diff options
Diffstat (limited to 'kernel/trace')
48 files changed, 6400 insertions, 1452 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 98da8998c25c..91e885194dbc 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -33,6 +33,9 @@ config HAVE_DYNAMIC_FTRACE config HAVE_DYNAMIC_FTRACE_WITH_REGS bool +config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + bool + config HAVE_FTRACE_MCOUNT_RECORD bool help @@ -76,7 +79,7 @@ config FTRACE_NMI_ENTER config EVENT_TRACING select CONTEXT_SWITCH_TRACER - select GLOB + select GLOB bool config CONTEXT_SWITCH_TRACER @@ -106,7 +109,6 @@ config PREEMPTIRQ_TRACEPOINTS config TRACING bool - select DEBUG_FS select RING_BUFFER select STACKTRACE if STACKTRACE_SUPPORT select TRACEPOINTS @@ -139,6 +141,15 @@ menuconfig FTRACE if FTRACE +config BOOTTIME_TRACING + bool "Boot-time Tracing support" + depends on BOOT_CONFIG && TRACING + default y + help + Enable developer to setup ftrace subsystem via supplemental + kernel cmdline at boot time for debugging (tracing) driver + initialization and boot process. + config FUNCTION_TRACER bool "Kernel Function Tracer" depends on HAVE_FUNCTION_TRACER @@ -146,7 +157,7 @@ config FUNCTION_TRACER select GENERIC_TRACER select CONTEXT_SWITCH_TRACER select GLOB - select TASKS_RCU if PREEMPT + select TASKS_RCU if PREEMPTION help Enable the kernel to trace every kernel function. This is done by using a compiler feature to insert a small, 5-byte No-Operation @@ -170,6 +181,77 @@ config FUNCTION_GRAPH_TRACER the return value. This is done by setting the current return address on the current task structure into a stack of calls. +config DYNAMIC_FTRACE + bool "enable/disable function tracing dynamically" + depends on FUNCTION_TRACER + depends on HAVE_DYNAMIC_FTRACE + default y + help + This option will modify all the calls to function tracing + dynamically (will patch them out of the binary image and + replace them with a No-Op instruction) on boot up. During + compile time, a table is made of all the locations that ftrace + can function trace, and this table is linked into the kernel + image. When this is enabled, functions can be individually + enabled, and the functions not enabled will not affect + performance of the system. + + See the files in /sys/kernel/debug/tracing: + available_filter_functions + set_ftrace_filter + set_ftrace_notrace + + This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but + otherwise has native performance as long as no tracing is active. + +config DYNAMIC_FTRACE_WITH_REGS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_REGS + +config DYNAMIC_FTRACE_WITH_DIRECT_CALLS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + +config FUNCTION_PROFILER + bool "Kernel function profiler" + depends on FUNCTION_TRACER + default n + help + This option enables the kernel function profiler. A file is created + in debugfs called function_profile_enabled which defaults to zero. + When a 1 is echoed into this file profiling begins, and when a + zero is entered, profiling stops. A "functions" file is created in + the trace_stat directory; this file shows the list of functions that + have been hit and their counters. + + If in doubt, say N. + +config STACK_TRACER + bool "Trace max stack" + depends on HAVE_FUNCTION_TRACER + select FUNCTION_TRACER + select STACKTRACE + select KALLSYMS + help + This special tracer records the maximum stack footprint of the + kernel and displays it in /sys/kernel/debug/tracing/stack_trace. + + This tracer works by hooking into every function call that the + kernel executes, and keeping a maximum stack depth value and + stack-trace saved. If this is configured with DYNAMIC_FTRACE + then it will not have any overhead while the stack tracer + is disabled. + + To enable the stack tracer on bootup, pass in 'stacktrace' + on the kernel command line. + + The stack tracer can also be enabled or disabled via the + sysctl kernel.stack_tracer_enabled + + Say N if unsure. + config TRACE_PREEMPT_TOGGLE bool help @@ -179,7 +261,7 @@ config TRACE_PREEMPT_TOGGLE config PREEMPTIRQ_EVENTS bool "Enable trace events for preempt and irq disable/enable" select TRACE_IRQFLAGS - select TRACE_PREEMPT_TOGGLE if PREEMPT + select TRACE_PREEMPT_TOGGLE if PREEMPTION select GENERIC_TRACER default n help @@ -214,7 +296,7 @@ config PREEMPT_TRACER bool "Preemption-off Latency Tracer" default n depends on !ARCH_USES_GETTIMEOFFSET - depends on PREEMPT + depends on PREEMPTION select GENERIC_TRACER select TRACER_MAX_TRACE select RING_BUFFER_ALLOW_SWAP @@ -280,6 +362,19 @@ config HWLAT_TRACER file. Every time a latency is greater than tracing_thresh, it will be recorded into the ring buffer. +config MMIOTRACE + bool "Memory mapped IO tracing" + depends on HAVE_MMIOTRACE_SUPPORT && PCI + select GENERIC_TRACER + help + Mmiotrace traces Memory Mapped I/O access and is meant for + debugging and reverse engineering. It is called from the ioremap + implementation and works via page faults. Tracing is disabled by + default and can be enabled at run-time. + + See Documentation/trace/mmiotrace.rst. + If you are not helping to develop drivers, say N. + config ENABLE_DEFAULT_TRACERS bool "Trace process context switches and events" depends on !GENERIC_TRACER @@ -308,7 +403,7 @@ config TRACER_SNAPSHOT cat snapshot config TRACER_SNAPSHOT_PER_CPU_SWAP - bool "Allow snapshot to swap per CPU" + bool "Allow snapshot to swap per CPU" depends on TRACER_SNAPSHOT select RING_BUFFER_ALLOW_SWAP help @@ -408,30 +503,6 @@ config BRANCH_TRACER Say N if unsure. -config STACK_TRACER - bool "Trace max stack" - depends on HAVE_FUNCTION_TRACER - select FUNCTION_TRACER - select STACKTRACE - select KALLSYMS - help - This special tracer records the maximum stack footprint of the - kernel and displays it in /sys/kernel/debug/tracing/stack_trace. - - This tracer works by hooking into every function call that the - kernel executes, and keeping a maximum stack depth value and - stack-trace saved. If this is configured with DYNAMIC_FTRACE - then it will not have any overhead while the stack tracer - is disabled. - - To enable the stack tracer on bootup, pass in 'stacktrace' - on the kernel command line. - - The stack tracer can also be enabled or disabled via the - sysctl kernel.stack_tracer_enabled - - Say N if unsure. - config BLK_DEV_IO_TRACE bool "Support for tracing block IO actions" depends on SYSFS @@ -520,7 +591,8 @@ config BPF_EVENTS bool default y help - This allows the user to attach BPF programs to kprobe events. + This allows the user to attach BPF programs to kprobe, uprobe, and + tracepoint events. config DYNAMIC_EVENTS def_bool n @@ -528,48 +600,6 @@ config DYNAMIC_EVENTS config PROBE_EVENTS def_bool n -config DYNAMIC_FTRACE - bool "enable/disable function tracing dynamically" - depends on FUNCTION_TRACER - depends on HAVE_DYNAMIC_FTRACE - default y - help - This option will modify all the calls to function tracing - dynamically (will patch them out of the binary image and - replace them with a No-Op instruction) on boot up. During - compile time, a table is made of all the locations that ftrace - can function trace, and this table is linked into the kernel - image. When this is enabled, functions can be individually - enabled, and the functions not enabled will not affect - performance of the system. - - See the files in /sys/kernel/debug/tracing: - available_filter_functions - set_ftrace_filter - set_ftrace_notrace - - This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but - otherwise has native performance as long as no tracing is active. - -config DYNAMIC_FTRACE_WITH_REGS - def_bool y - depends on DYNAMIC_FTRACE - depends on HAVE_DYNAMIC_FTRACE_WITH_REGS - -config FUNCTION_PROFILER - bool "Kernel function profiler" - depends on FUNCTION_TRACER - default n - help - This option enables the kernel function profiler. A file is created - in debugfs called function_profile_enabled which defaults to zero. - When a 1 is echoed into this file profiling begins, and when a - zero is entered, profiling stops. A "functions" file is created in - the trace_stat directory; this file shows the list of functions that - have been hit and their counters. - - If in doubt, say N. - config BPF_KPROBE_OVERRIDE bool "Enable BPF programs to override a kprobed function" depends on BPF_EVENTS @@ -584,54 +614,6 @@ config FTRACE_MCOUNT_RECORD depends on DYNAMIC_FTRACE depends on HAVE_FTRACE_MCOUNT_RECORD -config FTRACE_SELFTEST - bool - -config FTRACE_STARTUP_TEST - bool "Perform a startup test on ftrace" - depends on GENERIC_TRACER - select FTRACE_SELFTEST - help - This option performs a series of startup tests on ftrace. On bootup - a series of tests are made to verify that the tracer is - 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 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 - with the event enabled. This adds a bit more time for kernel boot - up since it runs this on every system call defined. - - TBD - enable a way to actually call the syscalls as we test their - events - -config MMIOTRACE - bool "Memory mapped IO tracing" - depends on HAVE_MMIOTRACE_SUPPORT && PCI - select GENERIC_TRACER - help - Mmiotrace traces Memory Mapped I/O access and is meant for - debugging and reverse engineering. It is called from the ioremap - implementation and works via page faults. Tracing is disabled by - default and can be enabled at run-time. - - See Documentation/trace/mmiotrace.rst. - If you are not helping to develop drivers, say N. - config TRACING_MAP bool depends on ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -663,18 +645,17 @@ config HIST_TRIGGERS See Documentation/trace/histogram.rst. If in doubt, say N. -config MMIOTRACE_TEST - tristate "Test module for mmiotrace" - depends on MMIOTRACE && m +config TRACE_EVENT_INJECT + bool "Trace event injection" + depends on TRACING help - This is a dumb module for testing mmiotrace. It is very dangerous - as it will write garbage to IO memory starting at a given address. - However, it should be safe to use on e.g. unused portion of VRAM. + Allow user-space to inject a specific trace event into the ring + buffer. This is mainly used for testing purpose. - Say N, unless you absolutely know what you are doing. + If unsure, say N. config TRACEPOINT_BENCHMARK - bool "Add tracepoint that benchmarks tracepoints" + bool "Add tracepoint that benchmarks tracepoints" help This option creates the tracepoint "benchmark:benchmark_event". When the tracepoint is enabled, it kicks off a kernel thread that @@ -719,11 +700,86 @@ config RING_BUFFER_BENCHMARK If unsure, say N. +config TRACE_EVAL_MAP_FILE + bool "Show eval mappings for trace events" + depends on TRACING + help + The "print fmt" of the trace events will show the enum/sizeof names + instead of their values. This can cause problems for user space tools + that use this string to parse the raw data as user space does not know + how to convert the string to its value. + + To fix this, there's a special macro in the kernel that can be used + to convert an enum/sizeof into its value. If this macro is used, then + the print fmt strings will be converted to their values. + + If something does not get converted properly, this option can be + used to show what enums/sizeof the kernel tried to convert. + + This option is for debugging the conversions. A file is created + in the tracing directory called "eval_map" that will show the + names matched with their values and what trace event system they + belong too. + + Normally, the mapping of the strings to values will be freed after + boot up or module load. With this option, they will not be freed, as + they are needed for the "eval_map" file. Enabling this option will + increase the memory footprint of the running kernel. + + If unsure, say N. + +config GCOV_PROFILE_FTRACE + bool "Enable GCOV profiling on ftrace subsystem" + depends on GCOV_KERNEL + help + Enable GCOV profiling on ftrace subsystem for checking + which functions/lines are tested. + + If unsure, say N. + + Note that on a kernel compiled with this config, ftrace will + run significantly slower. + +config FTRACE_SELFTEST + bool + +config FTRACE_STARTUP_TEST + bool "Perform a startup test on ftrace" + depends on GENERIC_TRACER + select FTRACE_SELFTEST + help + This option performs a series of startup tests on ftrace. On bootup + a series of tests are made to verify that the tracer is + 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 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 + with the event enabled. This adds a bit more time for kernel boot + up since it runs this on every system call defined. + + TBD - enable a way to actually call the syscalls as we test their + events + config RING_BUFFER_STARTUP_TEST bool "Ring buffer startup self test" depends on RING_BUFFER help - Run a simple self test on the ring buffer on boot up. Late in the + Run a simple self test on the ring buffer on boot up. Late in the kernel boot sequence, the test will start that kicks off a thread per cpu. Each thread will write various size events into the ring buffer. Another thread is created to send IPIs @@ -742,8 +798,18 @@ config RING_BUFFER_STARTUP_TEST If unsure, say N +config MMIOTRACE_TEST + tristate "Test module for mmiotrace" + depends on MMIOTRACE && m + help + This is a dumb module for testing mmiotrace. It is very dangerous + as it will write garbage to IO memory starting at a given address. + However, it should be safe to use on e.g. unused portion of VRAM. + + Say N, unless you absolutely know what you are doing. + config PREEMPTIRQ_DELAY_TEST - tristate "Preempt / IRQ disable delay thread to test latency tracers" + tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers" depends on m help Select this option to build a test module that can help test latency @@ -751,51 +817,36 @@ config PREEMPTIRQ_DELAY_TEST configurable delay. The module busy waits for the duration of the critical section. - For example, the following invocation forces a one-time irq-disabled - critical section for 500us: - modprobe preemptirq_delay_test test_mode=irq delay=500000 + For example, the following invocation generates a burst of three + irq-disabled critical sections for 500us: + modprobe preemptirq_delay_test test_mode=irq delay=500 burst_size=3 If unsure, say N -config TRACE_EVAL_MAP_FILE - bool "Show eval mappings for trace events" - depends on TRACING - help - The "print fmt" of the trace events will show the enum/sizeof names - instead of their values. This can cause problems for user space tools - that use this string to parse the raw data as user space does not know - how to convert the string to its value. - - To fix this, there's a special macro in the kernel that can be used - to convert an enum/sizeof into its value. If this macro is used, then - the print fmt strings will be converted to their values. - - If something does not get converted properly, this option can be - used to show what enums/sizeof the kernel tried to convert. - - This option is for debugging the conversions. A file is created - in the tracing directory called "eval_map" that will show the - names matched with their values and what trace event system they - belong too. +config SYNTH_EVENT_GEN_TEST + tristate "Test module for in-kernel synthetic event generation" + depends on HIST_TRIGGERS + help + This option creates a test module to check the base + functionality of in-kernel synthetic event definition and + generation. - Normally, the mapping of the strings to values will be freed after - boot up or module load. With this option, they will not be freed, as - they are needed for the "eval_map" file. Enabling this option will - increase the memory footprint of the running kernel. + To test, insert the module, and then check the trace buffer + for the generated sample events. - If unsure, say N + If unsure, say N. -config GCOV_PROFILE_FTRACE - bool "Enable GCOV profiling on ftrace subsystem" - depends on GCOV_KERNEL +config KPROBE_EVENT_GEN_TEST + tristate "Test module for in-kernel kprobe event generation" + depends on KPROBE_EVENTS help - Enable GCOV profiling on ftrace subsystem for checking - which functions/lines are tested. + This option creates a test module to check the base + functionality of in-kernel kprobe event definition. - If unsure, say N. + To test, insert the module, and then check the trace buffer + for the generated kprobe events. - Note that on a kernel compiled with this config, ftrace will - run significantly slower. + If unsure, say N. endif # FTRACE diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index c2b2148bb1d2..f9dcd19165fa 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -44,6 +44,8 @@ obj-$(CONFIG_TRACING) += trace_stat.o obj-$(CONFIG_TRACING) += trace_printk.o obj-$(CONFIG_TRACING_MAP) += tracing_map.o obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o +obj-$(CONFIG_SYNTH_EVENT_GEN_TEST) += synth_event_gen_test.o +obj-$(CONFIG_KPROBE_EVENT_GEN_TEST) += kprobe_event_gen_test.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o obj-$(CONFIG_PREEMPTIRQ_TRACEPOINTS) += trace_preemptirq.o @@ -69,6 +71,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o endif obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o +obj-$(CONFIG_TRACE_EVENT_INJECT) += trace_events_inject.o obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o @@ -82,6 +85,7 @@ endif obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o +obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2d6e93ab0478..0735ae8545d8 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -64,19 +64,18 @@ static void blk_unregister_tracepoints(void); * Send out a notify message. */ static void trace_note(struct blk_trace *bt, pid_t pid, int action, - const void *data, size_t len, - union kernfs_node_id *cgid) + const void *data, size_t len, u64 cgid) { struct blk_io_trace *t; struct ring_buffer_event *event = NULL; - struct ring_buffer *buffer = NULL; + struct trace_buffer *buffer = NULL; int pc = 0; int cpu = smp_processor_id(); bool blk_tracer = blk_tracer_enabled; - ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; + ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (blk_tracer) { - buffer = blk_tr->trace_buffer.buffer; + buffer = blk_tr->array_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + len + cgid_len, @@ -100,8 +99,8 @@ record_it: t->pid = pid; t->cpu = cpu; t->pdu_len = len + cgid_len; - if (cgid) - memcpy((void *)t + sizeof(*t), cgid, cgid_len); + if (cgid_len) + memcpy((void *)t + sizeof(*t), &cgid, cgid_len); memcpy((void *) t + sizeof(*t) + cgid_len, data, len); if (blk_tracer) @@ -122,7 +121,7 @@ static void trace_note_tsk(struct task_struct *tsk) spin_lock_irqsave(&running_trace_lock, flags); list_for_each_entry(bt, &running_trace_list, running_list) { trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, - sizeof(tsk->comm), NULL); + sizeof(tsk->comm), 0); } spin_unlock_irqrestore(&running_trace_lock, flags); } @@ -139,7 +138,7 @@ static void trace_note_time(struct blk_trace *bt) words[1] = now.tv_nsec; local_irq_save(flags); - trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), NULL); + trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words), 0); local_irq_restore(flags); } @@ -172,9 +171,9 @@ void __trace_note_message(struct blk_trace *bt, struct blkcg *blkcg, blkcg = NULL; #ifdef CONFIG_BLK_CGROUP trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, - blkcg ? cgroup_get_kernfs_id(blkcg->css.cgroup) : NULL); + blkcg ? cgroup_id(blkcg->css.cgroup) : 1); #else - trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, NULL); + trace_note(bt, 0, BLK_TN_MESSAGE, buf, n, 0); #endif local_irq_restore(flags); } @@ -212,18 +211,18 @@ static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ), */ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, int op, int op_flags, u32 what, int error, int pdu_len, - void *pdu_data, union kernfs_node_id *cgid) + void *pdu_data, u64 cgid) { struct task_struct *tsk = current; struct ring_buffer_event *event = NULL; - struct ring_buffer *buffer = NULL; + struct trace_buffer *buffer = NULL; struct blk_io_trace *t; unsigned long flags = 0; unsigned long *sequence; pid_t pid; int cpu, pc = 0; bool blk_tracer = blk_tracer_enabled; - ssize_t cgid_len = cgid ? sizeof(*cgid) : 0; + ssize_t cgid_len = cgid ? sizeof(cgid) : 0; if (unlikely(bt->trace_state != Blktrace_running && !blk_tracer)) return; @@ -249,7 +248,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, if (blk_tracer) { tracing_record_cmdline(current); - buffer = blk_tr->trace_buffer.buffer; + buffer = blk_tr->array_buffer.buffer; pc = preempt_count(); event = trace_buffer_lock_reserve(buffer, TRACE_BLK, sizeof(*t) + pdu_len + cgid_len, @@ -294,7 +293,7 @@ record_it: t->pdu_len = pdu_len + cgid_len; if (cgid_len) - memcpy((void *)t + sizeof(*t), cgid, cgid_len); + memcpy((void *)t + sizeof(*t), &cgid, cgid_len); if (pdu_len) memcpy((void *)t + sizeof(*t) + cgid_len, pdu_data, pdu_len); @@ -751,31 +750,29 @@ void blk_trace_shutdown(struct request_queue *q) } #ifdef CONFIG_BLK_CGROUP -static union kernfs_node_id * -blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { struct blk_trace *bt = q->blk_trace; if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) - return NULL; + return 0; if (!bio->bi_blkg) - return NULL; - return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); + return 0; + return cgroup_id(bio_blkcg(bio)->css.cgroup); } #else -static union kernfs_node_id * -blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) +u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - return NULL; + return 0; } #endif -static union kernfs_node_id * +static u64 blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) { if (!rq->bio) - return NULL; + return 0; /* Use the first bio */ return blk_trace_bio_get_cgid(q, rq->bio); } @@ -797,8 +794,7 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) * **/ static void blk_add_trace_rq(struct request *rq, int error, - unsigned int nr_bytes, u32 what, - union kernfs_node_id *cgid) + unsigned int nr_bytes, u32 what, u64 cgid) { struct blk_trace *bt = rq->q->blk_trace; @@ -913,7 +909,7 @@ static void blk_add_trace_getrq(void *ignore, if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, - NULL, NULL); + NULL, 0); } } @@ -929,7 +925,7 @@ static void blk_add_trace_sleeprq(void *ignore, if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, - 0, 0, NULL, NULL); + 0, 0, NULL, 0); } } @@ -938,7 +934,7 @@ static void blk_add_trace_plug(void *ignore, struct request_queue *q) struct blk_trace *bt = q->blk_trace; if (bt) - __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, @@ -955,7 +951,7 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, else what = BLK_TA_UNPLUG_TIMER; - __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, NULL); + __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } } @@ -1172,19 +1168,17 @@ const struct blk_io_trace *te_blk_io_trace(const struct trace_entry *ent) static inline const void *pdu_start(const struct trace_entry *ent, bool has_cg) { - return (void *)(te_blk_io_trace(ent) + 1) + - (has_cg ? sizeof(union kernfs_node_id) : 0); + return (void *)(te_blk_io_trace(ent) + 1) + (has_cg ? sizeof(u64) : 0); } -static inline const void *cgid_start(const struct trace_entry *ent) +static inline u64 t_cgid(const struct trace_entry *ent) { - return (void *)(te_blk_io_trace(ent) + 1); + return *(u64 *)(te_blk_io_trace(ent) + 1); } static inline int pdu_real_len(const struct trace_entry *ent, bool has_cg) { - return te_blk_io_trace(ent)->pdu_len - - (has_cg ? sizeof(union kernfs_node_id) : 0); + return te_blk_io_trace(ent)->pdu_len - (has_cg ? sizeof(u64) : 0); } static inline u32 t_action(const struct trace_entry *ent) @@ -1257,7 +1251,7 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, fill_rwbs(rwbs, t); if (has_cg) { - const union kernfs_node_id *id = cgid_start(iter->ent); + u64 id = t_cgid(iter->ent); if (blk_tracer_flags.val & TRACE_BLK_OPT_CGNAME) { char blkcg_name_buf[NAME_MAX + 1] = "<...>"; @@ -1267,11 +1261,25 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, trace_seq_printf(&iter->seq, "%3d,%-3d %s %2s %3s ", MAJOR(t->device), MINOR(t->device), blkcg_name_buf, act, rwbs); - } else + } else { + /* + * The cgid portion used to be "INO,GEN". Userland + * builds a FILEID_INO32_GEN fid out of them and + * opens the cgroup using open_by_handle_at(2). + * While 32bit ino setups are still the same, 64bit + * ones now use the 64bit ino as the whole ID and + * no longer use generation. + * + * Regarldess of the content, always output + * "LOW32,HIGH32" so that FILEID_INO32_GEN fid can + * be mapped back to @id on both 64 and 32bit ino + * setups. See __kernfs_fh_to_dentry(). + */ trace_seq_printf(&iter->seq, - "%3d,%-3d %x,%-x %2s %3s ", + "%3d,%-3d %llx,%-llx %2s %3s ", MAJOR(t->device), MINOR(t->device), - id->ino, id->generation, act, rwbs); + id & U32_MAX, id >> 32, act, rwbs); + } } else trace_seq_printf(&iter->seq, "%3d,%-3d %2s %3s ", MAJOR(t->device), MINOR(t->device), act, rwbs); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ca1255d14576..19e793aa441a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -138,19 +138,140 @@ static const struct bpf_func_proto bpf_override_return_proto = { }; #endif -BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) +BPF_CALL_3(bpf_probe_read_user, void *, dst, u32, size, + const void __user *, unsafe_ptr) { - int ret; + int ret = probe_user_read(dst, unsafe_ptr, size); + + if (unlikely(ret < 0)) + memset(dst, 0, size); + + return ret; +} + +static const struct bpf_func_proto bpf_probe_read_user_proto = { + .func = bpf_probe_read_user, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_probe_read_user_str, void *, dst, u32, size, + const void __user *, unsafe_ptr) +{ + int ret = strncpy_from_unsafe_user(dst, unsafe_ptr, size); - ret = probe_kernel_read(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } -static const struct bpf_func_proto bpf_probe_read_proto = { - .func = bpf_probe_read, +static const struct bpf_func_proto bpf_probe_read_user_str_proto = { + .func = bpf_probe_read_user_str, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +static __always_inline int +bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr, + const bool compat) +{ + int ret = security_locked_down(LOCKDOWN_BPF_READ); + + if (unlikely(ret < 0)) + goto out; + ret = compat ? probe_kernel_read(dst, unsafe_ptr, size) : + probe_kernel_read_strict(dst, unsafe_ptr, size); + if (unlikely(ret < 0)) +out: + memset(dst, 0, size); + return ret; +} + +BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, false); +} + +static const struct bpf_func_proto bpf_probe_read_kernel_proto = { + .func = bpf_probe_read_kernel, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_probe_read_compat, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_common(dst, size, unsafe_ptr, true); +} + +static const struct bpf_func_proto bpf_probe_read_compat_proto = { + .func = bpf_probe_read_compat, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +static __always_inline int +bpf_probe_read_kernel_str_common(void *dst, u32 size, const void *unsafe_ptr, + const bool compat) +{ + int ret = security_locked_down(LOCKDOWN_BPF_READ); + + if (unlikely(ret < 0)) + goto out; + /* + * The strncpy_from_unsafe_*() call will likely not fill the entire + * buffer, but that's okay in this circumstance as we're probing + * arbitrary memory anyway similar to bpf_probe_read_*() and might + * as well probe the stack. Thus, memory is explicitly cleared + * only in error case, so that improper users ignoring return + * code altogether don't copy garbage; otherwise length of string + * is returned that can be used for bpf_perf_event_output() et al. + */ + ret = compat ? strncpy_from_unsafe(dst, unsafe_ptr, size) : + strncpy_from_unsafe_strict(dst, unsafe_ptr, size); + if (unlikely(ret < 0)) +out: + memset(dst, 0, size); + return ret; +} + +BPF_CALL_3(bpf_probe_read_kernel_str, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, false); +} + +static const struct bpf_func_proto bpf_probe_read_kernel_str_proto = { + .func = bpf_probe_read_kernel_str, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_probe_read_compat_str, void *, dst, u32, size, + const void *, unsafe_ptr) +{ + return bpf_probe_read_kernel_str_common(dst, size, unsafe_ptr, true); +} + +static const struct bpf_func_proto bpf_probe_read_compat_str_proto = { + .func = bpf_probe_read_compat_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, @@ -158,7 +279,7 @@ static const struct bpf_func_proto bpf_probe_read_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, +BPF_CALL_3(bpf_probe_write_user, void __user *, unsafe_ptr, const void *, src, u32, size) { /* @@ -181,10 +302,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; - if (!access_ok(unsafe_ptr, size)) - return -EPERM; - return probe_kernel_write(unsafe_ptr, src, size); + return probe_user_write(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { @@ -500,14 +619,17 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs); -static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd); +static DEFINE_PER_CPU(int, bpf_event_output_nest_level); +struct bpf_nested_pt_regs { + struct pt_regs regs[3]; +}; +static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs); +static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { - struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd); - struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs); + int nest_level = this_cpu_inc_return(bpf_event_output_nest_level); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, @@ -522,12 +644,25 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, .data = meta, }, }; + struct perf_sample_data *sd; + struct pt_regs *regs; + u64 ret; + + if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) { + ret = -EBUSY; + goto out; + } + sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]); + regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]); perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); sd->raw = &raw; - return __bpf_perf_event_output(regs, map, flags, sd); + ret = __bpf_perf_event_output(regs, map, flags, sd); +out: + this_cpu_dec(bpf_event_output_nest_level); + return ret; } BPF_CALL_0(bpf_get_current_task) @@ -564,40 +699,11 @@ static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size, - const void *, unsafe_ptr) -{ - int ret; - - /* - * The strncpy_from_unsafe() call will likely not fill the entire - * buffer, but that's okay in this circumstance as we're probing - * arbitrary memory anyway similar to bpf_probe_read() and might - * as well probe the stack. Thus, memory is explicitly cleared - * only in error case, so that improper users ignoring return - * code altogether don't copy garbage; otherwise length of string - * is returned that can be used for bpf_perf_event_output() et al. - */ - ret = strncpy_from_unsafe(dst, unsafe_ptr, size); - if (unlikely(ret < 0)) - memset(dst, 0, size); - - return ret; -} - -static const struct bpf_func_proto bpf_probe_read_str_proto = { - .func = bpf_probe_read_str, - .gpl_only = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_UNINIT_MEM, - .arg2_type = ARG_CONST_SIZE_OR_ZERO, - .arg3_type = ARG_ANYTHING, -}; - struct send_signal_irq_work { struct irq_work irq_work; struct task_struct *task; u32 sig; + enum pid_type type; }; static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); @@ -607,10 +713,10 @@ static void do_bpf_send_signal(struct irq_work *entry) struct send_signal_irq_work *work; work = container_of(entry, struct send_signal_irq_work, irq_work); - group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID); + group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); } -BPF_CALL_1(bpf_send_signal, u32, sig) +static int bpf_send_signal_common(u32 sig, enum pid_type type) { struct send_signal_irq_work *work = NULL; @@ -634,7 +740,7 @@ BPF_CALL_1(bpf_send_signal, u32, sig) return -EINVAL; work = this_cpu_ptr(&send_signal_work); - if (work->irq_work.flags & IRQ_WORK_BUSY) + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) return -EBUSY; /* Add the current task, which is the target of sending signal, @@ -643,11 +749,17 @@ BPF_CALL_1(bpf_send_signal, u32, sig) */ work->task = current; work->sig = sig; + work->type = type; irq_work_queue(&work->irq_work); return 0; } - return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID); + return group_send_sig_info(sig, SEND_SIG_PRIV, current, type); +} + +BPF_CALL_1(bpf_send_signal, u32, sig) +{ + return bpf_send_signal_common(sig, PIDTYPE_TGID); } static const struct bpf_func_proto bpf_send_signal_proto = { @@ -657,6 +769,18 @@ static const struct bpf_func_proto bpf_send_signal_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_1(bpf_send_signal_thread, u32, sig) +{ + return bpf_send_signal_common(sig, PIDTYPE_PID); +} + +static const struct bpf_func_proto bpf_send_signal_thread_proto = { + .func = bpf_send_signal_thread, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -673,8 +797,6 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; - case BPF_FUNC_probe_read: - return &bpf_probe_read_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_tail_call: @@ -701,14 +823,26 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; + case BPF_FUNC_probe_read_user: + return &bpf_probe_read_user_proto; + case BPF_FUNC_probe_read_kernel: + return &bpf_probe_read_kernel_proto; + case BPF_FUNC_probe_read: + return &bpf_probe_read_compat_proto; + case BPF_FUNC_probe_read_user_str: + return &bpf_probe_read_user_str_proto; + case BPF_FUNC_probe_read_kernel_str: + return &bpf_probe_read_kernel_str_proto; case BPF_FUNC_probe_read_str: - return &bpf_probe_read_str_proto; + return &bpf_probe_read_compat_str_proto; #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; + case BPF_FUNC_send_signal_thread: + return &bpf_send_signal_thread_proto; default: return NULL; } @@ -969,6 +1103,8 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +extern const struct bpf_func_proto bpf_skb_output_proto; + BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) { @@ -1036,13 +1172,25 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +static const struct bpf_func_proto * +tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { +#ifdef CONFIG_NET + case BPF_FUNC_skb_output: + return &bpf_skb_output_proto; +#endif + default: + return raw_tp_prog_func_proto(func_id, prog); + } +} + static bool raw_tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - /* largest tracepoint in the kernel has 12 args */ - if (off < 0 || off >= sizeof(__u64) * 12) + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) return false; if (type != BPF_READ) return false; @@ -1051,6 +1199,20 @@ static bool raw_tp_prog_is_valid_access(int off, int size, return true; } +static bool tracing_prog_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + return btf_ctx_access(off, size, type, prog, info); +} + const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_prog_is_valid_access, @@ -1059,6 +1221,14 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { const struct bpf_prog_ops raw_tracepoint_prog_ops = { }; +const struct bpf_verifier_ops tracing_verifier_ops = { + .get_func_proto = tracing_prog_func_proto, + .is_valid_access = tracing_prog_is_valid_access, +}; + +const struct bpf_prog_ops tracing_prog_ops = { +}; + static