linux-stable/kernel/extable.c

171 lines
4.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* Rewritten by Rusty Russell, on the backs of many others...
Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM.
*/
#include <linux/elf.h>
#include <linux/ftrace.h>
#include <linux/memory.h>
#include <linux/extable.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/init.h>
kprobes, extable: Identify kprobes trampolines as kernel text area Improve __kernel_text_address()/kernel_text_address() to return true if the given address is on a kprobe's instruction slot trampoline. This can help stacktraces to determine the address is on a text area or not. To implement this atomically in is_kprobe_*_slot(), also change the insn_cache page list to an RCU list. This changes timings a bit (it delays page freeing to the RCU garbage collection phase), but none of that is in the hot path. Note: this change can add small overhead to stack unwinders because it adds 2 additional checks to __kernel_text_address(). However, the impact should be very small, because kprobe_insn_pages list has 1 entry per 256 probes(on x86, on arm/arm64 it will be 1024 probes), and kprobe_optinsn_pages has 1 entry per 32 probes(on x86). In most use cases, the number of kprobe events may be less than 20, which means that is_kprobe_*_slot() will check just one entry. Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/148388747896.6869.6354262871751682264.stgit@devbox [ Improved the changelog and coding style. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-08 14:58:09 +00:00
#include <linux/kprobes.h>
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>
2017-02-16 21:24:50 +00:00
#include <linux/filter.h>
#include <asm/sections.h>
#include <linux/uaccess.h>
/*
* mutex protecting text section modification (dynamic code patching).
* some users need to sleep (allocating memory...) while they hold this lock.
*
kprobes, x86/alternatives: Use text_mutex to protect smp_alt_modules We use alternatives_text_reserved() to check if the address is in the fixed pieces of alternative reserved, but the problem is that we don't hold the smp_alt mutex when call this function. So the list traversal may encounter a deleted list_head if another path is doing alternatives_smp_module_del(). One solution is that we can hold smp_alt mutex before call this function, but the difficult point is that the callers of this functions, arch_prepare_kprobe() and arch_prepare_optimized_kprobe(), are called inside the text_mutex. So we must hold smp_alt mutex before we go into these arch dependent code. But we can't now, the smp_alt mutex is the arch dependent part, only x86 has it. Maybe we can export another arch dependent callback to solve this. But there is a simpler way to handle this problem. We can reuse the text_mutex to protect smp_alt_modules instead of using another mutex. And all the arch dependent checks of kprobes are inside the text_mutex, so it's safe now. Signed-off-by: Zhou Chengming <zhouchengming1@huawei.com> Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: bp@suse.de Fixes: 2cfa197 "ftrace/alternatives: Introducing *_text_reserved functions" Link: http://lkml.kernel.org/r/1509585501-79466-1-git-send-email-zhouchengming1@huawei.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-11-02 01:18:21 +00:00
* Note: Also protects SMP-alternatives modification on x86.
*
* NOT exported to modules - patching kernel text is a really delicate matter.
*/
DEFINE_MUTEX(text_mutex);
extern struct exception_table_entry __start___ex_table[];
extern struct exception_table_entry __stop___ex_table[];
/* Cleared by build time tools if the table is already sorted. */
u32 __initdata __visible main_extable_sort_needed = 1;
/* Sort the kernel's built-in exception table */
void __init sort_main_extable(void)
{
if (main_extable_sort_needed &&
&__stop___ex_table > &__start___ex_table) {
pr_notice("Sorting __ex_table...\n");
sort_extable(__start___ex_table, __stop___ex_table);
}
}
/* Given an address, look for it in the kernel exception table */
const
struct exception_table_entry *search_kernel_exception_table(unsigned long addr)
{
return search_extable(__start___ex_table,
__stop___ex_table - __start___ex_table, addr);
}
/* Given an address, look for it in the exception tables. */
const struct exception_table_entry *search_exception_tables(unsigned long addr)
{
const struct exception_table_entry *e;
e = search_kernel_exception_table(addr);
if (!e)
e = search_module_extables(addr);
bpf: Add support for BTF pointers to x86 JIT Pointer to BTF object is a pointer to kernel object or NULL. Such pointers can only be used by BPF_LDX instructions. The verifier changed their opcode from LDX|MEM|size to LDX|PROBE_MEM|size to make JITing easier. The number of entries in extable is the number of BPF_LDX insns that access kernel memory via "pointer to BTF type". Only these load instructions can fault. Since x86 extable is relative it has to be allocated in the same memory region as JITed code. Allocate it prior to last pass of JITing and let the last pass populate it. Pointer to extable in bpf_prog_aux is necessary to make page fault handling fast. Page fault handling is done in two steps: 1. bpf_prog_kallsyms_find() finds BPF program that page faulted. It's done by walking rb tree. 2. then extable for given bpf program