diff options
Diffstat (limited to 'include/linux/ftrace.h')
| -rw-r--r-- | include/linux/ftrace.h | 745 |
1 files changed, 591 insertions, 154 deletions
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 730876187344..770f0dc993cc 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -7,7 +7,9 @@ #ifndef _LINUX_FTRACE_H #define _LINUX_FTRACE_H +#include <linux/trace_recursion.h> #include <linux/trace_clock.h> +#include <linux/jump_label.h> #include <linux/kallsyms.h> #include <linux/linkage.h> #include <linux/bitops.h> @@ -29,16 +31,45 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif +#ifdef CONFIG_TRACING +extern void ftrace_boot_snapshot(void); +#else +static inline void ftrace_boot_snapshot(void) { } +#endif + +struct ftrace_ops; +struct ftrace_regs; +struct dyn_ftrace; + +char *arch_ftrace_match_adjust(char *str, const char *search); + +#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS +unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs); +#else +unsigned long ftrace_return_to_handler(unsigned long frame_pointer); +#endif + +#ifdef CONFIG_FUNCTION_TRACER /* * If the arch's mcount caller does not support all of ftrace's * features, then it must call an indirect function that - * does. Or at least does enough to prevent any unwelcomed side effects. + * does. Or at least does enough to prevent any unwelcome side effects. + * + * Also define the function prototype that these architectures use + * to call the ftrace_ops_list_func(). */ #if !ARCH_SUPPORTS_FTRACE_OPS # define FTRACE_FORCE_LIST_FUNC 1 +void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); #else # define FTRACE_FORCE_LIST_FUNC 0 +void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); #endif +extern const struct ftrace_ops ftrace_nop_ops; +extern const struct ftrace_ops ftrace_list_ops; +struct ftrace_ops *ftrace_find_unique_ops(struct dyn_ftrace *rec); +#endif /* CONFIG_FUNCTION_TRACER */ /* Main tracing buffer and events set up */ #ifdef CONFIG_TRACING @@ -54,19 +85,23 @@ struct ftrace_hash; #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_MODULES) && \ defined(CONFIG_DYNAMIC_FTRACE) -const char * +int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym); -int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value, - char *type, char *name, - char *module_name, int *exported); #else -static inline const char * +static inline int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { - return NULL; + return 0; } +#endif + +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value, + char *type, char *name, + char *module_name, int *exported); +#else static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) @@ -75,26 +110,180 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val } #endif - #ifdef CONFIG_FUNCTION_TRACER +#include <linux/ftrace_regs.h> + extern int ftrace_enabled; -extern int -ftrace_enable_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); -struct ftrace_ops; +/** + * ftrace_regs - ftrace partial/optimal register set + * + * ftrace_regs represents a group of registers which is used at the + * function entry and exit. There are three types of registers. + * + * - Registers for passing the parameters to callee, including the stack + * pointer. (e.g. rcx, rdx, rdi, rsi, r8, r9 and rsp on x86_64) + * - Registers for passing the return values to caller. + * (e.g. rax and rdx on x86_64) + * - Registers for hooking the function call and return including the + * frame pointer (the frame pointer is architecture/config dependent) + * (e.g. rip, rbp and rsp for x86_64) + * + * Also, architecture dependent fields can be used for internal process. + * (e.g. orig_ax on x86_64) + * + * Basically, ftrace_regs stores the registers related to the context. + * On function entry, registers for function parameters and hooking the + * function call are stored, and on function exit, registers for function + * return value and frame pointers are stored. + * + * And also, it dpends on the context that which registers are restored + * from the ftrace_regs. + * On the function entry, those registers will be restored except for + * the stack pointer, so that user can change the function parameters + * and instruction pointer (e.g. live patching.) + * On the function exit, only registers which is used for return values + * are restored. + * + * NOTE: user *must not* access regs