bool raw_tp_writable_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 8dfd5021b933..1af321dec0f1 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -96,11 +96,34 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, return 0; } +/* + * Not all archs define MCOUNT_INSN_SIZE which is used to look for direct + * functions. But those archs currently don't support direct functions + * anyway, and ftrace_find_rec_direct() is just a stub for them. + * Define MCOUNT_INSN_SIZE to keep those archs compiling. + */ +#ifndef MCOUNT_INSN_SIZE +/* Make sure this only works without direct calls */ +# ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +# error MCOUNT_INSN_SIZE not defined with direct calls enabled +# endif +# define MCOUNT_INSN_SIZE 0 +#endif + int function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { struct ftrace_graph_ent trace; + /* + * Skip graph tracing if the return location is served by direct trampoline, + * since call sequence and return addresses is unpredicatable anymore. + * Ex: BPF trampoline may call original function and may skip frame + * depending on type of BPF programs attached. + */ + if (ftrace_direct_func_count && + ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE)) + return -EBUSY; trace.func = func; trace.depth = ++current->curr_ret_depth; @@ -276,7 +299,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, int index = task->curr_ret_stack; int i; - if (ret != (unsigned long)return_to_handler) + if (ret != (unsigned long)dereference_kernel_function_descriptor(return_to_handler)) return ret; if (index < 0) @@ -294,7 +317,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, { int task_idx; - if (ret != (unsigned long)return_to_handler) + if (ret != (unsigned long)dereference_kernel_function_descriptor(return_to_handler)) return ret; task_idx = task->curr_ret_stack; @@ -332,9 +355,14 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace) return 0; } +/* + * Simply points to ftrace_stub, but with the proper protocol. + * Defined by the linker script in linux/vmlinux.lds.h + */ +extern void ftrace_stub_graph(struct ftrace_graph_ret *); + /* The callbacks that hook a function */ -trace_func_graph_ret_t ftrace_graph_return = - (trace_func_graph_ret_t)ftrace_stub; +trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph; trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub; static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub; @@ -614,7 +642,7 @@ void unregister_ftrace_graph(struct fgraph_ops *gops) goto out; ftrace_graph_active--; - ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub; + ftrace_graph_return = ftrace_stub_graph; ftrace_graph_entry = ftrace_graph_entry_stub; __ftrace_graph_entry = ftrace_graph_entry_stub; ftrace_shutdown(&graph_ops, FTRACE_STOP_FUNC_RET); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index eca34503f178..3f7ee102868a 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -18,6 +18,7 @@ #include <linux/clocksource.h> #include <linux/sched/task.h> #include <linux/kallsyms.h> +#include <linux/security.h> #include <linux/seq_file.h> #include <linux/tracefs.h> #include <linux/hardirq.h> @@ -61,8 +62,6 @@ }) /* hash bits for specific function selection */ -#define FTRACE_HASH_BITS 7 -#define FTRACE_FUNC_HASHSIZE (1 << FTRACE_HASH_BITS) #define FTRACE_HASH_DEFAULT_BITS 10 #define FTRACE_HASH_MAX_BITS 12 @@ -145,7 +144,7 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, { struct trace_array *tr = op->private; - if (tr && this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid)) + if (tr && this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid)) return; op->saved_func(ip, parent_ip, op, regs); @@ -325,6 +324,8 @@ int __register_ftrace_function(struct ftrace_ops *ops) if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) ops->flags |= FTRACE_OPS_FL_SAVE_REGS; #endif + if (!ftrace_enabled && (ops->flags & FTRACE_OPS_FL_PERMANENT)) + return -EBUSY; if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; @@ -462,10 +463,10 @@ static void *function_stat_start(struct tracer_stat *trace) #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* function graph compares on total time */ -static int function_stat_cmp(void *p1, void *p2) +static int function_stat_cmp(const void *p1, const void *p2) { - struct ftrace_profile *a = p1; - struct ftrace_profile *b = p2; + const struct ftrace_profile *a = p1; + const struct ftrace_profile *b = p2; if (a->time < b->time) return -1; @@ -476,10 +477,10 @@ static int function_stat_cmp(void *p1, void *p2) } #else /* not function graph compares against hits */ -static int function_stat_cmp(void *p1, void *p2) +static int function_stat_cmp(const void *p1, const void *p2) { - struct ftrace_profile *a = p1; - struct ftrace_profile *b = p2; + const struct ftrace_profile *a = p1; + const struct ftrace_profile *b = p2; if (a->counter < b->counter) return -1; @@ -523,8 +524,7 @@ static int function_stat_show(struct seq_file *m, void *v) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER - avg = rec->time; - do_div(avg, rec->counter); + avg = div64_ul(rec->time, rec->counter); if (tracing_thresh && (avg < tracing_thresh)) goto out; #endif @@ -550,7 +550,8 @@ static int function_stat_show(struct seq_file *m, void *v) * Divide only 1000 for ns^2 -> us^2 conversion. * trace_print_graph_duration will divide 1000 again. */ - do_div(stddev, rec->counter * (rec->counter - 1) * 1000); + stddev = div64_ul(stddev, + rec->counter * (rec->counter - 1) * 1000); } trace_seq_init(&s); @@ -1017,11 +1018,6 @@ static bool update_all_ops; # error Dynamic ftrace depends on MCOUNT_RECORD #endif -struct ftrace_func_entry { - struct hlist_node hlist; - unsigned long ip; -}; - struct ftrace_func_probe { struct ftrace_probe_ops *probe_ops; struct ftrace_ops ops; @@ -1105,9 +1101,6 @@ struct ftrace_page { #define ENTRY_SIZE sizeof(struct dyn_ftrace) #define ENTRIES_PER_PAGE (PAGE_SIZE / ENTRY_SIZE) -/* estimate from running different kernels */ -#define NR_TO_INIT 10000 - static struct ftrace_page *ftrace_pages_start; static struct ftrace_page *ftrace_pages; @@ -1369,24 +1362,16 @@ ftrace_hash_rec_enable_modify(struct ftrace_ops *ops, int filter_hash); static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops, struct ftrace_hash *new_hash); -static struct ftrace_hash * -__ftrace_hash_move(struct ftrace_hash *src) +static struct ftrace_hash *dup_hash(struct ftrace_hash *src, int size) { struct ftrace_func_entry *entry; - struct hlist_node *tn; - struct hlist_head *hhd; struct ftrace_hash *new_hash; - int size = src->count; + struct hlist_head *hhd; + struct hlist_node *tn; int bits = 0; int i; /* - * If the new source is empty, just return the empty_hash. - */ - if (ftrace_hash_empty(src)) - return EMPTY_HASH; - - /* * Make the hash size about 1/2 the # found */ for (size /= 2; size; size >>= 1) @@ -1410,10 +1395,23 @@ __ftrace_hash_move(struct ftrace_hash *src) __add_hash_entry(new_hash, entry); } } - return new_hash; } +static struct ftrace_hash * +__ftrace_hash_move(struct ftrace_hash *src) +{ + int size = src->count; + + /* + * If the new source is empty, just return the empty_hash. + */ + if (ftrace_hash_empty(src)) + return EMPTY_HASH; + + return dup_hash(src, size); +} + static int ftrace_hash_move(struct ftrace_ops *ops, int enable, struct ftrace_hash **dst, struct ftrace_hash *src) @@ -1533,6 +1531,26 @@ static int ftrace_cmp_recs(const void *a, const void *b) return 0; } +static struct dyn_ftrace *lookup_rec(unsigned long start, unsigned long end) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec = NULL; + struct dyn_ftrace key; + + key.ip = start; + key.flags = end; /* overload flags, as it is unsigned long */ + + for (pg = ftrace_pages_start; pg; pg = pg->next) { + if (end < pg->records[0].ip || + start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) + continue; + rec = bsearch(&key, pg->records, pg->index, + sizeof(struct dyn_ftrace), + ftrace_cmp_recs); + } + return rec; +} + /** * ftrace_location_range - return the first address of a traced location * if it touches the given ip range @@ -1547,23 +1565,11 @@ static int ftrace_cmp_recs(const void *a, const void *b) */ unsigned long ftrace_location_range(unsigned long start, unsigned long end) { - struct ftrace_page *pg; struct dyn_ftrace *rec; - struct dyn_ftrace key; - - key.ip = start; - key.flags = end; /* overload flags, as it is unsigned long */ - for (pg = ftrace_pages_start; pg; pg = pg->next) { - if (end < pg->records[0].ip || - start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE)) - continue; - rec = bsearch(&key, pg->records, pg->index, - sizeof(struct dyn_ftrace), - ftrace_cmp_recs); - if (rec) - return rec->ip; - } + rec = lookup_rec(start, end); + if (rec) + return rec->ip; return 0; } @@ -1714,6 +1720,9 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX)) return false; + if (ops->flags & FTRACE_OPS_FL_DIRECT) + rec->flags |= FTRACE_FL_DIRECT; + /* * If there's only a single callback registered to a * function, and the ops has a trampoline registered @@ -1742,6 +1751,15 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags--; /* + * Only the internal direct_ops should have the + * DIRECT flag set. Thus, if it is removing a + * function, then that function should no longer + * be direct. + */ + if (ops->flags & FTRACE_OPS_FL_DIRECT) + rec->flags &= ~FTRACE_FL_DIRECT; + + /* * If the rec had REGS enabled and the ops that is * being removed had REGS set, then see if there is * still any ops for this record that wants regs. @@ -2076,15 +2094,34 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * If enabling and the REGS flag does not match the REGS_EN, or * the TRAMP flag doesn't match the TRAMP_EN, then do not ignore * this record. Set flags to fail the compare against ENABLED. + * Same for direct calls. */ if (flag) { - if (!(rec->flags & FTRACE_FL_REGS) != + if (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN)) flag |= FTRACE_FL_REGS; - if (!(rec->flags & FTRACE_FL_TRAMP) != + if (!(rec->flags & FTRACE_FL_TRAMP) != !(rec->flags & FTRACE_FL_TRAMP_EN)) flag |= FTRACE_FL_TRAMP; + + /* + * Direct calls are special, as count matters. + * We must test the record for direct, if the + * DIRECT and DIRECT_EN do not match, but only + * if the count is 1. That's because, if the + * count is something other than one, we do not + * want the direct enabled (it will be done via the + * direct helper). But if DIRECT_EN is set, and + * the count is not one, we need to clear it. + */ + if (ftrace_rec_count(rec) == 1) { + if (!(rec->flags & FTRACE_FL_DIRECT) != + !(rec->flags & FTRACE_FL_DIRECT_EN)) + flag |= FTRACE_FL_DIRECT; + } else if (rec->flags & FTRACE_FL_DIRECT_EN) { + flag |= FTRACE_FL_DIRECT; + } } /* If the state of this record hasn't changed, then do nothing */ @@ -2109,6 +2146,25 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) else rec->flags &= ~FTRACE_FL_TRAMP_EN; } + if (flag & FTRACE_FL_DIRECT) { + /* + * If there's only one user (direct_ops helper) + * then we can call the direct function + * directly (no ftrace trampoline). + */ + if (ftrace_rec_count(rec) == 1) { + if (rec->flags & FTRACE_FL_DIRECT) + rec->flags |= FTRACE_FL_DIRECT_EN; + else + rec->flags &= ~FTRACE_FL_DIRECT_EN; + } else { + /* + * Can only call directly if there's + * only one callback to the function. + */ + rec->flags &= ~FTRACE_FL_DIRECT_EN; + } + } } /* @@ -2138,7 +2194,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * and REGS states. The _EN flags must be disabled though. */ rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN | - FTRACE_FL_REGS_EN); + FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN); } ftrace_bug_type = FTRACE_BUG_NOP; @@ -2293,6 +2349,47 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) return NULL; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +/* Protected by rcu_tasks for reading, and direct_mutex for writing */ +static struct ftrace_hash *direct_functions = EMPTY_HASH; +static DEFINE_MUTEX(direct_mutex); +int ftrace_direct_func_count; + +/* + * Search the direct_functions hash to see if the given instruction pointer + * has a direct caller attached to it. + */ +unsigned long ftrace_find_rec_direct(unsigned long ip) +{ + struct ftrace_func_entry *entry; + + entry = __ftrace_lookup_ip(direct_functions, ip); + if (!entry) + return 0; + + return entry->direct; +} + +static void call_direct_funcs(unsigned long ip, unsigned long pip, + struct ftrace_ops *ops, struct pt_regs *regs) +{ + unsigned long addr; + + addr = ftrace_find_rec_direct(ip); + if (!addr) + return; + + arch_ftrace_set_direct_caller(regs, addr); +} + +struct ftrace_ops direct_ops = { + .func = call_direct_funcs, + .flags = FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_RECURSION_SAFE + | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS + | FTRACE_OPS_FL_PERMANENT, +}; +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + /** * ftrace_get_addr_new - Get the call address to set to * @rec: The ftrace record descriptor @@ -2306,6 +2403,15 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) { struct ftrace_ops *ops; + unsigned long addr; + + if ((rec->flags & FTRACE_FL_DIRECT) && + (ftrace_rec_count(rec) == 1)) { + addr = ftrace_find_rec_direct(rec->ip); + if (addr) + return addr; + WARN_ON_ONCE(1); + } /* Trampolines take precedence over regs */ if (rec->flags & FTRACE_FL_TRAMP) { @@ -2338,6 +2444,15 @@ unsigned long ftrace_get_addr_new(struct dyn_ftrace *rec) unsigned long ftrace_get_addr_curr(struct dyn_ftrace *rec) { struct ftrace_ops *ops; + unsigned long addr; + + /* Direct calls take precedence over trampolines */ + if (rec->flags & FTRACE_FL_DIRECT_EN) { + addr = ftrace_find_rec_direct(rec->ip); + if (addr) + return addr; + WARN_ON_ONCE(1); + } /* Trampolines take precedence over regs */ if (rec->flags & FTRACE_FL_TRAMP_EN) { @@ -2493,14 +2608,14 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter) } static int -ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec) +ftrace_nop_initialize(struct module *mod, struct dyn_ftrace *rec) { int ret; if (unlikely(ftrace_disabled)) return 0; - ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR); + ret = ftrace_init_nop(mod, rec); if (ret) { ftrace_bug_type = FTRACE_BUG_INIT; ftrace_bug(ret, rec); @@ -2814,7 +2929,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) * synchornize_rcu_tasks() will wait for those tasks to * execute and either schedule voluntarily or enter user space. */ - if (IS_ENABLED(CONFIG_PREEMPT)) + if (IS_ENABLED(CONFIG_PREEMPTION)) synchronize_rcu_tasks(); free_ops: @@ -2860,6 +2975,8 @@ static void ftrace_shutdown_sysctl(void) static u64 ftrace_update_time; unsigned long ftrace_update_tot_cnt; +unsigned long ftrace_number_of_pages; +unsigned long ftrace_number_of_groups; static inline int ops_traces_mod(struct ftrace_ops *ops) { @@ -2942,7 +3059,7 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) * to the NOP instructions. */ if (!__is_defined(CC_USING_NOP_MCOUNT) && - !ftrace_code_disable(mod, p)) + !ftrace_nop_initialize(mod, p)) break; update_cnt++; @@ -2984,6 +3101,9 @@ static int ftrace_allocate_records(struct ftrace_page *pg, int count) goto again; } + ftrace_number_of_pages += 1 << order; + ftrace_number_of_groups++; + cnt = (PAGE_SIZE << order) / ENTRY_SIZE; pg->size = cnt; @@ -3039,6 +3159,8 @@ ftrace_allocate_pages(unsigned long num_to_init) start_pg = pg->next; kfree(pg); pg = start_pg; + ftrace_number_of_pages -= 1 << order; + ftrace_number_of_groups--; } pr_info("ftrace: FAILED to allocate memory for functions\n"); return NULL; @@ -3095,6 +3217,14 @@ t_probe_next(struct seq_file *m, loff_t *pos) hnd = &iter->probe_entry->hlist; hash = iter->probe->ops.func_hash->filter_hash; + + /* + * A probe being registered may temporarily have an empty hash + * and it's at the end of the func_probes list. + */ + if (!hash || hash == EMPTY_HASH) + return NULL; + size = 1 << hash->size_bits; retry: @@ -3441,10 +3571,11 @@ static int t_show(struct seq_file *m, void *v) if (iter->flags & FTRACE_ITER_ENABLED) { struct ftrace_ops *ops; - seq_printf(m, " (%ld)%s%s", + seq_printf(m, " (%ld)%s%s%s", ftrace_rec_count(rec), rec->flags & FTRACE_FL_REGS ? " R" : " ", - rec->flags & FTRACE_FL_IPMODIFY ? " I" : " "); + rec->flags & FTRACE_FL_IPMODIFY ? " I" : " ", + rec->flags & FTRACE_FL_DIRECT ? " D" : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) { @@ -3460,6 +3591,13 @@ static int t_show(struct seq_file *m, void *v) } else { add_trampoline_func(m, NULL, rec); } + if (rec->flags & FTRACE_FL_DIRECT) { + unsigned long direct; + + direct = ftrace_find_rec_direct(rec->ip); + if (direct) + seq_printf(m, "\n\tdirect-->%pS", (void *)direct); + } } seq_putc(m, '\n'); @@ -3478,6 +3616,11 @@ static int ftrace_avail_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; if (unlikely(ftrace_disabled)) return -ENODEV; @@ -3497,6 +3640,15 @@ ftrace_enabled_open(struct inode *inode, struct file *file) { struct ftrace_iterator *iter; + /* + * This shows us what functions are currently being + * traced and by what. Not sure if we want lockdown + * to hide such critical information for an admin. + * Although, perhaps it can show information we don't + * want people to see, but if something is tracing + * something, we probably want to know about it. + */ + iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter)); if (!iter) return -ENOMEM; @@ -3532,21 +3684,22 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, struct ftrace_hash *hash; struct list_head *mod_head; struct trace_array *tr = ops->private; - int ret = 0; + int ret = -ENOMEM; ftrace_ops_init(ops); if (unlikely(ftrace_disabled)) return -ENODEV; + if (tracing_check_open_get_tr(tr)) + return -ENODEV; + iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) - return -ENOMEM; + goto out; - if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) { - kfree(iter); - return -ENOMEM; - } + if (trace_parser_get_init(&iter->parser, FTRACE_BUFF_MAX)) + goto out; iter->ops = ops; iter->flags = flag; @@ -3576,13 +3729,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, if (!iter->hash) { trace_parser_put(&iter->parser); - kfree(iter); - ret = -ENOMEM; goto out_unlock; } } else iter->hash = hash; + ret = 0; + if (file->f_mode & FMODE_READ) { iter->pg = ftrace_pages_start; @@ -3594,7 +3747,6 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, /* Failed */ free_ftrace_hash(iter->hash); trace_parser_put(&iter->parser); - kfree(iter); } } else file->private_data = iter; @@ -3602,6 +3754,13 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag, out_unlock: mutex_unlock(&ops->func_hash->regex_lock); + out: + if (ret) { + kfree(iter); + if (tr) + trace_array_put(tr); + } + return ret; } @@ -3610,6 +3769,7 @@ ftrace_filter_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_FILTER | FTRACE_ITER_DO_PROBES, inode, file); @@ -3620,6 +3780,7 @@ ftrace_notrace_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_NOTRACE, inode, file); } @@ -4320,12 +4481,21 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, mutex_unlock(&ftrace_lock); + /* + * Note, there's a small window here that the func_hash->filter_hash + * may be NULL or empty. Need to be carefule when reading the loop. + */ mutex_lock(&probe->ops.func_hash->regex_lock); orig_hash = &probe->ops.func_hash->filter_hash; old_hash = *orig_hash; hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS, old_hash); + if (!hash) { + ret = -ENOMEM; + goto out; + } + ret = ftrace_match_records(hash, glob, strlen(glob)); /* Nothing found? */ @@ -4759,6 +4929,366 @@ ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, return ftrace_set_hash(ops, NULL, 0, ip, remove, reset, enable); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + +struct ftrace_direct_func { + struct list_head next; + unsigned long addr; + int count; +}; + +static LIST_HEAD(ftrace_direct_funcs); + +/** + * ftrace_find_direct_func - test an address if it is a registered direct caller + * @addr: The address of a registered direct caller + * + * This searches to see if a ftrace direct caller has been registered + * at a specific address, and if so, it returns a descriptor for it. + * + * This can be used by architecture code to see if an address is + * a direct caller (trampoline) attached to a fentry/mcount location. + * This is useful for the function_graph tracer, as it may need to + * do adjustments if it traced a location that also has a direct + * trampoline attached to it. + */ +struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) +{ + struct ftrace_direct_func *entry; + bool found = false; + + /* May be called by fgraph trampoline (protected by rcu tasks) */ + list_for_each_entry_rcu(entry, &ftrace_direct_funcs, next) { + if (entry->addr == addr) { + found = true; + break; + } + } + if (found) + return entry; + + return NULL; +} + +/** + * register_ftrace_direct - Call a custom trampoline directly + * @ip: The address of the nop at the beginning of a function + * @addr: The address of the trampoline to call at @ip + * + * This is used to connect a direct call from the nop location (@ip) + * at the start of ftrace traced functions. The location that it calls + * (@addr) must be able to handle a direct call, and save the parameters + * of the function being traced, and restore them (or inject new ones + * if needed), before returning. + * + * Returns: + * 0 on success + * -EBUSY - Another direct function is already attached (there can be only one) + * -ENODEV - @ip does not point to a ftrace nop location (or not supported) + * -ENOMEM - There was an allocation failure. + */ +int register_ftrace_direct(unsigned long ip, unsigned long addr) +{ + struct ftrace_direct_func *direct; + struct ftrace_func_entry *entry; + struct ftrace_hash *free_hash = NULL; + struct dyn_ftrace *rec; + int ret = -EBUSY; + + mutex_lock(&direct_mutex); + + /* See if there's a direct function at @ip already */ + if (ftrace_find_rec_direct(ip)) + goto out_unlock; + + ret = -ENODEV; + rec = lookup_rec(ip, ip); + if (!rec) + goto out_unlock; + + /* + * Check if the rec says it has a direct call but we didn't + * find one earlier? + */ + if (WARN_ON(rec->flags & FTRACE_FL_DIRECT)) + goto out_unlock; + + /* Make sure the ip points to the exact record */ + if (ip != rec->ip) { + ip = rec->ip; + /* Need to check this ip for a direct. */ + if (ftrace_find_rec_direct(ip)) + goto out_unlock; + } + + ret = -ENOMEM; + if (ftrace_hash_empty(direct_functions) || + direct_functions->count > 2 * (1 << direct_functions->size_bits)) { + struct ftrace_hash *new_hash; + int size = ftrace_hash_empty(direct_functions) ? 0 : + direct_functions->count + 1; + + if (size < 32) + size = 32; + + new_hash = dup_hash(direct_functions, size); + if (!new_hash) + goto out_unlock; + + free_hash = direct_functions; + direct_functions = new_hash; + } + + entry = kmalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) + goto out_unlock; + + direct = ftrace_find_direct_func(addr); + if (!direct) { + direct = kmalloc(sizeof(*direct), GFP_KERNEL); + if (!direct) { + kfree(entry); + goto out_unlock; + } + direct->addr = addr; + direct->count = 0; + list_add_rcu(&direct->next, &ftrace_direct_funcs); + ftrace_direct_func_count++; + } + + entry->ip = ip; + entry->direct = addr; + __add_hash_entry(direct_functions, entry); + + ret = ftrace_set_filter_ip(&direct_ops, ip, 0, 0); + if (ret) + remove_hash_entry(direct_functions, entry); + + if (!ret && !(direct_ops.flags & FTRACE_OPS_FL_ENABLED)) { + ret = register_ftrace_function(&direct_ops); + if (ret) + ftrace_set_filter_ip(&direct_ops, ip, 1, 0); + } + + if (ret) { + kfree(entry); + if (!direct->count) { + list_del_rcu(&direct->next); + synchronize_rcu_tasks(); + kfree(direct); + if (free_hash) + free_ftrace_hash(free_hash); + free_hash = NULL; + ftrace_direct_func_count--; + } + } else { + direct->count++; + } + out_unlock: + mutex_unlock(&direct_mutex); + + if (free_hash) { + synchronize_rcu_tasks(); + free_ftrace_hash(free_hash); + } + + return ret; +} +EXPORT_SYMBOL_GPL(register_ftrace_direct); + +static struct ftrace_func_entry *find_direct_entry(unsigned long *ip, + struct dyn_ftrace **recp) +{ + struct ftrace_func_entry *entry; + struct dyn_ftrace *rec; + + rec = lookup_rec(*ip, *ip); + if (!rec) + return NULL; + + entry = __ftrace_lookup_ip(direct_functions, rec->ip); + if (!entry) { + WARN_ON(rec->flags & FTRACE_FL_DIRECT); + return NULL; + } + + WARN_ON(!(rec->flags & FTRACE_FL_DIRECT)); + + /* Passed in ip just needs to be on the call site */ + *ip = rec->ip; + + if (recp) + *recp = rec; + + return entry; +} + +int unregister_ftrace_direct(unsigned long ip, unsigned long addr) +{ + struct ftrace_direct_func *direct; + struct ftrace_func_entry *entry; + int ret = -ENODEV; + + mutex_lock(&direct_mutex); + + entry = find_direct_entry(&ip, NULL); + if (!entry) + goto out_unlock; + + if (direct_functions->count == 1) + unregister_ftrace_function(&direct_ops); + + ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0); + + WARN_ON(ret); + + remove_hash_entry(direct_functions, entry); + + direct = ftrace_find_direct_func(addr); + if (!WARN_ON(!direct)) { + /* This is the good path (see the ! before WARN) */ + direct->count--; + WARN_ON(direct->count < 0); + if (!direct->count) { + list_del_rcu(&direct->next); + synchronize_rcu_tasks(); + kfree(direct); + ftrace_direct_func_count--; + } + } + out_unlock: + mutex_unlock(&direct_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(unregister_ftrace_direct); + +static struct ftrace_ops stub_ops = { + .func = ftrace_stub, +}; + +/** + * ftrace_modify_direct_caller - modify ftrace nop directly + * @entry: The ftrace hash entry of the direct helper for @rec + * @rec: The record representing the function site to patch + * @old_addr: The location that the site at @rec->ip currently calls + * @new_addr: The location that the site at @rec->ip should call + * + * An architecture may overwrite this function to optimize the + * changing of the direct callback on an ftrace nop location. + * This is called with the ftrace_lock mutex held, and no other + * ftrace callbacks are on the associated record (@rec). Thus, + * it is safe to modify the ftrace record, where it should be + * currently calling @old_addr directly, to call @new_addr. + * + * Safety checks should be made to make sure that the code at + * @rec->ip is currently calling @old_addr. And this must + * also update entry->direct to @new_addr. + */ +int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry, + struct dyn_ftrace *rec, + unsigned long old_addr, + unsigned long new_addr) +{ + unsigned long ip = rec->ip; + int ret; + + /* + * The ftrace_lock was used to determine if the record + * had more than one registered user to it. If it did, + * we needed to prevent that from changing to do the quick + * switch. But if it did not (only a direct caller was attached) + * then this function is called. But this function can deal + * with attached callers to the rec that we care about, and + * since this function uses standard ftrace calls that take + * the ftrace_lock mutex, we need to release it. + */ + mutex_unlock(&ftrace_lock); + + /* + * By setting a stub function at the same address, we force + * the code to call the iterator and the direct_ops helper. + * This means that @ip does not call the direct call, and + * we can simply modify it. + */ + ret = ftrace_set_filter_ip(&stub_ops, ip, 0, 0); + if (ret) + goto out_lock; + + ret = register_ftrace_function(&stub_ops); + if (ret) { + ftrace_set_filter_ip(&stub_ops, ip, 1, 0); + goto out_lock; + } + + entry->direct = new_addr; + + /* + * By removing the stub, we put back the direct call, calling + * the @new_addr. + */ + unregister_ftrace_function(&stub_ops); + ftrace_set_filter_ip(&stub_ops, ip, 1, 0); + + out_lock: + mutex_lock(&ftrace_lock); + + return ret; +} + +/** + * modify_ftrace_direct - Modify an existing direct call to call something else + * @ip: The instruction pointer to modify + * @old_addr: The address that the current @ip calls directly + * @new_addr: The address that the @ip should call + * + * This modifies a ftrace direct caller at an instruction pointer without + * having to disable it first. The direct call will switch over to the + * @new_addr without missing anything. + * + * Returns: zero on success. Non zero on error, which includes: + * -ENODEV : the @ip given has no direct caller attached + * -EINVAL : the @old_addr does not match the current direct caller + */ +int modify_ftrace_direct(unsigned long ip, + unsigned long old_addr, unsigned long new_addr) +{ + struct ftrace_func_entry *entry; + struct dyn_ftrace *rec; + int ret = -ENODEV; + + mutex_lock(&direct_mutex); + + mutex_lock(&ftrace_lock); + entry = find_direct_entry(&ip, &rec); + if (!entry) + goto out_unlock; + + ret = -EINVAL; + if (entry->direct != old_addr) + goto out_unlock; + + /* + * If there's no other ftrace callback on the rec->ip location, + * then it can be changed directly by the architecture. + * If there is another caller, then we just need to change the + * direct caller helper to point to @new_addr. + */ + if (ftrace_rec_count(rec) == 1) { + ret = ftrace_modify_direct_caller(entry, rec, old_addr, new_addr); + } else { + entry->direct = new_addr; + ret = 0; + } + + out_unlock: + mutex_unlock(&ftrace_lock); + mutex_unlock(&direct_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(modify_ftrace_direct); +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + /** * ftrace_set_filter_ip - set a function to filter on in ftrace by address * @ops - the ops to set the filter with @@ -4929,7 +5459,7 @@ static void __init set_ftrace_early_graph(char *buf, int enable) struct ftrace_hash *hash; hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS); - if (WARN_ON(!hash)) + if (MEM_FAIL(!hash, "Failed to allocate hash\n")) return; while (buf) { @@ -5020,6 +5550,8 @@ int ftrace_regex_release(struct inode *inode, struct file *file) mutex_unlock(&iter->ops->func_hash->regex_lock); free_ftrace_hash(iter->hash); + if (iter->tr) + trace_array_put(iter->tr); kfree(iter); return 0; @@ -5059,8 +5591,8 @@ static const struct file_operations ftrace_notrace_fops = { static DEFINE_MUTEX(graph_lock); -struct ftrace_hash *ftrace_graph_hash = EMPTY_HASH; -struct ftrace_hash *ftrace_graph_notrace_hash = EMPTY_HASH; +struct ftrace_hash __rcu *ftrace_graph_hash = EMPTY_HASH; +struct ftrace_hash __rcu *ftrace_graph_notrace_hash = EMPTY_HASH; enum graph_filter_type { GRAPH_FILTER_NOTRACE = 0, @@ -5177,9 +5709,13 @@ static int __ftrace_graph_open(struct inode *inode, struct file *file, struct ftrace_graph_data *fgd) { - int ret = 0; + int ret; struct ftrace_hash *new_hash = NULL; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if (file->f_mode & FMODE_WRITE) { const int size_bits = FTRACE_HASH_DEFAULT_BITS; @@ -5331,8 +5867,15 @@ ftrace_graph_release(struct inode *inode, struct file *file) mutex_unlock(&graph_lock); - /* Wait till all users are no longer using the old hash */ - synchronize_rcu(); + /* + * We need to do a hard force of sched synchronization. + * This is because we use preempt_disable() to do RCU, but + * the function tracers can be called where RCU is not watching + * (like before user_exit()). We can not rely on the RCU + * infrastructure to do the synchronization, thus we must do it + * ourselves. + */ + schedule_on_each_cpu(ftrace_sync); free_ftrace_hash(old_hash); } @@ -5771,6 +6314,8 @@ void ftrace_release_mod(struct module *mod) free_pages((unsigned long)pg->records, order); tmp_page = pg->next; kfree(pg); + ftrace_number_of_pages -= 1 << order; + ftrace_number_of_groups--; } } @@ -6019,11 +6564,7 @@ clear_func_from_hash(struct ftrace_init_func *func, struct ftrace_hash *hash) { struct ftrace_func_entry *entry; - if (ftrace_hash_empty(hash)) - return; - - entry = __ftrace_lookup_ip(hash, func->ip); - + entry = ftrace_lookup_ip(hash, func->ip); /* * Do not allow this rec to match again. * Yeah, it may waste some memory, but will be removed @@ -6057,7 +6598,7 @@ static void add_to_clear_hash_list(struct list_head *clear_list, func = kmalloc(sizeof(*func), GFP_KERNEL); if (!func) { - WARN_ONCE(1, "alloc failure, ftrace filter could be stale\n"); + MEM_FAIL(1, "alloc failure, ftrace filter could be stale\n"); return; } @@ -6116,6 +6657,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) *last_pg = pg->next; order = get_count_order(pg->size / ENTRIES_PER_PAGE); free_pages((unsigned long)pg->records, order); + ftrace_number_of_pages -= 1 << order; + ftrace_number_of_groups--; kfree(pg); pg = container_of(last_pg, struct ftrace_page, next); if (!(*last_pg)) @@ -6171,6 +6714,9 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); + pr_info("ftrace: allocated %ld pages with %ld groups\n", + ftrace_number_of_pages, ftrace_number_of_groups); + set_ftrace_early_filters(); return; @@ -6378,7 +6924,7 @@ ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, pid_list = rcu_dereference_sched(tr->function_pids); - this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid, + this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, trace_ignore_this_task(pid_list, next)); } @@ -6432,7 +6978,7 @@ static void clear_ftrace_pids(struct trace_array *tr) unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); for_each_possible_cpu(cpu) - per_cpu_ptr(tr->trace_buffer.data, cpu)->ftrace_ignore_pid = false; + per_cpu_ptr(tr->array_buffer.data, cpu)->ftrace_ignore_pid = false; rcu_assign_pointer(tr->function_pids, NULL); @@ -6487,9 +7033,10 @@ static void *fpid_next(struct seq_file *m, void *v, loff_t *pos) struct trace_array *tr = m->private; struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_pids); - if (v == FTRACE_NO_PIDS) + if (v == FTRACE_NO_PIDS) { + (*pos)++; return NULL; - + } return trace_pid_next(pid_list, v, pos); } @@ -6524,8 +7071,9 @@ ftrace_pid_open(struct inode *inode, struct file *file) struct seq_file *m; int ret = 0; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) @@ -6555,7 +7103,7 @@ static void ignore_task_cpu(void *data) pid_list = rcu_dereference_protected(tr->function_pids, mutex_is_locked(&ftrace_lock)); - this_cpu_write(tr->trace_buffer.data->ftrace_ignore_pid, + this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, trace_ignore_this_task(pid_list, current)); } @@ -6710,6 +7258,18 @@ int unregister_ftrace_function(struct ftrace_ops *ops) } EXPORT_SYMBOL_GPL(unregister_ftrace_function); +static bool is_permanent_ops_registered(void) +{ + struct ftrace_ops *op; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + if (op->flags & FTRACE_OPS_FL_PERMANENT) + return true; + } while_for_each_ftrace_op(op); + + return false; +} + int ftrace_enable_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -6727,8 +7287,6 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled)) goto out; - last_ftrace_enabled = !!ftrace_enabled; - if (ftrace_enabled) { /* we are starting ftrace again */ @@ -6739,12 +7297,19 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); } else { + if (is_permanent_ops_registered()) { + ftrace_enabled = true; + ret = -EBUSY; + goto out; + } + /* stopping ftrace calls (just send to ftrace_stub) */ ftrace_trace_function = ftrace_stub; ftrace_shutdown_sysctl(); } + last_ftrace_enabled = !!ftrace_enabled; out: mutex_unlock(&ftrace_lock); return ret; diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h index 0515a2096f90..0456e0a3dab1 100644 --- a/kernel/trace/ftrace_internal.h +++ b/kernel/trace/ftrace_internal.h @@ -6,22 +6,22 @@ /* * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw_notrace() is that elements removed from this list + * 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_notrace() calls are needed to handle + * mechanism. The rcu_dereference_raw_check() calls are needed to handle * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ #define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw_notrace(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_notrace((op)->next)) && \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ unlikely((op) != &ftrace_list_end)) extern struct ftrace_ops __rcu *ftrace_ops_list; diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c new file mode 100644 index 000000000000..18b0f1cbb947 --- /dev/null +++ b/kernel/trace/kprobe_event_gen_test.