972 lines · 24.3 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0/* * fprobe - Simple ftrace probe wrapper for function entry. */#define pr_fmt(fmt) "fprobe: " fmt #include <linux/err.h>#include <linux/fprobe.h>#include <linux/kallsyms.h>#include <linux/kprobes.h>#include <linux/list.h>#include <linux/mutex.h>#include <linux/rhashtable.h>#include <linux/slab.h>#include <linux/sort.h> #include <asm/fprobe.h> #include "trace.h" #define FPROBE_IP_HASH_BITS 8#define FPROBE_IP_TABLE_SIZE (1 << FPROBE_IP_HASH_BITS) #define FPROBE_HASH_BITS 6#define FPROBE_TABLE_SIZE (1 << FPROBE_HASH_BITS) #define SIZE_IN_LONG(x) ((x + sizeof(long) - 1) >> (sizeof(long) == 8 ? 3 : 2)) /* * fprobe_table: hold 'fprobe_hlist::hlist' for checking the fprobe still *   exists. The key is the address of fprobe instance. * fprobe_ip_table: hold 'fprobe_hlist::array[*]' for searching the fprobe *   instance related to the function address. The key is the ftrace IP *   address. * * When unregistering the fprobe, fprobe_hlist::fp and fprobe_hlist::array[*].fp * are set NULL and delete those from both hash tables (by hlist_del_rcu). * After an RCU grace period, the fprobe_hlist itself will be released. * * fprobe_table and fprobe_ip_table can be accessed from either *  - Normal hlist traversal and RCU add/del under 'fprobe_mutex' is held. *  - RCU hlist traversal under disabling preempt */static struct hlist_head fprobe_table[FPROBE_TABLE_SIZE];static struct rhltable fprobe_ip_table;static DEFINE_MUTEX(fprobe_mutex);static struct fgraph_ops fprobe_graph_ops; static u32 fprobe_node_hashfn(const void *data, u32 len, u32 seed){	return hash_ptr(*(unsigned long **)data, 32);} static int fprobe_node_cmp(struct rhashtable_compare_arg *arg,			   const void *ptr){	unsigned long key = *(unsigned long *)arg->key;	const struct fprobe_hlist_node *n = ptr; 	return n->addr != key;} static u32 fprobe_node_obj_hashfn(const void *data, u32 len, u32 seed){	const struct fprobe_hlist_node *n = data; 	return hash_ptr((void *)n->addr, 32);} static const struct rhashtable_params fprobe_rht_params = {	.head_offset		= offsetof(struct fprobe_hlist_node, hlist),	.key_offset		= offsetof(struct fprobe_hlist_node, addr),	.key_len		= sizeof_field(struct fprobe_hlist_node, addr),	.hashfn			= fprobe_node_hashfn,	.obj_hashfn		= fprobe_node_obj_hashfn,	.obj_cmpfn		= fprobe_node_cmp,	.automatic_shrinking	= true,}; /* Node insertion and deletion requires the fprobe_mutex */static int insert_fprobe_node(struct fprobe_hlist_node *node){	lockdep_assert_held(&fprobe_mutex); 	return rhltable_insert(&fprobe_ip_table, &node->hlist, fprobe_rht_params);} /* Return true if there are synonims */static bool delete_fprobe_node(struct fprobe_hlist_node *node){	lockdep_assert_held(&fprobe_mutex);	bool ret; 	/* Avoid double deleting */	if (READ_ONCE(node->fp) != NULL) {		WRITE_ONCE(node->fp, NULL);		rhltable_remove(&fprobe_ip_table, &node->hlist,				fprobe_rht_params);	} 	rcu_read_lock();	ret = !!rhltable_lookup(&fprobe_ip_table, &node->addr,				fprobe_rht_params);	rcu_read_unlock(); 	return ret;} /* Check existence of the fprobe */static bool is_fprobe_still_exist(struct fprobe *fp){	struct hlist_head *head;	struct fprobe_hlist *fph; 	head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)];	