ + if (cb->get_struct_member_by_name(Y, Z, &mi) == 0) \ + return FALSE; \ + X = mi.bit_pos / 8; \ + } else { \ + if ((X = cb->get_member_offset(Y, Z, DWARF_INFO_GET_MEMBER_OFFSET)) \ + == FAILED_DWARFINFO) \ + return FALSE; \ + } \ +} while (0) + +/*******************maple tree api***************************/ + +int maple_init(bool is_btf) +{ + int array_len = 16; + + MAPLE_SIZE_INIT(g_maple_tree, "maple_tree"); + MAPLE_SIZE_INIT(g_maple_node, "maple_node"); + MAPLE_OFFSET_INIT(g_maple_tree_ma_root, "maple_tree", "ma_root"); + MAPLE_OFFSET_INIT(g_maple_node_ma64, "maple_node", "ma64"); + MAPLE_OFFSET_INIT(g_maple_node_mr64, "maple_node", "mr64"); + MAPLE_OFFSET_INIT(g_maple_node_slot, "maple_node", "slot"); + MAPLE_OFFSET_INIT(g_maple_arange_64_pivot, "maple_arange_64", "pivot"); + MAPLE_OFFSET_INIT(g_maple_arange_64_slot, "maple_arange_64", "slot"); + MAPLE_OFFSET_INIT(g_maple_range_64_pivot, "maple_range_64", "pivot"); + MAPLE_OFFSET_INIT(g_maple_range_64_slot, "maple_range_64", "slot"); + mt_slots = calloc(array_len, sizeof(char)); + if (!mt_slots) { + fprintf(stderr, "%s: Not enough memory!\n", __func__); + return FALSE; + } + if (is_btf) { + READMEM(VADDR, cb->get_kallsyms_value_by_name("mt_slots"), + mt_slots, array_len * sizeof(char)); + } else { + READMEM(VADDR, cb->get_symbol_addr_all("mt_slots"), + mt_slots, array_len * sizeof(char)); + } + + mt_max[maple_dense] = mt_slots[maple_dense]; + mt_max[maple_leaf_64] = ULONG_MAX; + mt_max[maple_range_64] = ULONG_MAX; + mt_max[maple_arange_64] = ULONG_MAX; + return TRUE; +} + +#define MAPLE_CACHE 16 + +static struct maple_cache { + uint64_t tree; + uint64_t hits; + int elems_count; + uint64_t *elems; +} maple_cache[MAPLE_CACHE] = {0}; + +static VALUE_S *maple_tree(VALUE_S *ep_tree, int cmd, VALUE_S *ep_index) +{ + uint64_t tree = eppic_getval(ep_tree); + int index = eppic_getval(ep_index); + int found = -1, target = -1; + int min_hits = 0; + for (int i = 0; i < MAPLE_CACHE; i++) { + min_hits = maple_cache[i].hits < maple_cache[min_hits].hits ? + i : min_hits; + if (tree == maple_cache[i].tree) { + found = i; + } + } + + if (found >= 0) { + maple_cache[found].hits++; + target = found; + } else { + target = min_hits; + } + + switch (cmd) + { + case MAPLE_TREE_COUNT: + if (found < 0) { + if (maple_cache[target].elems) { + free(maple_cache[target].elems); + memset(&maple_cache[target], 0, sizeof(struct maple_cache)); + } + found = do_maple_tree(tree, MAPLE_TREE_COUNT, NULL); + maple_cache[target].elems = malloc(found * sizeof(u_int64_t)); + do_maple_tree(tree, MAPLE_TREE_GATHER, maple_cache[target].elems); + maple_cache[target].elems_count = found; + return eppic_makebtype(found); + } else { + return eppic_makebtype(maple_cache[target].elems_count); + } + case MAPLE_TREE_GATHER: + if (index > maple_cache[target].elems_count) { + printf("Invalid maple index %d(> %d) for tree %lx\n", + index, maple_cache[target].elems_count, tree); + return eppic_makebtype(0); + } + return eppic_makebtype(maple_cache[target].elems[index]); + default: + return eppic_makebtype(0); + } +} + +VALUE_S * +maple_count(VALUE_S *ep_tree) +{ + return maple_tree(ep_tree, MAPLE_TREE_COUNT, NULL); +} + +VALUE_S * +maple_elem(VALUE_S *ep_tree, VALUE_S *ep_index) +{ + return maple_tree(ep_tree, MAPLE_TREE_GATHER, ep_index); +} diff --git a/eppic_maple.h b/eppic_maple.h new file mode 100644 index 0000000..61bb32f --- /dev/null +++ b/eppic_maple.h @@ -0,0 +1,8 @@ +#ifndef _EPPIC_MAPLE_H +#define _EPPIC_MAPLE_H +#include "makedumpfile.h" +int maple_init(bool); +VALUE_S *maple_count(VALUE_S *); +VALUE_S *maple_elem(VALUE_S *, VALUE_S *); +#endif /*_EPPIC_MAPLE_H*/ + -- 2.47.0