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test module for in-kernel kprobe event creation and generation. + * + * Copyright (C) 2019 Tom Zanussi <zanussi@kernel.org> + */ + +#include <linux/module.h> +#include <linux/trace_events.h> + +/* + * This module is a simple test of basic functionality for in-kernel + * kprobe/kretprobe event creation. The first test uses + * kprobe_event_gen_cmd_start(), kprobe_event_add_fields() and + * kprobe_event_gen_cmd_end() to create a kprobe event, which is then + * enabled in order to generate trace output. The second creates a + * kretprobe event using kretprobe_event_gen_cmd_start() and + * kretprobe_event_gen_cmd_end(), and is also then enabled. + * + * To test, select CONFIG_KPROBE_EVENT_GEN_TEST and build the module. + * Then: + * + * # insmod kernel/trace/kprobe_event_gen_test.ko + * # cat /sys/kernel/debug/tracing/trace + * + * You should see many instances of the "gen_kprobe_test" and + * "gen_kretprobe_test" events in the trace buffer. + * + * To remove the events, remove the module: + * + * # rmmod kprobe_event_gen_test + * + */ + +static struct trace_event_file *gen_kprobe_test; +static struct trace_event_file *gen_kretprobe_test; + +/* + * Test to make sure we can create a kprobe event, then add more + * fields. + */ +static int __init test_gen_kprobe_cmd(void) +{ + struct dynevent_cmd cmd; + char *buf; + int ret; + + /* Create a buffer to hold the generated command */ + buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + /* Before generating the command, initialize the cmd object */ + kprobe_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN); + + /* + * Define the gen_kprobe_test event with the first 2 kprobe + * fields. + */ + ret = kprobe_event_gen_cmd_start(&cmd, "gen_kprobe_test", + "do_sys_open", + "dfd=%ax", "filename=%dx"); + if (ret) + goto free; + + /* Use kprobe_event_add_fields to add the rest of the fields */ + + ret = kprobe_event_add_fields(&cmd, "flags=%cx", "mode=+4($stack)"); + if (ret) + goto free; + + /* + * This actually creates the event. + */ + ret = kprobe_event_gen_cmd_end(&cmd); + if (ret) + goto free; + + /* + * Now get the gen_kprobe_test event file. We need to prevent + * the instance and event from disappearing from underneath + * us, which trace_get_event_file() does (though in this case + * we're using the top-level instance which never goes away). + */ + gen_kprobe_test = trace_get_event_file(NULL, "kprobes", + "gen_kprobe_test"); + if (IS_ERR(gen_kprobe_test)) { + ret = PTR_ERR(gen_kprobe_test); + goto delete; + } + + /* Enable the event or you won't see anything */ + ret = trace_array_set_clr_event(gen_kprobe_test->tr, + "kprobes", "gen_kprobe_test", true); + if (ret) { + trace_put_event_file(gen_kprobe_test); + goto delete; + } + out: + return ret; + delete: + /* We got an error after creating the event, delete it */ + ret = kprobe_event_delete("gen_kprobe_test"); + free: + kfree(buf); + + goto out; +} + +/* + * Test to make sure we can create a kretprobe event. + */ +static int __init test_gen_kretprobe_cmd(void) +{ + struct dynevent_cmd cmd; + char *buf; + int ret; + + /* Create a buffer to hold the generated command */ + buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + /* Before generating the command, initialize the cmd object */ + kprobe_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN); + + /* + * Define the kretprobe event. + */ + ret = kretprobe_event_gen_cmd_start(&cmd, "gen_kretprobe_test", + "do_sys_open", + "$retval"); + if (ret) + goto free; + + /* + * This actually creates the event. + */ + ret = kretprobe_event_gen_cmd_end(&cmd); + if (ret) + goto free; + + /* + * Now get the gen_kretprobe_test event file. We need to + * prevent the instance and event from disappearing from + * underneath us, which trace_get_event_file() does (though in + * this case we're using the top-level instance which never + * goes away). + */ + gen_kretprobe_test = trace_get_event_file(NULL, "kprobes", + "gen_kretprobe_test"); + if (IS_ERR(gen_kretprobe_test)) { + ret = PTR_ERR(gen_kretprobe_test); + goto delete; + } + + /* Enable the event or you won't see anything */ + ret = trace_array_set_clr_event(gen_kretprobe_test->tr, + "kprobes", "gen_kretprobe_test", true); + if (ret) { + trace_put_event_file(gen_kretprobe_test); + goto delete; + } + out: + return ret; + delete: + /* We got an error after creating the event, delete it */ + ret = kprobe_event_delete("gen_kretprobe_test"); + free: + kfree(buf); + + goto out; +} + +static int __init kprobe_event_gen_test_init(void) +{ + int ret; + + ret = test_gen_kprobe_cmd(); + if (ret) + return ret; + + ret = test_gen_kretprobe_cmd(); + if (ret) { + WARN_ON(trace_array_set_clr_event(gen_kretprobe_test->tr, + "kprobes", + "gen_kretprobe_test", false)); + trace_put_event_file(gen_kretprobe_test); + WARN_ON(kprobe_event_delete("gen_kretprobe_test")); + } + + return ret; +} + +static void __exit kprobe_event_gen_test_exit(void) +{ + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, + "kprobes", + "gen_kprobe_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(gen_kprobe_test); + + /* Now unregister and free the event */ + WARN_ON(kprobe_event_delete("gen_kprobe_test")); + + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(gen_kprobe_test->tr, + "kprobes", + "gen_kretprobe_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(gen_kretprobe_test); + + /* Now unregister and free the event */ + WARN_ON(kprobe_event_delete("gen_kretprobe_test")); +} + +module_init(kprobe_event_gen_test_init) +module_exit(kprobe_event_gen_test_exit) + +MODULE_AUTHOR("Tom Zanussi"); +MODULE_DESCRIPTION("kprobe event generation test"); +MODULE_LICENSE("GPL v2"); diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index d8765c952fab..31c0fad4cb9e 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -10,18 +10,25 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kernel.h> +#include <linux/kobject.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/printk.h> #include <linux/string.h> +#include <linux/sysfs.h> static ulong delay = 100; -static char test_mode[10] = "irq"; +static char test_mode[12] = "irq"; +static uint burst_size = 1; -module_param_named(delay, delay, ulong, S_IRUGO); -module_param_string(test_mode, test_mode, 10, S_IRUGO); -MODULE_PARM_DESC(delay, "Period in microseconds (100 uS default)"); -MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt or irq (default irq)"); +module_param_named(delay, delay, ulong, 0444); +module_param_string(test_mode, test_mode, 12, 0444); +module_param_named(burst_size, burst_size, uint, 0444); +MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)"); +MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)"); +MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)"); + +#define MIN(x, y) ((x) < (y) ? (x) : (y)) static void busy_wait(ulong time) { @@ -34,37 +41,136 @@ static void busy_wait(ulong time) } while ((end - start) < (time * 1000)); } -static int preemptirq_delay_run(void *data) +static __always_inline void irqoff_test(void) { unsigned long flags; + local_irq_save(flags); + busy_wait(delay); + local_irq_restore(flags); +} - if (!strcmp(test_mode, "irq")) { - local_irq_save(flags); - busy_wait(delay); - local_irq_restore(flags); - } else if (!strcmp(test_mode, "preempt")) { - preempt_disable(); - busy_wait(delay); - preempt_enable(); +static __always_inline void preemptoff_test(void) +{ + preempt_disable(); + busy_wait(delay); + preempt_enable(); +} + +static void execute_preemptirqtest(int idx) +{ + if (!strcmp(test_mode, "irq")) + irqoff_test(); + else if (!strcmp(test_mode, "preempt")) + preemptoff_test(); + else if (!strcmp(test_mode, "alternate")) { + if (idx % 2 == 0) + irqoff_test(); + else + preemptoff_test(); } +} + +#define DECLARE_TESTFN(POSTFIX) \ + static void preemptirqtest_##POSTFIX(int idx) \ + { \ + execute_preemptirqtest(idx); \ + } \ +/* + * We create 10 different functions, so that we can get 10 different + * backtraces. + */ +DECLARE_TESTFN(0) +DECLARE_TESTFN(1) +DECLARE_TESTFN(2) +DECLARE_TESTFN(3) +DECLARE_TESTFN(4) +DECLARE_TESTFN(5) +DECLARE_TESTFN(6) +DECLARE_TESTFN(7) +DECLARE_TESTFN(8) +DECLARE_TESTFN(9) + +static void (*testfuncs[])(int) = { + preemptirqtest_0, + preemptirqtest_1, + preemptirqtest_2, + preemptirqtest_3, + preemptirqtest_4, + preemptirqtest_5, + preemptirqtest_6, + preemptirqtest_7, + preemptirqtest_8, + preemptirqtest_9, +}; + +#define NR_TEST_FUNCS ARRAY_SIZE(testfuncs) + +static int preemptirq_delay_run(void *data) +{ + int i; + int s = MIN(burst_size, NR_TEST_FUNCS); + + for (i = 0; i < s; i++) + (testfuncs[i])(i); return 0; } -static int __init preemptirq_delay_init(void) +static struct task_struct *preemptirq_start_test(void) { char task_name[50]; - struct task_struct *test_task; snprintf(task_name, sizeof(task_name), "%s_test", test_mode); + return kthread_run(preemptirq_delay_run, NULL, task_name); +} + + +static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr, + const char *buf, size_t count) +{ + preemptirq_start_test(); + return count; +} + +static struct kobj_attribute trigger_attribute = + __ATTR(trigger, 0200, NULL, trigger_store); + +static struct attribute *attrs[] = { + &trigger_attribute.attr, + NULL, +}; + +static struct attribute_group attr_group = { + .attrs = attrs, +}; + +static struct kobject *preemptirq_delay_kobj; + +static int __init preemptirq_delay_init(void) +{ + struct task_struct *test_task; + int retval; + + test_task = preemptirq_start_test(); + retval = PTR_ERR_OR_ZERO(test_task); + if (retval != 0) + return retval; + + preemptirq_delay_kobj = kobject_create_and_add("preemptirq_delay_test", + kernel_kobj); + if (!preemptirq_delay_kobj) + return -ENOMEM; + + retval = sysfs_create_group(preemptirq_delay_kobj, &attr_group); + if (retval) + kobject_put(preemptirq_delay_kobj); - test_task = kthread_run(preemptirq_delay_run, NULL, task_name); - return PTR_ERR_OR_ZERO(test_task); + return retval; } static void __exit preemptirq_delay_exit(void) { - return; + kobject_put(preemptirq_delay_kobj); } module_init(preemptirq_delay_init) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 66358d66c933..61f0e92ace99 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -11,6 +11,7 @@ #include <linux/trace_seq.h> #include <linux/spinlock.h> #include <linux/irq_work.h> +#include <linux/security.h> #include <linux/uaccess.h> #include <linux/hardirq.h> #include <linux/kthread.h> /* for self test */ @@ -299,8 +300,6 @@ u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event) /* Missed count stored at end */ #define RB_MISSED_STORED (1 << 30) -#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED) - struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ @@ -442,7 +441,7 @@ enum { struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; - struct ring_buffer *buffer; + struct trace_buffer *buffer; raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; struct lock_class_key lock_key; @@ -481,7 +480,7 @@ struct ring_buffer_per_cpu { struct rb_irq_work irq_work; }; -struct ring_buffer { +struct trace_buffer { unsigned flags; int cpus; atomic_t record_disabled; @@ -517,7 +516,7 @@ struct ring_buffer_iter { * * Returns the number of pages used by a per_cpu buffer of the ring buffer. */ -size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu) +size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu) { return buffer->buffers[cpu]->nr_pages; } @@ -529,7 +528,7 @@ size_t ring_buffer_nr_pages(struct ring_buffer *buffer, int cpu) * * Returns the number of pages that have content in the ring buffer. */ -size_t ring_buffer_nr_dirty_pages(struct ring_buffer *buffer, int cpu) +size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu) { size_t read; size_t cnt; @@ -572,7 +571,7 @@ static void rb_wake_up_waiters(struct irq_work *work) * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -int ring_buffer_wait(struct ring_buffer *buffer, int cpu, int full) +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) { struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer); DEFINE_WAIT(wait); @@ -683,7 +682,7 @@ int ring_buffer_wait(struct ring_buffer *buffer, int cpu, int full) * Returns EPOLLIN | EPOLLRDNORM if data exists in the buffers, * zero otherwise. */ -__poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, +__poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table) { struct ring_buffer_per_cpu *cpu_buffer; @@ -741,13 +740,13 @@ __poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, /* Up this if you want to test the TIME_EXTENTS and normalization */ #define DEBUG_SHIFT 0 -static inline u64 rb_time_stamp(struct ring_buffer *buffer) +static inline u64 rb_time_stamp(struct trace_buffer *buffer) { /* shift to debug/test normalization and TIME_EXTENTS */ return buffer->clock() << DEBUG_SHIFT; } -u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) +u64 ring_buffer_time_stamp(struct trace_buffer *buffer, int cpu) { u64 time; @@ -759,7 +758,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu) } EXPORT_SYMBOL_GPL(ring_buffer_time_stamp); -void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, +void ring_buffer_normalize_time_stamp(struct trace_buffer *buffer, int cpu, u64 *ts) { /* Just stupid testing the normalize function and deltas */ @@ -1282,7 +1281,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, } static struct ring_buffer_per_cpu * -rb_allocate_cpu_buffer(struct ring_buffer *buffer, long nr_pages, int cpu) +rb_allocate_cpu_buffer(struct trace_buffer *buffer, long nr_pages, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_page *bpage; @@ -1367,16 +1366,17 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) * __ring_buffer_alloc - allocate a new ring_buffer * @size: the size in bytes per cpu that is needed. * @flags: attributes to set for the ring buffer. + * @key: ring buffer reader_lock_key. * * Currently the only flag that is available is the RB_FL_OVERWRITE * flag. This flag means that the buffer will overwrite old data * when the buffer wraps. If this flag is not set, the buffer will * drop data when the tail hits the head. */ -struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, +struct trace_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key) { - struct ring_buffer *buffer; + struct trace_buffer *buffer; long nr_pages; int bsize; int cpu; @@ -1446,7 +1446,7 @@ EXPORT_SYMBOL_GPL(__ring_buffer_alloc); * @buffer: the buffer to free. */ void -ring_buffer_free(struct ring_buffer *buffer) +ring_buffer_free(struct trace_buffer *buffer) { int cpu; @@ -1462,18 +1462,18 @@ ring_buffer_free(struct ring_buffer *buffer) } EXPORT_SYMBOL_GPL(ring_buffer_free); -void ring_buffer_set_clock(struct ring_buffer *buffer, +void ring_buffer_set_clock(struct trace_buffer *buffer, u64 (*clock)(void)) { buffer->clock = clock; } -void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs) +void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs) { buffer->time_stamp_abs = abs; } -bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer) +bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer) { return buffer->time_stamp_abs; } @@ -1711,7 +1711,7 @@ static void update_pages_handler(struct work_struct *work) * * Returns 0 on success and < 0 on failure. */ -int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, +int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, int cpu_id) { struct ring_buffer_per_cpu *cpu_buffer; @@ -1890,7 +1890,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, } EXPORT_SYMBOL_GPL(ring_buffer_resize); -void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val) +void ring_buffer_change_overwrite(struct trace_buffer *buffer, int val) { mutex_lock(&buffer->mutex); if (val) @@ -2205,7 +2205,7 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer, { struct buffer_page *tail_page = info->tail_page; struct buffer_page *commit_page = cpu_buffer->commit_page; - struct ring_buffer *buffer = cpu_buffer->buffer; + struct trace_buffer *buffer = cpu_buffer->buffer; struct buffer_page *next_page; int ret; @@ -2329,11 +2329,11 @@ static inline bool rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer, /** * rb_update_event - update event type and data + * @cpu_buffer: The per cpu buffer of the @event * @event: the event to update - * @type: the type of event - * @length: the size of the event field in the ring buffer + * @info: The info to update the @event with (contains length and delta) * - * Update the type and data fields of the event. The length + * Update the type and data fields of the @event. The length * is the actual size that is written to the ring buffer, * and with this, we can determine what to place into the * data field. @@ -2608,7 +2608,7 @@ static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer, } static __always_inline void -rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) +rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) { size_t nr_pages; size_t dirty; @@ -2732,7 +2732,7 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) * Call this function before calling another ring_buffer_lock_reserve() and * call ring_buffer_nest_end() after the nested ring_buffer_unlock_commit(). */ -void ring_buffer_nest_start(struct ring_buffer *buffer) +void ring_buffer_nest_start(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; int cpu; @@ -2752,7 +2752,7 @@ void ring_buffer_nest_start(struct ring_buffer *buffer) * Must be called after ring_buffer_nest_start() and after the * ring_buffer_unlock_commit(). */ -void ring_buffer_nest_end(struct ring_buffer *buffer) +void ring_buffer_nest_end(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; int cpu; @@ -2774,7 +2774,7 @@ void ring_buffer_nest_end(struct ring_buffer *buffer) * * Must be paired with ring_buffer_lock_reserve. */ -int ring_buffer_unlock_commit(struct ring_buffer *buffer, +int ring_buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { struct ring_buffer_per_cpu *cpu_buffer; @@ -2867,7 +2867,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, } static __always_inline struct ring_buffer_event * -rb_reserve_next_event(struct ring_buffer *buffer, +rb_reserve_next_event(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer, unsigned long length) { @@ -2960,7 +2960,7 @@ rb_reserve_next_event(struct ring_buffer *buffer, * If NULL is returned, then nothing has been allocated or locked. */ struct ring_buffer_event * -ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length) +ring_buffer_lock_reserve(struct trace_buffer *buffer, unsigned long length) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; @@ -3061,7 +3061,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, * If this function is called, do not call ring_buffer_unlock_commit on * the event. */ -void ring_buffer_discard_commit(struct ring_buffer *buffer, +void ring_buffer_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { struct ring_buffer_per_cpu *cpu_buffer; @@ -3112,7 +3112,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_discard_commit); * Note, like ring_buffer_lock_reserve, the length is the length of the data * and not the length of the event which would hold the header. */ -int ring_buffer_write(struct ring_buffer *buffer, +int ring_buffer_write(struct trace_buffer *buffer, unsigned long length, void *data) { @@ -3192,7 +3192,7 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer) * * The caller should call synchronize_rcu() after this. */ -void ring_buffer_record_disable(struct ring_buffer *buffer) +void ring_buffer_record_disable(struct trace_buffer *buffer) { atomic_inc(&buffer->record_disabled); } @@ -3205,7 +3205,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable); * Note, multiple disables will need the same number of enables * to truly enable the writing (much like preempt_disable). */ -void ring_buffer_record_enable(struct ring_buffer *buffer) +void ring_buffer_record_enable(struct trace_buffer *buffer) { atomic_dec(&buffer->record_disabled); } @@ -3222,7 +3222,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable); * it works like an on/off switch, where as the disable() version * must be paired with a enable(). */ -void ring_buffer_record_off(struct ring_buffer *buffer) +void ring_buffer_record_off(struct trace_buffer *buffer) { unsigned int rd; unsigned int new_rd; @@ -3245,7 +3245,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_off); * it works like an on/off switch, where as the enable() version * must be paired with a disable(). */ -void ring_buffer_record_on(struct ring_buffer *buffer) +void ring_buffer_record_on(struct trace_buffer *buffer) { unsigned int rd; unsigned int new_rd; @@ -3263,7 +3263,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_on); * * Returns true if the ring buffer is in a state that it accepts writes. */ -bool ring_buffer_record_is_on(struct ring_buffer *buffer) +bool ring_buffer_record_is_on(struct trace_buffer *buffer) { return !atomic_read(&buffer->record_disabled); } @@ -3279,7 +3279,7 @@ bool ring_buffer_record_is_on(struct ring_buffer *buffer) * ring_buffer_record_disable(), as that is a temporary disabling of * the ring buffer. */ -bool ring_buffer_record_is_set_on(struct ring_buffer *buffer) +bool ring_buffer_record_is_set_on(struct trace_buffer *buffer) { return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF); } @@ -3294,7 +3294,7 @@ bool ring_buffer_record_is_set_on(struct ring_buffer *buffer) * * The caller should call synchronize_rcu() after this. */ -void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu) +void ring_buffer_record_disable_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; @@ -3314,7 +3314,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu); * Note, multiple disables will need the same number of enables * to truly enable the writing (much like preempt_disable). */ -void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu) +void ring_buffer_record_enable_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; @@ -3344,7 +3344,7 @@ rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer) * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ -u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu) +u64 ring_buffer_oldest_event_ts(struct trace_buffer *buffer, int cpu) { unsigned long flags; struct ring_buffer_per_cpu *cpu_buffer; @@ -3377,7 +3377,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts); * @buffer: The ring buffer * @cpu: The per CPU buffer to read from. */ -unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu) +unsigned long ring_buffer_bytes_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; @@ -3397,7 +3397,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_bytes_cpu); * @buffer: The ring buffer * @cpu: The per CPU buffer to get the entries from. */ -unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu) +unsigned long ring_buffer_entries_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; @@ -3416,7 +3416,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu); * @buffer: The ring buffer * @cpu: The per CPU buffer to get the number of overruns from */ -unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu) +unsigned long ring_buffer_overrun_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; @@ -3439,7 +3439,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu); * @cpu: The per CPU buffer to get the number of overruns from */ unsigned long -ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu) +ring_buffer_commit_overrun_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; @@ -3461,7 +3461,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu); * @cpu: The per CPU buffer to get the number of overruns from */ unsigned long -ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu) +ring_buffer_dropped_events_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long ret; @@ -3482,7 +3482,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu); * @cpu: The per CPU buffer to get the number of events read */ unsigned long -ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu) +ring_buffer_read_events_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; @@ -3501,7 +3501,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu); * Returns the total number of entries in the ring buffer * (all CPU entries) */ -unsigned long ring_buffer_entries(struct ring_buffer *buffer) +unsigned long ring_buffer_entries(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long entries = 0; @@ -3524,7 +3524,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_entries); * Returns the total number of overruns in the ring buffer * (all CPU entries) */ -unsigned long ring_buffer_overruns(struct ring_buffer *buffer) +unsigned long ring_buffer_overruns(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long overruns = 0; @@ -3948,7 +3948,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_peek); static struct ring_buffer_event * rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) { - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int nr_loops = 0; @@ -4076,7 +4076,7 @@ rb_reader_unlock(struct ring_buffer_per_cpu *cpu_buffer, bool locked) * not consume the data. */ struct ring_buffer_event * -ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts, +ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; @@ -4140,7 +4140,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts) * and eventually empty the ring buffer if the producer is slower. */ struct ring_buffer_event * -ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts, +ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_per_cpu *cpu_buffer; @@ -4200,7 +4200,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_consume); * This overall must be paired with ring_buffer_read_finish. */ struct ring_buffer_iter * -ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu, gfp_t flags) +ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) { struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_iter *iter; @@ -4330,8 +4330,9 @@ EXPORT_SYMBOL_GPL(ring_buffer_read); /** * ring_buffer_size - return the size of the ring buffer (in bytes) * @buffer: The ring buffer. + * @cpu: The CPU to get ring buffer size from. */ -unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu) +unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu) { /* * Earlier, this method returned @@ -4397,7 +4398,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer) * @buffer: The ring buffer to reset a per cpu buffer of * @cpu: The CPU buffer to be reset */ -void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu) +void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; unsigned long flags; @@ -4434,7 +4435,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); * ring_buffer_reset - reset a ring buffer * @buffer: The ring buffer to reset all cpu buffers */ -void ring_buffer_reset(struct ring_buffer *buffer) +void ring_buffer_reset(struct trace_buffer *buffer) { int cpu; @@ -4447,7 +4448,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_reset); * rind_buffer_empty - is the ring buffer empty? * @buffer: The ring buffer to test */ -bool ring_buffer_empty(struct ring_buffer *buffer) +bool ring_buffer_empty(struct trace_buffer *buffer) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; @@ -4477,7 +4478,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty); * @buffer: The ring buffer * @cpu: The CPU buffer to test */ -bool ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu) +bool ring_buffer_empty_cpu(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; unsigned long flags; @@ -4503,14 +4504,15 @@ EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu); * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers * @buffer_a: One buffer to swap with * @buffer_b: The other buffer to swap with + * @cpu: the CPU of the buffers to swap * * This function is useful for tracers that want to take a "snapshot" * of a CPU buffer and has another back up buffer lying around. * it is expected that the tracer handles the cpu buffer not being * used at the moment. */ -int ring_buffer_swap_cpu(struct ring_buffer *buffer_a, - struct ring_buffer *buffer_b, int cpu) +int ring_buffer_swap_cpu(struct trace_buffer *buffer_a, + struct trace_buffer *buffer_b, int cpu) { struct ring_buffer_per_cpu *cpu_buffer_a; struct ring_buffer_per_cpu *cpu_buffer_b; @@ -4589,7 +4591,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * Returns: * The page allocated, or ERR_PTR */ -void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) +void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; struct buffer_data_page *bpage = NULL; @@ -4636,7 +4638,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); * * Free a page allocated from ring_buffer_alloc_read_page. */ -void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data) +void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct buffer_data_page *bpage = data; @@ -4696,7 +4698,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * >=0 if data has been transferred, returns the offset of consumed data. * <0 if no data has been transferred. */ -int ring_buffer_read_page(struct ring_buffer *buffer, +int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page, size_t len, int cpu, int full) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; @@ -4867,12 +4869,12 @@ EXPORT_SYMBOL_GPL(ring_buffer_read_page); */ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node) { - struct ring_buffer *buffer; + struct trace_buffer *buffer; long nr_pages_same; int cpu_i; unsigned long nr_pages; - buffer = container_of(node, struct ring_buffer, node); + buffer = container_of(node, struct trace_buffer, node); if (cpumask_test_cpu(cpu, buffer->cpumask)) return 0; @@ -4922,7 +4924,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node) static struct task_struct *rb_threads[NR_CPUS] __initdata; struct rb_test_data { - struct ring_buffer *buffer; + struct trace_buffer *buffer; unsigned long events; unsigned long bytes_written; unsigned long bytes_alloc; @@ -5064,10 +5066,15 @@ static __init int rb_hammer_test(void *arg) static __init int test_ringbuffer(void) { struct task_struct *rb_hammer; - struct ring_buffer *buffer; + struct trace_buffer *buffer; int cpu; int ret = 0; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Lockdown is enabled, skipping ring buffer tests\n"); + return 0; + } + pr_info("Running ring buffer tests...\n"); buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 0564f6db0561..8df0aa810950 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -29,7 +29,7 @@ static int reader_finish; static DECLARE_COMPLETION(read_start); static DECLARE_COMPLETION(read_done); -static struct ring_buffer *buffer; +static struct trace_buffer *buffer; static struct task_struct *producer; static struct task_struct *consumer; static unsigned long read; @@ -267,12 +267,12 @@ static void ring_buffer_producer(void) if (consumer && !