alistair23-linux/kernel/kallsyms.c
Daniel Borkmann 74451e66d5 bpf: make jited programs visible in traces
Long standing issue with JITed programs is that stack traces from
function tracing check whether a given address is kernel code
through {__,}kernel_text_address(), which checks for code in core
kernel, modules and dynamically allocated ftrace trampolines. But
what is still missing is BPF JITed programs (interpreted programs
are not an issue as __bpf_prog_run() will be attributed to them),
thus when a stack trace is triggered, the code walking the stack
won't see any of the JITed ones. The same for address correlation
done from user space via reading /proc/kallsyms. This is read by
tools like perf, but the latter is also useful for permanent live
tracing with eBPF itself in combination with stack maps when other
eBPF types are part of the callchain. See offwaketime example on
dumping stack from a map.

This work tries to tackle that issue by making the addresses and
symbols known to the kernel. The lookup from *kernel_text_address()
is implemented through a latched RB tree that can be read under
RCU in fast-path that is also shared for symbol/size/offset lookup
for a specific given address in kallsyms. The slow-path iteration
through all symbols in the seq file done via RCU list, which holds
a tiny fraction of all exported ksyms, usually below 0.1 percent.
Function symbols are exported as bpf_prog_<tag>, in order to aide
debugging and attribution. This facility is currently enabled for
root-only when bpf_jit_kallsyms is set to 1, and disabled if hardening
is active in any mode. The rationale behind this is that still a lot
of systems ship with world read permissions on kallsyms thus addresses
should not get suddenly exposed for them. If that situation gets
much better in future, we always have the option to change the
default on this. Likewise, unprivileged programs are not allowed
to add entries there either, but that is less of a concern as most
such programs types relevant in this context are for root-only anyway.
If enabled, call graphs and stack traces will then show a correct
attribution; one example is illustrated below, where the trace is
now visible in tooling such as perf script --kallsyms=/proc/kallsyms
and friends.

Before:

  7fff8166889d bpf_clone_redirect+0x80007f0020ed (/lib/modules/4.9.0-rc8+/build/vmlinux)
         f5d80 __sendmsg_nocancel+0xffff006451f1a007 (/usr/lib64/libc-2.18.so)

After:

  7fff816688b7 bpf_clone_redirect+0x80007f002107 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fffa0575728 bpf_prog_33c45a467c9e061a+0x8000600020fb (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fffa07ef1fc cls_bpf_classify+0x8000600020dc (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff81678b68 tc_classify+0x80007f002078 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164d40b __netif_receive_skb_core+0x80007f0025fb (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164d718 __netif_receive_skb+0x80007f002018 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164e565 process_backlog+0x80007f002095 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8164dc71 net_rx_action+0x80007f002231 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff81767461 __softirqentry_text_start+0x80007f0020d1 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff817658ac do_softirq_own_stack+0x80007f00201c (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff810a2c20 do_softirq+0x80007f002050 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff810a2cb5 __local_bh_enable_ip+0x80007f002085 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8168d452 ip_finish_output2+0x80007f002152 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8168ea3d ip_finish_output+0x80007f00217d (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff8168f2af ip_output+0x80007f00203f (/lib/modules/4.9.0-rc8+/build/vmlinux)
  [...]
  7fff81005854 do_syscall_64+0x80007f002054 (/lib/modules/4.9.0-rc8+/build/vmlinux)
  7fff817649eb return_from_SYSCALL_64+0x80007f002000 (/lib/modules/4.9.0-rc8+/build/vmlinux)
         f5d80 __sendmsg_nocancel+0xffff01c484812007 (/usr/lib64/libc-2.18.so)

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-17 13:40:05 -05:00

670 lines
16 KiB
C

/*
* kallsyms.c: in-kernel printing of symbolic oopses and stack traces.