is binary searched. This process is similar to how page faulting is done for kernel modules. The exception handler skips over faulting x86 instruction and initializes destination register with zero. This mimics exact behavior of bpf_probe_read (when probe_kernel_read faults dest is zeroed). JITs for other architectures can add support in similar way. Until then they will reject unknown opcode and fallback to interpreter. Since extable should be aligned and placed near JITed code make bpf_jit_binary_alloc() return 4 byte aligned image offset, so that extable aligning formula in bpf_int_jit_compile() doesn't need to rely on internal implementation of bpf_jit_binary_alloc(). On x86 gcc defaults to 16-byte alignment for regular kernel functions due to better performance. JITed code may be aligned to 16 in the future, but it will use 4 in the meantime. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andriin@fb.com> Acked-by: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/bpf/20191016032505.2089704-10-ast@kernel.org
2019-10-16 03:25:03 +00:00
if (!e)
e = search_bpf_extables(addr);
return e;
}
int notrace core_kernel_text(unsigned long addr)
{
if (is_kernel_text(addr))
return 1;
if (system_state < SYSTEM_FREEING_INITMEM &&
is_kernel_inittext(addr))
return 1;
return 0;
}
int __kernel_text_address(unsigned long addr)
{
if (kernel_text_address(addr))
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>
2017-02-16 21:24:50 +00:00
return 1;
symbols, stacktrace: look up init symbols after module symbols Impact: fix incomplete stacktraces I noticed such weird stacktrace entries in lockdep dumps: [ 0.285956] {HARDIRQ-ON-W} state was registered at: [ 0.285956] [<ffffffff802bce90>] mark_irqflags+0xbe/0x125 [ 0.285956] [<ffffffff802bf2fd>] __lock_acquire+0x674/0x82d [ 0.285956] [<ffffffff802bf5b2>] lock_acquire+0xfc/0x128 [ 0.285956] [<ffffffff8135b636>] rt_spin_lock+0xc8/0xd0 [ 0.285956] [<ffffffffffffffff>] 0xffffffffffffffff The stacktrace entry is cut off after rt_spin_lock. After much debugging i found out that stacktrace entries that belong to init symbols dont get printed out, due to commit: a2da405: module: Don't report discarded init pages as kernel text. The reason is this check added to core_kernel_text(): - if (addr >= (unsigned long)_sinittext && + if (system_state == SYSTEM_BOOTING && + addr >= (unsigned long)_sinittext && addr <= (unsigned long)_einittext) return 1; This will discard inittext symbols even though their symbol table is still present and even though stacktraces done while the system was booting up might still be relevant. To not reintroduce the (not well-specified) bug addressed in that commit, first do a module symbols lookup, then a final init-symbols lookup. This will work fine on architectures that have separate address spaces for modules (such as x86) - and should not crash any other architectures either. Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> LKML-Reference: <new-discussion> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-19 12:21:44 +00:00
/*
* There might be init symbols in saved stacktraces.
* Give those symbols a chance to be printed in
* backtraces (such as lockdep traces).
*
* Since we are after the module-symbols check, there's
* no danger of address overlap:
*/
if (is_kernel_inittext(addr))
symbols, stacktrace: look up init symbols after module symbols Impact: fix incomplete stacktraces I noticed such weird stacktrace entries in lockdep dumps: [ 0.285956] {HARDIRQ-ON-W} state was registered at: [ 0.285956] [<ffffffff802bce90>] mark_irqflags+0xbe/0x125 [ 0.285956] [<ffffffff802bf2fd>] __lock_acquire+0x674/0x82d [ 0.285956] [<ffffffff802bf5b2>] lock_acquire+0xfc/0x128 [ 0.285956] [<ffffffff8135b636>] rt_spin_lock+0xc8/0xd0 [ 0.285956] [<ffffffffffffffff>] 0xffffffffffffffff The stacktrace entry is cut off after rt_spin_lock. After much debugging i found out that stacktrace entries that belong to init symbols dont get printed out, due to commit: a2da405: module: Don't report discarded init pages as kernel text. The reason is this check added to core_kernel_text(): - if (addr >= (unsigned long)_sinittext && + if (system_state == SYSTEM_BOOTING && + addr >= (unsigned long)_sinittext && addr <= (unsigned long)_einittext) return 1; This will discard inittext symbols even though their symbol table is still present and even though stacktraces done while the system was booting up might still be relevant. To not reintroduce the (not well-specified) bug addressed in that commit, first do a module symbols lookup, then a final init-symbols lookup. This will work fine on architectures that have separate address spaces for modules (such as x86) - and should not crash any other architectures either. Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Rusty Russell <rusty@rustcorp.com.au> LKML-Reference: <new-discussion> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-19 12:21:44 +00:00
return 1;
return 0;
}
int kernel_text_address(unsigned long addr)
{
bool no_rcu;
int ret = 1;
if (core_kernel_text(addr))
return 1;
/*
* If a stack dump happens while RCU is not watching, then
* RCU needs to be notified that it requires to start
* watching again. This can happen either by tracing that
* triggers a stack trace, or a WARN() that happens during
* coming back from idle, or cpu on or offlining.