(cnt % wakeup_interval)) wake_up_process(consumer); -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION /* - * If we are a non preempt kernel, the 10 second run will + * If we are a non preempt kernel, the 10 seconds run will * stop everything while it runs. Instead, we will call * cond_resched and also add any time that was lost by a - * rescedule. + * reschedule. * * Do a cond resched at the same frequency we would wake up * the reader. diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c new file mode 100644 index 000000000000..4aefe003cb7c --- /dev/null +++ b/kernel/trace/synth_event_gen_test.c @@ -0,0 +1,523 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test module for in-kernel sythetic event creation and generation. + * + * Copyright (C) 2019 Tom Zanussi <zanussi@kernel.org> + */ + +#include <linux/module.h> +#include <linux/trace_events.h> + +/* + * This module is a simple test of basic functionality for in-kernel + * synthetic event creation and generation, the first and second tests + * using synth_event_gen_cmd_start() and synth_event_add_field(), the + * third uses synth_event_create() to do it all at once with a static + * field array. + * + * Following that are a few examples using the created events to test + * various ways of tracing a synthetic event. + * + * To test, select CONFIG_SYNTH_EVENT_GEN_TEST and build the module. + * Then: + * + * # insmod kernel/trace/synth_event_gen_test.ko + * # cat /sys/kernel/debug/tracing/trace + * + * You should see several events in the trace buffer - + * "create_synth_test", "empty_synth_test", and several instances of + * "gen_synth_test". + * + * To remove the events, remove the module: + * + * # rmmod synth_event_gen_test + * + */ + +static struct trace_event_file *create_synth_test; +static struct trace_event_file *empty_synth_test; +static struct trace_event_file *gen_synth_test; + +/* + * Test to make sure we can create a synthetic event, then add more + * fields. + */ +static int __init test_gen_synth_cmd(void) +{ + struct dynevent_cmd cmd; + u64 vals[7]; + char *buf; + int ret; + + /* Create a buffer to hold the generated command */ + buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + /* Before generating the command, initialize the cmd object */ + synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN); + + /* + * Create the empty gen_synth_test synthetic event with the + * first 4 fields. + */ + ret = synth_event_gen_cmd_start(&cmd, "gen_synth_test", THIS_MODULE, + "pid_t", "next_pid_field", + "char[16]", "next_comm_field", + "u64", "ts_ns", + "u64", "ts_ms"); + if (ret) + goto free; + + /* Use synth_event_add_field to add the rest of the fields */ + + ret = synth_event_add_field(&cmd, "unsigned int", "cpu"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "char[64]", "my_string_field"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "int", "my_int_field"); + if (ret) + goto free; + + ret = synth_event_gen_cmd_end(&cmd); + if (ret) + goto free; + + /* + * Now get the gen_synth_test event file. We need to prevent + * the instance and event from disappearing from underneath + * us, which trace_get_event_file() does (though in this case + * we're using the top-level instance which never goes away). + */ + gen_synth_test = trace_get_event_file(NULL, "synthetic", + "gen_synth_test"); + if (IS_ERR(gen_synth_test)) { + ret = PTR_ERR(gen_synth_test); + goto delete; + } + + /* Enable the event or you won't see anything */ + ret = trace_array_set_clr_event(gen_synth_test->tr, + "synthetic", "gen_synth_test", true); + if (ret) { + trace_put_event_file(gen_synth_test); + goto delete; + } + + /* Create some bogus values just for testing */ + + vals[0] = 777; /* next_pid_field */ + vals[1] = (u64)"hula hoops"; /* next_comm_field */ + vals[2] = 1000000; /* ts_ns */ + vals[3] = 1000; /* ts_ms */ + vals[4] = smp_processor_id(); /* cpu */ + vals[5] = (u64)"thneed"; /* my_string_field */ + vals[6] = 598; /* my_int_field */ + + /* Now generate a gen_synth_test event */ + ret = synth_event_trace_array(gen_synth_test, vals, ARRAY_SIZE(vals)); + out: + return ret; + delete: + /* We got an error after creating the event, delete it */ + synth_event_delete("gen_synth_test"); + free: + kfree(buf); + + goto out; +} + +/* + * Test to make sure we can create an initially empty synthetic event, + * then add all the fields. + */ +static int __init test_empty_synth_event(void) +{ + struct dynevent_cmd cmd; + u64 vals[7]; + char *buf; + int ret; + + /* Create a buffer to hold the generated command */ + buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + /* Before generating the command, initialize the cmd object */ + synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN); + + /* + * Create the empty_synth_test synthetic event with no fields. + */ + ret = synth_event_gen_cmd_start(&cmd, "empty_synth_test", THIS_MODULE); + if (ret) + goto free; + + /* Use synth_event_add_field to add all of the fields */ + + ret = synth_event_add_field(&cmd, "pid_t", "next_pid_field"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "char[16]", "next_comm_field"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "u64", "ts_ns"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "u64", "ts_ms"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "unsigned int", "cpu"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "char[64]", "my_string_field"); + if (ret) + goto free; + + ret = synth_event_add_field(&cmd, "int", "my_int_field"); + if (ret) + goto free; + + /* All fields have been added, close and register the synth event */ + + ret = synth_event_gen_cmd_end(&cmd); + if (ret) + goto free; + + /* + * Now get the empty_synth_test event file. We need to + * prevent the instance and event from disappearing from + * underneath us, which trace_get_event_file() does (though in + * this case we're using the top-level instance which never + * goes away). + */ + empty_synth_test = trace_get_event_file(NULL, "synthetic", + "empty_synth_test"); + if (IS_ERR(empty_synth_test)) { + ret = PTR_ERR(empty_synth_test); + goto delete; + } + + /* Enable the event or you won't see anything */ + ret = trace_array_set_clr_event(empty_synth_test->tr, + "synthetic", "empty_synth_test", true); + if (ret) { + trace_put_event_file(empty_synth_test); + goto delete; + } + + /* Create some bogus values just for testing */ + + vals[0] = 777; /* next_pid_field */ + vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[2] = 1000000; /* ts_ns */ + vals[3] = 1000; /* ts_ms */ + vals[4] = smp_processor_id(); /* cpu */ + vals[5] = (u64)"thneed_2.0"; /* my_string_field */ + vals[6] = 399; /* my_int_field */ + + /* Now trace an empty_synth_test event */ + ret = synth_event_trace_array(empty_synth_test, vals, ARRAY_SIZE(vals)); + out: + return ret; + delete: + /* We got an error after creating the event, delete it */ + synth_event_delete("empty_synth_test"); + free: + kfree(buf); + + goto out; +} + +static struct synth_field_desc create_synth_test_fields[] = { + { .type = "pid_t", .name = "next_pid_field" }, + { .type = "char[16]", .name = "next_comm_field" }, + { .type = "u64", .name = "ts_ns" }, + { .type = "u64", .name = "ts_ms" }, + { .type = "unsigned int", .name = "cpu" }, + { .type = "char[64]", .name = "my_string_field" }, + { .type = "int", .name = "my_int_field" }, +}; + +/* + * Test synthetic event creation all at once from array of field + * descriptors. + */ +static int __init test_create_synth_event(void) +{ + u64 vals[7]; + int ret; + + /* Create the create_synth_test event with the fields above */ + ret = synth_event_create("create_synth_test", + create_synth_test_fields, + ARRAY_SIZE(create_synth_test_fields), + THIS_MODULE); + if (ret) + goto out; + + /* + * Now get the create_synth_test event file. We need to + * prevent the instance and event from disappearing from + * underneath us, which trace_get_event_file() does (though in + * this case we're using the top-level instance which never + * goes away). + */ + create_synth_test = trace_get_event_file(NULL, "synthetic", + "create_synth_test"); + if (IS_ERR(create_synth_test)) { + ret = PTR_ERR(create_synth_test); + goto delete; + } + + /* Enable the event or you won't see anything */ + ret = trace_array_set_clr_event(create_synth_test->tr, + "synthetic", "create_synth_test", true); + if (ret) { + trace_put_event_file(create_synth_test); + goto delete; + } + + /* Create some bogus values just for testing */ + + vals[0] = 777; /* next_pid_field */ + vals[1] = (u64)"tiddlywinks"; /* next_comm_field */ + vals[2] = 1000000; /* ts_ns */ + vals[3] = 1000; /* ts_ms */ + vals[4] = smp_processor_id(); /* cpu */ + vals[5] = (u64)"thneed"; /* my_string_field */ + vals[6] = 398; /* my_int_field */ + + /* Now generate a create_synth_test event */ + ret = synth_event_trace_array(create_synth_test, vals, ARRAY_SIZE(vals)); + out: + return ret; + delete: + /* We got an error after creating the event, delete it */ + ret = synth_event_delete("create_synth_test"); + + goto out; +} + +/* + * Test tracing a synthetic event by reserving trace buffer space, + * then filling in fields one after another. + */ +static int __init test_add_next_synth_val(void) +{ + struct synth_event_trace_state trace_state; + int ret; + + /* Start by reserving space in the trace buffer */ + ret = synth_event_trace_start(gen_synth_test, &trace_state); + if (ret) + return ret; + + /* Write some bogus values into the trace buffer, one after another */ + + /* next_pid_field */ + ret = synth_event_add_next_val(777, &trace_state); + if (ret) + goto out; + + /* next_comm_field */ + ret = synth_event_add_next_val((u64)"slinky", &trace_state); + if (ret) + goto out; + + /* ts_ns */ + ret = synth_event_add_next_val(1000000, &trace_state); + if (ret) + goto out; + + /* ts_ms */ + ret = synth_event_add_next_val(1000, &trace_state); + if (ret) + goto out; + + /* cpu */ + ret = synth_event_add_next_val(smp_processor_id(), &trace_state); + if (ret) + goto out; + + /* my_string_field */ + ret = synth_event_add_next_val((u64)"thneed_2.01", &trace_state); + if (ret) + goto out; + + /* my_int_field */ + ret = synth_event_add_next_val(395, &trace_state); + out: + /* Finally, commit the event */ + ret = synth_event_trace_end(&trace_state); + + return ret; +} + +/* + * Test tracing a synthetic event by reserving trace buffer space, + * then filling in fields using field names, which can be done in any + * order. + */ +static int __init test_add_synth_val(void) +{ + struct synth_event_trace_state trace_state; + int ret; + + /* Start by reserving space in the trace buffer */ + ret = synth_event_trace_start(gen_synth_test, &trace_state); + if (ret) + return ret; + + /* Write some bogus values into the trace buffer, using field names */ + + ret = synth_event_add_val("ts_ns", 1000000, &trace_state); + if (ret) + goto out; + + ret = synth_event_add_val("ts_ms", 1000, &trace_state); + if (ret) + goto out; + + ret = synth_event_add_val("cpu", smp_processor_id(), &trace_state); + if (ret) + goto out; + + ret = synth_event_add_val("next_pid_field", 777, &trace_state); + if (ret) + goto out; + + ret = synth_event_add_val("next_comm_field", (u64)"silly putty", + &trace_state); + if (ret) + goto out; + + ret = synth_event_add_val("my_string_field", (u64)"thneed_9", + &trace_state); + if (ret) + goto out; + + ret = synth_event_add_val("my_int_field", 3999, &trace_state); + out: + /* Finally, commit the event */ + ret = synth_event_trace_end(&trace_state); + + return ret; +} + +/* + * Test tracing a synthetic event all at once from array of values. + */ +static int __init test_trace_synth_event(void) +{ + int ret; + + /* Trace some bogus values just for testing */ + ret = synth_event_trace(create_synth_test, 7, /* number of values */ + 444, /* next_pid_field */ + (u64)"clackers", /* next_comm_field */ + 1000000, /* ts_ns */ + 1000, /* ts_ms */ + smp_processor_id(), /* cpu */ + (u64)"Thneed", /* my_string_field */ + 999); /* my_int_field */ + return ret; +} + +static int __init synth_event_gen_test_init(void) +{ + int ret; + + ret = test_gen_synth_cmd(); + if (ret) + return ret; + + ret = test_empty_synth_event(); + if (ret) { + WARN_ON(trace_array_set_clr_event(gen_synth_test->tr, + "synthetic", + "gen_synth_test", false)); + trace_put_event_file(gen_synth_test); + WARN_ON(synth_event_delete("gen_synth_test")); + goto out; + } + + ret = test_create_synth_event(); + if (ret) { + WARN_ON(trace_array_set_clr_event(gen_synth_test->tr, + "synthetic", + "gen_synth_test", false)); + trace_put_event_file(gen_synth_test); + WARN_ON(synth_event_delete("gen_synth_test")); + + WARN_ON(trace_array_set_clr_event(empty_synth_test->tr, + "synthetic", + "empty_synth_test", false)); + trace_put_event_file(empty_synth_test); + WARN_ON(synth_event_delete("empty_synth_test")); + goto out; + } + + ret = test_add_next_synth_val(); + WARN_ON(ret); + + ret = test_add_synth_val(); + WARN_ON(ret); + + ret = test_trace_synth_event(); + WARN_ON(ret); + out: + return ret; +} + +static void __exit synth_event_gen_test_exit(void) +{ + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(gen_synth_test->tr, + "synthetic", + "gen_synth_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(gen_synth_test); + + /* Now unregister and free the synthetic event */ + WARN_ON(synth_event_delete("gen_synth_test")); + + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(empty_synth_test->tr, + "synthetic", + "empty_synth_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(empty_synth_test); + + /* Now unregister and free the synthetic event */ + WARN_ON(synth_event_delete("empty_synth_test")); + + /* Disable the event or you can't remove it */ + WARN_ON(trace_array_set_clr_event(create_synth_test->tr, + "synthetic", + "create_synth_test", false)); + + /* Now give the file and instance back */ + trace_put_event_file(create_synth_test); + + /* Now unregister and free the synthetic event */ + WARN_ON(synth_event_delete("create_synth_test")); +} + +module_init(synth_event_gen_test_init) +module_exit(synth_event_gen_test_exit) + +MODULE_AUTHOR("Tom Zanussi"); +MODULE_DESCRIPTION("synthetic event generation test"); +MODULE_LICENSE("GPL v2"); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 525a97fbbc60..c797a15a1fc7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -17,6 +17,7 @@ #include <linux/stacktrace.h> #include <linux/writeback.h> #include <linux/kallsyms.h> +#include <linux/security.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/irqflags.h> @@ -44,6 +45,9 @@ #include <linux/trace.h> #include <linux/sched/clock.h> #include <linux/sched/rt.h> +#include <linux/fsnotify.h> +#include <linux/irq_work.h> +#include <linux/workqueue.h> #include "trace.h" #include "trace_output.h" @@ -158,8 +162,8 @@ union trace_eval_map_item { static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ -static int tracing_set_tracer(struct trace_array *tr, const char *buf); -static void ftrace_trace_userstack(struct ring_buffer *buffer, +int tracing_set_tracer(struct trace_array *tr, const char *buf); +static void ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc); #define MAX_TRACER_SIZE 100 @@ -297,15 +301,44 @@ static void __trace_array_put(struct trace_array *this_tr) this_tr->ref--; } +/** + * trace_array_put - Decrement the reference counter for this trace array. + * + * NOTE: Use this when we no longer need the trace array returned by + * trace_array_get_by_name(). This ensures the trace array can be later + * destroyed. + * + */ void trace_array_put(struct trace_array *this_tr) { + if (!this_tr) + return; + mutex_lock(&trace_types_lock); __trace_array_put(this_tr); mutex_unlock(&trace_types_lock); } +EXPORT_SYMBOL_GPL(trace_array_put); + +int tracing_check_open_get_tr(struct trace_array *tr) +{ + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + + if (tracing_disabled) + return -ENODEV; + + if (tr && trace_array_get(tr) < 0) + return -ENODEV; + + return 0; +} int call_filter_check_discard(struct trace_event_call *call, void *rec, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event) { if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) && @@ -570,7 +603,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, return read; } -static u64 buffer_ftrace_now(struct trace_buffer *buf, int cpu) +static u64 buffer_ftrace_now(struct array_buffer *buf, int cpu) { u64 ts; @@ -586,7 +619,7 @@ static u64 buffer_ftrace_now(struct trace_buffer *buf, int cpu) u64 ftrace_now(int cpu) { - return buffer_ftrace_now(&global_trace.trace_buffer, cpu); + return buffer_ftrace_now(&global_trace.array_buffer, cpu); } /** @@ -714,22 +747,22 @@ static inline void trace_access_lock_init(void) #endif #ifdef CONFIG_STACKTRACE -static void __ftrace_trace_stack(struct ring_buffer *buffer, +static void __ftrace_trace_stack(struct trace_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs); static inline void ftrace_trace_stack(struct trace_array *tr, - struct ring_buffer *buffer, + struct trace_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs); #else -static inline void __ftrace_trace_stack(struct ring_buffer *buffer, +static inline void __ftrace_trace_stack(struct trace_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs) { } static inline void ftrace_trace_stack(struct trace_array *tr, - struct ring_buffer *buffer, + struct trace_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs) { @@ -747,7 +780,7 @@ trace_event_setup(struct ring_buffer_event *event, } static __always_inline struct ring_buffer_event * -__trace_buffer_lock_reserve(struct ring_buffer *buffer, +__trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned long flags, int pc) @@ -763,8 +796,8 @@ __trace_buffer_lock_reserve(struct ring_buffer *buffer, void tracer_tracing_on(struct trace_array *tr) { - if (tr->trace_buffer.buffer) - ring_buffer_record_on(tr->trace_buffer.buffer); + if (tr->array_buffer.buffer) + ring_buffer_record_on(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to @@ -792,7 +825,7 @@ EXPORT_SYMBOL_GPL(tracing_on); static __always_inline void -__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event) +__buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { __this_cpu_write(trace_taskinfo_save, true); @@ -815,7 +848,7 @@ __buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *eve int __trace_puts(unsigned long ip, const char *str, int size) { struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct print_entry *entry; unsigned long irq_flags; int alloc; @@ -832,11 +865,14 @@ int __trace_puts(unsigned long ip, const char *str, int size) alloc = sizeof(*entry) + size + 2; /* possible \n added */ local_save_flags(irq_flags); - buffer = global_trace.trace_buffer.buffer; + buffer = global_trace.array_buffer.buffer; + ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, irq_flags, pc); - if (!event) - return 0; + if (!event) { + size = 0; + goto out; + } entry = ring_buffer_event_data(event); entry->ip = ip; @@ -852,7 +888,8 @@ int __trace_puts(unsigned long ip, const char *str, int size) __buffer_unlock_commit(buffer, event); ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL); - + out: + ring_buffer_nest_end(buffer); return size; } EXPORT_SYMBOL_GPL(__trace_puts); @@ -865,10 +902,11 @@ EXPORT_SYMBOL_GPL(__trace_puts); int __trace_bputs(unsigned long ip, const char *str) { struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct bputs_entry *entry; unsigned long irq_flags; int size = sizeof(struct bputs_entry); + int ret = 0; int pc; if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) @@ -880,11 +918,13 @@ int __trace_bputs(unsigned long ip, const char *str) return 0; local_save_flags(irq_flags); - buffer = global_trace.trace_buffer.buffer; + buffer = global_trace.array_buffer.buffer; + + ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, irq_flags, pc); if (!event) - return 0; + goto out; entry = ring_buffer_event_data(event); entry->ip = ip; @@ -893,7 +933,10 @@ int __trace_bputs(unsigned long ip, const char *str) __buffer_unlock_commit(buffer, event); ftrace_trace_stack(&global_trace, buffer, irq_flags, 4, pc, NULL); - return 1; + ret = 1; + out: + ring_buffer_nest_end(buffer); + return ret; } EXPORT_SYMBOL_GPL(__trace_bputs); @@ -1003,9 +1046,9 @@ void *tracing_cond_snapshot_data(struct trace_array *tr) } EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); -static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, - struct trace_buffer *size_buf, int cpu_id); -static void set_buffer_entries(struct trace_buffer *buf, unsigned long val); +static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, + struct array_buffer *size_buf, int cpu_id); +static void set_buffer_entries(struct array_buffer *buf, unsigned long val); int tracing_alloc_snapshot_instance(struct trace_array *tr) { @@ -1015,7 +1058,7 @@ int tracing_alloc_snapshot_instance(struct trace_array *tr) /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, - &tr->trace_buffer, RING_BUFFER_ALL_CPUS); + &tr->array_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; @@ -1218,8 +1261,8 @@ EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); void tracer_tracing_off(struct trace_array *tr) { - if (tr->trace_buffer.buffer) - ring_buffer_record_off(tr->trace_buffer.buffer); + if (tr->array_buffer.buffer) + ring_buffer_record_off(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to @@ -1261,8 +1304,8 @@ void disable_trace_on_warning(void) */ bool tracer_tracing_is_on(struct trace_array *tr) { - if (tr->trace_buffer.buffer) - return ring_buffer_record_is_on(tr->trace_buffer.buffer); + if (tr->array_buffer.buffer) + return ring_buffer_record_is_on(tr->array_buffer.buffer); return !tr->buffer_disabled; } @@ -1479,6 +1522,74 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) } unsigned long __read_mostly tracing_thresh; +static const struct file_operations tracing_max_lat_fops; + +#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \ + defined(CONFIG_FSNOTIFY) + +static struct workqueue_struct *fsnotify_wq; + +static void latency_fsnotify_workfn(struct work_struct *work) +{ + struct trace_array *tr = container_of(work, struct trace_array, + fsnotify_work); + fsnotify(tr->d_max_latency->d_inode, FS_MODIFY, + tr->d_max_latency->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0); +} + +static void latency_fsnotify_workfn_irq(struct irq_work *iwork) +{ + struct trace_array *tr = container_of(iwork, struct trace_array, + fsnotify_irqwork); + queue_work(fsnotify_wq, &tr->fsnotify_work); +} + +static void trace_create_maxlat_file(struct trace_array *tr, + struct dentry *d_tracer) +{ + INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn); + init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); + tr->d_max_latency = trace_create_file("tracing_max_latency", 0644, + d_tracer, &tr->max_latency, + &tracing_max_lat_fops); +} + +__init static int latency_fsnotify_init(void) +{ + fsnotify_wq = alloc_workqueue("tr_max_lat_wq", + WQ_UNBOUND | WQ_HIGHPRI, 0); + if (!fsnotify_wq) { + pr_err("Unable to allocate tr_max_lat_wq\n"); + return -ENOMEM; + } + return 0; +} + +late_initcall_sync(latency_fsnotify_init); + +void latency_fsnotify(struct trace_array *tr) +{ + if (!fsnotify_wq) + return; + /* + * We cannot call queue_work(&tr->fsnotify_work) from here because it's + * possible that we are called from __schedule() or do_idle(), which + * could cause a deadlock. + */ + irq_work_queue(&tr->fsnotify_irqwork); +} + +/* + * (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \ + * defined(CONFIG_FSNOTIFY) + */ +#else + +#define trace_create_maxlat_file(tr, d_tracer) \ + trace_create_file("tracing_max_latency", 0644, d_tracer, \ + &tr->max_latency, &tracing_max_lat_fops) + +#endif #ifdef CONFIG_TRACER_MAX_TRACE /* @@ -1489,8 +1600,8 @@ unsigned long __read_mostly tracing_thresh; static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct trace_buffer *trace_buf = &tr->trace_buffer; - struct trace_buffer *max_buf = &tr->max_buffer; + struct array_buffer *trace_buf = &tr->array_buffer; + struct array_buffer *max_buf = &tr->max_buffer; struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); @@ -1518,6 +1629,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) /* record this tasks comm */ tracing_record_cmdline(tsk); + latency_fsnotify(tr); } /** @@ -1547,8 +1659,8 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, arch_spin_lock(&tr->max_lock); - /* Inherit the recordable setting from trace_buffer */ - if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer)) + /* Inherit the recordable setting from array_buffer */ + if (ring_buffer_record_is_set_on(tr->array_buffer.buffer)) ring_buffer_record_on(tr->max_buffer.buffer); else ring_buffer_record_off(tr->max_buffer.buffer); @@ -1557,7 +1669,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) goto out_unlock; #endif - swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); + swap(tr->array_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); @@ -1567,9 +1679,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, /** * update_max_tr_single - only copy one trace over, and reset the rest - * @tr - tracer - * @tsk - task with the latency - * @cpu - the cpu of the buffer to copy. + * @tr: tracer + * @tsk: task with the latency + * @cpu: the cpu of the buffer to copy. * * Flip the trace of a single CPU buffer between the @tr and the max_tr. */ @@ -1590,7 +1702,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); - ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->trace_buffer.buffer, cpu); + ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->array_buffer.buffer, cpu); if (ret == -EBUSY) { /* @@ -1616,7 +1728,7 @@ static int wait_on_pipe(struct trace_iterator *iter, int full) if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file, + return ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); } @@ -1667,7 +1779,7 @@ static int run_tracer_selftest(struct tracer *type) * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); tr->current_trace = type; @@ -1693,7 +1805,7 @@ static int run_tracer_selftest(struct tracer *type) return -1; } /* Only reset on passing, to avoid touching corrupted buffers */ - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { @@ -1767,7 +1879,7 @@ static void __init apply_trace_boot_options(void); /** * register_tracer - register a tracer with the ftrace system. - * @type - the plugin for the tracer + * @type: the plugin for the tracer * * Register a new plugin tracer. */ @@ -1786,6 +1898,12 @@ int __init register_tracer(struct tracer *type) return -1; } + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not register tracer %s due to lockdown\n", + type->name); + return -EPERM; + } + mutex_lock(&trace_types_lock); tracing_selftest_running = true; @@ -1854,9 +1972,9 @@ int __init register_tracer(struct tracer *type) return ret; } -void tracing_reset(struct trace_buffer *buf, int cpu) +static void tracing_reset_cpu(struct array_buffer *buf, int cpu) { - struct ring_buffer *buffer = buf->buffer; + struct trace_buffer *buffer = buf->buffer; if (!buffer) return; @@ -1870,9 +1988,9 @@ void tracing_reset(struct trace_buffer *buf, int cpu) ring_buffer_record_enable(buffer); } -void tracing_reset_online_cpus(struct trace_buffer *buf) +void tracing_reset_online_cpus(struct array_buffer *buf) { - struct ring_buffer *buffer = buf->buffer; + struct trace_buffer *buffer = buf->buffer; int cpu; if (!buffer) @@ -1900,7 +2018,7 @@ void tracing_reset_all_online_cpus(void) if (!tr->clear_trace) continue; tr->clear_trace = false; - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE tracing_reset_online_cpus(&tr->max_buffer); #endif @@ -1990,7 +2108,7 @@ int is_tracing_stopped(void) */ void tracing_start(void) { - struct ring_buffer *buffer; + struct trace_buffer *buffer; unsigned long flags; if (tracing_disabled) @@ -2009,7 +2127,7 @@ void tracing_start(void) /* Prevent the buffers from switching */ arch_spin_lock(&global_trace.max_lock); - buffer = global_trace.trace_buffer.buffer; + buffer = global_trace.array_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); @@ -2027,7 +2145,7 @@ void tracing_start(void) static void tracing_start_tr(struct trace_array *tr) { - struct ring_buffer *buffer; + struct trace_buffer *buffer; unsigned long flags; if (tracing_disabled) @@ -2048,7 +2166,7 @@ static void tracing_start_tr(struct trace_array *tr) goto out; } - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); @@ -2064,7 +2182,7 @@ static void tracing_start_tr(struct trace_array *tr) */ void tracing_stop(void) { - struct ring_buffer *buffer; + struct trace_buffer *buffer; unsigned long flags; raw_spin_lock_irqsave(&global_trace.start_lock, flags); @@ -2074,7 +2192,7 @@ void tracing_stop(void) /* Prevent the buffers from switching */ arch_spin_lock(&global_trace.max_lock); - buffer = global_trace.trace_buffer.buffer; + buffer = global_trace.array_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); @@ -2092,7 +2210,7 @@ void tracing_stop(void) static void tracing_stop_tr(struct trace_array *tr) { - struct ring_buffer *buffer; + struct trace_buffer *buffer; unsigned long flags; /* If global, we need to also stop the max tracer */ @@ -2103,7 +2221,7 @@ static void tracing_stop_tr(struct trace_array *tr) if (tr->stop_count++) goto out; - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); @@ -2230,9 +2348,9 @@ static bool tracing_record_taskinfo_skip(int flags) /** * tracing_record_taskinfo - record the task info of a task * - * @task - task to record - * @flags - TRACE_RECORD_CMDLINE for recording comm - * - TRACE_RECORD_TGID for recording tgid + * @task: task to record + * @flags: TRACE_RECORD_CMDLINE for recording comm + * TRACE_RECORD_TGID for recording tgid */ void tracing_record_taskinfo(struct task_struct *task, int flags) { @@ -2258,10 +2376,10 @@ void tracing_record_taskinfo(struct task_struct *task, int flags) /** * tracing_record_taskinfo_sched_switch - record task info for sched_switch * - * @prev - previous task during sched_switch - * @next - next task during sched_switch - * @flags - TRACE_RECORD_CMDLINE for recording comm - * TRACE_RECORD_TGID for recording tgid + * @prev: previous task during sched_switch + * @next: next task during sched_switch + * @flags: TRACE_RECORD_CMDLINE for recording comm + * TRACE_RECORD_TGID for recording tgid */ void tracing_record_taskinfo_sched_switch(struct task_struct *prev, struct task_struct *next, int flags) @@ -2334,7 +2452,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned short type, EXPORT_SYMBOL_GPL(tracing_generic_entry_update); struct ring_buffer_event * -trace_buffer_lock_reserve(struct ring_buffer *buffer, +trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned long flags, int pc) @@ -2453,10 +2571,10 @@ void trace_buffered_event_disable(void) preempt_enable(); } -static struct ring_buffer *temp_buffer; +static struct trace_buffer *temp_buffer; struct ring_buffer_event * -trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, +trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, struct trace_event_file *trace_file, int type, unsigned long len, unsigned long flags, int pc) @@ -2464,7 +2582,7 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb, struct ring_buffer_event *entry; int val; - *current_rb = trace_file->tr->trace_buffer.buffer; + *current_rb = trace_file->tr->array_buffer.buffer; if (!ring_buffer_time_stamp_abs(*current_rb) && (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) && @@ -2502,6 +2620,7 @@ static DEFINE_MUTEX(tracepoint_printk_mutex); static void output_printk(struct trace_event_buffer *fbuffer) { struct trace_event_call *event_call; + struct trace_event_file *file; struct trace_event *event; unsigned long flags; struct trace_iterator *iter = tracepoint_print_iter; @@ -2515,6 +2634,12 @@ static void output_printk(struct trace_event_buffer *fbuffer) !event_call->event.funcs->trace) return; + file = fbuffer->trace_file; + if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || + (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && + !filter_match_preds(file->filter, fbuffer->entry))) + return; + event = &fbuffer->trace_file->event_call->event; spin_lock_irqsave(&tracepoint_iter_lock, flags); @@ -2565,9 +2690,9 @@ void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); - event_trigger_unlock_commit(fbuffer->trace_file, fbuffer->buffer, + event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer, fbuffer->event, fbuffer->entry, - fbuffer->flags, fbuffer->pc); + fbuffer->flags, fbuffer->pc, fbuffer->regs); } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); @@ -2581,7 +2706,7 @@ EXPORT_SYMBOL_GPL(trace_event_buffer_commit); # define STACK_SKIP 3 void trace_buffer_unlock_commit_regs(struct trace_array *tr, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc, struct pt_regs *regs) @@ -2602,7 +2727,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, * Similar to trace_buffer_unlock_commit_regs() but do not dump stack. */ void -trace_buffer_unlock_commit_nostack(struct ring_buffer *buffer, +trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event) { __buffer_unlock_commit(buffer, event); @@ -2642,10 +2767,10 @@ static void ftrace_exports(struct ring_buffer_event *event) preempt_disable_notrace(); - export = rcu_dereference_raw_notrace(ftrace_exports_list); + export = rcu_dereference_raw_check(ftrace_exports_list); while (export) { trace_process_export(export, event); - export = rcu_dereference_raw_notrace(export->next); + export = rcu_dereference_raw_check(export->next); } preempt_enable_notrace(); @@ -2737,7 +2862,7 @@ trace_function(struct trace_array *tr, int pc) { struct trace_event_call *call = &event_function; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; @@ -2775,7 +2900,7 @@ struct ftrace_stacks { static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); -static void __ftrace_trace_stack(struct ring_buffer *buffer, +static void __ftrace_trace_stack(struct trace_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs) { @@ -2850,7 +2975,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer, } static inline void ftrace_trace_stack(struct trace_array *tr, - struct ring_buffer *buffer, + struct trace_buffer *buffer, unsigned long flags, int skip, int pc, struct pt_regs *regs) { @@ -2863,7 +2988,7 @@ static inline void ftrace_trace_stack(struct trace_array *tr, void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc) { - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; if (rcu_is_watching()) { __ftrace_trace_stack(buffer, flags, skip, pc, NULL); @@ -2901,7 +3026,7 @@ void trace_dump_stack(int skip) /* Skip 1 to skip this function. */ skip++; #endif - __ftrace_trace_stack(global_trace.trace_buffer.buffer, + __ftrace_trace_stack(global_trace.array_buffer.buffer, flags, skip, preempt_count(), NULL); } EXPORT_SYMBOL_GPL(trace_dump_stack); @@ -2910,7 +3035,7 @@ EXPORT_SYMBOL_GPL(trace_dump_stack); static DEFINE_PER_CPU(int, user_stack_count); static void -ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) +ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; @@ -2955,7 +3080,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc) preempt_enable(); } #else /* CONFIG_USER_STACKTRACE_SUPPORT */ -static void ftrace_trace_userstack(struct ring_buffer *buffer, +static void ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) { } @@ -3001,7 +3126,7 @@ static int alloc_percpu_trace_buffer(void) struct trace_buffer_struct *buffers; buffers = alloc_percpu(struct trace_buffer_struct); - if (WARN(!buffers, "Could not allocate percpu trace_printk buffer")) + if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer")) return -ENOMEM; trace_percpu_buffer = buffers; @@ -3046,7 +3171,7 @@ void trace_printk_init_buffers(void) * directly here. If the global_trace.buffer is already * allocated here, then this was called by module code. */ - if (global_trace.trace_buffer.buffer) + if (global_trace.array_buffer.buffer) tracing_start_cmdline_record(); } EXPORT_SYMBOL_GPL(trace_printk_init_buffers); @@ -3072,13 +3197,15 @@ static void trace_printk_start_stop_comm(int enabled) /** * trace_vbprintk - write binary msg to tracing buffer - * + * @ip: The address of the caller + * @fmt: The string format to write to the buffer + * @args: Arguments for @fmt */ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) { struct trace_event_call *call = &event_bprint; struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct trace_array *tr = &global_trace; struct bprint_entry *entry; unsigned long flags; @@ -3103,11 +3230,12 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) - goto out; + goto out_put; local_save_flags(flags); size = sizeof(*entry) + sizeof(u32) * len; - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; + ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, flags, pc); if (!event) @@ -3123,6 +3251,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) } out: + ring_buffer_nest_end(buffer); +out_put: put_trace_buf(); out_nobuffer: @@ -3135,7 +3265,7 @@ EXPORT_SYMBOL_GPL(trace_vbprintk); __printf(3, 0) static int -__trace_array_vprintk(struct ring_buffer *buffer, +__trace_array_vprintk(struct trace_buffer *buffer, unsigned long ip, const char *fmt, va_list args) { struct trace_event_call *call = &event_print; @@ -3165,6 +3295,7 @@ __trace_array_vprintk(struct ring_buffer *buffer, local_save_flags(flags); size = sizeof(*entry) + len + 1; + ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, flags, pc); if (!event) @@ -3179,6 +3310,7 @@ __trace_array_vprintk(struct ring_buffer *buffer, } out: + ring_buffer_nest_end(buffer); put_trace_buf(); out_nobuffer: @@ -3192,7 +3324,7 @@ __printf(3, 0) int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { - return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args); + return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } __printf(3, 0) @@ -3205,6 +3337,9 @@ int trace_array_printk(struct trace_array *tr, if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) return 0; + if (!tr) + return -ENOENT; + va_start(ap, fmt); ret = trace_array_vprintk(tr, ip, fmt, ap); va_end(ap); @@ -3213,7 +3348,7 @@ int trace_array_printk(struct trace_array *tr, EXPORT_SYMBOL_GPL(trace_array_printk); __printf(3, 4) -int trace_array_printk_buf(struct ring_buffer *buffer, +int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...) { int ret; @@ -3254,7 +3389,7 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, if (buf_iter) event = ring_buffer_iter_peek(buf_iter, ts); else - event = ring_buffer_peek(iter->trace_buffer->buffer, cpu, ts, + event = ring_buffer_peek(iter->array_buffer->buffer, cpu, ts, lost_events); if (event) { @@ -3269,7 +3404,7 @@ static struct trace_entry * __find_next_entry(struct trace_iterator *iter, int *ent_cpu, unsigned long *missing_events, u64 *ent_ts) { - struct ring_buffer *buffer = iter->trace_buffer->buffer; + struct trace_buffer *buffer = iter->array_buffer->buffer; struct trace_entry *ent, *next = NULL; unsigned long lost_events = 0, next_lost = 0; int cpu_file = iter->cpu_file; @@ -3346,7 +3481,7 