*
* Rewritten and vastly simplified by Rusty Russell for in-kernel
* module loader:
* Copyright 2002 Rusty Russell <rusty@rustcorp.com.au> IBM Corporation
*
* ChangeLog:
*
* (25/Aug/2004) Paulo Marques <pmarques@grupopie.com>
* Changed the compression method from stem compression to "table lookup"
* compression (see scripts/kallsyms.c for a more complete description)
*/
#include <linux/kallsyms.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/fs.h>
#include <linux/kdb.h>
#include <linux/err.h>
#include <linux/proc_fs.h>
#include <linux/sched.h> /* for cond_resched */
#include <linux/mm.h>
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/filter.h>
#include <linux/compiler.h>
#include <asm/sections.h>
#ifdef CONFIG_KALLSYMS_ALL
#define all_var 1
#else
#define all_var 0
#endif
/*
* These will be re-linked against their real values
* during the second link stage.
*/
extern const unsigned long kallsyms_addresses[] __weak;
extern const int kallsyms_offsets[] __weak;
extern const u8 kallsyms_names[] __weak;
/*
* Tell the compiler that the count isn't in the small data section if the arch
* has one (eg: FRV).
*/
extern const unsigned long kallsyms_num_syms
__attribute__((weak, section(".rodata")));
extern const unsigned long kallsyms_relative_base
__attribute__((weak, section(".rodata")));
extern const u8 kallsyms_token_table[] __weak;
extern const u16 kallsyms_token_index[] __weak;
extern const unsigned long kallsyms_markers[] __weak;
static inline int is_kernel_inittext(unsigned long addr)
{
if (addr >= (unsigned long)_sinittext
&& addr <= (unsigned long)_einittext)
return 1;
return 0;
}
static inline int is_kernel_text(unsigned long addr)
{
if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) ||
arch_is_kernel_text(addr))
return 1;
return in_gate_area_no_mm(addr);
}
static inline int is_kernel(unsigned long addr)
{
if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end)
return 1;
return in_gate_area_no_mm(addr);
}
static int is_ksym_addr(unsigned long addr)
{
if (all_var)
return is_kernel(addr);
return is_kernel_text(addr) || is_kernel_inittext(addr);
}
/*
* Expand a compressed symbol data into the resulting uncompressed string,
* if uncompressed string is too long (>= maxlen), it will be truncated,
* given the offset to where the symbol is in the compressed stream.
*/
static unsigned int kallsyms_expand_symbol(unsigned int off,
char *result, size_t maxlen)
{
int len, skipped_first = 0;
const u8 *tptr, *data;
/* Get the compressed symbol length from the first symbol byte. */
data = &kallsyms_names[off];
len = *data;
data++;
/*
* Update the offset to return the offset for the next symbol on
* the compressed stream.
*/
off += len + 1;
/*
* For every byte on the compressed symbol data, copy the table
* entry for that byte.
*/
while (len) {
tptr = &kallsyms_token_table[kallsyms_token_index[*data]];
data++;
len--;
while (*tptr) {
if (skipped_first) {
if (maxlen <= 1)
goto tail;
*result = *tptr;
result++;
maxlen--;
} else
skipped_first = 1;
tptr++;
}
}
tail:
if (maxlen)
*result = '\0';
/* Return to offset to the next symbol. */
return off;
}
/*
* Get symbol type information. This is encoded as a single char at the
* beginning of the symbol name.
*/
static char kallsyms_get_symbol_type(unsigned int off)
{
/*
* Get just the first code, look it up in the token table,
* and return the first char from this token.
*/
return kallsyms_token_table[kallsyms_token_index[kallsyms_names[off + 1]]];
}
/*
* Find the offset on the compressed stream given and index in the
* kallsyms array.
*/
static unsigned int get_symbol_offset(unsigned long pos)
{
const u8 *name;
int i;
/*
* Use the closest marker we have. We have markers every 256 positions,
* so that should be close enough.
*/
name = &kallsyms_names[kallsyms_markers[pos >> 8]];
/*
* Sequentially scan all the symbols up to the point we're searching
* for. Every symbol is stored in a [<len>][<len> bytes of data] format,
* so we just need to add the len to the current pointer for every
* symbol we wish to skip.