*
* is_module_text_address() as well as the kprobe slots,
* is_bpf_text_address() and is_bpf_image_address require
* RCU to be watching.
*/
no_rcu = !rcu_is_watching();
/* Treat this like an NMI as it can happen anywhere */
if (no_rcu)
ct_nmi_enter();
if (is_module_text_address(addr))
goto out;
kprobes, extable: Identify kprobes trampolines as kernel text area Improve __kernel_text_address()/kernel_text_address() to return true if the given address is on a kprobe's instruction slot trampoline. This can help stacktraces to determine the address is on a text area or not. To implement this atomically in is_kprobe_*_slot(), also change the insn_cache page list to an RCU list. This changes timings a bit (it delays page freeing to the RCU garbage collection phase), but none of that is in the hot path. Note: this change can add small overhead to stack unwinders because it adds 2 additional checks to __kernel_text_address(). However, the impact should be very small, because kprobe_insn_pages list has 1 entry per 256 probes(on x86, on arm/arm64 it will be 1024 probes), and kprobe_optinsn_pages has 1 entry per 32 probes(on x86). In most use cases, the number of kprobe events may be less than 20, which means that is_kprobe_*_slot() will check just one entry. Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/148388747896.6869.6354262871751682264.stgit@devbox [ Improved the changelog and coding style. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-08 14:58:09 +00:00
if (is_ftrace_trampoline(addr))
goto out;
kprobes, extable: Identify kprobes trampolines as kernel text area Improve __kernel_text_address()/kernel_text_address() to return true if the given address is on a kprobe's instruction slot trampoline. This can help stacktraces to determine the address is on a text area or not. To implement this atomically in is_kprobe_*_slot(), also change the insn_cache page list to an RCU list. This changes timings a bit (it delays page freeing to the RCU garbage collection phase), but none of that is in the hot path. Note: this change can add small overhead to stack unwinders because it adds 2 additional checks to __kernel_text_address(). However, the impact should be very small, because kprobe_insn_pages list has 1 entry per 256 probes(on x86, on arm/arm64 it will be 1024 probes), and kprobe_optinsn_pages has 1 entry per 32 probes(on x86). In most use cases, the number of kprobe events may be less than 20, which means that is_kprobe_*_slot() will check just one entry. Tested-by: Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andrey Konovalov <andreyknvl@google.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/148388747896.6869.6354262871751682264.stgit@devbox [ Improved the changelog and coding style. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-08 14:58:09 +00:00
if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
goto out;
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>
2017-02-16 21:24:50 +00:00
if (is_bpf_text_address(addr))
goto out;
ret = 0;
out:
if (no_rcu)
ct_nmi_exit();
return ret;
}
/*
* On some architectures (PPC64, IA64, PARISC) function pointers
* are actually only tokens to some data that then holds the
* real function address. As a result, to find if a function
* pointer is part of the kernel text, we need to do some
* special dereferencing first.
*/
#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS
void *dereference_function_descriptor(void *ptr)
{
func_desc_t *desc = ptr;
void *p;
if (!get_kernel_nofault(p, (void *)&desc->addr))
ptr = p;
return ptr;
}
EXPORT_SYMBOL_GPL(dereference_function_descriptor);
void *dereference_kernel_function_descriptor(void *ptr)
{
if (ptr < (void *)__start_opd || ptr >= (void *)__end_opd)
return ptr;
return dereference_function_descriptor(ptr);
}
#endif
int func_ptr_is_kernel_text(void *ptr)
{
unsigned long addr;
addr = (unsigned long) dereference_function_descriptor(ptr);
if (core_kernel_text(addr))
return 1;
return is_module_text_address(addr);
}