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter) static void trace_consume(struct trace_iterator *iter) { - ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, &iter->ts, + ring_buffer_consume(iter->array_buffer->buffer, iter->cpu, &iter->ts, &iter->lost_events); } @@ -3384,7 +3519,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) unsigned long entries = 0; u64 ts; - per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = 0; + per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) @@ -3398,13 +3533,13 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) * by the timestamp being before the start of the buffer. */ while ((event = ring_buffer_iter_peek(buf_iter, &ts))) { - if (ts >= iter->trace_buffer->time_start) + if (ts >= iter->array_buffer->time_start) break; entries++; ring_buffer_read(buf_iter, NULL); } - per_cpu_ptr(iter->trace_buffer->data, cpu)->skipped_entries = entries; + per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries; } /* @@ -3489,7 +3624,7 @@ static void s_stop(struct seq_file *m, void *p) } static void -get_total_entries_cpu(struct trace_buffer *buf, unsigned long *total, +get_total_entries_cpu(struct array_buffer *buf, unsigned long *total, unsigned long *entries, int cpu) { unsigned long count; @@ -3511,7 +3646,7 @@ get_total_entries_cpu(struct trace_buffer *buf, unsigned long *total, } static void -get_total_entries(struct trace_buffer *buf, +get_total_entries(struct array_buffer *buf, unsigned long *total, unsigned long *entries) { unsigned long t, e; @@ -3534,7 +3669,7 @@ unsigned long trace_total_entries_cpu(struct trace_array *tr, int cpu) if (!tr) tr = &global_trace; - get_total_entries_cpu(&tr->trace_buffer, &total, &entries, cpu); + get_total_entries_cpu(&tr->array_buffer, &total, &entries, cpu); return entries; } @@ -3546,7 +3681,7 @@ unsigned long trace_total_entries(struct trace_array *tr) if (!tr) tr = &global_trace; - get_total_entries(&tr->trace_buffer, &total, &entries); + get_total_entries(&tr->array_buffer, &total, &entries); return entries; } @@ -3563,7 +3698,7 @@ static void print_lat_help_header(struct seq_file *m) "# \\ / ||||| \\ | / \n"); } -static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +static void print_event_info(struct array_buffer *buf, struct seq_file *m) { unsigned long total; unsigned long entries; @@ -3574,7 +3709,7 @@ static void print_event_info(struct trace_buffer *buf, struct seq_file *m) seq_puts(m, "#\n"); } -static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m, +static void print_func_help_header(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; @@ -3585,7 +3720,7 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m, seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } -static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m, +static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; @@ -3607,7 +3742,7 @@ void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (global_trace.trace_flags & TRACE_ITER_SYM_MASK); - struct trace_buffer *buf = iter->trace_buffer; + struct array_buffer *buf = iter->array_buffer; struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu); struct tracer *type = iter->trace; unsigned long entries; @@ -3634,6 +3769,8 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) "desktop", #elif defined(CONFIG_PREEMPT) "preempt", +#elif defined(CONFIG_PREEMPT_RT) + "preempt_rt", #else "unknown", #endif @@ -3680,7 +3817,7 @@ static void test_cpu_buff_start(struct trace_iterator *iter) cpumask_test_cpu(iter->cpu, iter->started)) return; - if (per_cpu_ptr(iter->trace_buffer->data, iter->cpu)->skipped_entries) + if (per_cpu_ptr(iter->array_buffer->data, iter->cpu)->skipped_entries) return; if (cpumask_available(iter->started)) @@ -3814,7 +3951,7 @@ int trace_empty(struct trace_iterator *iter) if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } return 1; @@ -3826,7 +3963,7 @@ int trace_empty(struct trace_iterator *iter) if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { - if (!ring_buffer_empty_cpu(iter->trace_buffer->buffer, cpu)) + if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } } @@ -3916,10 +4053,10 @@ void trace_default_header(struct seq_file *m) } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) - print_func_help_header_irq(iter->trace_buffer, + print_func_help_header_irq(iter->array_buffer, m, trace_flags); else - print_func_help_header(iter->trace_buffer, m, + print_func_help_header(iter->array_buffer, m, trace_flags); } } @@ -4077,21 +4214,21 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) #ifdef CONFIG_TRACER_MAX_TRACE /* Currently only the top directory has a snapshot */ if (tr->current_trace->print_max || snapshot) - iter->trace_buffer = &tr->max_buffer; + iter->array_buffer = &tr->max_buffer; else #endif - iter->trace_buffer = &tr->trace_buffer; + iter->array_buffer = &tr->array_buffer; iter->snapshot = snapshot; iter->pos = -1; iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); /* Notify the tracer early; before we stop tracing. */ - if (iter->trace && iter->trace->open) + if (iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ - if (ring_buffer_overruns(iter->trace_buffer->buffer)) + if (ring_buffer_overruns(iter->array_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ @@ -4105,7 +4242,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->trace_buffer->buffer, + ring_buffer_read_prepare(iter->array_buffer->buffer, cpu, GFP_KERNEL); } ring_buffer_read_prepare_sync(); @@ -4116,7 +4253,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = - ring_buffer_read_prepare(iter->trace_buffer->buffer, + ring_buffer_read_prepare(iter->array_buffer->buffer, cpu, GFP_KERNEL); ring_buffer_read_prepare_sync(); ring_buffer_read_start(iter->buffer_iter[cpu]); @@ -4138,8 +4275,11 @@ release: int tracing_open_generic(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; filp->private_data = inode->i_private; return 0; @@ -4154,15 +4294,14 @@ bool tracing_is_disabled(void) * Open and update trace_array ref count. * Must have the current trace_array passed to it. */ -static int tracing_open_generic_tr(struct inode *inode, struct file *filp) +int tracing_open_generic_tr(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; + int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; filp->private_data = inode->i_private; @@ -4231,15 +4370,16 @@ static int tracing_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; - int ret = 0; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); - struct trace_buffer *trace_buf = &tr->trace_buffer; + struct array_buffer *trace_buf = &tr->array_buffer; #ifdef CONFIG_TRACER_MAX_TRACE if (tr->current_trace->print_max) @@ -4249,7 +4389,7 @@ static int tracing_open(struct inode *inode, struct file *file) if (cpu == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(trace_buf); else - tracing_reset(trace_buf, cpu); + tracing_reset_cpu(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { @@ -4350,12 +4490,15 @@ static int show_traces_open(struct inode *inode, struct file *file) struct seq_file *m; int ret; - if (tracing_disabled) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = seq_open(file, &show_traces_seq_ops); - if (ret) + if (ret) { + trace_array_put(tr); return ret; + } m = file->private_data; m->private = tr; @@ -4363,6 +4506,14 @@ static int show_traces_open(struct inode *inode, struct file *file) return 0; } +static int show_traces_release(struct inode *inode, struct file *file) +{ + struct trace_array *tr = inode->i_private; + + trace_array_put(tr); + return seq_release(inode, file); +} + static ssize_t tracing_write_stub(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) @@ -4393,8 +4544,8 @@ static const struct file_operations tracing_fops = { static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, - .release = seq_release, .llseek = seq_lseek, + .release = show_traces_release, }; static ssize_t @@ -4425,20 +4576,13 @@ out_err: return count; } -static ssize_t -tracing_cpumask_write(struct file *filp, const char __user *ubuf, - size_t count, loff_t *ppos) +int tracing_set_cpumask(struct trace_array *tr, + cpumask_var_t tracing_cpumask_new) { - struct trace_array *tr = file_inode(filp)->i_private; - cpumask_var_t tracing_cpumask_new; - int err, cpu; - - if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) - return -ENOMEM; + int cpu; - err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); - if (err) - goto err_unlock; + if (!tr) + return -EINVAL; local_irq_disable(); arch_spin_lock(&tr->max_lock); @@ -4449,24 +4593,47 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf, */ if (cpumask_test_cpu(cpu, tr->tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_inc(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); - ring_buffer_record_disable_cpu(tr->trace_buffer.buffer, cpu); + atomic_inc(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); + ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { - atomic_dec(&per_cpu_ptr(tr->trace_buffer.data, cpu)->disabled); - ring_buffer_record_enable_cpu(tr->trace_buffer.buffer, cpu); + atomic_dec(&per_cpu_ptr(tr->array_buffer.data, cpu)->disabled); + ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); } } arch_spin_unlock(&tr->max_lock); local_irq_enable(); cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new); + + return 0; +} + +static ssize_t +tracing_cpumask_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct trace_array *tr = file_inode(filp)->i_private; + cpumask_var_t tracing_cpumask_new; + int err; + + if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) + return -ENOMEM; + + err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); + if (err) + goto err_free; + + err = tracing_set_cpumask(tr, tracing_cpumask_new); + if (err) + goto err_free; + free_cpumask_var(tracing_cpumask_new); return count; -err_unlock: +err_free: free_cpumask_var(tracing_cpumask_new); return err; @@ -4556,6 +4723,10 @@ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { + if ((mask == TRACE_ITER_RECORD_TGID) || + (mask == TRACE_ITER_RECORD_CMD)) + lockdep_assert_held(&event_mutex); + /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; @@ -4575,7 +4746,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) if (mask == TRACE_ITER_RECORD_TGID) { if (!tgid_map) - tgid_map = kcalloc(PID_MAX_DEFAULT + 1, + tgid_map = kvcalloc(PID_MAX_DEFAULT + 1, sizeof(*tgid_map), GFP_KERNEL); if (!tgid_map) { @@ -4593,7 +4764,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) ftrace_pid_follow_fork(tr, enabled); if (mask == TRACE_ITER_OVERWRITE) { - ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled); + ring_buffer_change_overwrite(tr->array_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); #endif @@ -4607,7 +4778,7 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) return 0; } -static int trace_set_options(struct trace_array *tr, char *option) +int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; @@ -4623,6 +4794,7 @@ static int trace_set_options(struct trace_array *tr, char *option) cmp += len; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); @@ -4633,6 +4805,7 @@ static int trace_set_options(struct trace_array *tr, char *option) ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, @@ -4695,11 +4868,9 @@ static int tracing_trace_options_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_trace_options_show, inode->i_private); if (ret < 0) @@ -4813,15 +4984,15 @@ static const char readme_msg[] = #endif #endif /* CONFIG_STACK_TRACER */ #ifdef CONFIG_DYNAMIC_EVENTS - " dynamic_events\t\t- Add/remove/show the generic dynamic events\n" + " dynamic_events\t\t- Create/append/remove/show the generic dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_KPROBE_EVENTS - " kprobe_events\t\t- Add/remove/show the kernel dynamic events\n" + " kprobe_events\t\t- Create/append/remove/show the kernel dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_UPROBE_EVENTS - " uprobe_events\t\t- Add/remove/show the userspace dynamic events\n" + " uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) @@ -4846,7 +5017,7 @@ static const char readme_msg[] = #else "\t $stack<index>, $stack, $retval, $comm,\n" #endif - "\t +|-[u]<offset>(<fetcharg>)\n" + "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\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>, ustring,\n" "\t <type>\\[<array-size>\\]\n" @@ -5036,8 +5207,11 @@ static const struct seq_operations tracing_saved_tgids_seq_ops = { static int tracing_saved_tgids_open(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; return seq_open(filp, &tracing_saved_tgids_seq_ops); } @@ -5113,8 +5287,11 @@ static const struct seq_operations tracing_saved_cmdlines_seq_ops = { static int tracing_saved_cmdlines_open(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; return seq_open(filp, &tracing_saved_cmdlines_seq_ops); } @@ -5222,14 +5399,12 @@ static void *eval_map_next(struct seq_file *m, void *v, loff_t *pos) * Paranoid! If ptr points to end, we don't want to increment past it. * This really should never happen. */ + (*pos)++; ptr = update_eval_map(ptr); if (WARN_ON_ONCE(!ptr)) return NULL; ptr++; - - (*pos)++; - ptr = update_eval_map(ptr); return ptr; @@ -5278,8 +5453,11 @@ static const struct seq_operations tracing_eval_map_seq_ops = { static int tracing_eval_map_open(struct inode *inode, struct file *filp) { - if (tracing_disabled) - return -ENODEV; + int ret; + + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; return seq_open(filp, &tracing_eval_map_seq_ops); } @@ -5392,11 +5570,11 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf, int tracer_init(struct tracer *t, struct trace_array *tr) { - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); return t->init(tr); } -static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) +static void set_buffer_entries(struct array_buffer *buf, unsigned long val) { int cpu; @@ -5406,8 +5584,8 @@ static void set_buffer_entries(struct trace_buffer *buf, unsigned long val) #ifdef CONFIG_TRACER_MAX_TRACE /* resize @tr's buffer to the size of @size_tr's entries */ -static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf, - struct trace_buffer *size_buf, int cpu_id) +static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, + struct array_buffer *size_buf, int cpu_id) { int cpu, ret = 0; @@ -5445,10 +5623,10 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, ring_buffer_expanded = true; /* May be called before buffers are initialized */ - if (!tr->trace_buffer.buffer) + if (!tr->array_buffer.buffer) return 0; - ret = ring_buffer_resize(tr->trace_buffer.buffer, size, cpu); + ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu); if (ret < 0) return ret; @@ -5459,8 +5637,8 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); if (ret < 0) { - int r = resize_buffer_duplicate_size(&tr->trace_buffer, - &tr->trace_buffer, cpu); + int r = resize_buffer_duplicate_size(&tr->array_buffer, + &tr->array_buffer, cpu); if (r < 0) { /* * AARGH! We are left with different @@ -5491,15 +5669,15 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, #endif /* CONFIG_TRACER_MAX_TRACE */ if (cpu == RING_BUFFER_ALL_CPUS) - set_buffer_entries(&tr->trace_buffer, size); + set_buffer_entries(&tr->array_buffer, size); else - per_cpu_ptr(tr->trace_buffer.data, cpu)->entries = size; + per_cpu_ptr(tr->array_buffer.data, cpu)->entries = size; return ret; } -static ssize_t tracing_resize_ring_buffer(struct trace_array *tr, - unsigned long size, int cpu_id) +ssize_t tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu_id) { int ret = size; @@ -5578,7 +5756,7 @@ static void add_tracer_options(struct trace_array *tr, struct tracer *t) create_trace_option_files(tr, t); } -static int tracing_set_tracer(struct trace_array *tr, const char *buf) +int tracing_set_tracer(struct trace_array *tr, const char *buf) { struct tracer *t; #ifdef CONFIG_TRACER_MAX_TRACE @@ -5802,13 +5980,11 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; - int ret = 0; - - if (tracing_disabled) - return -ENODEV; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; mutex_lock(&trace_types_lock); @@ -5839,7 +6015,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; iter->tr = tr; - iter->trace_buffer = &tr->trace_buffer; + iter->array_buffer = &tr->array_buffer; iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); filp->private_data = iter; @@ -5899,7 +6075,7 @@ trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_tabl */ return EPOLLIN | EPOLLRDNORM; else - return ring_buffer_poll_wait(iter->trace_buffer->buffer, iter->cpu_file, + return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file, filp, poll_table); } @@ -5997,6 +6173,7 @@ waitagain: sizeof(struct trace_iterator) - offsetof(struct trace_iterator, seq)); cpumask_clear(iter->started); + trace_seq_init(&iter->seq); iter->pos = -1; trace_event_read_lock(); @@ -6215,8 +6392,8 @@ tracing_entries_read(struct file *filp, char __user *ubuf, for_each_tracing_cpu(cpu) { /* fill in the size from first enabled cpu */ if (size == 0) - size = per_cpu_ptr(tr->trace_buffer.data, cpu)->entries; - if (size != per_cpu_ptr(tr->trace_buffer.data, cpu)->entries) { + size = per_cpu_ptr(tr->array_buffer.data, cpu)->entries; + if (size != per_cpu_ptr(tr->array_buffer.data, cpu)->entries) { buf_size_same = 0; break; } @@ -6232,7 +6409,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf, } else r = sprintf(buf, "X\n"); } else - r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10); + r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10); mutex_unlock(&trace_types_lock); @@ -6279,7 +6456,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf, mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { - size += per_cpu_ptr(tr->trace_buffer.data, cpu)->entries >> 10; + size += per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10; if (!ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } @@ -6329,7 +6506,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; enum event_trigger_type tt = ETT_NONE; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct print_entry *entry; unsigned long irq_flags; ssize_t written; @@ -6358,7 +6535,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (cnt < FAULTED_SIZE) size += FAULTED_SIZE - cnt; - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, irq_flags, preempt_count()); if (unlikely(!event)) @@ -6409,7 +6586,7 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, { struct trace_array *tr = filp->private_data; struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct raw_data_entry *entry; unsigned long irq_flags; ssize_t written; @@ -6438,7 +6615,7 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf, if (cnt < FAULT_SIZE_ID) size += FAULT_SIZE_ID - cnt; - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size, irq_flags, preempt_count()); if (!event) @@ -6493,13 +6670,13 @@ int tracing_set_clock(struct trace_array *tr, const char *clockstr) tr->clock_id = i; - ring_buffer_set_clock(tr->trace_buffer.buffer, trace_clocks[i].func); + ring_buffer_set_clock(tr->array_buffer.buffer, trace_clocks[i].func); /* * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (tr->max_buffer.buffer) @@ -6545,11 +6722,9 @@ static int tracing_clock_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr)) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_clock_show, inode->i_private); if (ret < 0) @@ -6564,7 +6739,7 @@ static int tracing_time_stamp_mode_show(struct seq_file *m, void *v) mutex_lock(&trace_types_lock); - if (ring_buffer_time_stamp_abs(tr->trace_buffer.buffer)) + if (ring_buffer_time_stamp_abs(tr->array_buffer.buffer)) seq_puts(m, "delta [absolute]\n"); else seq_puts(m, "[delta] absolute\n"); @@ -6579,11 +6754,9 @@ static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr)) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private); if (ret < 0) @@ -6611,7 +6784,7 @@ int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs) goto out; } - ring_buffer_set_time_stamp_abs(tr->trace_buffer.buffer, abs); + ring_buffer_set_time_stamp_abs(tr->array_buffer.buffer, abs); #ifdef CONFIG_TRACER_MAX_TRACE if (tr->max_buffer.buffer) @@ -6636,10 +6809,11 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; struct trace_iterator *iter; struct seq_file *m; - int ret = 0; + int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); @@ -6659,7 +6833,7 @@ static int tracing_snapshot_open(struct inode *inode, struct file *file) ret = 0; iter->tr = tr; - iter->trace_buffer = &tr->max_buffer; + iter->array_buffer = &tr->max_buffer; iter->cpu_file = tracing_get_cpu(inode); m->private = iter; file->private_data = m; @@ -6722,7 +6896,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, #endif if (tr->allocated_snapshot) ret = resize_buffer_duplicate_size(&tr->max_buffer, - &tr->trace_buffer, iter->cpu_file); + &tr->array_buffer, iter->cpu_file); else ret = tracing_alloc_snapshot_instance(tr); if (ret < 0) @@ -6740,7 +6914,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, if (iter->cpu_file == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(&tr->max_buffer); else - tracing_reset(&tr->max_buffer, iter->cpu_file); + tracing_reset_cpu(&tr->max_buffer, iter->cpu_file); } break; } @@ -6784,6 +6958,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) struct ftrace_buffer_info *info; int ret; + /* The following checks for tracefs lockdown */ ret = tracing_buffers_open(inode, filp); if (ret < 0) return ret; @@ -6796,7 +6971,7 @@ static int snapshot_raw_open(struct inode *inode, struct file *filp) } info->iter.snapshot = true; - info->iter.trace_buffer = &info->iter.tr->max_buffer; + info->iter.array_buffer = &info->iter.tr->max_buffer; return ret; } @@ -7103,8 +7278,9 @@ static int tracing_err_log_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret = 0; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; /* If this file was opened for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) @@ -7155,11 +7331,9 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) struct ftrace_buffer_info *info; int ret; - if (tracing_disabled) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) { @@ -7172,7 +7346,7 @@ static int tracing_buffers_open(struct inode *inode, struct file *filp) info->iter.tr = tr; info->iter.cpu_file = tracing_get_cpu(inode); info->iter.trace = tr->current_trace; - info->iter.trace_buffer = &tr->trace_buffer; + info->iter.array_buffer = &tr->array_buffer; info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; @@ -7217,7 +7391,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, #endif if (!info->spare) { - info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, + info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file); if (IS_ERR(info->spare)) { ret = PTR_ERR(info->spare); @@ -7235,7 +7409,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, again: trace_access_lock(iter->cpu_file); - ret = ring_buffer_read_page(iter->trace_buffer->buffer, + ret = ring_buffer_read_page(iter->array_buffer->buffer, &info->spare, count, iter->cpu_file, 0); @@ -7285,7 +7459,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); if (info->spare) - ring_buffer_free_read_page(iter->trace_buffer->buffer, + ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); kfree(info); @@ -7295,7 +7469,7 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) } struct buffer_ref { - struct ring_buffer *buffer; + struct trace_buffer *buffer; void *page; int cpu; refcount_t refcount; @@ -7390,7 +7564,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, again: trace_access_lock(iter->cpu_file); - entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= PAGE_SIZE) { struct page *page; @@ -7403,7 +7577,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, } refcount_set(&ref->refcount, 1); - ref->buffer = iter->trace_buffer->buffer; + ref->buffer = iter->array_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { ret = PTR_ERR(ref->page); @@ -7431,7 +7605,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, spd.nr_pages++; *ppos += PAGE_SIZE; - entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file); + entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); } trace_access_unlock(iter->cpu_file); @@ -7475,7 +7649,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; - struct trace_buffer *trace_buf = &tr->trace_buffer; + struct array_buffer *trace_buf = &tr->array_buffer; int cpu = tracing_get_cpu(inode); struct trace_seq *s; unsigned long cnt; @@ -7546,14 +7720,23 @@ static ssize_t tracing_read_dyn_info(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { - unsigned long *p = filp->private_data; - char buf[64]; /* Not too big for a shallow stack */ + ssize_t ret; + char *buf; int r; - r = scnprintf(buf, 63, "%ld", *p); - buf[r++] = '\n'; + /* 256 should be plenty to hold the amount needed */ + buf = kmalloc(256, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + r = scnprintf(buf, 256, "%ld pages:%ld groups: %ld\n", + ftrace_update_tot_cnt, + ftrace_number_of_pages, + ftrace_number_of_groups); - return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + kfree(buf); + return ret; } static const struct file_operations tracing_dyn_info_fops = { @@ -7747,7 +7930,7 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer); - WARN_ONCE(!tr->percpu_dir, + MEM_FAIL(!tr->percpu_dir, "Could not create tracefs directory 'per_cpu/%d'\n", cpu); return tr->percpu_dir; @@ -7935,9 +8118,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; + mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); if (ret < 0) return ret; @@ -8066,7 +8251,7 @@ create_trace_option_files(struct trace_array *tr, struct tracer *tracer) for (cnt = 0; opts[cnt].name; cnt++) { create_trace_option_file(tr, &topts[cnt], flags, &opts[cnt]); - WARN_ONCE(topts[cnt].entry == NULL, + MEM_FAIL(topts[cnt].entry == NULL, "Failed to create trace option: %s", opts[cnt].name); } @@ -8123,7 +8308,7 @@ rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; unsigned long val; int ret; @@ -8213,7 +8398,7 @@ static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer); static int -allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size) +allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) { enum ring_buffer_flags rb_flags; @@ -8233,8 +8418,8 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size } /* Allocate the first page for all buffers */ - set_buffer_entries(&tr->trace_buffer, - ring_buffer_size(tr->trace_buffer.buffer, 0)); + set_buffer_entries(&tr->array_buffer, + ring_buffer_size(tr->array_buffer.buffer, 0)); return 0; } @@ -8243,18 +8428,18 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) { int ret; - ret = allocate_trace_buffer(tr, &tr->trace_buffer, size); + ret = allocate_trace_buffer(tr, &tr->array_buffer, size); if (ret) return ret; #ifdef CONFIG_TRACER_MAX_TRACE ret = allocate_trace_buffer(tr, &tr->max_buffer, allocate_snapshot ? size : 1); - if (WARN_ON(ret)) { - ring_buffer_free(tr->trace_buffer.buffer); - tr->trace_buffer.buffer = NULL; - free_percpu(tr->trace_buffer.data); - tr->trace_buffer.data = NULL; + if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) { + ring_buffer_free(tr->array_buffer.buffer); + tr->array_buffer.buffer = NULL; + free_percpu(tr->array_buffer.data); + tr->array_buffer.data = NULL; return -ENOMEM; } tr->allocated_snapshot = allocate_snapshot; @@ -8268,7 +8453,7 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) return 0; } -static void free_trace_buffer(struct trace_buffer *buf) +static void free_trace_buffer(struct array_buffer *buf) { if (buf->buffer) { ring_buffer_free(buf->buffer); @@ -8283,7 +8468,7 @@ static void free_trace_buffers(struct trace_array *tr) if (!tr) return; - free_trace_buffer(&tr->trace_buffer); + free_trace_buffer(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE free_trace_buffer(&tr->max_buffer); @@ -8314,24 +8499,43 @@ static void update_tracer_options(struct trace_array *tr) mutex_unlock(&trace_types_lock); } -struct trace_array *trace_array_create(const char *name) +/* Must have trace_types_lock held */ +struct trace_array *trace_array_find(const char *instance) +{ + struct trace_array *tr, *found = NULL; + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, instance) == 0) { + found = tr; + break; + } + } + + return found; +} + +struct trace_array *trace_array_find_get(const char *instance) { struct trace_array *tr; - int ret; - mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); + tr = trace_array_find(instance); + if (tr) + tr->ref++; + mutex_unlock(&trace_types_lock); - ret = -EEXIST; - list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr->name && strcmp(tr->name, name) == 0) - goto out_unlock; - } + return tr; +} + +static struct trace_array *trace_array_create(const char *name) +{ + struct trace_array *tr; + int ret; ret = -ENOMEM; tr = kzalloc(sizeof(*tr), GFP_KERNEL); if (!tr) - goto out_unlock; + return ERR_PTR(ret); tr->name = kstrdup(name, GFP_KERNEL); if (!tr->name) @@ -8364,7 +8568,7 @@ struct trace_array *trace_array_create(const char *name) ret = event_trace_add_tracer(tr->dir, tr); if (ret) { - tracefs_remove_recursive(tr->dir); + tracefs_remove(tr->dir); goto out_free_tr; } @@ -8376,8 +8580,8 @@ struct trace_array *trace_array_create(const char *name) list_add(&tr->list, &ftrace_trace_arrays); - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); + tr->ref++; + return tr; @@ -8387,24 +8591,79 @@ struct trace_array *trace_array_create(const char *name) kfree(tr->name); kfree(tr); - out_unlock: - mutex_unlock(&trace_types_lock); - mutex_unlock(&event_mutex); - return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(trace_array_create); static int instance_mkdir(const char *name) { - return PTR_ERR_OR_ZERO(trace_array_create(name)); + struct trace_array *tr; + int ret; + + mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); + + ret = -EEXIST; + if (trace_array_find(name)) + goto out_unlock; + + tr = trace_array_create(name); + + ret = PTR_ERR_OR_ZERO(tr); + +out_unlock: + mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); + return ret; } +/** + * trace_array_get_by_name - Create/Lookup a trace array, given its name. + * @name: The name of the trace array to be looked up/created. + * + * Returns pointer to trace array with given name. + * NULL, if it cannot be created. + * + * NOTE: This function increments the reference counter associated with the + * trace array returned. This makes sure it cannot be freed while in use. + * Use trace_array_put() once the trace array is no longer needed. + * If the trace_array is to be freed, trace_array_destroy() needs to + * be called after the trace_array_put(), or simply let user space delete + * it from the tracefs instances directory. But until the + * trace_array_put() is called, user space can not delete it. + * + */ +struct trace_array *trace_array_get_by_name(const char *name) +{ + struct trace_array *tr; + + mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr->name && strcmp(tr->name, name) == 0) + goto out_unlock; + } + + tr = trace_array_create(name); + + if (IS_ERR(tr)) + tr = NULL; +out_unlock: + if (tr) + tr->ref++; + + mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); + return tr; +} +EXPORT_SYMBOL_GPL(trace_array_get_by_name); + static int __remove_instance(struct trace_array *tr) { int i; - if (tr->ref || (tr->current_trace && tr->current_trace->ref)) + /* Reference counter for a newly created trace array = 1. */ + if (tr->ref > 1 || (tr->current_trace && tr->current_trace->ref)) return -EBUSY; list_del(&tr->list); @@ -8420,7 +8679,7 @@ static int __remove_instance(struct trace_array *tr) event_trace_del_tracer(tr); ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); - tracefs_remove_recursive(tr->dir); + tracefs_remove(tr->dir); free_trace_buffers(tr); for (i = 0; i < tr->nr_topts; i++) { @@ -8436,17 +8695,26 @@ static int __remove_instance(struct trace_array *tr) return 0; } -int trace_array_destroy(struct trace_array *tr) +int trace_array_destroy(struct trace_array *this_tr) { + struct trace_array *tr; int ret; - if (!tr) + if (!this_tr) return -EINVAL; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); - ret = __remove_instance(tr); + ret = -ENODEV; + + /* Making sure trace array exists before destroying it. */ + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr == this_tr) { + ret = __remove_instance(tr); + break; + } + } mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); @@ -8464,12 +8732,9 @@ static int instance_rmdir(const char *name) mutex_lock(&trace_types_lock); ret = -ENODEV; - list_for_each_entry(tr, &ftrace_trace_arrays, list) { - if (tr->name && strcmp(tr->name, name) == 0) { - ret = __remove_instance(tr); - break; - } - } + tr = trace_array_find(name); + if (tr) + ret = __remove_instance(tr); mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); @@ -8482,7 +8747,7 @@ static __init void create_trace_instances(struct dentry *d_tracer) trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer, instance_mkdir, instance_rmdir); - if (WARN_ON(!trace_instance_dir)) + if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n")) return; } @@ -8548,12 +8813,11 @@ init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) create_trace_options_dir(tr); #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) - trace_create_file("tracing_max_latency", 0644, d_tracer, - &tr->max_latency, &tracing_max_lat_fops); + trace_create_maxlat_file(tr, d_tracer); #endif if (ftrace_create_function_files(tr, d_tracer)) - WARN(1, "Could not allocate function filter files"); + MEM_FAIL(1, "Could not allocate function filter files"); #ifdef CONFIG_TRACER_SNAPSHOT trace_create_file("snapshot", 0644, d_tracer, @@ -8602,6 +8866,11 @@ struct dentry *tracing_init_dentry(void) { struct trace_array *tr = &global_trace; + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Tracing disabled due to lockdown\n"); + return ERR_PTR(-EPERM); + } + /* The top level trace array uses NULL as parent */ if (tr->dir) return NULL; @@ -8745,7 +9014,7 @@ static __init int tracer_init_tracefs(void) #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, - &ftrace_update_tot_cnt, &tracing_dyn_info_fops); + NULL, &tracing_dyn_info_fops); #endif create_trace_instances(d_tracer); @@ -8830,13 +9099,13 @@ void trace_init_global_iter(struct trace_iterator *iter) iter->tr = &global_trace; iter->trace = iter->tr->current_trace; iter->cpu_file = RING_BUFFER_ALL_CPUS; - iter->trace_buffer = &global_trace.trace_buffer; + iter->array_buffer = &global_trace.array_buffer; if (iter->trace && iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ - if (ring_buffer_overruns(iter->trace_buffer->buffer)) + if (ring_buffer_overruns(iter->array_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ @@ -8877,7 +9146,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) trace_init_global_iter(&iter); for_each_tracing_cpu(cpu) { - atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); + atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); } old_userobj = tr->trace_flags & TRACE_ITER_SYM_USEROBJ; @@ -8945,7 +9214,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) tr->trace_flags |= old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); } atomic_dec(&dump_running); printk_nmi_direct_exit(); @@ -9044,6 +9313,12 @@ __init static int tracer_alloc_buffers(void) int ring_buf_size; int ret = -ENOMEM; + + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Tracing disabled due to lockdown\n"); + return -EPERM; + } + /* * Make sure we don't accidently add more trace options * than we have bits for. @@ -9094,8 +9369,7 @@ __init static int tracer_alloc_buffers(void) /* TODO: make the number of buffers hot pluggable with CPUS */ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { - printk(KERN_ERR "tracer: failed to allocate ring buffer!