*/
for (i = 0; i < (pos & 0xFF); i++)
name = name + (*name) + 1;
return name - kallsyms_names;
}
static unsigned long kallsyms_sym_address(int idx)
{
if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
return kallsyms_addresses[idx];
/* values are unsigned offsets if --absolute-percpu is not in effect */
if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
/* ...otherwise, positive offsets are absolute values */
if (kallsyms_offsets[idx] >= 0)
return kallsyms_offsets[idx];
/* ...and negative offsets are relative to kallsyms_relative_base - 1 */
return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
}
/* Lookup the address for this symbol. Returns 0 if not found. */
unsigned long kallsyms_lookup_name(const char *name)
{
char namebuf[KSYM_NAME_LEN];
unsigned long i;
unsigned int off;
for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
if (strcmp(namebuf, name) == 0)
return kallsyms_sym_address(i);
}
return module_kallsyms_lookup_name(name);
}
EXPORT_SYMBOL_GPL(kallsyms_lookup_name);
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
unsigned long),
void *data)
{
char namebuf[KSYM_NAME_LEN];
unsigned long i;
unsigned int off;
int ret;
for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
ret = fn(data, namebuf, NULL, kallsyms_sym_address(i));
if (ret != 0)
return ret;
}
return module_kallsyms_on_each_symbol(fn, data);
}
EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol);
static unsigned long get_symbol_pos(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset)
{
unsigned long symbol_start = 0, symbol_end = 0;
unsigned long i, low, high, mid;
/* This kernel should never had been booted. */
if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
BUG_ON(!kallsyms_addresses);
else
BUG_ON(!kallsyms_offsets);
/* Do a binary search on the sorted kallsyms_addresses array. */
low = 0;
high = kallsyms_num_syms;
while (high - low > 1) {
mid = low + (high - low) / 2;
if (kallsyms_sym_address(mid) <= addr)
low = mid;
else
high = mid;
}
/*
* Search for the first aliased symbol. Aliased
* symbols are symbols with the same address.
*/
while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low))
--low;
symbol_start = kallsyms_sym_address(low);
/* Search for next non-aliased symbol. */
for (i = low + 1; i < kallsyms_num_syms; i++) {
if (kallsyms_sym_address(i) > symbol_start) {
symbol_end = kallsyms_sym_address(i);
break;
}
}
/* If we found no next symbol, we use the end of the section. */
if (!symbol_end) {
if (is_kernel_inittext(addr))
symbol_end = (unsigned long)_einittext;
else if (all_var)
symbol_end = (unsigned long)_end;
else
symbol_end = (unsigned long)_etext;
}
if (symbolsize)
*symbolsize = symbol_end - symbol_start;
if (offset)
*offset = addr - symbol_start;
return low;
}
/*
* Lookup an address but don't bother to find any names.
*/
int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
unsigned long *offset)
{
char namebuf[KSYM_NAME_LEN];
if (is_ksym_addr(addr))
return !!get_symbol_pos(addr, symbolsize, offset);
return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) ||
!!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
}
/*
* Lookup an address
* - modname is set to NULL if it's in the kernel.
* - We guarantee that the returned name is valid until we reschedule even if.
* It resides in a module.
* - We also guarantee that modname will be valid until rescheduled.
