diff options
33 files changed, 861 insertions, 411 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index a5f4004e8705..f0461456d910 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2011,6 +2011,19 @@ Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y, the default is off. + kprobe_event=[probe-list] + [FTRACE] Add kprobe events and enable at boot time. + The probe-list is a semicolon delimited list of probe + definitions. Each definition is same as kprobe_events + interface, but the parameters are comma delimited. + For example, to add a kprobe event on vfs_read with + arg1 and arg2, add to the command line; + + kprobe_event=p,vfs_read,$arg1,$arg2 + + See also Documentation/trace/kprobetrace.rst "Kernel + Boot Parameter" section. + kpti= [ARM64] Control page table isolation of user and kernel address spaces. Default: enabled on cores which need mitigation. diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst index 7d2b0178d3f3..fbb314bfa112 100644 --- a/Documentation/trace/kprobetrace.rst +++ b/Documentation/trace/kprobetrace.rst @@ -51,15 +51,17 @@ Synopsis of kprobe_events $argN : Fetch the Nth function argument. (N >= 1) (\*1) $retval : Fetch return value.(\*2) $comm : Fetch current task comm. - +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(\*3) + +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4) NAME=FETCHARG : Set NAME as the argument name of FETCHARG. FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types - (x8/x16/x32/x64), "string" and bitfield are supported. + (x8/x16/x32/x64), "string", "ustring" and bitfield + are supported. (\*1) only for the probe on function entry (offs == 0). (\*2) only for return probe. (\*3) this is useful for fetching a field of data structures. + (\*4) "u" means user-space dereference. See :ref:`user_mem_access`. Types ----- @@ -77,7 +79,8 @@ apply it to registers/stack-entries etc. (for example, '$stack1:x8[8]' is wrong, but '+8($stack):x8[8]' is OK.) String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container -has been paged out. +has been paged out. "ustring" type is an alternative of string for user-space. +See :ref:`user_mem_access` for more info.. The string array type is a bit different from other types. For other base types, <base-type>[1] is equal to <base-type> (e.g. +0(%di):x32[1] is same as +0(%di):x32.) But string[1] is not equal to string. The string type itself @@ -92,6 +95,25 @@ Symbol type('symbol') is an alias of u32 or u64 type (depends on BITS_PER_LONG) which shows given pointer in "symbol+offset" style. For $comm, the default type is "string"; any other type is invalid. +.. _user_mem_access: +User Memory Access +------------------ +Kprobe events supports user-space memory access. For that purpose, you can use +either user-space dereference syntax or 'ustring' type. + +The user-space dereference syntax allows you to access a field of a data +structure in user-space. This is done by adding the "u" prefix to the +dereference syntax. For example, +u4(%si) means it will read memory from the +address in the register %si offset by 4, and the memory is expected to be in +user-space. You can use this for strings too, e.g. +u0(%si):string will read +a string from the address in the register %si that is expected to be in user- +space. 'ustring' is a shortcut way of performing the same task. That is, ++0(%si):ustring is equivalent to +u0(%si):string. + +Note that kprobe-event provides the user-memory access syntax but it doesn't +use it transparently. This means if you use normal dereference or string type +for user memory, it might fail, and may always fail on some archs. The user +has to carefully check if the target data is in kernel or user space. Per-Probe Event Filtering ------------------------- @@ -124,6 +146,20 @@ You can check the total number of probe hits and probe miss-hits via The first column is event name, the second is the number of probe hits, the third is the number of probe miss-hits. +Kernel Boot Parameter +--------------------- +You can add and enable new kprobe events when booting up the kernel by +"kprobe_event=" parameter. The parameter accepts a semicolon-delimited +kprobe events, which format is similar to the kprobe_events. +The difference is that the probe definition parameters are comma-delimited +instead of space. For example, adding myprobe event on do_sys_open like below + + p:myprobe do_sys_open dfd=%ax filename=%dx flags=%cx mode=+4($stack) + +should be below for kernel boot parameter (just replace spaces with comma) + + p:myprobe,do_sys_open,dfd=%ax,filename=%dx,flags=%cx,mode=+4($stack) + Usage examples -------------- diff --git a/Documentation/trace/uprobetracer.rst b/Documentation/trace/uprobetracer.rst index 0b21305fabdc..6e75a6c5a2c8 100644 --- a/Documentation/trace/uprobetracer.rst +++ b/Documentation/trace/uprobetracer.rst @@ -42,16 +42,18 @@ Synopsis of uprobe_tracer @+OFFSET : Fetch memory at OFFSET (OFFSET from same file as PATH) $stackN : Fetch Nth entry of stack (N >= 0) $stack : Fetch stack address. - $retval : Fetch return value.