directly, only do it via APIs, because + * the member can be changed according to the architecture. + * This is why the structure is empty here, so that nothing accesses + * the ftrace_regs directly. + */ +struct ftrace_regs { + /* Nothing to see here, use the accessor functions! */ +}; + +#define ftrace_regs_size() sizeof(struct __arch_ftrace_regs) + +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +/* + * Architectures that define HAVE_DYNAMIC_FTRACE_WITH_ARGS must define their own + * arch_ftrace_get_regs() where it only returns pt_regs *if* it is fully + * populated. It should return NULL otherwise. + */ +static inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) +{ + return &arch_ftrace_regs(fregs)->regs; +} + +/* + * ftrace_regs_set_instruction_pointer() is to be defined by the architecture + * if to allow setting of the instruction pointer from the ftrace_regs when + * HAVE_DYNAMIC_FTRACE_WITH_ARGS is set and it supports live kernel patching. + */ +#define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0) +#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ + +#ifdef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS + +static_assert(sizeof(struct pt_regs) == ftrace_regs_size()); + +#endif /* CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ + +static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs) +{ + if (!fregs) + return NULL; + + return arch_ftrace_get_regs(fregs); +} + +#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \ + defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS) + +#ifndef arch_ftrace_partial_regs +#define arch_ftrace_partial_regs(regs) do {} while (0) +#endif + +static __always_inline struct pt_regs * +ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + /* + * If CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS=y, ftrace_regs memory + * layout is including pt_regs. So always returns that address. + * Since arch_ftrace_get_regs() will check some members and may return + * NULL, we can not use it. + */ + regs = &arch_ftrace_regs(fregs)->regs; + + /* Allow arch specific updates to regs. */ + arch_ftrace_partial_regs(regs); + return regs; +} + +#endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS + +/* + * Please define arch dependent pt_regs which compatible to the + * perf_arch_fetch_caller_regs() but based on ftrace_regs. + * This requires + * - user_mode(_regs) returns false (always kernel mode). + * - able to use the _regs for stack trace. + */ +#ifndef arch_ftrace_fill_perf_regs +/* As same as perf_arch_fetch_caller_regs(), do nothing by default */ +#define arch_ftrace_fill_perf_regs(fregs, _regs) do {} while (0) +#endif + +static __always_inline struct pt_regs * +ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + arch_ftrace_fill_perf_regs(fregs, regs); + return regs; +} + +#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ + +static __always_inline struct pt_regs * +ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs) +{ + return &arch_ftrace_regs(fregs)->regs; +} + +#endif + +/* + * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs. + * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs. + */ +static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs) +{ + if (IS_ENABLED(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS)) + return true; + + return ftrace_get_regs(fregs) != NULL; +} + +#ifdef CONFIG_HAVE_REGS_AND_STACK_ACCESS_API +static __always_inline unsigned long +ftrace_regs_get_kernel_stack_nth(struct ftrace_regs *fregs, unsigned int nth) +{ + unsigned long *stackp; + + stackp = (unsigned long *)ftrace_regs_get_stack_pointer(fregs); + if (((unsigned long)(stackp + nth) & ~(THREAD_SIZE - 1)) == + ((unsigned long)stackp & ~(THREAD_SIZE - 1))) + return *(stackp + nth); + + return 0; +} +#else /* !CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ +#define ftrace_regs_get_kernel_stack_nth(fregs, nth) (0L) +#endif /* CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */ typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *regs); + struct ftrace_ops *op, struct ftrace_regs *fregs); ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); /* * FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are * set in the flags member. - * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION_SAFE, STUB and + * CONTROL, SAVE_REGS, SAVE_REGS_IF_SUPPORTED, RECURSION, STUB and * IPMODIFY are a kind of attribute flags which can be set only before * registering the ftrace_ops, and can not be modified while registered. * Changing those attribute flags after registering ftrace_ops will @@ -117,10 +306,10 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * passing regs to the handler. * Note, if this flag is set, the SAVE_REGS flag will automatically * get set upon registering the ftrace_ops, if the arch supports it. - * RECURSION_SAFE - The ftrace_ops can set this to tell the ftrace infrastructure - * that the call back has its own recursion protection. If it does - * not set this, then the ftrace infrastructure will add recursion - * protection for the caller. + * RECURSION - The ftrace_ops can set this to tell the ftrace infrastructure + * that the call back needs recursion protection. If it does + * not set this, then the ftrace infrastructure will assume + * that the callback can handle recursion on its own. * STUB - The ftrace_ops is just a place holder. * INITIALIZED - The ftrace_ops has already been initialized (first use time * register_ftrace_function() is called, it will initialized the ops) @@ -142,26 +331,80 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * PID - Is affected by set_ftrace_pid (allows filtering on those pids) * RCU - Set when the ops can only be called when RCU is watching. * TRACE_ARRAY - The ops->private points to a trace_array descriptor. + * PERMANENT - Set when the ops is permanent and should not be affected by + * ftrace_enabled. + * DIRECT - Used by the direct ftrace_ops helper for direct functions + * (internal ftrace only, should not be used by others) + * SUBOP - Is controlled by another op in field managed. + * GRAPH - Is a component of the fgraph_ops structure */ enum { - FTRACE_OPS_FL_ENABLED = 1 << 0, - FTRACE_OPS_FL_DYNAMIC = 1 << 1, - FTRACE_OPS_FL_SAVE_REGS = 1 << 2, - FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = 1 << 3, - FTRACE_OPS_FL_RECURSION_SAFE = 1 << 4, - FTRACE_OPS_FL_STUB = 1 << 5, - FTRACE_OPS_FL_INITIALIZED = 1 << 6, - FTRACE_OPS_FL_DELETED = 1 << 7, - FTRACE_OPS_FL_ADDING = 1 << 8, - FTRACE_OPS_FL_REMOVING = 1 << 9, - FTRACE_OPS_FL_MODIFYING = 1 << 10, - FTRACE_OPS_FL_ALLOC_TRAMP = 1 << 11, - FTRACE_OPS_FL_IPMODIFY = 1 << 12, - FTRACE_OPS_FL_PID = 1 << 13, - FTRACE_OPS_FL_RCU = 1 << 14, - FTRACE_OPS_FL_TRACE_ARRAY = 1 << 15, + FTRACE_OPS_FL_ENABLED = BIT(0), + FTRACE_OPS_FL_DYNAMIC = BIT(1), + FTRACE_OPS_FL_SAVE_REGS = BIT(2), + FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED = BIT(3), + FTRACE_OPS_FL_RECURSION = BIT(4), + FTRACE_OPS_FL_STUB = BIT(5), + FTRACE_OPS_FL_INITIALIZED = BIT(6), + FTRACE_OPS_FL_DELETED = BIT(7), + FTRACE_OPS_FL_ADDING = BIT(8), + FTRACE_OPS_FL_REMOVING = BIT(9), + FTRACE_OPS_FL_MODIFYING = BIT(10), + FTRACE_OPS_FL_ALLOC_TRAMP = BIT(11), + FTRACE_OPS_FL_IPMODIFY = BIT(12), + FTRACE_OPS_FL_PID = BIT(13), + FTRACE_OPS_FL_RCU = BIT(14), + FTRACE_OPS_FL_TRACE_ARRAY = BIT(15), + FTRACE_OPS_FL_PERMANENT = BIT(16), + FTRACE_OPS_FL_DIRECT = BIT(17), + FTRACE_OPS_FL_SUBOP = BIT(18), + FTRACE_OPS_FL_GRAPH = BIT(19), + FTRACE_OPS_FL_JMP = BIT(20), }; +#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +#define FTRACE_OPS_FL_SAVE_ARGS FTRACE_OPS_FL_SAVE_REGS +#else +#define FTRACE_OPS_FL_SAVE_ARGS 0 +#endif + +/* + * FTRACE_OPS_CMD_* commands allow the ftrace core logic to request changes + * to a ftrace_ops. Note, the requests may fail. + * + * ENABLE_SHARE_IPMODIFY_SELF - enable a DIRECT ops to work on the same + * function as an ops with IPMODIFY. Called + * when the DIRECT ops is being registered. + * This is called with both direct_mutex and + * ftrace_lock are locked. + * + * ENABLE_SHARE_IPMODIFY_PEER - enable a DIRECT ops to work on the same + * function as an ops with IPMODIFY. Called + * when the other ops (the one with IPMODIFY) + * is being registered. + * This is called with direct_mutex locked. + * + * DISABLE_SHARE_IPMODIFY_PEER - disable a DIRECT ops to work on the same + * function as an ops with IPMODIFY. Called + * when the other ops (the one with IPMODIFY) + * is being unregistered. + * This is called with direct_mutex locked. + */ +enum ftrace_ops_cmd { + FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_SELF, + FTRACE_OPS_CMD_ENABLE_SHARE_IPMODIFY_PEER, + FTRACE_OPS_CMD_DISABLE_SHARE_IPMODIFY_PEER, +}; + +/* + * For most