hlist_for_each_entry_rcu(fph, head, hlist,				 lockdep_is_held(&fprobe_mutex)) {		if (fph->fp == fp)			return true;	}	return false;}NOKPROBE_SYMBOL(is_fprobe_still_exist); static int add_fprobe_hash(struct fprobe *fp){	struct fprobe_hlist *fph = fp->hlist_array;	struct hlist_head *head; 	lockdep_assert_held(&fprobe_mutex); 	if (WARN_ON_ONCE(!fph))		return -EINVAL; 	if (is_fprobe_still_exist(fp))		return -EEXIST; 	head = &fprobe_table[hash_ptr(fp, FPROBE_HASH_BITS)];	hlist_add_head_rcu(&fp->hlist_array->hlist, head);	return 0;} static int del_fprobe_hash(struct fprobe *fp){	struct fprobe_hlist *fph = fp->hlist_array; 	lockdep_assert_held(&fprobe_mutex); 	if (WARN_ON_ONCE(!fph))		return -EINVAL; 	if (!is_fprobe_still_exist(fp))		return -ENOENT; 	fph->fp = NULL;	hlist_del_rcu(&fph->hlist);	return 0;} #ifdef ARCH_DEFINE_ENCODE_FPROBE_HEADER /* The arch should encode fprobe_header info into one unsigned long */#define FPROBE_HEADER_SIZE_IN_LONG	1 static inline bool write_fprobe_header(unsigned long *stack,					struct fprobe *fp, unsigned int size_words){	if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD ||			 !arch_fprobe_header_encodable(fp)))		return false; 	*stack = arch_encode_fprobe_header(fp, size_words);	return true;} static inline void read_fprobe_header(unsigned long *stack,					struct fprobe **fp, unsigned int *size_words){	*fp = arch_decode_fprobe_header_fp(*stack);	*size_words = arch_decode_fprobe_header_size(*stack);} #else /* Generic fprobe_header */struct __fprobe_header {	struct fprobe *fp;	unsigned long size_words;} __packed; #define FPROBE_HEADER_SIZE_IN_LONG	SIZE_IN_LONG(sizeof(struct __fprobe_header)) static inline bool write_fprobe_header(unsigned long *stack,					struct fprobe *fp, unsigned int size_words){	struct __fprobe_header *fph = (struct __fprobe_header *)stack; 	if (WARN_ON_ONCE(size_words > MAX_FPROBE_DATA_SIZE_WORD))		return false; 	fph->fp = fp;	fph->size_words = size_words;	return true;} static inline void read_fprobe_header(unsigned long *stack,					struct fprobe **fp, unsigned int *size_words){	struct __fprobe_header *fph = (struct __fprobe_header *)stack; 	*fp = fph->fp;	*size_words = fph->size_words;} #endif /* * fprobe shadow stack management: * Since fprobe shares a single fgraph_ops, it needs to share the stack entry * among the probes on the same function exit. Note that a new probe can be * registered before a target function is returning, we can not use the hash * table to find the corresponding probes. Thus the probe address is stored on * the shadow stack with its entry data size. * */static inline int __fprobe_handler(unsigned long ip, unsigned long parent_ip,				   struct fprobe *fp, struct ftrace_regs *fregs,				   void *data){	if (!fp->entry_handler)		return 0; 	return fp->entry_handler(fp, ip, parent_ip, fregs, data);} static inline int __fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip,					  struct fprobe *fp, struct ftrace_regs *fregs,					  void *data){	int ret;	/*	 * This user handler is shared with other kprobes and is not expected to be	 * called recursively. So if any other kprobe handler is running, this will	 * exit as kprobe does. See the section 'Share the callbacks with kprobes'	 * in Documentation/trace/fprobe.rst for more information.	 */	if (unlikely(kprobe_running())) {		fp->nmissed++;		return 0;	} 	kprobe_busy_begin();	ret = __fprobe_handler(ip, parent_ip, fp, fregs, data);	kprobe_busy_end();	return ret;} #if defined(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) || defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS)/* ftrace_ops callback, this processes fprobes which have only entry_handler. */static void fprobe_ftrace_entry(unsigned long ip, unsigned long parent_ip,	struct ftrace_ops *ops, struct ftrace_regs *fregs){	struct fprobe_hlist_node *node;	struct rhlist_head *head, *pos;	struct fprobe *fp;	int bit; 	bit = ftrace_test_recursion_trylock(ip, parent_ip);	if (bit < 0)		return; 	/*	 * ftrace_test_recursion_trylock() disables preemption, but	 * rhltable_lookup() checks whether rcu_read_lcok is held.	 * So we take rcu_read_lock() here.	 */	rcu_read_lock();	head = rhltable_lookup(&fprobe_ip_table, &ip, fprobe_rht_params); 	rhl_for_each_entry_rcu(node, pos, head, hlist) {		if (node->addr != ip)			break;		fp = READ_ONCE(node->fp);		if (unlikely(!fp || fprobe_disabled(fp) || fp->exit_handler))			continue; 		if (fprobe_shared_with_kprobes(fp))			__fprobe_kprobe_handler(ip, parent_ip, fp, fregs, NULL);		else			__fprobe_handler(ip, parent_ip, fp, fregs, NULL);	}	rcu_read_unlock();	ftrace_test_recursion_unlock(bit);}NOKPROBE_SYMBOL(fprobe_ftrace_entry); static struct ftrace_ops fprobe_ftrace_ops = {	.func	= fprobe_ftrace_entry,	.flags	= FTRACE_OPS_FL_SAVE_ARGS,};static int fprobe_ftrace_active; static int fprobe_ftrace_add_ips(unsigned long *addrs, int num){	int ret; 	lockdep_assert_held(&fprobe_mutex); 	ret = ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 0, 0);	if (ret)		return ret; 	if (!fprobe_ftrace_active) {		ret = register_ftrace_function(&fprobe_ftrace_ops);		if (ret) {			ftrace_free_filter(&fprobe_ftrace_ops);			return ret;		}	}	fprobe_ftrace_active++;	return 0;} static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num){	lockdep_assert_held(&fprobe_mutex); 	fprobe_ftrace_active--;	if (!fprobe_ftrace_active)		unregister_ftrace_function(&fprobe_ftrace_ops);	if (num)		ftrace_set_filter_ips(&fprobe_ftrace_ops, addrs, num, 1, 0);} static bool fprobe_is_ftrace(struct fprobe *fp){	return !fp->exit_handler;} #ifdef CONFIG_MODULESstatic void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,			   int reset){	ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);	ftrace_set_filter_ips(&fprobe_ftrace_ops, ips, cnt, remove, reset);}#endif#elsestatic int fprobe_ftrace_add_ips(unsigned long *addrs, int num){	return -ENOENT;} static void fprobe_ftrace_remove_ips(unsigned long *addrs, int num){} static bool fprobe_is_ftrace(struct fprobe *fp){	return false;} #ifdef CONFIG_MODULESstatic void fprobe_set_ips(unsigned long *ips, unsigned int cnt, int remove,			   int reset){	ftrace_set_filter_ips(&fprobe_graph_ops.ops, ips, cnt, remove, reset);}#endif#endif /* !CONFIG_DYNAMIC_FTRACE_WITH_ARGS && !CONFIG_DYNAMIC_FTRACE_WITH_REGS */ /* fgraph_ops callback, this processes fprobes which have exit_handler. */static int fprobe_fgraph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,			       struct ftrace_regs *fregs){	unsigned long *fgraph_data = NULL;	unsigned long func = trace->func;	struct fprobe_hlist_node *node;	struct rhlist_head *head, *pos;	unsigned long ret_ip;	int reserved_words;	struct fprobe *fp;	int used, ret; 	if (WARN_ON_ONCE(!fregs))		return 0; 	guard(rcu)();	head = rhltable_lookup(&fprobe_ip_table, &func, fprobe_rht_params);	reserved_words = 0;	rhl_for_each_entry_rcu(node, pos, head, hlist) {		if (node->addr != func)			continue;		fp = READ_ONCE(node->fp);		if (!fp || !fp->exit_handler)			continue;		/*		 * Since fprobe can be enabled until the next loop, we ignore the		 * fprobe's disabled flag in this loop.		 */		reserved_words +=			FPROBE_HEADER_SIZE_IN_LONG + SIZE_IN_LONG(fp->entry_data_size);	}	if (reserved_words) {		fgraph_data = fgraph_reserve_data(gops->idx, reserved_words * sizeof(long));		if (unlikely(!fgraph_data)) {			rhl_for_each_entry_rcu(node, pos, head, hlist) {				if (node->addr != func)					continue;				fp = READ_ONCE(node->fp);				if (fp && !fprobe_disabled(fp) && !fprobe_is_ftrace(fp))					fp->nmissed++;			}			return 0;		}	} 	/*	 * TODO: recursion detection has been done in the fgraph. Thus we need	 * to add a callback to increment missed counter.	 */	ret_ip = ftrace_regs_get_return_address(fregs);	used = 0;	rhl_for_each_entry_rcu(node, pos, head, hlist) {		int data_size;		void *data; 		if (node->addr != func)			continue;		fp = READ_ONCE(node->fp);		if (unlikely(!fp || fprobe_disabled(fp) || fprobe_is_ftrace(fp)))			continue; 		data_size = fp->entry_data_size;		if (data_size && fp->exit_handler)			data = fgraph_data + used + FPROBE_HEADER_SIZE_IN_LONG;		else			data = NULL; 		if (fprobe_shared_with_kprobes(fp))			ret = __fprobe_kprobe_handler(func, ret_ip, fp, fregs, data);		else			ret = __fprobe_handler(func, ret_ip, fp, fregs, data); 		/* If entry_handler returns !0, nmissed is not counted but skips exit_handler. */		if (!ret && fp->exit_handler) {			int size_words = SIZE_IN_LONG(data_size); 			if (write_fprobe_header(&fgraph_data[used], fp, size_words))				used += FPROBE_HEADER_SIZE_IN_LONG + size_words;		}	}	if (used < reserved_words)		memset(fgraph_data + used, 0, reserved_words - used); 	/* If any exit_handler is set, data must be used. */	return used != 0;}NOKPROBE_SYMBOL(fprobe_fgraph_entry); static void fprobe_return(struct ftrace_graph_ret *trace,			  struct fgraph_ops *gops,			  struct ftrace_regs *fregs){	unsigned long *fgraph_data = NULL;	unsigned long ret_ip;	struct fprobe *fp;	int size, curr;	int size_words; 	fgraph_data = (unsigned long *)fgraph_retrieve_data(gops->idx, &size);	if (WARN_ON_ONCE(!fgraph_data))		return;	size_words = SIZE_IN_LONG(size);	ret_ip = ftrace_regs_get_instruction_pointer(fregs); 	preempt_disable_notrace(); 	curr = 0;	while (size_words > curr) {		read_fprobe_header(&fgraph_data[curr], &fp, &size);		if (!fp)			break;		curr += FPROBE_HEADER_SIZE_IN_LONG;		if (is_fprobe_still_exist(fp) && !fprobe_disabled(fp)) {			if (WARN_ON_ONCE(curr + size > size_words))				break;			fp->exit_handler(fp, trace->func, ret_ip, fregs,					 size ? fgraph_data + curr : NULL);		}		curr += size;	}	preempt_enable_notrace();}NOKPROBE_SYMBOL(fprobe_return); static struct fgraph_ops fprobe_graph_ops = {	.entryfunc	= fprobe_fgraph_entry,	.retfunc	= fprobe_return,};

Lines 1–500 of 972.