\n"); - WARN_ON(1); + MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n"); goto out_free_savedcmd; } @@ -9168,7 +9442,8 @@ void __init early_trace_init(void) if (tracepoint_printk) { tracepoint_print_iter = kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL); - if (WARN_ON(!tracepoint_print_iter)) + if (MEM_FAIL(!tracepoint_print_iter, + "Failed to allocate trace iterator\n")) tracepoint_printk = 0; else static_key_enable(&tracepoint_printk_key.key); @@ -9208,6 +9483,11 @@ __init static int tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not set tracing clock due to lockdown\n"); + return -EPERM; + } + printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 005f08629b8b..99372dd7d168 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -11,11 +11,14 @@ #include <linux/mmiotrace.h> #include <linux/tracepoint.h> #include <linux/ftrace.h> +#include <linux/trace.h> #include <linux/hw_breakpoint.h> #include <linux/trace_seq.h> #include <linux/trace_events.h> #include <linux/compiler.h> #include <linux/glob.h> +#include <linux/irq_work.h> +#include <linux/workqueue.h> #ifdef CONFIG_FTRACE_SYSCALLS #include <asm/unistd.h> /* For NR_SYSCALLS */ @@ -49,6 +52,9 @@ enum trace_type { #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_struct #define __field_struct(type, item) __field(type, item) @@ -68,29 +74,37 @@ enum trace_type { #define F_STRUCT(args...) args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct struct_name { \ struct trace_entry ent; \ tstruct \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter) +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print, \ - filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) __packed +#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) __packed #include "trace_entries.h" +/* Use this for memory failure errors */ +#define MEM_FAIL(condition, fmt, ...) ({ \ + static bool __section(.data.once) __warned; \ + int __ret_warn_once = !!(condition); \ + \ + if (unlikely(__ret_warn_once && !__warned)) { \ + __warned = true; \ + pr_err("ERROR: " fmt, ##__VA_ARGS__); \ + } \ + unlikely(__ret_warn_once); \ +}) + /* * syscalls are special, and need special handling, this is why * they are not included in trace_entries.h @@ -173,9 +187,9 @@ struct trace_array_cpu { struct tracer; struct trace_option_dentry; -struct trace_buffer { +struct array_buffer { struct trace_array *tr; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct trace_array_cpu __percpu *data; u64 time_start; int cpu; @@ -246,7 +260,7 @@ struct cond_snapshot { struct trace_array { struct list_head list; char *name; - struct trace_buffer trace_buffer; + struct array_buffer array_buffer; #ifdef CONFIG_TRACER_MAX_TRACE /* * The max_buffer is used to snapshot the trace when a maximum @@ -254,16 +268,21 @@ struct trace_array { * Some tracers will use this to store a maximum trace while * it continues examining live traces. * - * The buffers for the max_buffer are set up the same as the trace_buffer + * The buffers for the max_buffer are set up the same as the array_buffer * When a snapshot is taken, the buffer of the max_buffer is swapped - * with the buffer of the trace_buffer and the buffers are reset for - * the trace_buffer so the tracing can continue. + * with the buffer of the array_buffer and the buffers are reset for + * the array_buffer so the tracing can continue. */ - struct trace_buffer max_buffer; + struct array_buffer max_buffer; bool allocated_snapshot; #endif #if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER) unsigned long max_latency; +#ifdef CONFIG_FSNOTIFY + struct dentry *d_max_latency; + struct work_struct fsnotify_work; + struct irq_work fsnotify_irqwork; +#endif #endif struct trace_pid_list __rcu *filtered_pids; /* @@ -337,7 +356,9 @@ extern struct list_head ftrace_trace_arrays; extern struct mutex trace_types_lock; extern int trace_array_get(struct trace_array *tr); -extern void trace_array_put(struct trace_array *tr); +extern int tracing_check_open_get_tr(struct trace_array *tr); +extern struct trace_array *trace_array_find(const char *instance); +extern struct trace_array *trace_array_find_get(const char *instance); extern int tracing_set_time_stamp_abs(struct trace_array *tr, bool abs); extern int tracing_set_clock(struct trace_array *tr, const char *clockstr); @@ -365,11 +386,11 @@ static inline struct trace_array *top_trace_array(void) __builtin_types_compatible_p(typeof(var), type *) #undef IF_ASSIGN -#define IF_ASSIGN(var, entry, etype, id) \ - if (FTRACE_CMP_TYPE(var, etype)) { \ - var = (typeof(var))(entry); \ - WARN_ON(id && (entry)->type != id); \ - break; \ +#define IF_ASSIGN(var, entry, etype, id) \ + if (FTRACE_CMP_TYPE(var, etype)) { \ + var = (typeof(var))(entry); \ + WARN_ON(id != 0 && (entry)->type != id); \ + break; \ } /* Will cause compile errors if type is not found. */ @@ -677,11 +698,11 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu) int tracer_init(struct tracer *t, struct trace_array *tr); int tracing_is_enabled(void); -void tracing_reset(struct trace_buffer *buf, int cpu); -void tracing_reset_online_cpus(struct trace_buffer *buf); +void tracing_reset_online_cpus(struct array_buffer *buf); void tracing_reset_current(int cpu); void tracing_reset_all_online_cpus(void); int tracing_open_generic(struct inode *inode, struct file *filp); +int tracing_open_generic_tr(struct inode *inode, struct file *filp); bool tracing_is_disabled(void); bool tracer_tracing_is_on(struct trace_array *tr); void tracer_tracing_on(struct trace_array *tr); @@ -697,7 +718,7 @@ struct dentry *tracing_init_dentry(void); struct ring_buffer_event; struct ring_buffer_event * -trace_buffer_lock_reserve(struct ring_buffer *buffer, +trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned long flags, @@ -709,7 +730,7 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); -void trace_buffer_unlock_commit_nostack(struct ring_buffer *buffer, +void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event); int trace_empty(struct trace_iterator *iter); @@ -785,6 +806,17 @@ void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu); #endif /* CONFIG_TRACER_MAX_TRACE */ +#if (defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)) && \ + defined(CONFIG_FSNOTIFY) + +void latency_fsnotify(struct trace_array *tr); + +#else + +static inline void latency_fsnotify(struct trace_array *tr) { } + +#endif + #ifdef CONFIG_STACKTRACE void __trace_stack(struct trace_array *tr, unsigned long flags, int skip, int pc); @@ -803,6 +835,8 @@ extern void trace_event_follow_fork(struct trace_array *tr, bool enable); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; +extern unsigned long ftrace_number_of_pages; +extern unsigned long ftrace_number_of_groups; void ftrace_init_trace_array(struct trace_array *tr); #else static inline void ftrace_init_trace_array(struct trace_array *tr) { } @@ -852,9 +886,7 @@ trace_vprintk(unsigned long ip, const char *fmt, va_list args); extern int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args); -int trace_array_printk(struct trace_array *tr, - unsigned long ip, const char *fmt, ...); -int trace_array_printk_buf(struct ring_buffer *buffer, +int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...); void trace_printk_seq(struct trace_seq *s); enum print_line_t print_trace_line(struct trace_iterator *iter); @@ -931,22 +963,31 @@ extern void __trace_graph_return(struct trace_array *tr, unsigned long flags, int pc); #ifdef CONFIG_DYNAMIC_FTRACE -extern struct ftrace_hash *ftrace_graph_hash; -extern struct ftrace_hash *ftrace_graph_notrace_hash; +extern struct ftrace_hash __rcu *ftrace_graph_hash; +extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash; static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { unsigned long addr = trace->func; int ret = 0; + struct ftrace_hash *hash; preempt_disable_notrace(); - if (ftrace_hash_empty(ftrace_graph_hash)) { + /* + * Have to open code "rcu_dereference_sched()" because the + * function graph tracer can be called when RCU is not + * "watching". + * Protected with schedule_on_each_cpu(ftrace_sync) + */ + hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible()); + + if (ftrace_hash_empty(hash)) { ret = 1; goto out; } - if (ftrace_lookup_ip(ftrace_graph_hash, addr)) { + if (ftrace_lookup_ip(hash, addr)) { /* * This needs to be cleared on the return functions @@ -982,10 +1023,20 @@ static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) static inline int ftrace_graph_notrace_addr(unsigned long addr) { int ret = 0; + struct ftrace_hash *notrace_hash; preempt_disable_notrace(); - if (ftrace_lookup_ip(ftrace_graph_notrace_hash, addr)) + /* + * Have to open code "rcu_dereference_sched()" because the + * function graph tracer can be called when RCU is not + * "watching". + * Protected with schedule_on_each_cpu(ftrace_sync) + */ + notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash, + !preemptible()); + + if (ftrace_lookup_ip(notrace_hash, addr)) ret = 1; preempt_enable_notrace(); @@ -1038,7 +1089,7 @@ struct ftrace_func_command { extern bool ftrace_filter_param __initdata; static inline int ftrace_trace_task(struct trace_array *tr) { - return !this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid); + return !this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid); } extern int ftrace_is_dead(void); int ftrace_create_function_files(struct trace_array *tr, @@ -1126,6 +1177,11 @@ int unregister_ftrace_command(struct ftrace_func_command *cmd); void ftrace_create_filter_files(struct ftrace_ops *ops, struct dentry *parent); void ftrace_destroy_filter_files(struct ftrace_ops *ops); + +extern int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset); +extern int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, + int len, int reset); #else struct ftrace_func_command; @@ -1348,17 +1404,17 @@ struct trace_subsystem_dir { }; extern int call_filter_check_discard(struct trace_event_call *call, void *rec, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event); void trace_buffer_unlock_commit_regs(struct trace_array *tr, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc, struct pt_regs *regs); static inline void trace_buffer_unlock_commit(struct trace_array *tr, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event, unsigned long flags, int pc) { @@ -1371,7 +1427,7 @@ void trace_buffered_event_disable(void); void trace_buffered_event_enable(void); static inline void -__trace_event_discard_commit(struct ring_buffer *buffer, +__trace_event_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { if (this_cpu_read(trace_buffered_event) == event) { @@ -1397,7 +1453,7 @@ __trace_event_discard_commit(struct ring_buffer *buffer, */ static inline bool __event_trigger_test_discard(struct trace_event_file *file, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event, void *entry, enum event_trigger_type *tt) @@ -1432,7 +1488,7 @@ __event_trigger_test_discard(struct trace_event_file *file, */ static inline void event_trigger_unlock_commit(struct trace_event_file *file, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc) { @@ -1463,7 +1519,7 @@ event_trigger_unlock_commit(struct trace_event_file *file, */ static inline void event_trigger_unlock_commit_regs(struct trace_event_file *file, - struct ring_buffer *buffer, + struct trace_buffer *buffer, struct ring_buffer_event *event, void *entry, unsigned long irq_flags, int pc, struct pt_regs *regs) @@ -1582,6 +1638,7 @@ extern struct list_head ftrace_events; extern const struct file_operations event_trigger_fops; extern const struct file_operations event_hist_fops; +extern const struct file_operations event_inject_fops; #ifdef CONFIG_HIST_TRIGGERS extern int register_trigger_hist_cmd(void); @@ -1869,11 +1926,19 @@ extern const char *__start___tracepoint_str[]; extern const char *__stop___tracepoint_str[]; void trace_printk_control(bool enabled); -void trace_printk_init_buffers(void); void trace_printk_start_comm(void); int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled); +/* Used from boot time tracer */ +extern int trace_set_options(struct trace_array *tr, char *option); +extern int tracing_set_tracer(struct trace_array *tr, const char *buf); +extern ssize_t tracing_resize_ring_buffer(struct trace_array *tr, + unsigned long size, int cpu_id); +extern int tracing_set_cpumask(struct trace_array *tr, + cpumask_var_t tracing_cpumask_new); + + #define MAX_EVENT_NAME_LEN 64 extern int trace_run_command(const char *buf, int (*createfn)(int, char**)); @@ -1898,17 +1963,15 @@ extern void tracing_log_err(struct trace_array *tr, #define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ extern struct trace_event_call \ __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" @@ -1933,6 +1996,9 @@ static inline const char *get_syscall_name(int syscall) #ifdef CONFIG_EVENT_TRACING void trace_event_init(void); void trace_event_eval_update(struct trace_eval_map **map, int len); +/* Used from boot time tracer */ +extern int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set); +extern int trigger_process_regex(struct trace_event_file *file, char *buff); #else static inline void __init trace_event_init(void) { } static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { } diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 80e0b2aca703..2e9a4746ea85 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -178,14 +178,14 @@ static int benchmark_event_kthread(void *arg) int trace_benchmark_reg(void) { if (!ok_to_run) { - pr_warning("trace benchmark cannot be started via kernel command line\n"); + pr_warn("trace benchmark cannot be started via kernel command line\n"); return -EBUSY; } bm_event_thread = kthread_run(benchmark_event_kthread, NULL, "event_benchmark"); if (IS_ERR(bm_event_thread)) { - pr_warning("trace benchmark failed to create kernel thread\n"); + pr_warn("trace benchmark failed to create kernel thread\n"); return PTR_ERR(bm_event_thread); } diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c new file mode 100644 index 000000000000..06d7feb5255f --- /dev/null +++ b/kernel/trace/trace_boot.c @@ -0,0 +1,334 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace_boot.c + * Tracing kernel boot-time + */ + +#define pr_fmt(fmt) "trace_boot: " fmt + +#include <linux/bootconfig.h> +#include <linux/cpumask.h> +#include <linux/ftrace.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/trace.h> +#include <linux/trace_events.h> + +#include "trace.h" + +#define MAX_BUF_LEN 256 + +static void __init +trace_boot_set_instance_options(struct trace_array *tr, struct xbc_node *node) +{ + struct xbc_node *anode; + const char *p; + char buf[MAX_BUF_LEN]; + unsigned long v = 0; + + /* Common ftrace options */ + xbc_node_for_each_array_value(node, "options", anode, p) { + if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) { + pr_err("String is too long: %s\n", p); + continue; + } + + if (trace_set_options(tr, buf) < 0) + pr_err("Failed to set option: %s\n", buf); + } + + p = xbc_node_find_value(node, "trace_clock", NULL); + if (p && *p != '\0') { + if (tracing_set_clock(tr, p) < 0) + pr_err("Failed to set trace clock: %s\n", p); + } + + p = xbc_node_find_value(node, "buffer_size", NULL); + if (p && *p != '\0') { + v = memparse(p, NULL); + if (v < PAGE_SIZE) + pr_err("Buffer size is too small: %s\n", p); + if (tracing_resize_ring_buffer(tr, v, RING_BUFFER_ALL_CPUS) < 0) + pr_err("Failed to resize trace buffer to %s\n", p); + } + + p = xbc_node_find_value(node, "cpumask", NULL); + if (p && *p != '\0') { + cpumask_var_t new_mask; + + if (alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + if (cpumask_parse(p, new_mask) < 0 || + tracing_set_cpumask(tr, new_mask) < 0) + pr_err("Failed to set new CPU mask %s\n", p); + free_cpumask_var(new_mask); + } + } +} + +#ifdef CONFIG_EVENT_TRACING +static void __init +trace_boot_enable_events(struct trace_array *tr, struct xbc_node *node) +{ + struct xbc_node *anode; + char buf[MAX_BUF_LEN]; + const char *p; + + xbc_node_for_each_array_value(node, "events", anode, p) { + if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) { + pr_err("String is too long: %s\n", p); + continue; + } + + if (ftrace_set_clr_event(tr, buf, 1) < 0) + pr_err("Failed to enable event: %s\n", p); + } +} + +#ifdef CONFIG_KPROBE_EVENTS +static int __init +trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) +{ + struct dynevent_cmd cmd; + struct xbc_node *anode; + char buf[MAX_BUF_LEN]; + const char *val; + int ret; + + kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); + + ret = kprobe_event_gen_cmd_start(&cmd, event, NULL); + if (ret) + return ret; + + xbc_node_for_each_array_value(node, "probes", anode, val) { + ret = kprobe_event_add_field(&cmd, val); + if (ret) + return ret; + } + + ret = kprobe_event_gen_cmd_end(&cmd); + if (ret) + pr_err("Failed to add probe: %s\n", buf); + + return ret; +} +#else +static inline int __init +trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) +{ + pr_err("Kprobe event is not supported.\n"); + return -ENOTSUPP; +} +#endif + +#ifdef CONFIG_HIST_TRIGGERS +static int __init +trace_boot_add_synth_event(struct xbc_node *node, const char *event) +{ + struct dynevent_cmd cmd; + struct xbc_node *anode; + char buf[MAX_BUF_LEN]; + const char *p; + int ret; + + synth_event_cmd_init(&cmd, buf, MAX_BUF_LEN); + + ret = synth_event_gen_cmd_start(&cmd, event, NULL); + if (ret) + return ret; + + xbc_node_for_each_array_value(node, "fields", anode, p) { + ret = synth_event_add_field_str(&cmd, p); + if (ret) + return ret; + } + + ret = synth_event_gen_cmd_end(&cmd); + if (ret < 0) + pr_err("Failed to add synthetic event: %s\n", buf); + + return ret; +} +#else +static inline int __init +trace_boot_add_synth_event(struct xbc_node *node, const char *event) +{ + pr_err("Synthetic event is not supported.\n"); + return -ENOTSUPP; +} +#endif + +static void __init +trace_boot_init_one_event(struct trace_array *tr, struct xbc_node *gnode, + struct xbc_node *enode) +{ + struct trace_event_file *file; + struct xbc_node *anode; + char buf[MAX_BUF_LEN]; + const char *p, *group, *event; + + group = xbc_node_get_data(gnode); + event = xbc_node_get_data(enode); + + if (!strcmp(group, "kprobes")) + if (trace_boot_add_kprobe_event(enode, event) < 0) + return; + if (!strcmp(group, "synthetic")) + if (trace_boot_add_synth_event(enode, event) < 0) + return; + + mutex_lock(&event_mutex); + file = find_event_file(tr, group, event); + if (!file) { + pr_err("Failed to find event: %s:%s\n", group, event); + goto out; + } + + p = xbc_node_find_value(enode, "filter", NULL); + if (p && *p != '\0') { + if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) + pr_err("filter string is too long: %s\n", p); + else if (apply_event_filter(file, buf) < 0) + pr_err("Failed to apply filter: %s\n", buf); + } + + xbc_node_for_each_array_value(enode, "actions", anode, p) { + if (strlcpy(buf, p, ARRAY_SIZE(buf)) >= ARRAY_SIZE(buf)) + pr_err("action string is too long: %s\n", p); + else if (trigger_process_regex(file, buf) < 0) + pr_err("Failed to apply an action: %s\n", buf); + } + + if (xbc_node_find_value(enode, "enable", NULL)) { + if (trace_event_enable_disable(file, 1, 0) < 0) + pr_err("Failed to enable event node: %s:%s\n", + group, event); + } +out: + mutex_unlock(&event_mutex); +} + +static void __init +trace_boot_init_events(struct trace_array *tr, struct xbc_node *node) +{ + struct xbc_node *gnode, *enode; + + node = xbc_node_find_child(node, "event"); + if (!node) + return; + /* per-event key starts with "event.GROUP.EVENT" */ + xbc_node_for_each_child(node, gnode) + xbc_node_for_each_child(gnode, enode) + trace_boot_init_one_event(tr, gnode, enode); +} +#else +#define trace_boot_enable_events(tr, node) do {} while (0) +#define trace_boot_init_events(tr, node) do {} while (0) +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE +static void __init +trace_boot_set_ftrace_filter(struct trace_array *tr, struct xbc_node *node) +{ + struct xbc_node *anode; + const char *p; + char *q; + + xbc_node_for_each_array_value(node, "ftrace.filters", anode, p) { + q = kstrdup(p, GFP_KERNEL); + if (!q) + return; + if (ftrace_set_filter(tr->ops, q, strlen(q), 0) < 0) + pr_err("Failed to add %s to ftrace filter\n", p); + else + ftrace_filter_param = true; + kfree(q); + } + xbc_node_for_each_array_value(node, "ftrace.notraces", anode, p) { + q = kstrdup(p, GFP_KERNEL); + if (!q) + return; + if (ftrace_set_notrace(tr->ops, q, strlen(q), 0) < 0) + pr_err("Failed to add %s to ftrace filter\n", p); + else + ftrace_filter_param = true; + kfree(q); + } +} +#else +#define trace_boot_set_ftrace_filter(tr, node) do {} while (0) +#endif + +static void __init +trace_boot_enable_tracer(struct trace_array *tr, struct xbc_node *node) +{ + const char *p; + + trace_boot_set_ftrace_filter(tr, node); + + p = xbc_node_find_value(node, "tracer", NULL); + if (p && *p != '\0') { + if (tracing_set_tracer(tr, p) < 0) + pr_err("Failed to set given tracer: %s\n", p); + } +} + +static void __init +trace_boot_init_one_instance(struct trace_array *tr, struct xbc_node *node) +{ + trace_boot_set_instance_options(tr, node); + trace_boot_init_events(tr, node); + trace_boot_enable_events(tr, node); + trace_boot_enable_tracer(tr, node); +} + +static void __init +trace_boot_init_instances(struct xbc_node *node) +{ + struct xbc_node *inode; + struct trace_array *tr; + const char *p; + + node = xbc_node_find_child(node, "instance"); + if (!node) + return; + + xbc_node_for_each_child(node, inode) { + p = xbc_node_get_data(inode); + if (!p || *p == '\0') + continue; + + tr = trace_array_get_by_name(p); + if (!tr) { + pr_err("Failed to get trace instance %s\n", p); + continue; + } + trace_boot_init_one_instance(tr, inode); + trace_array_put(tr); + } +} + +static int __init trace_boot_init(void) +{ + struct xbc_node *trace_node; + struct trace_array *tr; + + trace_node = xbc_find_node("ftrace"); + if (!trace_node) + return 0; + + tr = top_trace_array(); + if (!tr) + return 0; + + /* Global trace array is also one instance */ + trace_boot_init_one_instance(tr, trace_node); + trace_boot_init_instances(trace_node); + + return 0; +} + +fs_initcall(trace_boot_init); diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 3ea65cdff30d..eff099123aa2 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -32,10 +32,10 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect) { struct trace_event_call *call = &event_branch; struct trace_array *tr = branch_tracer; + struct trace_buffer *buffer; struct trace_array_cpu *data; struct ring_buffer_event *event; struct trace_branch *entry; - struct ring_buffer *buffer; unsigned long flags; int pc; const char *p; @@ -55,12 +55,12 @@ probe_likely_condition(struct ftrace_likely_data *f, int val, int expect) raw_local_irq_save(flags); current->trace_recursion |= TRACE_BRANCH_BIT; - data = this_cpu_ptr(tr->trace_buffer.data); + data = this_cpu_ptr(tr->array_buffer.data); if (atomic_read(&data->disabled)) goto out; pc = preempt_count(); - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_BRANCH, sizeof(*entry), flags, pc); if (!event) @@ -244,7 +244,7 @@ static int annotated_branch_stat_headers(struct seq_file *m) return 0; } -static inline long get_incorrect_percent(struct ftrace_branch_data *p) +static inline long get_incorrect_percent(const struct ftrace_branch_data *p) { long percent; @@ -332,10 +332,10 @@ annotated_branch_stat_next(void *v, int idx) return p; } -static int annotated_branch_stat_cmp(void *p1, void *p2) +static int annotated_branch_stat_cmp(const void *p1, const void *p2) { - struct ftrace_branch_data *a = p1; - struct ftrace_branch_data *b = p2; + const struct ftrace_branch_data *a = p1; + const struct ftrace_branch_data *b = p2; long percent_a, percent_b; diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index fa100ed3b4de..9f2e8520b748 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -47,6 +47,7 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type) return -EINVAL; event++; } + argc--; argv++; p = strchr(event, '/'); if (p) { @@ -61,10 +62,13 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type) for_each_dyn_event_safe(pos, n) { if (type && type != pos->ops) continue; - if (pos->ops->match(system, event, pos)) { - ret = pos->ops->free(pos); + if (!pos->ops->match(system, event, + argc, (const char **)argv, pos)) + continue; + + ret = pos->ops->free(pos); + if (ret) break; - } } mutex_unlock(&event_mutex); @@ -170,6 +174,10 @@ static int dyn_event_open(struct inode *inode, struct file *file) { int ret; + ret = tracing_check_open_get_tr(NULL); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(NULL); if (ret < 0) @@ -215,3 +223,215 @@ static __init int init_dynamic_event(void) return 0; } fs_initcall(init_dynamic_event); + +/** + * dynevent_arg_add - Add an arg to a dynevent_cmd + * @cmd: A pointer to the dynevent_cmd struct representing the new event cmd + * @arg: The argument to append to the current cmd + * @check_arg: An (optional) pointer to a function checking arg sanity + * + * Append an argument to a dynevent_cmd. The argument string will be + * appended to the current cmd string, followed by a separator, if + * applicable. Before the argument is added, the @check_arg function, + * if present, will be used to check the sanity of the current arg + * string. + * + * The cmd string and separator should be set using the + * dynevent_arg_init() before any arguments are added using this + * function. + * + * Return: 0 if successful, error otherwise. + */ +int dynevent_arg_add(struct dynevent_cmd *cmd, + struct dynevent_arg *arg, + dynevent_check_arg_fn_t check_arg) +{ + int ret = 0; + + if (check_arg) { + ret = check_arg(arg); + if (ret) + return ret; + } + + ret = seq_buf_printf(&cmd->seq, " %s%c", arg->str, arg->separator); + if (ret) { + pr_err("String is too long: %s%c\n", arg->str, arg->separator); + return -E2BIG; + } + + return ret; +} + +/** + * dynevent_arg_pair_add - Add an arg pair to a dynevent_cmd + * @cmd: A pointer to the dynevent_cmd struct representing the new event cmd + * @arg_pair: The argument pair to append to the current cmd + * @check_arg: An (optional) pointer to a function checking arg sanity + * + * Append an argument pair to a dynevent_cmd. An argument pair + * consists of a left-hand-side argument and a right-hand-side + * argument separated by an operator, which can be whitespace, all + * followed by a separator, if applicable. This can be used to add + * arguments of the form 'type variable_name;' or 'x+y'. + * + * The lhs argument string will be appended to the current cmd string, + * followed by an operator, if applicable, followd by the rhs string, + * followed finally by a separator, if applicable. Before the + * argument is added, the @check_arg function, if present, will be + * used to check the sanity of the current arg strings. + * + * The cmd strings, operator, and separator should be set using the + * dynevent_arg_pair_init() before any arguments are added using this + * function. + * + * Return: 0 if successful, error otherwise. + */ +int dynevent_arg_pair_add(struct dynevent_cmd *cmd, + struct dynevent_arg_pair *arg_pair, + dynevent_check_arg_fn_t check_arg) +{ + int ret = 0; + + if (check_arg) { + ret = check_arg(arg_pair); + if (ret) + return ret; + } + + ret = seq_buf_printf(&cmd->seq, " %s%c%s%c", arg_pair->lhs, + arg_pair->operator, arg_pair->rhs, + arg_pair->separator); + if (ret) { + pr_err("field string is too long: %s%c%s%c\n", arg_pair->lhs, + arg_pair->operator, arg_pair->rhs, + arg_pair->separator); + return -E2BIG; + } + + return ret; +} + +/** + * dynevent_str_add - Add a string to a dynevent_cmd + * @cmd: A pointer to the dynevent_cmd struct representing the new event cmd + * @str: The string to append to the current cmd + * + * Append a string to a dynevent_cmd. The string will be appended to + * the current cmd string as-is, with nothing prepended or appended. + * + * Return: 0 if successful, error otherwise. + */ +int dynevent_str_add(struct dynevent_cmd *cmd, const char *str) +{ + int ret = 0; + + ret = seq_buf_puts(&cmd->seq, str); + if (ret) { + pr_err("String is too long: %s\n", str); + return -E2BIG; + } + + return ret; +} + +/** + * dynevent_cmd_init - Initialize a dynevent_cmd object + * @cmd: A pointer to the dynevent_cmd struct representing the cmd + * @buf: A pointer to the buffer to generate the command into + * @maxlen: The length of the buffer the command will be generated into + * @type: The type of the cmd, checked against further operations + * @run_command: The type-specific function that will actually run the command + * + * Initialize a dynevent_cmd. A dynevent_cmd is used to build up and + * run dynamic event creation commands, such as commands for creating + * synthetic and kprobe events. Before calling any of the functions + * used to build the command, a dynevent_cmd object should be + * instantiated and initialized using this function. + * + * The initialization sets things up by saving a pointer to the + * user-supplied buffer and its length via the @buf and @maxlen + * params, and by saving the cmd-specific @type and @run_command + * params which are used to check subsequent dynevent_cmd operations + * and actually run the command when complete. + */ +void dynevent_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen, + enum dynevent_type type, + dynevent_create_fn_t run_command) +{ + memset(cmd, '\0', sizeof(*cmd)); + + seq_buf_init(&cmd->seq, buf, maxlen); + cmd->type = type; + cmd->run_command = run_command; +} + +/** + * dynevent_arg_init - Initialize a dynevent_arg object + * @arg: A pointer to the dynevent_arg struct representing the arg + * @separator: An (optional) separator, appended after adding the arg + * + * Initialize a dynevent_arg object. A dynevent_arg represents an + * object used to append single arguments to the current command + * string. After the arg string is successfully appended to the + * command string, the optional @separator is appended. If no + * separator was specified when initializing the arg, a space will be + * appended. + */ +void dynevent_arg_init(struct dynevent_arg *arg, + char separator) +{ + memset(arg, '\0', sizeof(*arg)); + + if (!separator) + separator = ' '; + arg->separator = separator; +} + +/** + * dynevent_arg_pair_init - Initialize a dynevent_arg_pair object + * @arg_pair: A pointer to the dynevent_arg_pair struct representing the arg + * @operator: An (optional) operator, appended after adding the first arg + * @separator: An (optional) separator, appended after adding the second arg + * + * Initialize a dynevent_arg_pair object. A dynevent_arg_pair + * represents an object used to append argument pairs such as 'type + * variable_name;' or 'x+y' to the current command string. An + * argument pair consists of a left-hand-side argument and a + * right-hand-side argument separated by an operator, which can be + * whitespace, all followed by a separator, if applicable. After the + * first arg string is successfully appended to the command string, + * the optional @operator is appended, followed by the second arg and + * and optional @separator. If no separator was specified when + * initializing the arg, a space will be appended. + */ +void dynevent_arg_pair_init(struct dynevent_arg_pair *arg_pair, + char operator, char separator) +{ + memset(arg_pair, '\0', sizeof(*arg_pair)); + + if (!operator) + operator = ' '; + arg_pair->operator = operator; + + if (!separator) + separator = ' '; + arg_pair->separator = separator; +} + +/** + * dynevent_create - Create the dynamic event contained in dynevent_cmd + * @cmd: The dynevent_cmd object containing the dynamic event creation command + * + * Once a dynevent_cmd object has been successfully built up via the + * dynevent_cmd_init(), dynevent_arg_add() and dynevent_arg_pair_add() + * functions, this function runs the final command to actually create + * the event. + * + * Return: 0 if the event was successfully created, error otherwise. + */ +int dynevent_create(struct dynevent_cmd *cmd) +{ + return cmd->run_command(cmd); +} +EXPORT_SYMBOL_GPL(dynevent_create); diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h index 8c334064e4d6..d6857a254ede 100644 --- a/kernel/trace/trace_dynevent.h +++ b/kernel/trace/trace_dynevent.h @@ -31,8 +31,9 @@ struct dyn_event; * @is_busy: Check whether given event is busy so that it can not be deleted. * Return true if it is busy, otherwides false. * @free: Delete the given event. Return 0 if success, otherwides error. - * @match: Check whether given event and system name match this event. - * Return true if it matches, otherwides false. + * @match: Check whether given event and system name match this event. The argc + * and argv is used for exact match. Return true if it matches, otherwides + * false. * * Except for @create, these methods are called under holding event_mutex. */ @@ -43,7 +44,7 @@ struct dyn_event_operations { bool (*is_busy)(struct dyn_event *ev); int (*free)(struct dyn_event *ev); bool (*match)(const char *system, const char *event, - struct dyn_event *ev); + int argc, const char **argv, struct dyn_event *ev); }; /* Register new dyn_event type -- must be called at first */ @@ -116,4 +117,36 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type); #define for_each_dyn_event_safe(pos, n) \ list_for_each_entry_safe(pos, n, &dyn_event_list, list) +extern void dynevent_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen, + enum dynevent_type type, + dynevent_create_fn_t run_command); + +typedef int (*dynevent_check_arg_fn_t)(void *data); + +struct dynevent_arg { + const char *str; + char separator; /* e.g. ';', ',', or nothing */ +}; + +extern void dynevent_arg_init(struct dynevent_arg *arg, + char separator); +extern int dynevent_arg_add(struct dynevent_cmd *cmd, + struct dynevent_arg *arg, + dynevent_check_arg_fn_t check_arg); + +struct dynevent_arg_pair { + const char *lhs; + const char *rhs; + char operator; /* e.g. '=' or nothing */ + char separator; /* e.g. ';', ',', or nothing */ +}; + +extern void dynevent_arg_pair_init(struct dynevent_arg_pair *arg_pair, + char operator, char separator); + +extern int dynevent_arg_pair_add(struct dynevent_cmd *cmd, + struct dynevent_arg_pair *arg_pair, + dynevent_check_arg_fn_t check_arg); +extern int dynevent_str_add(struct dynevent_cmd *cmd, const char *str); + #endif diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index fc8e97328e54..f22746f3c132 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -61,15 +61,13 @@ FTRACE_ENTRY_REG(function, ftrace_entry, TRACE_FN, F_STRUCT( - __field( unsigned long, ip ) - __field( unsigned long, parent_ip ) + __field_fn( unsigned long, ip ) + __field_fn( unsigned long, parent_ip ) ), F_printk(" %ps <-- %ps", (void *)__entry->ip, (void *)__entry->parent_ip), - FILTER_TRACE_FN, - perf_ftrace_event_register ); @@ -84,9 +82,7 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry, __field_desc( int, graph_ent, depth ) ), - F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth), - - FILTER_OTHER + F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth) ); /* Function return entry */ @@ -97,18 +93,16 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, F_STRUCT( __field_struct( struct ftrace_graph_ret, ret ) __field_desc( unsigned long, ret, func ) + __field_desc( unsigned long, ret, overrun ) __field_desc( unsigned long long, ret, calltime) __field_desc( unsigned long long, ret, rettime ) - __field_desc( unsigned long, ret, overrun ) __field_desc( int, ret, depth ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d", (void *)__entry->func, __entry->depth, __entry->calltime, __entry->rettime, - __entry->depth), - - FILTER_OTHER + __entry->depth) ); /* @@ -137,9 +131,7 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry, F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -157,9 +149,7 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -174,7 +164,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, F_STRUCT( __field( int, size ) - __dynamic_array(unsigned long, caller ) + __array( unsigned long, caller, FTRACE_STACK_ENTRIES ) ), F_printk("\t=> %ps\n\t=> %ps\n\t=> %ps\n" @@ -183,9 +173,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); FTRACE_ENTRY(user_stack, userstack_entry, @@ -203,9 +191,7 @@ FTRACE_ENTRY(user_stack, userstack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); /* @@ -222,9 +208,7 @@ FTRACE_ENTRY(bprint, bprint_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->fmt), - - FILTER_OTHER + (void *)__entry->ip, __entry->fmt) ); FTRACE_ENTRY_REG(print, print_entry, @@ -239,8 +223,6 @@ FTRACE_ENTRY_REG(print, print_entry, F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), - FILTER_OTHER, - ftrace_event_register ); @@ -254,9 +236,7 @@ FTRACE_ENTRY(raw_data, raw_data_entry, ), F_printk("id:%04x %08x", - __entry->id, (int)__entry->buf[0]), - - FILTER_OTHER + __entry->id, (int)__entry->buf[0]) ); FTRACE_ENTRY(bputs, bputs_entry, @@ -269,9 +249,7 @@ FTRACE_ENTRY(bputs, bputs_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->str), - - FILTER_OTHER + (void *)__entry->ip, __entry->str) ); FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, @@ -283,16 +261,14 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, __field_desc( resource_size_t, rw, phys ) __field_desc( unsigned long, rw, value ) __field_desc( unsigned long, rw, pc ) - __field_desc( int, rw, map_id ) + __field_desc( int, rw, map_id ) __field_desc( unsigned char, rw, opcode ) __field_desc( unsigned char, rw, width ) ), F_printk("%lx %lx %lx %d %x %x", (unsigned long)__entry->phys, __entry->value, __entry->pc, - __entry->map_id, __entry->opcode, __entry->width), - - FILTER_OTHER + __entry->map_id, __entry->opcode, __entry->width) ); FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, @@ -304,15 +280,13 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, __field_desc( resource_size_t, map, phys ) __field_desc( unsigned long, map, virt ) __field_desc( unsigned long, map, len ) - __field_desc( int, map, map_id ) + __field_desc( int, map, map_id ) __field_desc( unsigned char, map, opcode ) ), F_printk("%lx %lx %lx %d %x", (unsigned long)__entry->phys, __entry->virt, __entry->len, - __entry->map_id, __entry->opcode), - - FILTER_OTHER + __entry->map_id, __entry->opcode) ); @@ -334,9 +308,7 @@ FTRACE_ENTRY(branch, trace_branch, F_printk("%u:%s:%s (%u)%s", __entry->line, __entry->func, __entry->file, __entry->correct, - __entry->constant ? " CONSTANT" : ""), - - FILTER_OTHER + __entry->constant ? " CONSTANT" : "") ); @@ -362,7 +334,5 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __entry->duration, __entry->outer_duration, __entry->nmi_total_ts, - __entry->nmi_count), - - FILTER_OTHER + __entry->nmi_count) ); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 0892e38ed6fb..643e0b19920d 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -8,6 +8,7 @@ #include <linux/module.h> #include <linux/kprobes.h> +#include <linux/security.h> #include "trace.h" #include "trace_probe.h" @@ -26,8 +27,10 @@ static int total_ref_count; static int perf_trace_event_perm(struct trace_event_call *tp_event, struct perf_event *p_event) { + int ret; + if (tp_event->perf_perm) { - int ret = tp_event->perf_perm(tp_event, p_event); + ret = tp_event->perf_perm(tp_event, p_event); if (ret) return ret; } @@ -46,8 +49,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event, /* The ftrace function trace is allowed only for root. */ if (ftrace_event_is_function(tp_event)) { - if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) - return -EPERM; + ret = perf_allow_tracepoint(&p_event->attr); + if (ret) + return ret; if (!is_sampling_event(p_event)) return 0; @@ -82,8 +86,9 @@ static int perf_trace_event_perm(struct trace_event_call *tp_event, * ...otherwise raw tracepoint data can be a severe data leak, * only allow root to have these. */ - if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN)) - return -EPERM; + ret = perf_allow_tracepoint(&p_event->attr); + if (ret) + return ret; return 0; } @@ -272,9 +277,11 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe) goto out; } + mutex_lock(&event_mutex); ret = perf_trace_event_init(tp_event, p_event); if (ret) destroy_local_trace_kprobe(tp_event); + mutex_unlock(&event_mutex); out: kfree(func); return ret; @@ -282,8 +289,10 @@ out: void perf_kprobe_destroy(struct perf_event *p_event) { + mutex_lock(&event_mutex); perf_trace_event_close(p_event); perf_trace_event_unreg(p_event); + mutex_unlock(&event_mutex); destroy_local_trace_kprobe(p_event->tp_event); } diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c7506bc81b75..f38234ecea18 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) fmt #include <linux/workqueue.h> +#include <linux/security.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/tracefs.h> @@ -23,6 +24,7 @@ #include <linux/delay.h> #include <trace/events/sched.h> +#include <trace/syscall.h> #include <asm/setup.h> @@ -236,7 +238,7 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file) if (!pid_list) return false; - data = this_cpu_ptr(tr->trace_buffer.data); + data = this_cpu_ptr(tr->array_buffer.data); return data->ignore_pid; } @@ -255,12 +257,12 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, local_save_flags(fbuffer->flags); fbuffer->pc = preempt_count(); /* - * If CONFIG_PREEMPT is enabled, then the tracepoint itself disables + * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables * preemption (adding one to the preempt_count). Since we are * interested in the preempt_count at the time the tracepoint was * hit, we need to subtract one to offset the increment. */ - if (IS_ENABLED(CONFIG_PREEMPT)) + if (IS_ENABLED(CONFIG_PREEMPTION)) fbuffer->pc--; fbuffer->trace_file = trace_file; @@ -271,6 +273,7 @@ void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer, if (!fbuffer->event) return NULL; + fbuffer->regs = NULL; fbuffer->entry = ring_buffer_event_data(fbuffer->event); return fbuffer->entry; } @@ -319,7 +322,8 @@ void trace_event_enable_cmd_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) @@ -333,7 +337,6 @@ void trace_event_enable_cmd_record(bool enable) clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } void trace_event_enable_tgid_record(bool enable) @@ -341,7 +344,8 @@ void trace_event_enable_tgid_record(bool enable) struct trace_event_file *file; struct trace_array *tr; - mutex_lock(&event_mutex); + lockdep_assert_held(&event_mutex); + do_for_each_event_file(tr, file) { if (!(file->flags & EVENT_FILE_FL_ENABLED)) continue; @@ -355,7 +359,6 @@ void trace_event_enable_tgid_record(bool enable) &file->flags); } } while_for_each_event_file(); - mutex_unlock(&event_mutex); } static int __ftrace_event_enable_disable(struct trace_event_file *file, @@ -545,7 +548,7 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, pid_list = rcu_dereference_sched(tr->filtered_pids); - this_cpu_write(tr->trace_buffer.data->ignore_pid, + this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, prev) && trace_ignore_this_task(pid_list, next)); } @@ -559,7 +562,7 @@ event_filter_pid_sched_switch_probe_post(void *data, bool preempt, pid_list = rcu_dereference_sched(tr->filtered_pids); - this_cpu_write(tr->trace_buffer.data->ignore_pid, + this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, next)); } @@ -570,12 +573,12 @@ event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task) struct trace_pid_list *pid_list; /* Nothing to do if we are already tracing */ - if (!this_cpu_read(tr->trace_buffer.data->ignore_pid)) + if (!this_cpu_read(tr->array_buffer.data->ignore_pid)) return; pid_list = rcu_dereference_sched(tr->filtered_pids); - this_cpu_write(tr->trace_buffer.data->ignore_pid, + this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, task)); } @@ -586,13 +589,13 @@ event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task) struct trace_pid_list *pid_list; /* Nothing to do if we are not tracing */ - if (this_cpu_read(tr->trace_buffer.data->ignore_pid)) + if (this_cpu_read(tr->array_buffer.data->ignore_pid)) return; pid_list = rcu_dereference_sched(tr->filtered_pids); /* Set tracing if current is enabled */ - this_cpu_write(tr->trace_buffer.data->ignore_pid, + this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, current)); } @@ -624,7 +627,7 @@ static void __ftrace_clear_event_pids(struct trace_array *tr) } for_each_possible_cpu(cpu) - per_cpu_ptr(tr->trace_buffer.data, cpu)->ignore_pid = false; + per_cpu_ptr(tr->array_buffer.data, cpu)->ignore_pid = false; rcu_assign_pointer(tr->filtered_pids, NULL); @@ -696,7 +699,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) return; if (!--dir->nr_events) { - tracefs_remove_recursive(dir->entry); + tracefs_remove(dir->entry); list_del(&dir->list); __put_system_dir(dir); } @@ -715,7 +718,7 @@ static void remove_event_file_dir(struct trace_event_file *file) } spin_unlock(&dir->d_lock); - tracefs_remove_recursive(dir); + tracefs_remove(dir); } list_del(&file->list); @@ -787,11 +790,13 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match, return ret; } -static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) +int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) { char *event = NULL, *sub = NULL, *match; int ret; + if (!tr) + return -ENOENT; /* * The buf format can be <subsystem>:<event-name> * *:<event-name> means any event by that name. @@ -824,7 +829,6 @@ static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set) return ret; } -EXPORT_SYMBOL_GPL(ftrace_set_clr_event); /** * trace_set_clr_event - enable or disable an event @@ -849,6 +853,32 @@ int trace_set_clr_event(const char *system, const char *event, int set) } EXPORT_SYMBOL_GPL(trace_set_clr_event); +/** + * trace_array_set_clr_event - enable or disable an event for a trace array. + * @tr: concerned trace array. + * @system: system name to match (NULL for any system) + * @event: event name to match (NULL for all events, within system) + * @enable: true to enable, false to disable + * + * This is a way for other parts of the kernel to enable or disable + * event recording. + * + * Returns 0 on success, -EINVAL if the parameters do not match any + * registered events. + */ +int trace_array_set_clr_event(struct trace_array *tr, const char *system, + const char *event, bool enable) +{ + int set; + + if (!tr) + return -ENOENT; + + set = (enable == true) ? 1 : 0; + return __ftrace_set_clr_event(tr, NULL, system, event, set); +} +EXPORT_SYMBOL_GPL(trace_array_set_clr_event); + /* 128 should be much more than enough */ #define EVENT_BUF_SIZE 127 @@ -1294,6 +1324,8 @@ static int trace_format_open(struct inode *inode, struct file *file) struct seq_file *m; int ret; + /* Do we want to hide event format files on tracefs lockdown? */ + ret = seq_open(file, &trace_format_seq_ops); if (ret < 0) return ret; @@ -1440,28 +1472,17 @@ static int system_tr_open(struct inode *inode, struct file *filp) struct trace_array *tr = inode->i_private; int ret; - if (tracing_is_disabled()) - return -ENODEV; - - if (trace_array_get(tr) < 0) - return -ENODEV; - /* Make a temporary dir that has no system but points to tr */ dir = kzalloc(sizeof(*dir), GFP_KERNEL); - if (!dir) { - trace_array_put(tr); + if (!dir) return -ENOMEM; - } - - dir->tr = tr; - ret = tracing_open_generic(inode, filp); + ret = tracing_open_generic_tr(inode, filp); if (ret < 0) { - trace_array_put(tr); kfree(dir); return ret; } - + dir->tr = tr; filp->private_data = dir; return 0; @@ -1575,7 +1596,7 @@ static void ignore_task_cpu(void *data) pid_list = rcu_dereference_protected(tr->filtered_pids, mutex_is_locked(&event_mutex)); - this_cpu_write(tr->trace_buffer.data->ignore_pid, + this_cpu_write(tr->array_buffer.data->ignore_pid, trace_ignore_this_task(pid_list, current)); } @@ -1771,6 +1792,10 @@ ftrace_event_open(struct inode *inode, struct file *file, struct seq_file *m; int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + ret = seq_open(file, seq_ops); if (ret < 0) return ret; @@ -1795,6 +1820,7 @@ ftrace_event_avail_open(struct inode *inode, struct file *file) { const struct seq_operations *seq_ops = &show_event_seq_ops; + /* Checks for tracefs lockdown */ return ftrace_event_open(inode, file, seq_ops); } @@ -1805,8 +1831,9 @@ ftrace_event_set_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) @@ -1825,8 +1852,9 @@ ftrace_event_set_pid_open(struct inode *inode, struct file *file) struct trace_array *tr = inode->i_private; int ret; - if (trace_array_get(tr) < 0) - return -ENODEV; + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) @@ -1991,7 +2019,24 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) */ head = trace_get_fields(call); if (list_empty(head)) { - ret = call->class->define_fields(call); + struct trace_event_fields *field = call->class->fields_array; + unsigned int offset = sizeof(struct trace_entry); + + for (; field->type; field++) { + if (field->type == TRACE_FUNCTION_TYPE) { + ret = field->define_fields(call); + break; + } + + offset = ALIGN(offset, field->align); + ret = trace_define_field(call, field->type, field->name, + offset, field->size, + field->is_signed, field->filter_type); + if (ret) + break; + + offset += field->size; + } if (ret < 0) { pr_warn("Could not initialize trace point events/%s\n", name); @@ -2018,6 +2063,12 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) trace_create_file("format", 0444, file->dir, call, &ftrace_event_format_fops); +#ifdef CONFIG_TRACE_EVENT_INJECT + if (call->event.type && call->class->reg) + trace_create_file("inject", 0200, file->dir, file, + &event_inject_fops); +#endif + return 0; } @@ -2503,6 +2554,91 @@ find_event_file(struct trace_array *tr, const char *system, const char *event) return file; } +/** + * trace_get_event_file - Find and return a trace event file + * @instance: The name of the trace instance containing the event + * @system: The name of the system containing the event + * @event: The name of the event + * + * Return a trace event file given the trace instance name, trace + * system, and trace event name. If the instance name is NULL, it + * refers to the top-level trace array. + * + * This function will look it up and return it if found, after calling + * trace_array_get() to prevent the instance from going away, and + * increment the event's module refcount to prevent it from being + * removed. + * + * To release the file, call trace_put_event_file(), which will call + * trace_array_put() and decrement the event's module refcount. + * + * Return: The trace event on success, ERR_PTR otherwise. + */ +struct trace_event_file *trace_get_event_file(const char *instance, + const char *system, + const char *event) +{ + struct trace_array *tr = top_trace_array(); + struct trace_event_file *file = NULL; + int ret = -EINVAL; + + if (instance) { + tr = trace_array_find_get(instance); + if (!tr) + return ERR_PTR(-ENOENT); + } else { + ret = trace_array_get(tr); + if (ret) + return ERR_PTR(ret); + } + + mutex_lock(&event_mutex); + + file = find_event_file(tr, system, event); + if (!file) { + trace_array_put(tr); + ret = -EINVAL; + goto out; + } + + /* Don't let event modules unload while in use */ + ret = try_module_get(file->event_call->mod); + if (!ret) { + trace_array_put(tr); + ret = -EBUSY; + goto out; + } + + ret = 0; + out: + mutex_unlock(&event_mutex); + + if (ret) + file = ERR_PTR(ret); + + return file; +} +EXPORT_SYMBOL_GPL(trace_get_event_file); + +/** + * trace_put_event_file - Release a file from trace_get_event_file() + * @file: The trace event file + * + * If a file was retrieved using trace_get_event_file(), this should + * be called when it's no longer needed. It will cancel the previous + * trace_array_get() called by that function, and decrement the + * event's module refcount. + */ +void trace_put_event_file(struct trace_event_file *file) +{ + mutex_lock(&event_mutex); + module_put(file->event_call->mod); + mutex_unlock(&event_mutex); + + trace_array_put(file->tr); +} +EXPORT_SYMBOL_GPL(trace_put_event_file); + #ifdef CONFIG_DYNAMIC_FTRACE /* Avoid typos */ @@ -3032,7 +3168,7 @@ int event_trace_del_tracer(struct trace_array *tr) down_write(&trace_event_sem); __trace_remove_event_dirs(tr); - tracefs_remove_recursive(tr->event_dir); + tracefs_remove(tr->event_dir); up_write(&trace_event_sem); tr->event_dir = NULL; @@ -3359,8 +3495,8 @@ static void __init function_test_events_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) { + struct trace_buffer *buffer; struct ring_buffer_event *event; - struct ring_buffer *buffer; struct ftrace_entry *entry; unsigned long flags; long disabled; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c773b8fb270c..bf44f6bbd0c3 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -452,8 +452,10 @@ predicate_parse(const char *str, int nr_parens, int nr_preds, switch (*next) { case '(': /* #2 */ - if (top - op_stack > nr_parens) - return ERR_PTR(-EINVAL); + if (top - op_stack > nr_parens) { + ret = -EINVAL; + goto out_free; + } *(++top) = invert; continue; case '!': /* #3 */ @@ -1660,7 +1662,7 @@ static int process_system_preds(struct trace_subsystem_dir *dir, parse_error(pe, FILT_ERR_BAD_SUBSYS_FILTER, 0); return -EINVAL; fail_mem: - kfree(filter); + __free_filter(filter); /* If any call succeeded, we still need to sync */ if (!fail) tracepoint_synchronize_unregister(); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ca6b0dff60c5..483b3fd1094f 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -7,18 +7,23 @@ #include <linux/module.h> #include <linux/kallsyms.h> +#include <linux/security.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/stacktrace.h> #include <linux/rculist.h> #include <linux/tracefs.h> +/* for gfp flag names */ +#include <linux/trace_events.h> +#include <trace/events/mmflags.h> + #include "tracing_map.h" #include "trace.h" #include "trace_dynevent.h" #define SYNTH_SYSTEM "synthetic" -#define SYNTH_FIELDS_MAX 16 +#define SYNTH_FIELDS_MAX 32 #define STR_VAR_LEN_MAX 32 /* must be multiple of sizeof(u64) */ @@ -61,7 +66,12 @@ C(INVALID_SUBSYS_EVENT, "Invalid subsystem or event name"), \ C(INVALID_REF_KEY, "Using variable references in keys not supported"), \ C(VAR_NOT_FOUND, "Couldn't find variable"), \ - C(FIELD_NOT_FOUND, "Couldn't find field"), + C(FIELD_NOT_FOUND, "Couldn't find field"), \ + C(EMPTY_ASSIGNMENT, "Empty assignment"), \ + C(INVALID_SORT_MODIFIER,"Invalid sort modifier"), \ + C(EMPTY_SORT_FIELD, "Empty sort field"), \ + C(TOO_MANY_SORT_FIELDS, "Too many sort fields (Max = 2)"), \ + C(INVALID_SORT_FIELD, "Sort field must be a key or a val"), #undef C #define C(a, b) HIST_ERR_##a @@ -111,6 +121,7 @@ struct hist_field { struct ftrace_event_field *field; unsigned long flags; hist_field_fn_t fn; + unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -369,15 +380,15 @@ struct hist_trigger_data { unsigned int n_save_var_str; }; -static int synth_event_create(int argc, const char **argv); +static int create_synth_event(int argc, const char **argv); static int synth_event_show(struct seq_file *m, struct dyn_event *ev); static int synth_event_release(struct dyn_event *ev); static bool synth_event_is_busy(struct dyn_event *ev); static bool synth_event_match(const char *system, const char *event, - struct dyn_event *ev); + int argc, const char **argv, struct dyn_event *ev); static struct dyn_event_operations synth_event_ops = { - .create = synth_event_create, + .create = create_synth_event, .show = synth_event_show, .is_busy = synth_event_is_busy, .free = synth_event_release, @@ -388,6 +399,7 @@ struct synth_field { char *type; char *name; size_t size; + unsigned int offset; bool is_signed; bool is_string; }; @@ -402,6 +414,7 @@ struct synth_event { struct trace_event_class class; struct trace_event_call call; struct tracepoint *tp; + struct module *mod; }; static bool is_synth_event(struct dyn_event *ev) @@ -422,7 +435,7 @@ static bool synth_event_is_busy(struct dyn_event *ev) } static bool synth_event_match(const char *system, const char *event, - struct dyn_event *ev) + int argc, const char **argv, struct dyn_event *ev) { struct synth_event *sev = to_synth_event(ev); @@ -464,11 +477,12 @@ struct action_data { * When a histogram trigger is hit, the values of any * references to variables, including variables being passed * as parameters to synthetic events, are collected into a - * var_ref_vals array. This var_ref_idx is the index of the - * first param in the array to be passed to the synthetic - * event invocation. + * var_ref_vals array. This var_ref_idx array is an array of + * indices into the var_ref_vals array, one for each synthetic + * event param, and is passed to the synthetic event + * invocation. */ - unsigned int var_ref_idx; + unsigned int var_ref_idx[TRACING_MAP_VARS_MAX]; struct synth_event *synth_event; bool use_trace_keyword; char *synth_event_name; @@ -602,7 +616,8 @@ static void last_cmd_set(struct trace_event_file *file, char *str) if (!str) return; - strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1); + strcpy(last_cmd, "hist:"); + strncat(last_cmd, str, MAX_FILTER_STR_VAL - 1 - sizeof("hist:")); if (file) { call = file->event_call; @@ -656,6 +671,8 @@ static int synth_event_define_fields(struct trace_event_call *call) if (ret) break; + event->fields[i]->offset = n_u64; + if (event->fields[i]->is_string) { offset += STR_VAR_LEN_MAX; n_u64 += STR_VAR_LEN_MAX / sizeof(u64); @@ -674,6 +691,8 @@ static bool synth_field_signed(char *type) { if (str_has_prefix(type, "u")) return false; + if (strcmp(type, "gfp_t") == 0) + return false; return true; } @@ -752,6 +771,8 @@ static int synth_field_size(char *type) size = sizeof(unsigned long); else if (strcmp(type, "pid_t") == 0) size = sizeof(pid_t); + else if (strcmp(type, "gfp_t") == 0) + size = sizeof(gfp_t); else if (synth_field_is_string(type)) size = synth_field_string_size(type); @@ -792,6 +813,8 @@ static const char *synth_field_fmt(char *type) fmt = "%lu"; else if (strcmp(type, "pid_t") == 0) fmt = "%d"; + else if (strcmp(type, "gfp_t") == 0) + fmt = "%x"; else if (synth_field_is_string(type)) fmt = "%s"; @@ -822,7 +845,7 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, fmt = synth_field_fmt(se->fields[i]->type); /* parameter types */ - if (tr->trace_flags & TRACE_ITER_VERBOSE) + if (tr && tr->trace_flags & TRACE_ITER_VERBOSE) trace_seq_printf(s, "%s ", fmt); snprintf(print_fmt, sizeof(print_fmt), "%%s=%s%%s", fmt); @@ -834,9 +857,20 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, i == se->n_fields - 1 ? "" : " "); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { + struct trace_print_flags __flags[] = { + __def_gfpflag_names, {-1, NULL} }; + trace_seq_printf(s, print_fmt, se->fields[i]->name, entry->fields[n_u64], i == se->n_fields - 1 ? "" : " "); + + if (strcmp(se->fields[i]->type, "gfp_t") == 0) { + trace_seq_puts(s, " ("); + trace_print_flags_seq(s, "|", + entry->fields[n_u64], + __flags); + trace_seq_putc(s, ')'); + } n_u64++; } } @@ -852,14 +886,14 @@ static struct trace_event_functions synth_event_funcs = { static notrace void trace_event_raw_event_synth(void *__data, u64 *var_ref_vals, - unsigned int var_ref_idx) + unsigned int *var_ref_idx) { struct trace_event_file *trace_file = __data; struct synth_trace_event *entry; struct trace_event_buffer fbuffer; - struct ring_buffer *buffer; + struct trace_buffer *buffer; struct synth_event *event; - unsigned int i, n_u64; + unsigned int i, n_u64, val_idx; int fields_size = 0; event = trace_file->event_call->data; @@ -873,7 +907,7 @@ static notrace void trace_event_raw_event_synth(void *__data, * Avoid ring buffer recursion detection, as this event * is being performed within another event. */ - buffer = trace_file->tr->trace_buffer.buffer; + buffer = trace_file->tr->array_buffer.buffer; ring_buffer_nest_start(buffer); entry = trace_event_buffer_reserve(&fbuffer, trace_file, @@ -882,14 +916,34 @@ static notrace void trace_event_raw_event_synth(void *__data, goto out; for (i = 0, n_u64 = 0; i < event->n_fields; i++) { + val_idx = var_ref_idx[i]; if (event->fields[i]->is_string) { - char *str_val = (char *)(long)var_ref_vals[var_ref_idx + i]; + char *str_val = (char *)(long)var_ref_vals[val_idx]; char *str_field = (char *)&entry->fields[n_u64]; strscpy(str_field, str_val, STR_VAR_LEN_MAX); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { - entry->fields[n_u64] = var_ref_vals[var_ref_idx + i]; + struct synth_field *field = event->fields[i]; + u64 val = var_ref_vals[val_idx]; + + switch (field->size) { + case 1: + *(u8 *)&entry->fields[n_u64] = (u8)val; + break; + + case 2: + *(u16 *)&entry->fields[n_u64] = (u16)val; + break; + + case 4: + *(u32 *)&entry->fields[n_u64] = (u32)val; + break; + + default: + entry->fields[n_u64] = val; + break; + } n_u64++; } } @@ -1071,10 +1125,10 @@ static struct tracepoint *alloc_synth_tracepoint(char *name) } typedef void (*synth_probe_func_t) (void *__data, u64 *var_ref_vals, - unsigned int var_ref_idx); + unsigned int *var_ref_idx); static inline void trace_synth(struct synth_event *event, u64 *var_ref_vals, - unsigned int var_ref_idx) + unsigned int *var_ref_idx) { struct tracepoint *tp = event->tp; @@ -1113,6 +1167,12 @@ static struct synth_event *find_synth_event(const char *name) return NULL; } +static struct trace_event_fields synth_event_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = synth_event_define_fields }, + {} +}; + static int register_synth_event(struct synth_event *event) { struct trace_event_call *call = &event->call; @@ -1134,7 +1194,7 @@ static int register_synth_event(struct synth_event *event) INIT_LIST_HEAD(&call->class->fields); call->event.funcs = &synth_event_funcs; - call->class->define_fields = synth_event_define_fields; + call->class->fields_array = synth_event_fields_array; ret = register_trace_event(&call->event); if (!ret) { @@ -1245,6 +1305,273 @@ struct hist_var_data { struct hist_trigger_data *hist_data; }; +static int synth_event_check_arg_fn(void *data) +{ + struct dynevent_arg_pair *arg_pair = data; + int size; + + size = synth_field_size((char *)arg_pair->lhs); + + return size ? 0 : -EINVAL; +} + +/** + * synth_event_add_field - Add a new field to a synthetic event cmd + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @type: The type of the new field to add + * @name: The name of the new field to add + * + * Add a new field to a synthetic event cmd object. Field ordering is in + * the same order the fields are added. + * + * See synth_field_size() for available types. If field_name contains + * [n] the field is considered to be an array. + * + * Return: 0 if successful, error otherwise. + */ +int synth_event_add_field(struct dynevent_cmd *cmd, const char *type, + const char *name) +{ + struct dynevent_arg_pair arg_pair; + int ret; + + if (cmd->type != DYNEVENT_TYPE_SYNTH) + return -EINVAL; + + if (!type || !name) + return -EINVAL; + + dynevent_arg_pair_init(&arg_pair, 0, ';'); + + arg_pair.lhs = type; + arg_pair.rhs = name; + + ret = dynevent_arg_pair_add(cmd, &arg_pair, synth_event_check_arg_fn); + if (ret) + return ret; + + if (++cmd->n_fields > SYNTH_FIELDS_MAX) + ret = -EINVAL; + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_add_field); + +/** + * synth_event_add_field_str - Add a new field to a synthetic event cmd + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @type_name: The type and name of the new field to add, as a single string + * + * Add a new field to a synthetic event cmd object, as a single + * string. The @type_name string is expected to be of the form 'type + * name', which will be appended by ';'. No sanity checking is done - + * what's passed in is assumed to already be well-formed. Field + * ordering is in the same order the fields are added. + * + * See synth_field_size() for available types. If field_name contains + * [n] the field is considered to be an array. + * + * Return: 0 if successful, error otherwise. + */ +int synth_event_add_field_str(struct dynevent_cmd *cmd, const char *type_name) +{ + struct dynevent_arg arg; + int ret; + + if (cmd->type != DYNEVENT_TYPE_SYNTH) + return -EINVAL; + + if (!type_name) + return -EINVAL; + + dynevent_arg_init(&arg, ';'); + + arg.str = type_name; + + ret = dynevent_arg_add(cmd, &arg, NULL); + if (ret) + return ret; + + if (++cmd->n_fields > SYNTH_FIELDS_MAX) + ret = -EINVAL; + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_add_field_str); + +/** + * synth_event_add_fields - Add multiple fields to a synthetic event cmd + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @fields: An array of type/name field descriptions + * @n_fields: The number of field descriptions contained in the fields array + * + * Add a new set of fields to a synthetic event cmd object. The event + * fields that will be defined for the event should be passed in as an + * array of struct synth_field_desc, and the number of elements in the + * array passed in as n_fields. Field ordering will retain the + * ordering given in the fields array. + * + * See synth_field_size() for available types. If field_name contains + * [n] the field is considered to be an array. + * + * Return: 0 if successful, error otherwise. + */ +int synth_event_add_fields(struct dynevent_cmd *cmd, + struct synth_field_desc *fields, + unsigned int n_fields) +{ + unsigned int i; + int ret = 0; + + for (i = 0; i < n_fields; i++) { + if (fields[i].type == NULL || fields[i].name == NULL) { + ret = -EINVAL; + break; + } + + ret = synth_event_add_field(cmd, fields[i].type, fields[i].name); + if (ret) + break; + } + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_add_fields); + +/** + * __synth_event_gen_cmd_start - Start a synthetic event command from arg list + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @name: The name of the synthetic event + * @mod: The module creating the event, NULL if not created from a module + * @args: Variable number of arg (pairs), one pair for each field + * + * NOTE: Users normally won't want to call this function directly, but + * rather use the synth_event_gen_cmd_start() wrapper, which + * automatically adds a NULL to the end of the arg list. If this + * function is used directly, make sure the last arg in the variable + * arg list is NULL. + * + * Generate a synthetic event command to be executed by + * synth_event_gen_cmd_end(). This function can be used to generate + * the complete command or only the first part of it; in the latter + * case, synth_event_add_field(), synth_event_add_field_str(), or + * synth_event_add_fields() can be used to add more fields following + * this. + * + * There should be an even number variable args, each pair consisting + * of a type followed by a field name. + * + * See synth_field_size() for available types. If field_name contains + * [n] the field is considered to be an array. + * + * Return: 0 if successful, error otherwise. + */ +int __synth_event_gen_cmd_start(struct dynevent_cmd *cmd, const char *name, + struct module *mod, ...) +{ + struct dynevent_arg arg; + va_list args; + int ret; + + cmd->event_name = name; + cmd->private_data = mod; + + if (cmd->type != DYNEVENT_TYPE_SYNTH) + return -EINVAL; + + dynevent_arg_init(&arg, 0); + arg.str = name; + ret = dynevent_arg_add(cmd, &arg, NULL); + if (ret) + return ret; + + va_start(args, mod); + for (;;) { + const char *type, *name; + + type = va_arg(args, const char *); + if (!type) + break; + name = va_arg(args, const char *); + if (!name) + break; + + if (++cmd->n_fields > SYNTH_FIELDS_MAX) { + ret = -EINVAL; + break; + } + + ret = synth_event_add_field(cmd, type, name); + if (ret) + break; + } + va_end(args); + + return ret; +} +EXPORT_SYMBOL_GPL(__synth_event_gen_cmd_start); + +/** + * synth_event_gen_cmd_array_start - Start synthetic event command from an array + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @name: The name of the synthetic event + * @fields: An array of type/name field descriptions + * @n_fields: The number of field descriptions contained in the fields array + * + * Generate a synthetic event command to be executed by + * synth_event_gen_cmd_end(). This function can be used to generate + * the complete command or only the first part of it; in the latter + * case, synth_event_add_field(), synth_event_add_field_str(), or + * synth_event_add_fields() can be used to add more fields following + * this. + * + * The event fields that will be defined for the event should be + * passed in as an array of struct synth_field_desc, and the number of + * elements in the array passed in as n_fields. Field ordering will + * retain the ordering given in the fields array. + * + * See synth_field_size() for available types. If field_name contains + * [n] the field is considered to be an array. + * + * Return: 0 if successful, error otherwise. + */ +int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name, + struct module *mod, + struct synth_field_desc *fields, + unsigned int n_fields) +{ + struct dynevent_arg arg; + unsigned int i; + int ret = 0; + + cmd->event_name = name; + cmd->private_data = mod; + + if (cmd->type != DYNEVENT_TYPE_SYNTH) + return -EINVAL; + + if (n_fields > SYNTH_FIELDS_MAX) + return -EINVAL; + + dynevent_arg_init(&arg, 0); + arg.str = name; + ret = dynevent_arg_add(cmd, &arg, NULL); + if (ret) + return ret; + + for (i = 0; i < n_fields; i++) { + if (fields[i].type == NULL || fields[i].name == NULL) + return -EINVAL; + + ret = synth_event_add_field(cmd, fields[i].type, fields[i].name); + if (ret) + break; + } + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_gen_cmd_array_start); + static int __create_synth_event(int argc, const char *name, const char **argv) { struct synth_field *field, *fields[SYNTH_FIELDS_MAX]; @@ -1313,29 +1640,123 @@ static int __create_synth_event(int argc, const char *name, const char **argv) goto out; } +/** + * synth_event_create - Create a new synthetic event + * @name: The name of the new sythetic event + * @fields: An array of type/name field descriptions + * @n_fields: The number of field descriptions contained in the fields array + * @mod: The module creating the event, NULL if not created from a module + * + * Create a new synthetic event with the given name under the + * trace/events/synthetic/ directory. The event fields that will be + * defined for the event should be passed in as an array of struct + * synth_field_desc, and the number elements in the array passed in as + * n_fields. Field ordering will retain the ordering given in the + * fields array. + * + * If the new synthetic event is being created from a module, the mod + * param must be non-NULL. This will ensure that the trace buffer + * won't contain unreadable events. + * + * The new synth event should be deleted using synth_event_delete() + * function. The new synthetic event can be generated from modules or + * other kernel code using trace_synth_event() and related functions. + * + * Return: 0 if successful, error otherwise. + */ +int synth_event_create(const char *name, struct synth_field_desc *fields, + unsigned int n_fields, struct module *mod) +{ + struct dynevent_cmd cmd; + char *buf; + int ret; + + buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + synth_event_cmd_init(&cmd, buf, MAX_DYNEVENT_CMD_LEN); + + ret = synth_event_gen_cmd_array_start(&cmd, name, mod, + fields, n_fields); + if (ret) + goto out; + + ret = synth_event_gen_cmd_end(&cmd); + out: + kfree(buf); + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_create); + +static int destroy_synth_event(struct synth_event *se) +{ + int ret; + + if (se->ref) + ret = -EBUSY; + else { + ret = unregister_synth_event(se); + if (!ret) { + dyn_event_remove(&se->devent); + free_synth_event(se); + } + } + + return ret; +} + +/** + * synth_event_delete - Delete a synthetic event + * @event_name: The name of the new sythetic event + * + * Delete a synthetic event that was created with synth_event_create(). + * + * Return: 0 if successful, error otherwise. + */ +int synth_event_delete(const char *event_name) +{ + struct synth_event *se = NULL; + struct module *mod = NULL; + int ret = -ENOENT; + + mutex_lock(&event_mutex); + se = find_synth_event(event_name); + if (se) { + mod = se->mod; + ret = destroy_synth_event(se); + } + mutex_unlock(&event_mutex); + + if (mod) { + mutex_lock(&trace_types_lock); + /* + * It is safest to reset the ring buffer if the module + * being unloaded registered any events that were + * used. The only worry is if a new module gets + * loaded, and takes on the same id as the events of + * this module. When printing out the buffer, traced + * events left over from this module may be passed to + * the new module events and unexpected results may + * occur. + */ + tracing_reset_all_online_cpus(); + mutex_unlock(&trace_types_lock); + } + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_delete); + static int create_or_delete_synth_event(int argc, char **argv) { const char *name = argv[0]; - struct synth_event *event = NULL; int ret; /* trace_run_command() ensures argc != 0 */ if (name[0] == '!') { - mutex_lock(&event_mutex); - event = find_synth_event(name + 1); - if (event) { - if (event->ref) - ret = -EBUSY; - else { - ret = unregister_synth_event(event); - if (!ret) { - dyn_event_remove(&event->devent); - free_synth_event(event); - } - } - } else - ret = -ENOENT; - mutex_unlock(&event_mutex); + ret = synth_event_delete(name + 1); return ret; } @@ -1343,7 +1764,419 @@ static int create_or_delete_synth_event(int argc, char **argv) return ret == -ECANCELED ? -EINVAL : ret; } -static int synth_event_create(int argc, const char **argv) +static int synth_event_run_command(struct dynevent_cmd *cmd) +{ + struct synth_event *se; + int ret; + + ret = trace_run_command(cmd->seq.buffer, create_or_delete_synth_event); + if (ret) + return ret; + + se = find_synth_event(cmd->event_name); + if (WARN_ON(!se)) + return -ENOENT; + + se->mod = cmd->private_data; + + return ret; +} + +/** + * synth_event_cmd_init - Initialize a synthetic event command object + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @buf: A pointer to the buffer used to build the command + * @maxlen: The length of the buffer passed in @buf + * + * Initialize a synthetic event command object. Use this before + * calling any of the other dyenvent_cmd functions. + */ +void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen) +{ + dynevent_cmd_init(cmd, buf, maxlen, DYNEVENT_TYPE_SYNTH, + synth_event_run_command); +} +EXPORT_SYMBOL_GPL(synth_event_cmd_init); + +static inline int +__synth_event_trace_start(struct trace_event_file *file, + struct synth_event_trace_state *trace_state) +{ + int entry_size, fields_size = 0; + int ret = 0; + + /* + * Normal event tracing doesn't get called at all unless the + * ENABLED bit is set (which attaches the probe thus allowing + * this code to be called, etc). Because this is called + * directly by the user, we don't have that but we still need + * to honor not logging when disabled. For the the iterated + * trace case, we save the enabed state upon start and just + * ignore the following data calls. + */ + if (!