ftrace_ops_cmd, + * Returns: + * 0 - Success. + * Negative on failure. The return value is dependent on the + * callback. + */ +typedef int (*ftrace_ops_func_t)(struct ftrace_ops *op, enum ftrace_ops_cmd cmd); + #ifdef CONFIG_DYNAMIC_FTRACE /* The hash used to know what functions callbacks trace */ struct ftrace_ops_hash { @@ -173,7 +416,10 @@ struct ftrace_ops_hash { void ftrace_free_init_mem(void); void ftrace_free_mem(struct module *mod, void *start, void *end); #else -static inline void ftrace_free_init_mem(void) { } +static inline void ftrace_free_init_mem(void) +{ + ftrace_boot_snapshot(); +} static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } #endif @@ -200,9 +446,39 @@ struct ftrace_ops { struct ftrace_ops_hash old_hash; unsigned long trampoline; unsigned long trampoline_size; + struct list_head list; + struct list_head subop_list; + ftrace_ops_func_t ops_func; + struct ftrace_ops *managed; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + unsigned long direct_call; +#endif #endif }; +extern struct ftrace_ops __rcu *ftrace_ops_list; +extern struct ftrace_ops ftrace_list_end; + +/* + * Traverse the ftrace_ops_list, invoking all entries. The reason that we + * can use rcu_dereference_raw_check() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw_check() calls are needed to handle + * concurrent insertions into the ftrace_ops_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw_check(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + /* * Type of the current tracing. */ @@ -225,8 +501,10 @@ int register_ftrace_function(struct ftrace_ops *ops); int unregister_ftrace_function(struct ftrace_ops *ops); extern void ftrace_stub(unsigned long a0, unsigned long a1, - struct ftrace_ops *op, struct pt_regs *regs); + struct ftrace_ops *op, struct ftrace_regs *fregs); + +int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs); #else /* !CONFIG_FUNCTION_TRACER */ /* * (un)register_ftrace_function must be a macro since the ops parameter @@ -237,25 +515,105 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1, static inline void ftrace_kill(void) { } static inline void ftrace_free_init_mem(void) { } static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { } +static inline int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *addrs) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_FUNCTION_TRACER */ -#ifdef CONFIG_STACK_TRACER +struct ftrace_func_entry { + struct hlist_node hlist; + unsigned long ip; + unsigned long direct; /* for direct lookup only */ +}; -#define STACK_TRACE_ENTRIES 500 +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +unsigned long ftrace_find_rec_direct(unsigned long ip); +int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); +int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, + bool free_filters); +int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); +int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr); -struct stack_trace; +void ftrace_stub_direct_tramp(void); -extern unsigned stack_trace_index[]; -extern struct stack_trace stack_trace_max; -extern unsigned long stack_trace_max_size; -extern arch_spinlock_t stack_trace_max_lock; +#else +struct ftrace_ops; +static inline unsigned long ftrace_find_rec_direct(unsigned long ip) +{ + return 0; +} +static inline int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) +{ + return -ENODEV; +} +static inline int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, + bool free_filters) +{ + return -ENODEV; +} +static inline int modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr) +{ + return -ENODEV; +} +static inline int modify_ftrace_direct_nolock(struct ftrace_ops *ops, unsigned long addr) +{ + return -ENODEV; +} -extern int stack_tracer_enabled; -void stack_trace_print(void); -int -stack_trace_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +/* + * This must be implemented by the architecture. + * It is the way the ftrace direct_ops helper, when called + * via ftrace (because there's other callbacks besides the + * direct call), can inform the architecture's trampoline that this + * routine has a direct caller, and what the caller is. + * + * For example, in x86, it returns the direct caller + * callback function via the regs->orig_ax parameter. + * Then in the ftrace trampoline, if this is set, it makes + * the return from the trampoline jump to the direct caller + * instead of going back to the function it just traced. + */ +static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, + unsigned long addr) { } +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP +static inline bool ftrace_is_jmp(unsigned long addr) +{ + return addr & 1; +} + +static inline unsigned long ftrace_jmp_set(unsigned long addr) +{ + return addr | 1UL; +} + +static inline unsigned long ftrace_jmp_get(unsigned long addr) +{ + return addr & ~1UL; +} +#else +static inline bool ftrace_is_jmp(unsigned long addr) +{ + return false; +} + +static inline unsigned long ftrace_jmp_set(unsigned long addr) +{ + return addr; +} + +static inline unsigned long ftrace_jmp_get(unsigned long addr) +{ + return addr; +} +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_JMP */ + +#ifdef CONFIG_STACK_TRACER + +int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ DECLARE_PER_CPU(int, disable_stack_tracer); @@ -273,7 +631,7 @@ DECLARE_PER_CPU(int, disable_stack_tracer); */ static inline void stack_tracer_disable(void) { - /* Preemption or interupts must be disabled */ + /* Preemption or interrupts must be disabled */ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) WARN_ON_ONCE(!preempt_count() || !irqs_disabled()); this_cpu_inc(disable_stack_tracer); @@ -296,12 +654,34 @@ static inline void stack_tracer_disable(void) { } static inline void stack_tracer_enable(void) { } #endif -#ifdef CONFIG_DYNAMIC_FTRACE +enum { + FTRACE_UPDATE_CALLS = (1 << 0), + FTRACE_DISABLE_CALLS = (1 << 1), + FTRACE_UPDATE_TRACE_FUNC = (1 << 2), + FTRACE_START_FUNC_RET = (1 << 3), + FTRACE_STOP_FUNC_RET = (1 << 4), + FTRACE_MAY_SLEEP = (1 << 5), +}; -int ftrace_arch_code_modify_prepare(void); -int ftrace_arch_code_modify_post_process(void); +/* Arches can override ftrace_get_symaddr() to convert fentry_ip to symaddr. */ +#ifndef ftrace_get_symaddr +/** + * ftrace_get_symaddr - return the symbol address from fentry_ip + * @fentry_ip: the address of ftrace location + * + * Get the symbol address from @fentry_ip (fast path). If there is no fast + * search path, this returns 0. + * User may need to use kallsyms API to find the symbol address. + */ +#define ftrace_get_symaddr(fentry_ip) (0) +#endif -struct dyn_ftrace; +void ftrace_sync_ipi(void *data); + +#ifdef CONFIG_DYNAMIC_FTRACE + +void ftrace_arch_code_modify_prepare(void); +void ftrace_arch_code_modify_post_process(void); enum ftrace_bug_type { FTRACE_BUG_UNKNOWN, @@ -340,9 +720,14 @@ bool is_ftrace_trampoline(unsigned long addr); * REGS_EN - the function is set up to save regs. * IPMODIFY - the record allows for the IP address to be changed. * DISABLED - the record is not ready to be touched yet + * DIRECT - there is a direct function to call + * CALL_OPS - the record can use callsite-specific ops + * CALL_OPS_EN - the function is set up to use callsite-specific ops + * TOUCHED - A callback was added since boot up + * MODIFIED - The function had IPMODIFY or DIRECT attached to it * * When a new ftrace_ops is registered and wants a function to save - * pt_regs, the rec->flag REGS is set. When the function has been + * pt_regs, the rec->flags REGS is set. When the function has been * set up to save regs, the REG_EN flag is set. Once a function * starts saving regs it will do so until all ftrace_ops are removed * from tracing that function. @@ -355,15 +740,18 @@ enum { FTRACE_FL_TRAMP_EN = (1UL << 27), FTRACE_FL_IPMODIFY = (1UL << 26), FTRACE_FL_DISABLED = (1UL << 25), + FTRACE_FL_DIRECT = (1UL << 24), + FTRACE_FL_DIRECT_EN = (1UL << 23), + FTRACE_FL_CALL_OPS = (1UL << 22), + FTRACE_FL_CALL_OPS_EN = (1UL << 21), + FTRACE_FL_TOUCHED = (1UL << 20), + FTRACE_FL_MODIFIED = (1UL << 19), }; -#define FTRACE_REF_MAX_SHIFT 25 -#define FTRACE_FL_BITS 7 -#define FTRACE_FL_MASKED_BITS ((1UL << FTRACE_FL_BITS) - 1) -#define FTRACE_FL_MASK (FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT) +#define FTRACE_REF_MAX_SHIFT 19 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) -#define ftrace_rec_count(rec) ((rec)->flags & ~FTRACE_FL_MASK) +#define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) struct dyn_ftrace { unsigned long ip; /* address of mcount call-site */ @@ -371,9 +759,10 @@ struct dyn_ftrace { struct dyn_arch_ftrace arch; }; -int ftrace_force_update(void); int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset); +int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, + unsigned