Since dwarf and btf have different apiops, so making it as parameter to eppic_init, and initialized respectively. Signed-off-by: Tao Liu <ltao(a)redhat.com&gt; --- erase_info.c | 8 +++++--- extension_eppic.c | 34 +++++++++++++++++++++++++++++++--- extension_eppic.h | 6 ++++-- 3 files changed, 40 insertions(+), 8 deletions(-) diff --git a/erase_info.c b/erase_info.c index 9ec1813..eeb2c3b 100644 --- a/erase_info.c +++ b/erase_info.c @@ -2202,7 +2202,7 @@ get_die_member_all(unsigned long long die_off, int index, long *offset, /* Process the eppic macro using eppic library */ static int -process_eppic_file(char *name_config) +process_eppic_file(char *name_config, bool is_btf) { void *handle; void (*eppic_load)(char *), (*eppic_unload)(char *); @@ -2221,7 +2221,9 @@ process_eppic_file(char *name_config) * Support specifying eppic macros in makedumpfile.conf file */ - eppic_init = dlsym(handle, "eppic_init"); + if (!is_btf) { + eppic_init = dlsym(handle, "eppic_dwarf_init"); + } if (!eppic_init) { ERRMSG("Could not find eppic_init function\n"); return FALSE; @@ -2368,7 +2370,7 @@ gather_filter_info(void) ret = process_config_file(info->name_filterconfig); if (info->name_eppic_config) - ret &= process_eppic_file(info->name_eppic_config); + ret &= process_eppic_file(info->name_eppic_config, false); /* * Remove modules symbol information, we dont need now. diff --git a/extension_eppic.c b/extension_eppic.c index c4a13b9..59178e5 100644 --- a/extension_eppic.c +++ b/extension_eppic.c @@ -23,8 +23,10 @@ #include "makedumpfile.h" #include "extension_eppic.h" +#include "eppic_maple.h" static int apigetctype(int, char *, type_t *); +struct call_back *cb; /* * Most of the functions included in this file performs similar @@ -416,7 +418,7 @@ apifindsym(char *p) return NULL; } -apiops icops = { +apiops dwarf_icops = { apigetmem, apiputmem, apimember, @@ -449,17 +451,27 @@ eppic_memset(VALUE_S *vaddr, VALUE_S *vch, VALUE_S *vlen) return eppic_makebtype(1); } +VALUE_S * +eppic_filter_pages(VALUE_S *p, VALUE_S *n) +{ + unsigned long pfn = eppic_getval(p); + unsigned long num = eppic_getval(n); + + UPDATE_FILTER_PAGE_INFO(pfn, num); + return eppic_makebtype(1); +} + /* Initialize eppic */ int -eppic_init(void *fun_ptr) +eppic_init(void *fun_ptr, apiops *ops, bool is_btf) { cb = (struct call_back *)fun_ptr; if (eppic_open() >= 0) { /* Register call back functions */ - eppic_apiset(&icops, 3, sizeof(long), 0); + eppic_apiset(ops, 3, sizeof(long), 0); /* set the new function callback */ eppic_setcallback(reg_callback); @@ -468,8 +480,24 @@ eppic_init(void *fun_ptr) eppic_builtin("int memset(char *, int, int)", (bf_t *)eppic_memset); + if (maple_init(is_btf) == FALSE) + return 1; + + eppic_builtin("int maple_count(char *)", + (bf_t *)maple_count); + + eppic_builtin("unsigned long maple_elem(char *, int)", + (bf_t *)maple_elem); + + eppic_builtin("unsigned long filter_pages(unsigned long, unsigned long)", + (bf_t *)eppic_filter_pages); + return 0; } return 1; } +int eppic_dwarf_init(void *fun_ptr) +{ + return eppic_init(fun_ptr, &dwarf_icops, false); +} diff --git a/extension_eppic.h b/extension_eppic.h index 08f1db0..ff92f01 100644 --- a/extension_eppic.h +++ b/extension_eppic.h @@ -79,8 +79,7 @@ do { \ fprintf(stderr, x); \ } while (0) - -struct call_back *cb; +extern struct call_back *cb; #define GET_DOMAIN_ALL cb->get_domain_all #define READMEM cb->readmem @@ -92,5 +91,8 @@ struct call_back *cb; #define GET_DIE_NFIELDS_ALL cb->get_die_nfields_all #define GET_SYMBOL_ADDR_ALL cb->get_symbol_addr_all #define UPDATE_FILTER_INFO_RAW cb->update_filter_info_raw +#define UPDATE_FILTER_PAGE_INFO cb->update_filter_pages_info + +int eppic_init(void *, apiops *, bool); #endif /* _EXTENSION_EPPIC_H */ -- 2.47.0

This patch will introduce 2 eppic scripts. One is for filtering out amdgpu mm pages, the other is for printing all tasks VMAs. dwarf & btf eppic extension should produce the same result for every eppic script, mainly for test use. Signed-off-by: Tao Liu <ltao(a)redhat.com&gt; --- eppic_scripts/filter_amdgpu_mm_pages.c | 36 ++++++++++++++++++++++++++ eppic_scripts/print_all_vma.c | 29 +++++++++++++++++++++ 2 files changed, 65 insertions(+) create mode 100644 eppic_scripts/filter_amdgpu_mm_pages.c create mode 100644 eppic_scripts/print_all_vma.c diff --git a/eppic_scripts/filter_amdgpu_mm_pages.c b/eppic_scripts/filter_amdgpu_mm_pages.c new file mode 100644 index 0000000..2936a54 --- /dev/null +++ b/eppic_scripts/filter_amdgpu_mm_pages.c @@ -0,0 +1,36 @@ +int main() +{ + struct task_struct *p; + unsigned long p_off; + int i, c; + struct vm_area_struct *vma; + struct ttm_buffer_object *tbo; + unsigned long pfn, num, mt; + + p = (struct task_struct *)&init_task; + p_off = (unsigned long)&(p->tasks) - (unsigned long)p; + + do { + if (!(p->mm)) { + p = (struct task_struct *)((unsigned long)(p->tasks.next) - p_off); + continue; + } + mt = (unsigned long)&(p->mm->mm_mt); + + c = maple_count((char *)mt); + for (i = 0; i < c; i++) { + vma = (struct vm_area_struct *)maple_elem((char *)mt, i); + if (vma->vm_ops == &amdgpu_gem_vm_ops) { + tbo = (struct ttm_buffer_object *)(vma->vm_private_data); + if (tbo->ttm) { + num = (unsigned long)(tbo->ttm->num_pages); + pfn = ((unsigned long)(tbo->ttm->pages[0]) - *(unsigned long *)&vmemmap_base) / sizeof(struct page); + filter_pages(pfn, num); + } + } + } + p = (struct task_struct *)((unsigned long)(p->tasks.next) - p_off); + } while(p != &init_task); + + return 1; +} diff --git a/eppic_scripts/print_all_vma.c b/eppic_scripts/print_all_vma.c new file mode 100644 index 0000000..e8e49c2 --- /dev/null +++ b/eppic_scripts/print_all_vma.c @@ -0,0 +1,29 @@ +int main() +{ + struct task_struct *p; + unsigned long p_off; + int i, c; + struct vm_area_struct *vma; + unsigned long mt; + + p = (struct task_struct *)&init_task; + p_off = (unsigned long)&(p->tasks) - (unsigned long)p; + + do { + if (!(p->mm)) { + p = (struct task_struct *)((unsigned long)(p->tasks.next) - p_off); + continue; + } + printf("PID: %d\n", (int)(p->pid)); + mt = (unsigned long)&(p->mm->mm_mt); + + c = maple_count((char *)mt); + for (i = 0; i < c; i++) { + vma = (struct vm_area_struct *)maple_elem((char *)mt, i); + printf("%lx\n", vma); + } + p = (struct task_struct *)((unsigned long)(p->tasks.next) - p_off); + } while(p != &init_task); + + return 1; +} -- 2.47.0