diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt index d71fafffce90..da5404ab7569 100644 --- a/Documentation/kprobes.txt +++ b/Documentation/kprobes.txt @@ -14,6 +14,7 @@ CONTENTS 8. Kprobes Example 9. Jprobes Example 10. Kretprobes Example +Appendix A: The kprobes debugfs interface 1. Concepts: Kprobes, Jprobes, Return Probes @@ -349,9 +350,12 @@ for instrumentation and error reporting.) If the number of times a function is called does not match the number of times it returns, registering a return probe on that function may -produce undesirable results. We have the do_exit() case covered. -do_execve() and do_fork() are not an issue. We're unaware of other -specific cases where this could be a problem. +produce undesirable results. In such a case, a line: +kretprobe BUG!: Processing kretprobe d000000000041aa8 @ c00000000004f48c +gets printed. With this information, one will be able to correlate the +exact instance of the kretprobe that caused the problem. We have the +do_exit() case covered. do_execve() and do_fork() are not an issue. +We're unaware of other specific cases where this could be a problem. If, upon entry to or exit from a function, the CPU is running on a stack other than that of the current task, registering a return @@ -614,3 +618,27 @@ http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe http://www.redhat.com/magazine/005mar05/features/kprobes/ http://www-users.cs.umn.edu/~boutcher/kprobes/ http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115) + + +Appendix A: The kprobes debugfs interface + +With recent kernels (> 2.6.20) the list of registered kprobes is visible +under the /debug/kprobes/ directory (assuming debugfs is mounted at /debug). + +/debug/kprobes/list: Lists all registered probes on the system + +c015d71a k vfs_read+0x0 +c011a316 j do_fork+0x0 +c03dedc5 r tcp_v4_rcv+0x0 + +The first column provides the kernel address where the probe is inserted. +The second column identifies the type of probe (k - kprobe, r - kretprobe +and j - jprobe), while the third column specifies the symbol+offset of +the probe. If the probed function belongs to a module, the module name +is also specified. + +/debug/kprobes/enabled: Turn kprobes ON/OFF + +Provides a knob to globally turn registered kprobes ON or OFF. By default, +all kprobes are enabled. By echoing "0" to this file, all registered probes +will be disarmed, till such time a "1" is echoed to this file. diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c index b6a9d64c2251..dde828a333c3 100644 --- a/arch/i386/kernel/kprobes.c +++ b/arch/i386/kernel/kprobes.c @@ -743,6 +743,11 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) return 0; } +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} + int __init arch_init_kprobes(void) { return 0; diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 0b72f0f94192..4f5fd0960ba7 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -1012,3 +1012,12 @@ int __init arch_init_kprobes(void) (kprobe_opcode_t *)((struct fnptr *)kretprobe_trampoline)->ip; return register_kprobe(&trampoline_p); } + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + if (p->addr == + (kprobe_opcode_t *)((struct fnptr *)kretprobe_trampoline)->ip) + return 1; + + return 0; +} diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index aed58e1cb91f..088b8c6defa0 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -550,3 +550,11 @@ int __init arch_init_kprobes(void) { return register_kprobe(&trampoline_p); } + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + return 1; + + return 0; +} diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 9d0f0d09d473..e39333ae0fcf 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -661,3 +661,10 @@ int __init arch_init_kprobes(void) { return register_kprobe(&trampoline_p); } + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + if (p->addr == (kprobe_opcode_t *) & kretprobe_trampoline) + return 1; + return 0; +} diff --git a/arch/x86_64/kernel/kprobes.c b/arch/x86_64/kernel/kprobes.c index f995bea6e2c1..d4a0d0ac9935 100644 --- a/arch/x86_64/kernel/kprobes.c +++ b/arch/x86_64/kernel/kprobes.c @@ -743,3 +743,11 @@ int __init arch_init_kprobes(void) { return register_kprobe(&trampoline_p); } + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + return 1; + + return 0; +} diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 6fc623e41fd8..23adf6075ae4 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -125,11 +125,16 @@ DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); #ifdef ARCH_SUPPORTS_KRETPROBES extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs); +extern int arch_trampoline_kprobe(struct kprobe *p); #else /* ARCH_SUPPORTS_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { } +static inline int arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} #endif /* ARCH_SUPPORTS_KRETPROBES */ /* * Function-return probe - diff --git a/kernel/kprobes.c b/kernel/kprobes.c index f58f171bd65f..9e47d8c493f3 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -43,9 +43,11 @@ #include #include #include + #include #include #include +#include #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) @@ -64,6 +66,9 @@ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE]; static atomic_t kprobe_count; +/* NOTE: change this value only with kprobe_mutex held */ +static bool kprobe_enabled; + DEFINE_MUTEX(kprobe_mutex); /* Protects kprobe_table */ DEFINE_SPINLOCK(kretprobe_lock); /* Protects kretprobe_inst_table */ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; @@ -564,12 +569,13 @@ static int __kprobes __register_kprobe(struct kprobe *p, hlist_add_head_rcu(&p->hlist, &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); - if (atomic_add_return(1, &kprobe_count) == \ + if (kprobe_enabled) { + if (atomic_add_return(1, &kprobe_count) == \ (ARCH_INACTIVE_KPROBE_COUNT + 1)) - register_page_fault_notifier(&kprobe_page_fault_nb); - - arch_arm_kprobe(p); + register_page_fault_notifier(&kprobe_page_fault_nb); + arch_arm_kprobe(p); + } out: mutex_unlock(&kprobe_mutex); @@ -607,8 +613,13 @@ valid_p: if (old_p == p || (old_p->pre_handler == aggr_pre_handler && p->list.next == &old_p->list && p->list.prev == &old_p->list)) { - /* Only probe on the hash list */ - arch_disarm_kprobe(p); + /* + * Only probe on the hash list. Disarm only if kprobes are + * enabled - otherwise, the breakpoint would already have + * been removed. We save on flushing icache. + */ + if (kprobe_enabled) + arch_disarm_kprobe(p); hlist_del_rcu(&old_p->hlist); cleanup_p = 1; } else { @@ -797,6 +808,9 @@ static int __init init_kprobes(void) } atomic_set(&kprobe_count, 0); + /* By default, kprobes are enabled */ + kprobe_enabled = true; + err = arch_init_kprobes(); if (!err) err = register_die_notifier(&kprobe_exceptions_nb); @@ -806,7 +820,7 @@ static int __init init_kprobes(void) #ifdef CONFIG_DEBUG_FS static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, - const char *sym, int offset,char *modname) + const char *sym, int offset,char *modname) { char *kprobe_type; @@ -885,9 +899,130 @@ static struct file_operations debugfs_kprobes_operations = { .release = seq_release, }; +static void __kprobes enable_all_kprobes(void) +{ + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + + mutex_lock(&kprobe_mutex); + + /* If kprobes are already enabled, just return */ + if (kprobe_enabled) + goto already_enabled; + + /* + * Re-register the page fault notifier only if there are any + * active probes at the time of enabling kprobes globally + */ + if (atomic_read(&kprobe_count) > ARCH_INACTIVE_KPROBE_COUNT) + register_page_fault_notifier(&kprobe_page_fault_nb); + + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) + arch_arm_kprobe(p); + } + + kprobe_enabled = true; + printk(KERN_INFO "Kprobes globally enabled\n"); + +already_enabled: + mutex_unlock(&kprobe_mutex); + return; +} + +static void __kprobes disable_all_kprobes(void) +{ + struct hlist_head *head; + struct hlist_node *node; + struct kprobe *p; + unsigned int i; + + mutex_lock(&kprobe_mutex); + + /* If kprobes are already disabled, just return */ + if (!kprobe_enabled) + goto already_disabled; + + kprobe_enabled = false; + printk(KERN_INFO "Kprobes globally disabled\n"); + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry_rcu(p, node, head, hlist) { + if (!arch_trampoline_kprobe(p)) + arch_disarm_kprobe(p); + } + } + + mutex_unlock(&kprobe_mutex); + /* Allow all currently running kprobes to complete */ + synchronize_sched(); + + mutex_lock(&kprobe_mutex); + /* Unconditionally unregister the page_fault notifier */ + unregister_page_fault_notifier(&kprobe_page_fault_nb); + +already_disabled: + mutex_unlock(&kprobe_mutex); + return; +} + +/* + * XXX: The debugfs bool file interface doesn't allow for callbacks + * when the bool state is switched. We can reuse that facility when + * available + */ +static ssize_t read_enabled_file_bool(struct file *file, + char __user *user_buf, size_t count, loff_t *ppos) +{ + char buf[3]; + + if (kprobe_enabled) + buf[0] = '1'; + else + buf[0] = '0'; + buf[1] = '\n'; + buf[2] = 0x00; + return simple_read_from_buffer(user_buf, count, ppos, buf, 2); +} + +static ssize_t write_enabled_file_bool(struct file *file, + const char __user *user_buf, size_t count, loff_t *ppos) +{ + char buf[32]; + int buf_size; + + buf_size = min(count, (sizeof(buf)-1)); + if (copy_from_user(buf, user_buf, buf_size)) + return -EFAULT; + + switch (buf[0]) { + case 'y': + case 'Y': + case '1': + enable_all_kprobes(); + break; + case 'n': + case 'N': + case '0': + disable_all_kprobes(); + break; + } + + return count; +} + +static struct file_operations fops_kp = { + .read = read_enabled_file_bool, + .write = write_enabled_file_bool, +}; + static int __kprobes debugfs_kprobe_init(void) { struct dentry *dir, *file; + unsigned int value = 1; dir = debugfs_create_dir("kprobes", NULL); if (!dir) @@ -900,6 +1035,13 @@ static int __kprobes debugfs_kprobe_init(void) return -ENOMEM; } + file = debugfs_create_file("enabled", 0600, dir, + &value, &fops_kp); + if (!file) { + debugfs_remove(dir); + return -ENOMEM; + } + return 0; }