(*) + $retval : Fetch return value.(\*1) $comm : Fetch current task comm. - +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**) + +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*2)(\*3) NAME=FETCHARG : Set NAME as the argument name of FETCHARG. FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types (x8/x16/x32/x64), "string" and bitfield are supported. - (*) only for return probe. - (**) this is useful for fetching a field of data structures. + (\*1) only for return probe. + (\*2) this is useful for fetching a field of data structures. + (\*3) Unlike kprobe event, "u" prefix will just be ignored, becuse uprobe + events can access only user-space memory. Types ----- diff --git a/arch/Kconfig b/arch/Kconfig index e8d19c3cb91f..6dd1faab6ccb 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -128,22 +128,6 @@ config UPROBES managed by the kernel and kept transparent to the probed application. ) -config HAVE_64BIT_ALIGNED_ACCESS - def_bool 64BIT && !HAVE_EFFICIENT_UNALIGNED_ACCESS - help - Some architectures require 64 bit accesses to be 64 bit - aligned, which also requires structs containing 64 bit values - to be 64 bit aligned too. This includes some 32 bit - architectures which can do 64 bit accesses, as well as 64 bit - architectures without unaligned access. - - This symbol should be selected by an architecture if 64 bit - accesses are required to be 64 bit aligned in this way even - though it is not a 64 bit architecture. - - See Documentation/unaligned-memory-access.txt for more - information on the topic of unaligned memory accesses. - config HAVE_EFFICIENT_UNALIGNED_ACCESS bool help diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index c82abd6e4ca3..9c4435307ff8 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -66,7 +66,9 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un }) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -# define WARN_ON_IN_IRQ() WARN_ON_ONCE(!in_task()) +static inline bool pagefault_disabled(void); +# define WARN_ON_IN_IRQ() \ + WARN_ON_ONCE(!in_task() && !pagefault_disabled()) #else # define WARN_ON_IN_IRQ() #endif diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4b73f5937f41..024c3053dbba 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -373,7 +373,7 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } -static int add_breakpoints(struct dyn_ftrace *rec, int enable) +static int add_breakpoints(struct dyn_ftrace *rec, bool enable) { unsigned long ftrace_addr; int ret; @@ -481,7 +481,7 @@ static int add_update_nop(struct dyn_ftrace *rec) return add_update_code(ip, new); } -static int add_update(struct dyn_ftrace *rec, int enable) +static int add_update(struct dyn_ftrace *rec, bool enable) { unsigned long ftrace_addr; int ret; @@ -527,7 +527,7 @@ static int finish_update_nop(struct dyn_ftrace *rec) return ftrace_write(ip, new, 1); } -static int finish_update(struct dyn_ftrace *rec, int enable) +static int finish_update(struct dyn_ftrace *rec, bool enable) { unsigned long ftrace_addr; int ret; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 25e2995d4a4c..8a8cb3c401b2 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -427,8 +427,8 @@ 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); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 8a62731673f7..5150436783e8 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -142,6 +142,7 @@ enum print_line_t { enum print_line_t trace_handle_return(struct trace_seq *s); void tracing_generic_entry_update(struct trace_entry *entry, + unsigned short type, unsigned long flags, int pc); struct trace_event_file; @@ -317,6 +318,14 @@ trace_event_name(struct trace_event_call *call) return call->name; } +static inline struct list_head * +trace_get_fields(struct trace_event_call *event_call) +{ + if (!event_call->class->get_fields) + return &event_call->class->fields; + return event_call->class->get_fields(event_call); +} + struct trace_array; struct trace_subsystem_dir; diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 2b70130af585..34a038563d97 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -203,7 +203,10 @@ static inline void pagefault_enable(void) /* * Is the pagefault handler disabled? If so, user access methods will not sleep. */ -#define pagefault_disabled() (current->pagefault_disabled != 0) +static inline bool pagefault_disabled(void) +{ + return current->pagefault_disabled != 0; +} /* * The pagefault handler is in general disabled by pagefault_disable() or @@ -240,6 +243,18 @@ extern long probe_kernel_read(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size); /* + * probe_user_read(): safely attempt to read from a location in user space + * @dst: pointer to the buffer that shall take the data + * @src: address to read from + * @size: size of the data chunk + * + * Safely read from address @src to the buffer at @dst. If