summaryrefslogtreecommitdiffstats
path: root/kernel/kallsyms.c
diff options
context:
space:
mode:
authorDaniel Borkmann <daniel@iogearbox.net>2017-02-16 22:24:50 +0100
committerDavid S. Miller <davem@davemloft.net>2017-02-17 13:40:05 -0500
commit74451e66d516c55e309e8d89a4a1e7596e46aacd (patch)
tree62d6243fab97ce01fee6863bae0f36e87efcb92b /kernel/kallsyms.c
parent9383191da4e40360a5d880fbe6bb03911c61621b (diff)
downloadlinux-74451e66d516c55e309e8d89a4a1e7596e46aacd.tar.gz
linux-74451e66d516c55e309e8d89a4a1e7596e46aacd.tar.bz2
linux-74451e66d516c55e309e8d89a4a1e7596e46aacd.zip
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>
Diffstat (limited to 'kernel/kallsyms.c')
-rw-r--r--kernel/kallsyms.c61
1 files changed, 49 insertions, 12 deletions
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fafd1a3ef0da..6a3b249a2ae1 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -23,6 +23,7 @@
#include <linux/mm.h>
#include <linux/ctype.h>
#include <linux/slab.h>
+#include <linux/filter.h>
#include <linux/compiler.h>
#include <asm/sections.h>
@@ -300,10 +301,11 @@ 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);
+ return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) ||
+ !!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
}
/*
@@ -318,6 +320,8 @@ const char *kallsyms_lookup(unsigned long addr,
unsigned long *offset,
char **modname, char *namebuf)
{
+ const char *ret;
+
namebuf[KSYM_NAME_LEN - 1] = 0;
namebuf[0] = 0;
@@ -333,9 +337,13 @@ const char *kallsyms_lookup(unsigned long addr,
return namebuf;
}
- /* See if it's in a module. */
- return module_address_lookup(addr, symbolsize, offset, modname,
- 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)
@@ -471,6 +479,7 @@ 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;
@@ -481,13 +490,27 @@ struct kallsym_iter {
static int get_ksymbol_mod(struct kallsym_iter *iter)
{
- if (module_get_kallsym(iter->pos - kallsyms_num_syms, &iter->value,
- &iter->type, iter->name, iter->module_name,
- &iter->exported) < 0)
+ 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)
{
@@ -508,16 +531,30 @@ 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) {
- iter->pos = pos;
- return get_ksymbol_mod(iter);
- }
+ 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)