*/
const char *kallsyms_lookup(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset,
char **modname, char *namebuf)
{
const char *ret;
namebuf[KSYM_NAME_LEN - 1] = 0;
namebuf[0] = 0;
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, symbolsize, offset);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
namebuf, KSYM_NAME_LEN);
if (modname)
*modname = NULL;
return namebuf;
}
/* See if it's in a module or a BPF JITed image. */
ret = module_address_lookup(addr, symbolsize, offset,
modname, namebuf);
if (!ret)
ret = bpf_address_lookup(addr, symbolsize,
offset, modname, namebuf);
return ret;
}
int lookup_symbol_name(unsigned long addr, char *symname)
{
symname[0] = '\0';
symname[KSYM_NAME_LEN - 1] = '\0';
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, NULL, NULL);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
symname, KSYM_NAME_LEN);
return 0;
}
/* See if it's in a module. */
return lookup_module_symbol_name(addr, symname);
}
int lookup_symbol_attrs(unsigned long addr, unsigned long *size,
unsigned long *offset, char *modname, char *name)
{
name[0] = '\0';
name[KSYM_NAME_LEN - 1] = '\0';
if (is_ksym_addr(addr)) {
unsigned long pos;
pos = get_symbol_pos(addr, size, offset);
/* Grab name */
kallsyms_expand_symbol(get_symbol_offset(pos),
name, KSYM_NAME_LEN);
modname[0] = '\0';
return 0;
}
/* See if it's in a module. */
return lookup_module_symbol_attrs(addr, size, offset, modname, name);
}
/* Look up a kernel symbol and return it in a text buffer. */
static int __sprint_symbol(char *buffer, unsigned long address,
int symbol_offset, int add_offset)
{
char *modname;
const char *name;
unsigned long offset, size;
int len;
address += symbol_offset;
name = kallsyms_lookup(address, &size, &offset, &modname, buffer);
if (!name)
return sprintf(buffer, "0x%lx", address - symbol_offset);
if (name != buffer)
strcpy(buffer, name);
len = strlen(buffer);
offset -= symbol_offset;
if (add_offset)
len += sprintf(buffer + len, "+%#lx/%#lx", offset, size);
if (modname)
len += sprintf(buffer + len, " [%s]", modname);
return len;
}
/**
* sprint_symbol - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function looks up a kernel symbol with @address and stores its name,
* offset, size and module name to @buffer if possible. If no symbol was found,
* just saves its @address as is.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_symbol(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, 0, 1);
}
EXPORT_SYMBOL_GPL(sprint_symbol);
/**
* sprint_symbol_no_offset - Look up a kernel symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function looks up a kernel symbol with @address and stores its name
* and module name to @buffer if possible. If no symbol was found, just saves
* its @address as is.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_symbol_no_offset(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, 0, 0);
}
EXPORT_SYMBOL_GPL(sprint_symbol_no_offset);
/**
* sprint_backtrace - Look up a backtrace symbol and return it in a text buffer
* @buffer: buffer to be stored
* @address: address to lookup
*
* This function is for stack backtrace and does the same thing as
* sprint_symbol() but with modified/decreased @address. If there is a
* tail-call to the function marked "noreturn", gcc optimized out code after
* the call so that the stack-saved return address could point outside of the
* caller. This function ensures that kallsyms will find the original caller
* by decreasing @address.
*
* This function returns the number of bytes stored in @buffer.
*/
int sprint_backtrace(char *buffer, unsigned long address)
{
return __sprint_symbol(buffer, address, -1, 1);
}
/* Look up a kernel symbol and print it to the kernel messages. */
void __print_symbol(const char *fmt, unsigned long address)
{
char buffer[KSYM_SYMBOL_LEN];
sprint_symbol(buffer, address);
printk(fmt, buffer);
}
EXPORT_SYMBOL(__print_symbol);
/* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
struct kallsym_iter {
loff_t pos;