a kernel fault + * happens, handle that and return -EFAULT. + */ +extern long probe_user_read(void *dst, const void __user *src, size_t size); +extern long __probe_user_read(void *dst, const void __user *src, size_t size); + +/* * probe_kernel_write(): safely attempt to write to a location * @dst: address to write to * @src: pointer to the data that shall be written @@ -252,6 +267,9 @@ extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); +extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, + long count); +extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); /** * probe_kernel_address(): safely attempt to read from a location diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 9f5433a52488..9873fc627d61 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2276,6 +2276,7 @@ static int __init init_kprobes(void) init_test_probes(); return err; } +subsys_initcall(init_kprobes); #ifdef CONFIG_DEBUG_FS static void report_probe(struct seq_file *pi, struct kprobe *p, @@ -2588,5 +2589,3 @@ static int __init debugfs_kprobe_init(void) late_initcall(debugfs_kprobe_init); #endif /* CONFIG_DEBUG_FS */ - -module_init(init_kprobes); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 564e5fdb025f..98da8998c25c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -597,9 +597,19 @@ config FTRACE_STARTUP_TEST functioning properly. It will do tests on all the configured tracers of ftrace. +config EVENT_TRACE_STARTUP_TEST + bool "Run selftest on trace events" + depends on FTRACE_STARTUP_TEST + default y + help + This option performs a test on all trace events in the system. + It basically just enables each event and runs some code that + will trigger events (not necessarily the event it enables) + This may take some time run as there are a lot of events. + config EVENT_TRACE_TEST_SYSCALLS bool "Run selftest on syscall events" - depends on FTRACE_STARTUP_TEST + depends on EVENT_TRACE_STARTUP_TEST help This option will also enable testing every syscall event. It only enables the event and disables it and runs various loads diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 576c41644e77..eca34503f178 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1622,6 +1622,11 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) return keep_regs; } +static struct ftrace_ops * +ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); +static struct ftrace_ops * +ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); + static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, int filter_hash, bool inc) @@ -1750,15 +1755,17 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, } /* - * If the rec had TRAMP enabled, then it needs to - * be cleared. As TRAMP can only be enabled iff - * there is only a single ops attached to it. - * In otherwords, always disable it on decrementing. - * In the future, we may set it if rec count is - * decremented to one, and the ops that is left - * has a trampoline. + * The TRAMP needs to be set only if rec count + * is decremented to one, and the ops that is + * left has a trampoline. As TRAMP can only be + * enabled if there is only a single ops attached + * to it. */ - rec->flags &= ~FTRACE_FL_TRAMP; + if (ftrace_rec_count(rec) == 1 && + ftrace_find_tramp_ops_any(rec)) + rec->flags |= FTRACE_FL_TRAMP; + else + rec->flags &= ~FTRACE_FL_TRAMP; /* * flags will be cleared in ftrace_check_record() @@ -1768,7 +1775,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, count++; /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */ - update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE; + update |= ftrace_test_record(rec, true) != FTRACE_UPDATE_IGNORE; /* Shortcut, if we handled all records, we are done. */ if (!all && count == hash->count) @@ -1951,11 +1958,6 @@ static void print_ip_ins(const char *fmt, const unsigned char *p) printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]); } -static struct ftrace_ops * -ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); -static struct ftrace_ops * -ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); - enum ftrace_bug_type ftrace_bug_type; const void *ftrace_expected; @@ -2047,7 +2049,7 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec) } } -static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) +static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) { unsigned long flag = 0UL; @@ -2146,28 +2148,28 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) /** * ftrace_update_record, set a record that now is tracing or not * @rec: the record to update - * @enable: set to 1 if the record is tracing, zero to force disable + * @enable: set to true if the record is tracing, false to force disable * * The records that represent all functions that can be traced need * to be updated when tracing has been enabled. */ -int ftrace_update_record(struct dyn_ftrace *rec, int enable) +int ftrace_update_record(struct dyn_ftrace *rec, bool enable) { - return