Introduce NOKPROBE_SYMBOL() macro which builds a kprobe
blacklist in build time. The usage of this macro is similar
to the EXPORT_SYMBOL, put the NOKPROBE_SYMBOL(function); just
after the function definition.
If CONFIG_KPROBES=y, the macro is expanded to the definition
of a static data structure of kprobe_blackpoint which is
initialized for the function and put the address of the data
structure in the "_kprobe_blacklist" section.
Since the data structures are not fully initialized by the
macro (because there is no "size" information), those
are re-initialized at boot time by using kallsyms.
Changes from previous version:
- fix indent of the macro by using tabs.
- fix macro for expanding nested macro.
- update Documentations/kprobes.txt
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Ananth N Mavinakayanahalli <ananth@xxxxxxxxxx>
Cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
Cc: Rob Landley <rob@xxxxxxxxxxx>
Cc: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
Cc: Chris Wright <chrisw@xxxxxxxxxxxx>
Cc: Alok Kataria <akataria@xxxxxxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
---
Documentation/kprobes.txt | 16 ++++++-
arch/x86/kernel/paravirt.c | 4 ++
include/asm-generic/vmlinux.lds.h | 9 ++++
include/linux/kprobes.h | 20 ++++++++
kernel/kprobes.c | 88 ++++++++++++++++++-------------------
kernel/sched/core.c | 1
6 files changed, 91 insertions(+), 47 deletions(-)
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 0cfb00f..7062631 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -22,8 +22,9 @@ Appendix B: The kprobes sysctl interface
Kprobes enables you to dynamically break into any kernel routine and
collect debugging and performance information non-disruptively. You
-can trap at almost any kernel code address, specifying a handler
+can trap at almost any kernel code address(*), specifying a handler
routine to be invoked when the breakpoint is hit.
+(*: at some part of kernel code can not be trapped, see 1.5 Blacklist)
There are currently three types of probes: kprobes, jprobes, and
kretprobes (also called return probes). A kprobe can be inserted
@@ -273,6 +274,19 @@ using one of the following techniques:
or
- Execute 'sysctl -w debug.kprobes_optimization=n'
+1.5 Blacklist
+
+Kprobes can probe almost of the kernel except itself. This means
+that there are some functions where kprobes cannot probe. Probing
+(trapping) such functions can cause recursive trap (e.g. double
+fault) or at least the nested probe handler never be called.
+Kprobes manages such functions as a blacklist.
+If you want to add a function into the blacklist, you just need
+to (1) include linux/kprobes.h and (2) use NOKPROBE_SYMBOL() macro
+to specify a blacklisted function.
+Kprobes checks given probe address with the blacklist and reject
+registering if the given address is in the blacklist.
+
2. Architectures Supported
Kprobes, jprobes, and return probes are implemented on the following
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1b10af8..4c785fd 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -23,6 +23,7 @@
#include <linux/efi.h>
#include <linux/bcd.h>
#include <linux/highmem.h>
+#include <linux/kprobes.h>
#include <asm/bug.h>
#include <asm/paravirt.h>
@@ -389,6 +390,9 @@ __visible struct pv_cpu_ops pv_cpu_ops = {
.end_context_switch = paravirt_nop,
};
+/* At this point, native_get_debugreg has real function entry */
+NOKPROBE_SYMBOL(native_get_debugreg);
+
struct pv_apic_ops pv_apic_ops = {
#ifdef CONFIG_X86_LOCAL_APIC
.startup_ipi_hook = paravirt_nop,
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 83e2c31..294ea96 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -109,6 +109,14 @@
#define BRANCH_PROFILE()
#endif
+#ifdef CONFIG_KPROBES
+#define KPROBE_BLACKLIST() VMLINUX_SYMBOL(__start_kprobe_blacklist) = .; \
+ *(_kprobe_blacklist) \
+ VMLINUX_SYMBOL(__stop_kprobe_blacklist) = .;
+#else
+#define KPROBE_BLACKLIST()
+#endif
+
#ifdef CONFIG_EVENT_TRACING
#define FTRACE_EVENTS() . = ALIGN(8); \
VMLINUX_SYMBOL(__start_ftrace_events) = .; \
@@ -487,6 +495,7 @@
*(.init.rodata) \
FTRACE_EVENTS() \
TRACE_SYSCALLS() \
+ KPROBE_BLACKLIST() \
MEM_DISCARD(init.rodata) \
CLK_OF_TABLES() \
CLKSRC_OF_TABLES() \
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 925eaf2..404cfca 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -206,6 +206,7 @@ struct kretprobe_blackpoint {
};
struct kprobe_blackpoint {
+ struct list_head list;
const char *name;
unsigned long start_addr;
unsigned long range;
@@ -476,4 +477,23 @@ static inline int enable_jprobe(struct jprobe *jp)
return enable_kprobe(&jp->kp);
}
+#ifdef CONFIG_KPROBES
+/*
+ * Blacklist ganerating macro. Specify functions which is not probed
+ * by using this macro.