loff_t pos_mod_end;
unsigned long value;
unsigned int nameoff; /* If iterating in core kernel symbols. */
char type;
char name[KSYM_NAME_LEN];
char module_name[MODULE_NAME_LEN];
int exported;
};
static int get_ksymbol_mod(struct kallsym_iter *iter)
{
int ret = module_get_kallsym(iter->pos - kallsyms_num_syms,
&iter->value, &iter->type,
iter->name, iter->module_name,
&iter->exported);
if (ret < 0) {
iter->pos_mod_end = iter->pos;
return 0;
}
return 1;
}
static int get_ksymbol_bpf(struct kallsym_iter *iter)
{
iter->module_name[0] = '\0';
iter->exported = 0;
return bpf_get_kallsym(iter->pos - iter->pos_mod_end,
&iter->value, &iter->type,
iter->name) < 0 ? 0 : 1;
}
/* Returns space to next name. */
static unsigned long get_ksymbol_core(struct kallsym_iter *iter)
{
unsigned off = iter->nameoff;
iter->module_name[0] = '\0';
iter->value = kallsyms_sym_address(iter->pos);
iter->type = kallsyms_get_symbol_type(off);
off = kallsyms_expand_symbol(off, iter->name, ARRAY_SIZE(iter->name));
return off - iter->nameoff;
}
static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
{
iter->name[0] = '\0';
iter->nameoff = get_symbol_offset(new_pos);
iter->pos = new_pos;
if (new_pos == 0)
iter->pos_mod_end = 0;
}
static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
{
iter->pos = pos;
if (iter->pos_mod_end > 0 &&
iter->pos_mod_end < iter->pos)
return get_ksymbol_bpf(iter);
if (!get_ksymbol_mod(iter))
return get_ksymbol_bpf(iter);
return 1;
}
/* Returns false if pos at or past end of file. */
static int update_iter(struct kallsym_iter *iter, loff_t pos)
{
/* Module symbols can be accessed randomly. */
if (pos >= kallsyms_num_syms)
return update_iter_mod(iter, pos);
/* If we're not on the desired position, reset to new position. */
if (pos != iter->pos)
reset_iter(iter, pos);
iter->nameoff += get_ksymbol_core(iter);
iter->pos++;
return 1;
}
static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
(*pos)++;
if (!update_iter(m->private, *pos))
return NULL;
return p;
}
static void *s_start(struct seq_file *m, loff_t *pos)
{
if (!update_iter(m->private, *pos))
return NULL;
return m->private;
}
static void s_stop(struct seq_file *m, void *p)
{
}
static int s_show(struct seq_file *m, void *p)
{
struct kallsym_iter *iter = m->private;
/* Some debugging symbols have no name. Ignore them. */
if (!iter->name[0])
return 0;
if (iter->module_name[0]) {
char type;
/*
* Label it "global" if it is exported,
* "local" if not exported.
*/
type = iter->exported ? toupper(iter->type) :
tolower(iter->type);
seq_printf(m, "%pK %c %s\t[%s]\n", (void *)iter->value,
type, iter->name, iter->module_name);
} else
seq_printf(m, "%pK %c %s\n", (void *)iter->value,
iter->type, iter->name);
return 0;
}
static const struct seq_operations kallsyms_op = {
.start = s_start,
.next = s_next,
.stop = s_stop,
.show = s_show
};
static int kallsyms_open(struct inode *inode, struct file *file)
{
/*
* We keep iterator in m->private, since normal case is to
* s_start from where we left off, so we avoid doing
* using get_symbol_offset for every symbol.
*/
struct kallsym_iter *iter;
iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter));
if (!iter)
return -ENOMEM;
reset_iter(iter, 0);
return 0;
}
#ifdef CONFIG_KGDB_KDB
const char *kdb_walk_kallsyms(loff_t *pos)
{
static struct kallsym_iter kdb_walk_kallsyms_iter;
if (*pos == 0) {
memset(&kdb_walk_kallsyms_iter, 0,
sizeof(kdb_walk_kallsyms_iter));
reset_iter(&kdb_walk_kallsyms_iter, 0);
}
while (1) {
if (!update_iter(&kdb_walk_kallsyms_iter, *pos))
return NULL;
++*pos;
/* Some debugging symbols have no name. Ignore them. */
if (kdb_walk_kallsyms_iter.name[0])
return kdb_walk_kallsyms_iter.name;
}
}
#endif /* CONFIG_KGDB_KDB */
static const struct file_operations kallsyms_operations = {
.open = kallsyms_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_private,
};
static int __init kallsyms_init(void)
{
proc_create("kallsyms", 0444, NULL, &kallsyms_operations);
return 0;
}
device_initcall(kallsyms_init);