int cnt, int remove, int reset); int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset); int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, @@ -383,15 +772,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); void ftrace_free_filter(struct ftrace_ops *ops); void ftrace_ops_set_global_filter(struct ftrace_ops *ops); -enum { - FTRACE_UPDATE_CALLS = (1 << 0), - FTRACE_DISABLE_CALLS = (1 << 1), - FTRACE_UPDATE_TRACE_FUNC = (1 << 2), - FTRACE_START_FUNC_RET = (1 << 3), - FTRACE_STOP_FUNC_RET = (1 << 4), - FTRACE_MAY_SLEEP = (1 << 5), -}; - /* * The FTRACE_UPDATE_* enum is used to pass information back * from the ftrace_update_record() and ftrace_test_record() @@ -418,6 +798,8 @@ enum { FTRACE_ITER_PROBE = (1 << 4), FTRACE_ITER_MOD = (1 << 5), FTRACE_ITER_ENABLED = (1 << 6), + FTRACE_ITER_TOUCHED = (1 << 7), + FTRACE_ITER_ADDRS = (1 << 8), }; void arch_ftrace_update_code(int command); @@ -437,8 +819,8 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter); iter = ftrace_rec_iter_next(iter)) -int ftrace_update_record(struct dyn_ftrace *rec, int enable); -int ftrace_test_record(struct dyn_ftrace *rec, int enable); +int ftrace_update_record(struct dyn_ftrace *rec, bool enable); +int ftrace_test_record(struct dyn_ftrace *rec, bool enable); void ftrace_run_stop_machine(int command); unsigned long ftrace_location(unsigned long ip); unsigned long ftrace_location_range(unsigned long start, unsigned long end); @@ -459,7 +841,6 @@ void __init ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable); /* defined in arch */ -extern int ftrace_ip_converted(unsigned long ip); extern int ftrace_dyn_arch_init(void); extern void ftrace_replace_code(int enable); extern int ftrace_update_ftrace_func(ftrace_func_t func); @@ -509,7 +890,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } /** * ftrace_make_nop - convert code into nop * @mod: module structure if called by module load initialization - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should be calling * * This is a very sensitive operation and great care needs @@ -531,8 +912,53 @@ extern int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr); /** + * ftrace_need_init_nop - return whether nop call sites should be initialized + * + * Normally the compiler's -mnop-mcount generates suitable nops, so we don't + * need to call ftrace_init_nop() if the code is built with that flag. + * Architectures where this is not always the case may define their own + * condition. + * + * Return must be: + * 0 if ftrace_init_nop() should be called + * Nonzero if ftrace_init_nop() should not be called + */ + +#ifndef ftrace_need_init_nop +#define ftrace_need_init_nop() (!__is_defined(CC_USING_NOP_MCOUNT)) +#endif + +/** + * ftrace_init_nop - initialize a nop call site + * @mod: module structure if called by module load initialization + * @rec: the call site record (e.g. mcount/fentry) + * + * This is a very sensitive operation and great care needs + * to be taken by the arch. The operation should carefully + * read the location, check to see if what is read is indeed + * what we expect it to be, and then on success of the compare, + * it should write to the location. + * + * The code segment at @rec->ip should contain the contents created by + * the compiler + * + * Return must be: + * 0 on success + * -EFAULT on error reading the location + * -EINVAL on a failed compare of the contents + * -EPERM on error writing to the location + * Any other value will be considered a failure. + */ +#ifndef ftrace_init_nop +static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + return ftrace_make_nop(mod, rec, MCOUNT_ADDR); +} +#endif + +/** * ftrace_make_call - convert a nop call site into a call to addr - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should call * * This is a very sensitive operation and great care needs @@ -552,10 +978,12 @@ extern int ftrace_make_nop(struct module *mod, */ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \ + defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) || \ + defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) /** * ftrace_modify_call - convert from one addr to another (no nop) - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @old_addr: the address expected to be currently called to * @addr: the address to change to * @@ -565,6 +993,9 