+ */
+#define __NOKPROBE_SYMBOL(fname) \
+static struct kprobe_blackpoint __used \
+ _kprobe_bp_##fname = { \
+ .name = #fname, \
+ .start_addr = (unsigned long)fname, \
+ }; \
+static struct kprobe_blackpoint __used \
+ __attribute__((section("_kprobe_blacklist"))) \
+ *_p_kprobe_bp_##fname = &_kprobe_bp_##fname;
+#define NOKPROBE_SYMBOL(fname) __NOKPROBE_SYMBOL(fname)
+#else
+#define NOKPROBE_SYMBOL(fname)
+#endif
+
#endif /* _LINUX_KPROBES_H */
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ec0dbc7..a3b323e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -86,18 +86,8 @@ static raw_spinlock_t *kretprobe_table_lock_ptr(unsigned long hash)
return &(kretprobe_table_locks[hash].lock);
}
-/*
- * Normally, functions that we'd want to prohibit kprobes in, are marked
- * __kprobes. But, there are cases where such functions already belong to
- * a different section (__sched for preempt_schedule)
- *
- * For such cases, we now have a blacklist
- */
-static struct kprobe_blackpoint kprobe_blacklist[] = {
- {"preempt_schedule",},
- {"native_get_debugreg",},
- {NULL} /* Terminator */
-};
+/* Blacklist -- list of struct kprobe_blackpoint */
+static LIST_HEAD(kprobe_blacklist);
#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
/*
@@ -1321,9 +1311,9 @@ out:
return ret;
}
-static int __kprobes in_kprobes_functions(unsigned long addr)
+static int __kprobes in_nokprobe_functions(unsigned long addr)
{
- struct kprobe_blackpoint *kb;
+ struct kprobe_blackpoint *bp;
/* The __kprobes marked functions and entry code must not be probed */
if ((addr >= (unsigned long)__kprobes_text_start &&
@@ -1335,12 +1325,10 @@ static int __kprobes in_kprobes_functions(unsigned long addr)
* If there exists a kprobe_blacklist, verify and
* fail any probe registration in the prohibited area
*/
- for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
- if (kb->start_addr) {
- if (addr >= kb->start_addr &&
- addr < (kb->start_addr + kb->range))
- return -EINVAL;
- }
+ list_for_each_entry(bp, &kprobe_blacklist, list) {
+ if (addr >= bp->start_addr &&
+ addr < (bp->start_addr + bp->range))
+ return -EINVAL;
}
return 0;
}
@@ -1433,7 +1421,7 @@ static __kprobes int check_kprobe_address_safe(struct kprobe *p,
/* Ensure it is not in reserved area nor out of text */
if (!kernel_text_address((unsigned long) p->addr) ||
- in_kprobes_functions((unsigned long) p->addr) ||
+ in_nokprobe_functions((unsigned long) p->addr) ||
jump_label_text_reserved(p->addr, p->addr)) {
ret = -EINVAL;
goto out;
@@ -2062,14 +2050,41 @@ static struct notifier_block kprobe_module_nb = {
.priority = 0
};
-static int __init init_kprobes(void)
+/*
+ * Lookup and populate the kprobe_blacklist.
+ *
+ * Unlike the kretprobe blacklist, we'll need to determine
+ * the range of addresses that belong to the said functions,
+ * since a kprobe need not necessarily be at the beginning
+ * of a function.
+ */
+static void __init populate_kprobe_blacklist(struct kprobe_blackpoint **start,
+ struct kprobe_blackpoint **end)
{
- int i, err = 0;
+ struct kprobe_blackpoint **iter, *bp;
unsigned long offset = 0, size = 0;
char *modname, namebuf[128];
const char *symbol_name;
- void *addr;
- struct kprobe_blackpoint *kb;
+
+ for (iter = start; (unsigned long)iter < (unsigned long)end; iter++) {
+ bp = *iter;
+ symbol_name = kallsyms_lookup(bp->start_addr,
+ &size, &offset, &modname, namebuf);
+ if (!symbol_name)
+ continue;
+
+ bp->range = size;
+ INIT_LIST_HEAD(&bp->list);
+ list_add_tail(&bp->list, &kprobe_blacklist);
+ }
+}
+
+extern struct kprobe_blackpoint *__start_kprobe_blacklist[];
+extern struct kprobe_blackpoint *__stop_kprobe_blacklist[];
+
+static int __init init_kprobes(void)
+{
+ int i, err = 0;
/* FIXME allocate the probe table, currently defined statically */
/* initialize all list heads */
@@ -2079,27 +2094,8 @@ static int __init init_kprobes(void)
raw_spin_lock_init(&(kretprobe_table_locks[i].lock));
}
- /*
- * Lookup and populate the kprobe_blacklist.
- *
- * Unlike the kretprobe blacklist, we'll need to determine
- * the range of addresses that belong to the said functions,
- * since a kprobe need not necessarily be at the beginning
- * of a function.
- */
- for (kb = kprobe_blacklist; kb->name != NULL; kb++) {
- kprobe_lookup_name(kb->name, addr);
- if (!addr)
- continue;
-
- kb->start_addr = (unsigned long)addr;
- symbol_name = kallsyms_lookup(kb->start_addr,
- &size, &offset, &modname, namebuf);
- if (!symbol_name)
- kb->range = 0;
- else
- kb->range = size;
- }
+ populate_kprobe_blacklist(__start_kprobe_blacklist,
+ __stop_kprobe_blacklist);
if (kretprobe_blacklist_size) {
/* lookup the function address from its name */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c180860..504fdbd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2659,6 +2659,7 @@ asmlinkage void __sched notrace preempt_schedule(void)
barrier();
} while (need_resched());
}
+NOKPROBE_SYMBOL(preempt_schedule);
EXPORT_SYMBOL(preempt_schedule);
/*
_______________________________________________
Virtualization mailing list
Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