ftrace_check_record(rec, enable, 1); + return ftrace_check_record(rec, enable, true); } /** * ftrace_test_record, check if the record has been enabled or not * @rec: the record to test - * @enable: set to 1 to check if enabled, 0 if it is disabled + * @enable: set to true to check if enabled, false if it is disabled * * The arch code may need to test if a record is already set to * tracing to determine how to modify the function code that it * represents. */ -int ftrace_test_record(struct dyn_ftrace *rec, int enable) +int ftrace_test_record(struct dyn_ftrace *rec, bool enable) { - return ftrace_check_record(rec, enable, 0); + return ftrace_check_record(rec, enable, false); } static struct ftrace_ops * @@ -2356,7 +2358,7 @@ unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) } static int -__ftrace_replace_code(struct dyn_ftrace *rec, int enable) +__ftrace_replace_code(struct dyn_ftrace *rec, bool enable) { unsigned long ftrace_old_addr; unsigned long ftrace_addr; @@ -2395,7 +2397,7 @@ void __weak ftrace_replace_code(int mod_flags) { struct dyn_ftrace *rec; struct ftrace_page *pg; - int enable = mod_flags & FTRACE_MODIFY_ENABLE_FL; + bool enable = mod_flags & FTRACE_MODIFY_ENABLE_FL; int schedulable = mod_flags & FTRACE_MODIFY_MAY_SLEEP_FL; int failed; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 05b0b3139ebc..66358d66c933 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -128,16 +128,7 @@ int ring_buffer_print_entry_header(struct trace_seq *s) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) #define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ - -#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS -# define RB_FORCE_8BYTE_ALIGNMENT 0 -# define RB_ARCH_ALIGNMENT RB_ALIGNMENT -#else -# define RB_FORCE_8BYTE_ALIGNMENT 1 -# define RB_ARCH_ALIGNMENT 8U -#endif - -#define RB_ALIGN_DATA __aligned(RB_ARCH_ALIGNMENT) +#define RB_ALIGN_DATA __aligned(RB_ALIGNMENT) /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX @@ -2373,7 +2364,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, event->time_delta = delta; length -= RB_EVNT_HDR_SIZE; - if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) { + if (length > RB_MAX_SMALL_DATA) { event->type_len = 0; event->array[0] = length; } else @@ -2388,11 +2379,11 @@ static unsigned rb_calculate_event_length(unsigned length) if (!length) length++; - if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) + if (length > RB_MAX_SMALL_DATA) length += sizeof(event.array[0]); length += RB_EVNT_HDR_SIZE; - length = ALIGN(length, RB_ARCH_ALIGNMENT); + length = ALIGN(length, RB_ALIGNMENT); /* * In case the time delta is larger than the 27 bits for it diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c90c687cf950..525a97fbbc60 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -366,7 +366,7 @@ trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct } /** - * trace_pid_filter_add_remove_task - Add or remove a task from a pid_list + * trace_filter_add_remove_task - Add or remove a task from a pid_list * @pid_list: The list to modify * @self: The current task for fork or NULL for exit * @task: The task to add or remove @@ -743,8 +743,7 @@ trace_event_setup(struct ring_buffer_event *event, { struct trace_entry *ent = ring_buffer_event_data(event); - tracing_generic_entry_update(ent, flags, pc); - ent->type = type; + tracing_generic_entry_update(ent, type, flags, pc); } static __always_inline struct ring_buffer_event * @@ -2312,13 +2311,14 @@ enum print_line_t trace_handle_return(struct trace_seq *s) EXPORT_SYMBOL_GPL(trace_handle_return); void -tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags, - int pc) +tracing_generic_entry_update(struct trace_entry *entry, unsigned short type, + unsigned long flags, int pc) { struct task_struct *tsk = current; entry->preempt_count = pc & 0xff; entry->pid = (tsk) ? tsk->pid : 0; + entry->type = type; entry->flags = #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | @@ -4842,12 +4842,13 @@ static const char readme_msg[] = "\t args: <name>=fetcharg[:type]\n" "\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n" #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API - "\t $stack<index>, $stack, $retval, $comm, $arg<N>\n" + "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n" #else - "\t $stack<index>, $stack, $retval, $comm\n" + "\t $stack<index>, $stack, $retval, $comm,\n" #endif + "\t +|-[u]<offset>(<fetcharg>)\n" "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n" - "\t b<bit-width>@<bit-offset>/<container-size>,\n" + "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" "\t <type>\\[<array-size>\\]\n" #ifdef CONFIG_HIST_TRIGGERS "\t field: <stype> <name>;\n" diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 4629a6104474..0892e38ed6fb 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -416,8 +416,7 @@ void perf_trace_buf_update(void *record, u16 type) unsigned long flags; local_save_flags(flags); - tracing_generic_entry_update(entry, flags, pc); - entry->type = type; + tracing_generic_entry_update(entry, type, flags, pc); } NOKPROBE_SYMBOL(perf_trace_buf_update); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 0ce3db67f556..c7506bc81b75 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -70,14 +70,6 @@ static int system_refcount_dec(struct event_subsystem *system) #define while_for_each_event_file() \ } -static struct list_head * -trace_get_fields(struct trace_event_call *event_call) -{ - if (!event_call->class->get_fields) - return &event_call->class->fields; - return event_call->class->get_fields(event_call); -} - static struct ftrace_event_field * __find_event_field(struct list_head *head, char *name) { @@ -3190,7 +3182,7 @@ void __init trace_event_init(void) event_trace_enable(); } -#ifdef CONFIG_FTRACE_STARTUP_TEST +#ifdef CONFIG_EVENT_TRACE_STARTUP_TEST static DEFINE_SPINLOCK(test_spinlock); static DEFINE_SPINLOCK(test_spinlock_irq); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 5079d1db3754..c773b8fb270c 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1084,6 +1084,9 @@ int filter_assign_type(const char *type) if (strchr(type, '[') && strstr(type, "char")) return FILTER_STATIC_STRING; + if (strcmp(type, "char *") == 0 || strcmp(type, "const char *") == 0) + return FILTER_PTR_STRING; + return FILTER_OTHER; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7d736248a070..9d483ad9bb6c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -12,6 +12,8 @@ #include <linux/rculist.h> #include <linux/error-injection.h> +#include <asm/setup.h> /* for COMMAND_LINE_SIZE */ + #include "trace_dynevent.h" #include "trace_kprobe_selftest.h" #include "trace_probe.h" @@ -19,6 +21,18 @@ #define KPROBE_EVENT_SYSTEM "kprobes" #define KRETPROBE_MAXACTIVE_MAX 4096 +#define MAX_KPROBE_CMDLINE_SIZE 1024 + +/* Kprobe early definition from command line */ +static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata; +static bool kprobe_boot_events_enabled __initdata; + +static int __init set_kprobe_boot_events(char *str) +{ + strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE); + return 0; +} +__setup("kprobe_event=", set_kprobe_boot_events); static int trace_kprobe_create(int argc, const char **argv); static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev); @@ -128,8 +142,8 @@ static bool trace_kprobe_match(const char *system, const char *event, { struct trace_kprobe *tk = to_trace_kprobe(ev); - return strcmp(trace_event_name(&tk->tp.call), event) == 0 && - (!system || strcmp(tk->tp.call.class->system, system) == 0); + return strcmp(trace_probe_name(&tk->tp), event) == 0 && + (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0); } static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) @@ -143,6 +157,12 @@ static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) return nhit; } +static nokprobe_inline bool trace_kprobe_is_registered(struct trace_kprobe *tk) +{ + return !(list_empty(&tk->rp.kp.list) && + hlist_unhashed(&tk->rp.kp.hlist)); +} + /* Return 0 if it fails to find the symbol address */ static nokprobe_inline unsigned long trace_kprobe_address(struct trace_kprobe *tk) @@ -183,6 +203,16 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs); static int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs); +static void free_trace_kprobe(struct trace_kprobe *tk) +{ + if (tk) { + trace_probe_cleanup(&tk->tp); + kfree(tk->symbol); + free_percpu(tk->nhit); + kfree(tk); + } +} + /* * Allocate new trace_probe and initialize it (including kprobes). */ @@ -220,49 +250,20 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, tk->rp.kp.pre_handler = kprobe_dispatcher; tk->rp.maxactive = maxactive; + INIT_HLIST_NODE(&tk->rp.kp.hlist); + INIT_LIST_HEAD(&tk->rp.kp.list); - if (!event || !group) { - ret = -EINVAL; - goto error; - } - - tk->tp.call.class = &tk->tp.class; - tk->tp.call.name = kstrdup(event, GFP_KERNEL); - if (!tk->tp.call.name) - goto error; - - tk->tp.class.system = kstrdup(group, GFP_KERNEL); - if (!tk->tp.class.system) + ret = trace_probe_init(&tk->tp, event, group); + if (ret < 0) goto error; dyn_event_init(&tk->devent, &trace_kprobe_ops); - INIT_LIST_HEAD(&tk->tp.files); return tk; error: - kfree(tk->tp.call.name); - kfree(tk->symbol); - free_percpu(tk->nhit); - kfree(tk); + free_trace_kprobe(tk); return ERR_PTR(ret); } -static void free_trace_kprobe(struct trace_kprobe *tk) -{ - int i; - - if (!tk) - return; - - for (i = 0; i < tk->tp.nr_args; i++) - traceprobe_free_probe_arg(&tk->tp.args[i]); - - kfree(tk->tp.call.class->system); - kfree(tk->tp.call.name); - kfree(tk->symbol); - free_percpu(tk->nhit); - kfree(tk); -} - static struct trace_kprobe *find_trace_kprobe(const char *event, const char *group) { @@ -270,8 +271,8 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, struct trace_kprobe *tk; for_each_trace_kprobe(tk, pos) - if (strcmp(trace_event_name(&tk->tp.call), event) == 0 && - strcmp(tk->tp.call.class->system, group) == 0) + if (strcmp(t |