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); * what we expect it to be, and then on success of the compare, * it should write to the location. * + * When using call ops, this is called when the associated ops change, even + * when (addr == old_addr). + * * The code segment at @rec->ip should be a caller to @old_addr * * Return must be: @@ -585,21 +1016,12 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a } #endif -/* May be defined in arch */ -extern int ftrace_arch_read_dyn_info(char *buf, int size); - extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); extern void ftrace_module_enable(struct module *mod); extern void ftrace_release_mod(struct module *mod); - -extern void ftrace_disable_daemon(void); -extern void ftrace_enable_daemon(void); #else /* CONFIG_DYNAMIC_FTRACE */ static inline int skip_trace(unsigned long ip) { return 0; } -static inline int ftrace_force_update(void) { return 0; } -static inline void ftrace_disable_daemon(void) { } -static inline void ftrace_enable_daemon(void) { } static inline void ftrace_module_init(struct module *mod) { } static inline void ftrace_module_enable(struct module *mod) { } static inline void ftrace_release_mod(struct module *mod) { } @@ -620,6 +1042,7 @@ static inline unsigned long ftrace_location(unsigned long ip) #define ftrace_regex_open(ops, flag, inod, file) ({ -ENODEV; }) #define ftrace_set_early_filter(ops, buf, enable) do { } while (0) #define ftrace_set_filter_ip(ops, ip, remove, reset) ({ -ENODEV; }) +#define ftrace_set_filter_ips(ops, ips, cnt, remove, reset) ({ -ENODEV; }) #define ftrace_set_filter(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_set_notrace(ops, buf, len, reset) ({ -ENODEV; }) #define ftrace_free_filter(ops) do { } while (0) @@ -638,6 +1061,15 @@ static inline bool is_ftrace_trampoline(unsigned long addr) } #endif /* CONFIG_DYNAMIC_FTRACE */ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifndef ftrace_graph_func +#define ftrace_graph_func ftrace_stub +#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB +#else +#define FTRACE_OPS_GRAPH_STUB 0 +#endif +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); @@ -693,7 +1125,7 @@ static inline void __ftrace_enabled_restore(int enabled) #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5)) #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6)) -static inline unsigned long get_lock_parent_ip(void) +static __always_inline unsigned long get_lock_parent_ip(void) { unsigned long addr = CALLER_ADDR0; @@ -717,8 +1149,13 @@ static inline unsigned long get_lock_parent_ip(void) # define trace_preempt_off(a0, a1) do { } while (0) #endif -#ifdef CONFIG_FTRACE_MCOUNT_RECORD +#ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_init(void); +#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY +#define FTRACE_CALLSITE_SECTION "__patchable_function_entries" +#else +#define FTRACE_CALLSITE_SECTION "__mcount_loc" +#endif #else static inline void ftrace_init(void) { } #endif @@ -730,7 +1167,15 @@ static inline void ftrace_init(void) { } */ struct ftrace_graph_ent { unsigned long func; /* Current function */ - int depth; + unsigned long depth; +} __packed; + +/* + * Structure that defines an entry function trace with retaddr. + */ +struct fgraph_retaddr_ent { + struct ftrace_graph_ent ent; + unsigned long retaddr; /* Return address */ } __packed; /* @@ -740,24 +1185,44 @@ struct ftrace_graph_ent { */ struct ftrace_graph_ret { unsigned long func; /* Current function */ - /* Number of functions that overran the depth limit for current task */ - unsigned long overrun; - unsigned long long calltime; - unsigned long long rettime; +#ifdef CONFIG_FUNCTION_GRAPH_RETVAL + unsigned long retval; +#endif int depth; + /* Number of functions that overran the depth limit for current task */ + unsigned int overrun; } __packed; +struct fgraph_ops; + /* Type of the callback handlers for tracing function graph*/ -typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */ -typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */ +typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *, + struct fgraph_ops *, + struct ftrace_regs *); /* return */ +typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *, + struct fgraph_ops *, + struct ftrace_regs *); /* entry */ + +extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, + struct fgraph_ops *gops, + struct ftrace_regs *fregs); +bool ftrace_pids_enabled(struct ftrace_ops *ops); #ifdef CONFIG_FUNCTION_GRAPH_TRACER struct fgraph_ops { trace_func_graph_ent_t entryfunc; trace_func_graph_ret_t retfunc; + struct ftrace_ops ops; /* for the hash lists */ + void *private; + trace_func_graph_ent_t saved_func; + int idx; }; +void *fgraph_reserve_data(int idx, int size_bytes); +void *fgraph_retrieve_data(int idx, int *size_bytes); +void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth); + /* * Stack of return addresses for functions * of a thread. @@ -766,16 +1231,10 @@ struct fgraph_ops { struct ftrace_ret_stack { unsigned long ret; unsigned long func; - unsigned long long calltime; -#ifdef CONFIG_FUNCTION_PROFILER - unsigned long long subtime; -#endif #ifdef HAVE_FUNCTION_GRAPH_FP_TEST unsigned long fp; #endif -#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR unsigned long *retp; -#endif }; /* @@ -786,14 +1245,23 @@ struct ftrace_ret_stack { extern void return_to_handler(void); extern int -function_graph_enter(unsigned long ret, unsigned long func, - unsigned long frame_pointer, unsigned long *retp); +function_graph_enter_regs(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp, + struct ftrace_regs *fregs); + +static inline int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long fp, unsigned long *retp) +{ + return function_graph_enter_regs(ret, func, fp, retp, NULL); +} struct ftrace_ret_stack * -ftrace_graph_get_ret_stack(struct task_struct *task, int idx); +ftrace_graph_get_ret_stack(struct task_struct *task, int skip); +unsigned long ftrace_graph_top_ret_addr(struct task_struct *task); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); +unsigned long *fgraph_get_task_var(struct fgraph_ops *gops); /* * Sometimes we don't want to trace a function with the function @@ -808,7 +1276,20 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, extern int register_ftrace_graph(struct fgraph_ops *ops); extern void unregister_ftrace_graph(struct fgraph_ops *ops); -extern bool ftrace_graph_is_dead(void); +/** + * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called + * + * ftrace_graph_stop() is called when a severe error is detected in + * the function graph tracing. This function is called by the critical + * paths of function graph to keep those paths from doing any more harm. + */ +DECLARE_STATIC_KEY_FALSE(kill_ftrace_graph); + +static inline bool ftrace_graph_is_dead(void) +{ + return static_branch_unlikely(&kill_ftrace_graph); +} + extern void ftrace_graph_stop(void); /* The current handlers in use */ @@ -819,6 +1300,9 @@ extern void ftrace_graph_init_task(struct task_struct *t); extern void ftrace_graph_exit_task(struct task_struct *t); extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu); +/* Used by assembly, but to quiet sparse warnings */ +extern struct ftrace_ops *function_trace_op; + static inline void pause_graph_tracing(void) { atomic_inc(¤t->tracing_graph_pause); @@ -852,58 +1336,11 @@ static inline void unpause_graph_tracing(void) { } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef CONFIG_TRACING - -/* flags for current->trace */ -enum { - TSK_TRACE_FL_TRACE_BIT = 0, - TSK_TRACE_FL_GRAPH_BIT = 1, -}; -enum { - TSK_TRACE_FL_TRACE = 1 << TSK_TRACE_FL_TRACE_BIT, - TSK_TRACE_FL_GRAPH = 1 << TSK_TRACE_FL_GRAPH_BIT, -}; - -static inline void set_tsk_trace_trace(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_trace(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_TRACE_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_trace(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_TRACE; -} - -static inline void set_tsk_trace_graph(struct task_struct *tsk) -{ - set_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline void clear_tsk_trace_graph(struct task_struct *tsk) -{ - clear_bit(TSK_TRACE_FL_GRAPH_BIT, &tsk->trace); -} - -static inline int test_tsk_trace_graph(struct task_struct *tsk) -{ - return tsk->trace & TSK_TRACE_FL_GRAPH; -} - enum ftrace_dump_mode; -extern enum ftrace_dump_mode ftrace_dump_on_oops; -extern int tracepoint_printk; +extern int ftrace_dump_on_oops_enabled(void); extern void disable_trace_on_warning(void); -extern int __disable_trace_on_warning; - -int tracepoint_printk_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); #else /* CONFIG_TRACING */ static inline void disable_trace_on_warning(void) { } |