(file->flags & EVENT_FILE_FL_ENABLED) || + trace_trigger_soft_disabled(file)) { + trace_state->disabled = true; + ret = -ENOENT; + goto out; + } + + trace_state->event = file->event_call->data; + + fields_size = trace_state->event->n_u64 * sizeof(u64); + + /* + * Avoid ring buffer recursion detection, as this event + * is being performed within another event. + */ + trace_state->buffer = file->tr->array_buffer.buffer; + ring_buffer_nest_start(trace_state->buffer); + + entry_size = sizeof(*trace_state->entry) + fields_size; + trace_state->entry = trace_event_buffer_reserve(&trace_state->fbuffer, + file, + entry_size); + if (!trace_state->entry) { + ring_buffer_nest_end(trace_state->buffer); + ret = -EINVAL; + } +out: + return ret; +} + +static inline void +__synth_event_trace_end(struct synth_event_trace_state *trace_state) +{ + trace_event_buffer_commit(&trace_state->fbuffer); + + ring_buffer_nest_end(trace_state->buffer); +} + +/** + * synth_event_trace - Trace a synthetic event + * @file: The trace_event_file representing the synthetic event + * @n_vals: The number of values in vals + * @args: Variable number of args containing the event values + * + * Trace a synthetic event using the values passed in the variable + * argument list. + * + * The argument list should be a list 'n_vals' u64 values. The number + * of vals must match the number of field in the synthetic event, and + * must be in the same order as the synthetic event fields. + * + * All vals should be cast to u64, and string vals are just pointers + * to strings, cast to u64. Strings will be copied into space + * reserved in the event for the string, using these pointers. + * + * Return: 0 on success, err otherwise. + */ +int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) +{ + struct synth_event_trace_state state; + unsigned int i, n_u64; + va_list args; + int ret; + + ret = __synth_event_trace_start(file, &state); + if (ret) { + if (ret == -ENOENT) + ret = 0; /* just disabled, not really an error */ + return ret; + } + + va_start(args, n_vals); + for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { + u64 val; + + val = va_arg(args, u64); + + if (state.event->fields[i]->is_string) { + char *str_val = (char *)(long)val; + char *str_field = (char *)&state.entry->fields[n_u64]; + + strscpy(str_field, str_val, STR_VAR_LEN_MAX); + n_u64 += STR_VAR_LEN_MAX / sizeof(u64); + } else { + state.entry->fields[n_u64] = val; + n_u64++; + } + } + va_end(args); + + __synth_event_trace_end(&state); + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_trace); + +/** + * synth_event_trace_array - Trace a synthetic event from an array + * @file: The trace_event_file representing the synthetic event + * @vals: Array of values + * @n_vals: The number of values in vals + * + * Trace a synthetic event using the values passed in as 'vals'. + * + * The 'vals' array is just an array of 'n_vals' u64. The number of + * vals must match the number of field in the synthetic event, and + * must be in the same order as the synthetic event fields. + * + * All vals should be cast to u64, and string vals are just pointers + * to strings, cast to u64. Strings will be copied into space + * reserved in the event for the string, using these pointers. + * + * Return: 0 on success, err otherwise. + */ +int synth_event_trace_array(struct trace_event_file *file, u64 *vals, + unsigned int n_vals) +{ + struct synth_event_trace_state state; + unsigned int i, n_u64; + int ret; + + ret = __synth_event_trace_start(file, &state); + if (ret) { + if (ret == -ENOENT) + ret = 0; /* just disabled, not really an error */ + return ret; + } + + for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { + if (state.event->fields[i]->is_string) { + char *str_val = (char *)(long)vals[i]; + char *str_field = (char *)&state.entry->fields[n_u64]; + + strscpy(str_field, str_val, STR_VAR_LEN_MAX); + n_u64 += STR_VAR_LEN_MAX / sizeof(u64); + } else { + state.entry->fields[n_u64] = vals[i]; + n_u64++; + } + } + + __synth_event_trace_end(&state); + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_trace_array); + +/** + * synth_event_trace_start - Start piecewise synthetic event trace + * @file: The trace_event_file representing the synthetic event + * @trace_state: A pointer to object tracking the piecewise trace state + * + * Start the trace of a synthetic event field-by-field rather than all + * at once. + * + * This function 'opens' an event trace, which means space is reserved + * for the event in the trace buffer, after which the event's + * individual field values can be set through either + * synth_event_add_next_val() or synth_event_add_val(). + * + * A pointer to a trace_state object is passed in, which will keep + * track of the current event trace state until the event trace is + * closed (and the event finally traced) using + * synth_event_trace_end(). + * + * Note that synth_event_trace_end() must be called after all values + * have been added for each event trace, regardless of whether adding + * all field values succeeded or not. + * + * Note also that for a given event trace, all fields must be added + * using either synth_event_add_next_val() or synth_event_add_val() + * but not both together or interleaved. + * + * Return: 0 on success, err otherwise. + */ +int synth_event_trace_start(struct trace_event_file *file, + struct synth_event_trace_state *trace_state) +{ + int ret; + + if (!trace_state) + return -EINVAL; + + memset(trace_state, '\0', sizeof(*trace_state)); + + ret = __synth_event_trace_start(file, trace_state); + if (ret == -ENOENT) + ret = 0; /* just disabled, not really an error */ + + return ret; +} +EXPORT_SYMBOL_GPL(synth_event_trace_start); + +static int __synth_event_add_val(const char *field_name, u64 val, + struct synth_event_trace_state *trace_state) +{ + struct synth_field *field = NULL; + struct synth_trace_event *entry; + struct synth_event *event; + int i, ret = 0; + + if (!trace_state) { + ret = -EINVAL; + goto out; + } + + /* can't mix add_next_synth_val() with add_synth_val() */ + if (field_name) { + if (trace_state->add_next) { + ret = -EINVAL; + goto out; + } + trace_state->add_name = true; + } else { + if (trace_state->add_name) { + ret = -EINVAL; + goto out; + } + trace_state->add_next = true; + } + + if (trace_state->disabled) + goto out; + + event = trace_state->event; + if (trace_state->add_name) { + for (i = 0; i < event->n_fields; i++) { + field = event->fields[i]; + if (strcmp(field->name, field_name) == 0) + break; + } + if (!field) { + ret = -EINVAL; + goto out; + } + } else { + if (trace_state->cur_field >= event->n_fields) { + ret = -EINVAL; + goto out; + } + field = event->fields[trace_state->cur_field++]; + } + + entry = trace_state->entry; + if (field->is_string) { + char *str_val = (char *)(long)val; + char *str_field; + + if (!str_val) { + ret = -EINVAL; + goto out; + } + + str_field = (char *)&entry->fields[field->offset]; + strscpy(str_field, str_val, STR_VAR_LEN_MAX); + } else + entry->fields[field->offset] = val; + out: + return ret; +} + +/** + * synth_event_add_next_val - Add the next field's value to an open synth trace + * @val: The value to set the next field to + * @trace_state: A pointer to object tracking the piecewise trace state + * + * Set the value of the next field in an event that's been opened by + * synth_event_trace_start(). + * + * The val param should be the value cast to u64. If the value points + * to a string, the val param should be a char * cast to u64. + * + * This function assumes all the fields in an event are to be set one + * after another - successive calls to this function are made, one for + * each field, in the order of the fields in the event, until all + * fields have been set. If you'd rather set each field individually + * without regard to ordering, synth_event_add_val() can be used + * instead. + * + * Note however that synth_event_add_next_val() and + * synth_event_add_val() can't be intermixed for a given event trace - + * one or the other but not both can be used at the same time. + * + * Note also that synth_event_trace_end() must be called after all + * values have been added for each event trace, regardless of whether + * adding all field values succeeded or not. + * + * Return: 0 on success, err otherwise. + */ +int synth_event_add_next_val(u64 val, + struct synth_event_trace_state *trace_state) +{ + return __synth_event_add_val(NULL, val, trace_state); +} +EXPORT_SYMBOL_GPL(synth_event_add_next_val); + +/** + * synth_event_add_val - Add a named field's value to an open synth trace + * @field_name: The name of the synthetic event field value to set + * @val: The value to set the next field to + * @trace_state: A pointer to object tracking the piecewise trace state + * + * Set the value of the named field in an event that's been opened by + * synth_event_trace_start(). + * + * The val param should be the value cast to u64. If the value points + * to a string, the val param should be a char * cast to u64. + * + * This function looks up the field name, and if found, sets the field + * to the specified value. This lookup makes this function more + * expensive than synth_event_add_next_val(), so use that or the + * none-piecewise synth_event_trace() instead if efficiency is more + * important. + * + * Note however that synth_event_add_next_val() and + * synth_event_add_val() can't be intermixed for a given event trace - + * one or the other but not both can be used at the same time. + * + * Note also that synth_event_trace_end() must be called after all + * values have been added for each event trace, regardless of whether + * adding all field values succeeded or not. + * + * Return: 0 on success, err otherwise. + */ +int synth_event_add_val(const char *field_name, u64 val, + struct synth_event_trace_state *trace_state) +{ + return __synth_event_add_val(field_name, val, trace_state); +} +EXPORT_SYMBOL_GPL(synth_event_add_val); + +/** + * synth_event_trace_end - End piecewise synthetic event trace + * @trace_state: A pointer to object tracking the piecewise trace state + * + * End the trace of a synthetic event opened by + * synth_event_trace__start(). + * + * This function 'closes' an event trace, which basically means that + * it commits the reserved event and cleans up other loose ends. + * + * A pointer to a trace_state object is passed in, which will keep + * track of the current event trace state opened with + * synth_event_trace_start(). + * + * Note that this function must be called after all values have been + * added for each event trace, regardless of whether adding all field + * values succeeded or not. + * + * Return: 0 on success, err otherwise. + */ +int synth_event_trace_end(struct synth_event_trace_state *trace_state) +{ + if (!trace_state) + return -EINVAL; + + __synth_event_trace_end(trace_state); + + return 0; +} +EXPORT_SYMBOL_GPL(synth_event_trace_end); + +static int create_synth_event(int argc, const char **argv) { const char *name = argv[0]; int len; @@ -1429,6 +2262,10 @@ static int synth_events_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&synth_event_ops); if (ret < 0) @@ -1661,7 +2498,7 @@ static int save_hist_vars(struct hist_trigger_data *hist_data) if (var_data) return 0; - if (trace_array_get(tr) < 0) + if (tracing_check_open_get_tr(tr)) return -ENODEV; var_data = kzalloc(sizeof(*var_data), GFP_KERNEL); @@ -1721,11 +2558,13 @@ static struct hist_field *find_var(struct hist_trigger_data *hist_data, struct event_trigger_data *test; struct hist_field *hist_field; + lockdep_assert_held(&event_mutex); + hist_field = find_var_field(hist_data, var_name); if (hist_field) return hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -1775,7 +2614,9 @@ static struct hist_field *find_file_var(struct trace_event_file *file, struct event_trigger_data *test; struct hist_field *hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -1985,12 +2826,6 @@ static int parse_map_size(char *str) unsigned long size, map_bits; int ret; - strsep(&str, "="); - if (!str) { - ret = -EINVAL; - goto out; - } - ret = kstrtoul(str, 0, &size); if (ret) goto out; @@ -2050,25 +2885,25 @@ static int parse_action(char *str, struct hist_trigger_attrs *attrs) static int parse_assignment(struct trace_array *tr, char *str, struct hist_trigger_attrs *attrs) { - int ret = 0; + int len, ret = 0; - if ((str_has_prefix(str, "key=")) || - (str_has_prefix(str, "keys="))) { - attrs->keys_str = kstrdup(str, GFP_KERNEL); + if ((len = str_has_prefix(str, "key=")) || + (len = str_has_prefix(str, "keys="))) { + attrs->keys_str = kstrdup(str + len, GFP_KERNEL); if (!attrs->keys_str) { ret = -ENOMEM; goto out; } - } else if ((str_has_prefix(str, "val=")) || - (str_has_prefix(str, "vals=")) || - (str_has_prefix(str, "values="))) { - attrs->vals_str = kstrdup(str, GFP_KERNEL); + } else if ((len = str_has_prefix(str, "val=")) || + (len = str_has_prefix(str, "vals=")) || + (len = str_has_prefix(str, "values="))) { + attrs->vals_str = kstrdup(str + len, GFP_KERNEL); if (!attrs->vals_str) { ret = -ENOMEM; goto out; } - } else if (str_has_prefix(str, "sort=")) { - attrs->sort_key_str = kstrdup(str, GFP_KERNEL); + } else if ((len = str_has_prefix(str, "sort="))) { + attrs->sort_key_str = kstrdup(str + len, GFP_KERNEL); if (!attrs->sort_key_str) { ret = -ENOMEM; goto out; @@ -2079,12 +2914,8 @@ static int parse_assignment(struct trace_array *tr, ret = -ENOMEM; goto out; } - } else if (str_has_prefix(str, "clock=")) { - strsep(&str, "="); - if (!str) { - ret = -EINVAL; - goto out; - } + } else if ((len = str_has_prefix(str, "clock="))) { + str += len; str = strstrip(str); attrs->clock = kstrdup(str, GFP_KERNEL); @@ -2092,8 +2923,8 @@ static int parse_assignment(struct trace_array *tr, ret = -ENOMEM; goto out; } - } else if (str_has_prefix(str, "size=")) { - int map_bits = parse_map_size(str); + } else if ((len = str_has_prefix(str, "size="))) { + int map_bits = parse_map_size(str + len); if (map_bits < 0) { ret = map_bits; @@ -2133,8 +2964,15 @@ parse_hist_trigger_attrs(struct trace_array *tr, char *trigger_str) while (trigger_str) { char *str = strsep(&trigger_str, ":"); + char *rhs; - if (strchr(str, '=')) { + rhs = strchr(str, '='); + if (rhs) { + if (!strlen(++rhs)) { + ret = -EINVAL; + hist_err(tr, HIST_ERR_EMPTY_ASSIGNMENT, errpos(str)); + goto free; + } ret = parse_assignment(tr, str, attrs); if (ret) goto free; @@ -2378,8 +3216,16 @@ static int contains_operator(char *str) return field_op; } +static void get_hist_field(struct hist_field *hist_field) +{ + hist_field->ref++; +} + static void __destroy_hist_field(struct hist_field *hist_field) { + if (--hist_field->ref > 1) + return; + kfree(hist_field->var.name); kfree(hist_field->name); kfree(hist_field->type); @@ -2421,6 +3267,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; + hist_field->ref = 1; + hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -2595,6 +3443,22 @@ static int init_var_ref(struct hist_field *ref_field, goto out; } +static int find_var_ref_idx(struct hist_trigger_data *hist_data, + struct hist_field *var_field) +{ + struct hist_field *ref_field; + int i; + + for (i = 0; i < hist_data->n_var_refs; i++) { + ref_field = hist_data->var_refs[i]; + if (ref_field->var.idx == var_field->var.idx && + ref_field->var.hist_data == var_field->hist_data) + return i; + } + + return -ENOENT; +} + /** * create_var_ref - Create a variable reference and attach it to trigger * @hist_data: The trigger that will be referencing the variable @@ -2616,6 +3480,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, { unsigned long flags = HIST_FIELD_FL_VAR_REF; struct hist_field *ref_field; + int i; + + /* Check if the variable already exists */ + for (i = 0; i < hist_data->n_var_refs; i++) { + ref_field = hist_data->var_refs[i]; + if (ref_field->var.idx == var_field->var.idx && + ref_field->var.hist_data == var_field->hist_data) { + get_hist_field(ref_field); + return ref_field; + } + } ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { @@ -2785,6 +3660,8 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data, return NULL; } + alias->var_ref_idx = var_ref->var_ref_idx; + return alias; } @@ -3068,7 +3945,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data, { struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (test->private_data == hist_data) return test->filter_str; @@ -3119,9 +3998,11 @@ find_compatible_hist(struct hist_trigger_data *target_hist_data, struct event_trigger_data *test; unsigned int n_keys; + lockdep_assert_held(&event_mutex); + n_keys = target_hist_data->n_fields - target_hist_data->n_vals; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; @@ -4063,8 +4944,11 @@ static int check_synth_field(struct synth_event *event, field = event->fields[field_pos]; - if (strcmp(field->type, hist_field->type) != 0) - return -EINVAL; + if (strcmp(field->type, hist_field->type) != 0) { + if (field->size != hist_field->size || + field->is_signed != hist_field->is_signed) + return -EINVAL; + } return 0; } @@ -4151,11 +5035,11 @@ static int trace_action_create(struct hist_trigger_data *hist_data, struct trace_array *tr = hist_data->event_file->tr; char *event_name, *param, *system = NULL; struct hist_field *hist_field, *var_ref; - unsigned int i, var_ref_idx; + unsigned int i; unsigned int field_pos = 0; struct synth_event *event; char *synth_event_name; - int ret = 0; + int var_ref_idx, ret = 0; lockdep_assert_held(&event_mutex); @@ -4172,8 +5056,6 @@ static int trace_action_create(struct hist_trigger_data *hist_data, event->ref++; - var_ref_idx = hist_data->n_var_refs; - for (i = 0; i < data->n_params; i++) { char *p; @@ -4222,6 +5104,14 @@ static int trace_action_create(struct hist_trigger_data *hist_data, goto err; } + var_ref_idx = find_var_ref_idx(hist_data, var_ref); + if (WARN_ON(var_ref_idx < 0)) { + ret = var_ref_idx; + goto err; + } + + data->var_ref_idx[i] = var_ref_idx; + field_pos++; kfree(p); continue; @@ -4240,7 +5130,6 @@ static int trace_action_create(struct hist_trigger_data *hist_data, } data->synth_event = event; - data->var_ref_idx = var_ref_idx; out: return ret; err: @@ -4459,10 +5348,6 @@ static int create_val_fields(struct hist_trigger_data *hist_data, if (!fields_str) goto out; - strsep(&fields_str, "="); - if (!fields_str) - goto out; - for (i = 0, j = 1; i < TRACING_MAP_VALS_MAX && j < TRACING_MAP_VALS_MAX; i++) { field_str = strsep(&fields_str, ","); @@ -4557,10 +5442,6 @@ static int create_key_fields(struct hist_trigger_data *hist_data, if (!fields_str) goto out; - strsep(&fields_str, "="); - if (!fields_str) - goto out; - for (i = n_vals; i < n_vals + TRACING_MAP_KEYS_MAX; i++) { field_str = strsep(&fields_str, ","); if (!field_str) @@ -4692,7 +5573,7 @@ static int create_hist_fields(struct hist_trigger_data *hist_data, return ret; } -static int is_descending(const char *str) +static int is_descending(struct trace_array *tr, const char *str) { if (!str) return 0; @@ -4703,11 +5584,14 @@ static int is_descending(const char *str) if (strcmp(str, "ascending") == 0) return 0; + hist_err(tr, HIST_ERR_INVALID_SORT_MODIFIER, errpos((char *)str)); + return -EINVAL; } static int create_sort_keys(struct hist_trigger_data *hist_data) { + struct trace_array *tr = hist_data->event_file->tr; char *fields_str = hist_data->attrs->sort_key_str; struct tracing_map_sort_key *sort_key; int descending, ret = 0; @@ -4718,12 +5602,6 @@ static int create_sort_keys(struct hist_trigger_data *hist_data) if (!fields_str) goto out; - strsep(&fields_str, "="); - if (!fields_str) { - ret = -EINVAL; - goto out; - } - for (i = 0; i < TRACING_MAP_SORT_KEYS_MAX; i++) { struct hist_field *hist_field; char *field_str, *field_name; @@ -4732,25 +5610,30 @@ static int create_sort_keys(struct hist_trigger_data *hist_data) sort_key = &hist_data->sort_keys[i]; field_str = strsep(&fields_str, ","); - if (!field_str) { - if (i == 0) - ret = -EINVAL; + if (!field_str) + break; + + if (!*field_str) { + ret = -EINVAL; + hist_err(tr, HIST_ERR_EMPTY_SORT_FIELD, errpos("sort=")); break; } if ((i == TRACING_MAP_SORT_KEYS_MAX - 1) && fields_str) { + hist_err(tr, HIST_ERR_TOO_MANY_SORT_FIELDS, errpos("sort=")); ret = -EINVAL; break; } field_name = strsep(&field_str, "."); - if (!field_name) { + if (!field_name || !*field_name) { ret = -EINVAL; + hist_err(tr, HIST_ERR_EMPTY_SORT_FIELD, errpos("sort=")); break; } if (strcmp(field_name, "hitcount") == 0) { - descending = is_descending(field_str); + descending = is_descending(tr, field_str); if (descending < 0) { ret = descending; break; @@ -4772,7 +5655,7 @@ static int create_sort_keys(struct hist_trigger_data *hist_data) if (strcmp(field_name, test_name) == 0) { sort_key->field_idx = idx; - descending = is_descending(field_str); + descending = is_descending(tr, field_str); if (descending < 0) { ret = descending; goto out; @@ -4783,6 +5666,7 @@ static int create_sort_keys(struct hist_trigger_data *hist_data) } if (j == hist_data->n_fields) { ret = -EINVAL; + hist_err(tr, HIST_ERR_INVALID_SORT_FIELD, errpos(field_name)); break; } } @@ -5481,7 +6365,7 @@ static int hist_show(struct seq_file *m, void *v) goto out_unlock; } - list_for_each_entry_rcu(data, &event_file->triggers, list) { + list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } @@ -5494,6 +6378,12 @@ static int hist_show(struct seq_file *m, void *v) static int event_hist_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return single_open(file, hist_show, file); } @@ -5868,7 +6758,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, if (hist_data->attrs->name && !named_data) goto new; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -5952,10 +6844,12 @@ static bool have_hist_trigger_match(struct event_trigger_data *data, struct event_trigger_data *test, *named_data = NULL; bool match = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (hist_trigger_match(data, test, named_data, false)) { match = true; @@ -5973,10 +6867,12 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data, struct hist_trigger_data *hist_data = data->private_data; struct event_trigger_data *test, *named_data = NULL; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -5998,10 +6894,12 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test, *named_data = NULL; bool unregistered = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6027,7 +6925,9 @@ static bool hist_file_check_refs(struct trace_event_file *file) struct hist_trigger_data *hist_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; if (check_var_refs(hist_data)) @@ -6270,7 +7170,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec, struct enable_trigger_data *enable_data = data->private_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &enable_data->file->triggers, list) { + list_for_each_entry_rcu(test, &enable_data->file->triggers, list, + lockdep_is_held(&event_mutex)) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (enable_data->enable) test->paused = false; diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c new file mode 100644 index 000000000000..22bcf7c51d1e --- /dev/null +++ b/kernel/trace/trace_events_inject.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * trace_events_inject - trace event injection + * + * Copyright (C) 2019 Cong Wang <cwang@twitter.com> + */ + +#include <linux/module.h> +#include <linux/ctype.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/rculist.h> + +#include "trace.h" + +static int +trace_inject_entry(struct trace_event_file *file, void *rec, int len) +{ + struct trace_event_buffer fbuffer; + int written = 0; + void *entry; + + rcu_read_lock_sched(); + entry = trace_event_buffer_reserve(&fbuffer, file, len); + if (entry) { + memcpy(entry, rec, len); + written = len; + trace_event_buffer_commit(&fbuffer); + } + rcu_read_unlock_sched(); + + return written; +} + +static int +parse_field(char *str, struct trace_event_call *call, + struct ftrace_event_field **pf, u64 *pv) +{ + struct ftrace_event_field *field; + char *field_name; + int s, i = 0; + int len; + u64 val; + + if (!str[i]) + return 0; + /* First find the field to associate to */ + while (isspace(str[i])) + i++; + s = i; + while (isalnum(str[i]) || str[i] == '_') + i++; + len = i - s; + if (!len) + return -EINVAL; + + field_name = kmemdup_nul(str + s, len, GFP_KERNEL); + if (!field_name) + return -ENOMEM; + field = trace_find_event_field(call, field_name); + kfree(field_name); + if (!field) + return -ENOENT; + + *pf = field; + while (isspace(str[i])) + i++; + if (str[i] != '=') + return -EINVAL; + i++; + while (isspace(str[i])) + i++; + s = i; + if (isdigit(str[i]) || str[i] == '-') { + char *num, c; + int ret; + + /* Make sure the field is not a string */ + if (is_string_field(field)) + return -EINVAL; + + if (str[i] == '-') + i++; + + /* We allow 0xDEADBEEF */ + while (isalnum(str[i])) + i++; + num = str + s; + c = str[i]; + if (c != '\0' && !isspace(c)) + return -EINVAL; + str[i] = '\0'; + /* Make sure it is a value */ + if (field->is_signed) + ret = kstrtoll(num, 0, &val); + else + ret = kstrtoull(num, 0, &val); + str[i] = c; + if (ret) + return ret; + + *pv = val; + return i; + } else if (str[i] == '\'' || str[i] == '"') { + char q = str[i]; + + /* Make sure the field is OK for strings */ + if (!is_string_field(field)) + return -EINVAL; + + for (i++; str[i]; i++) { + if (str[i] == '\\' && str[i + 1]) { + i++; + continue; + } + if (str[i] == q) + break; + } + if (!str[i]) + return -EINVAL; + + /* Skip quotes */ + s++; + len = i - s; + if (len >= MAX_FILTER_STR_VAL) + return -EINVAL; + + *pv = (unsigned long)(str + s); + str[i] = 0; + /* go past the last quote */ + i++; + return i; + } + + return -EINVAL; +} + +static int trace_get_entry_size(struct trace_event_call *call) +{ + struct ftrace_event_field *field; + struct list_head *head; + int size = 0; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (field->size + field->offset > size) + size = field->size + field->offset; + } + + return size; +} + +static void *trace_alloc_entry(struct trace_event_call *call, int *size) +{ + int entry_size = trace_get_entry_size(call); + struct ftrace_event_field *field; + struct list_head *head; + void *entry = NULL; + + /* We need an extra '\0' at the end. */ + entry = kzalloc(entry_size + 1, GFP_KERNEL); + if (!entry) + return NULL; + + head = trace_get_fields(call); + list_for_each_entry(field, head, link) { + if (!is_string_field(field)) + continue; + if (field->filter_type == FILTER_STATIC_STRING) + continue; + if (field->filter_type == FILTER_DYN_STRING) { + u32 *str_item; + int str_loc = entry_size & 0xffff; + + str_item = (u32 *)(entry + field->offset); + *str_item = str_loc; /* string length is 0. */ + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = ""; + } + } + + *size = entry_size + 1; + return entry; +} + +#define INJECT_STRING "STATIC STRING CAN NOT BE INJECTED" + +/* Caller is responsible to free the *pentry. */ +static int parse_entry(char *str, struct trace_event_call *call, void **pentry) +{ + struct ftrace_event_field *field; + unsigned long irq_flags; + void *entry = NULL; + int entry_size; + u64 val = 0; + int len; + + entry = trace_alloc_entry(call, &entry_size); + *pentry = entry; + if (!entry) + return -ENOMEM; + + local_save_flags(irq_flags); + tracing_generic_entry_update(entry, call->event.type, irq_flags, + preempt_count()); + + while ((len = parse_field(str, call, &field, &val)) > 0) { + if (is_function_field(field)) + return -EINVAL; + + if (is_string_field(field)) { + char *addr = (char *)(unsigned long) val; + + if (field->filter_type == FILTER_STATIC_STRING) { + strlcpy(entry + field->offset, addr, field->size); + } else if (field->filter_type == FILTER_DYN_STRING) { + int str_len = strlen(addr) + 1; + int str_loc = entry_size & 0xffff; + u32 *str_item; + + entry_size += str_len; + *pentry = krealloc(entry, entry_size, GFP_KERNEL); + if (!*pentry) { + kfree(entry); + return -ENOMEM; + } + entry = *pentry; + + strlcpy(entry + (entry_size - str_len), addr, str_len); + str_item = (u32 *)(entry + field->offset); + *str_item = (str_len << 16) | str_loc; + } else { + char **paddr; + + paddr = (char **)(entry + field->offset); + *paddr = INJECT_STRING; + } + } else { + switch (field->size) { + case 1: { + u8 tmp = (u8) val; + + memcpy(entry + field->offset, &tmp, 1); + break; + } + case 2: { + u16 tmp = (u16) val; + + memcpy(entry + field->offset, &tmp, 2); + break; + } + case 4: { + u32 tmp = (u32) val; + + memcpy(entry + field->offset, &tmp, 4); + break; + } + case 8: + memcpy(entry + field->offset, &val, 8); + break; + default: + return -EINVAL; + } + } + + str += len; + } + + if (len < 0) + return len; + + return entry_size; +} + +static ssize_t +event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt, + loff_t *ppos) +{ + struct trace_event_call *call; + struct trace_event_file *file; + int err = -ENODEV, size; + void *entry = NULL; + char *buf; + + if (cnt >= PAGE_SIZE) + return -EINVAL; + + buf = memdup_user_nul(ubuf, cnt); + if (IS_ERR(buf)) + return PTR_ERR(buf); + strim(buf); + + mutex_lock(&event_mutex); + file = event_file_data(filp); + if (file) { + call = file->event_call; + size = parse_entry(buf, call, &entry); + if (size < 0) + err = size; + else + err = trace_inject_entry(file, entry, size); + } + mutex_unlock(&event_mutex); + + kfree(entry); + kfree(buf); + + if (err < 0) + return err; + + *ppos += err; + return cnt; +} + +static ssize_t +event_inject_read(struct file *file, char __user *buf, size_t size, + loff_t *ppos) +{ + return -EPERM; +} + +const struct file_operations event_inject_fops = { + .open = tracing_open_generic, + .read = event_inject_read, + .write = event_inject_write, +}; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2a2912cb4533..dd34a1b46a86 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -5,6 +5,7 @@ * Copyright (C) 2013 Tom Zanussi <tom.zanussi@linux.intel.com> */ +#include <linux/security.h> #include <linux/module.h> #include <linux/ctype.h> #include <linux/mutex.h> @@ -115,9 +116,10 @@ static void *trigger_next(struct seq_file *m, void *t, loff_t *pos) { struct trace_event_file *event_file = event_file_data(m->private); - if (t == SHOW_AVAILABLE_TRIGGERS) + if (t == SHOW_AVAILABLE_TRIGGERS) { + (*pos)++; return NULL; - + } return seq_list_next(t, &event_file->triggers, pos); } @@ -173,7 +175,11 @@ static const struct seq_operations event_triggers_seq_ops = { static int event_trigger_regex_open(struct inode *inode, struct file *file) { - int ret = 0; + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; mutex_lock(&event_mutex); @@ -208,7 +214,7 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file) return ret; } -static int trigger_process_regex(struct trace_event_file *file, char *buff) +int trigger_process_regex(struct trace_event_file *file, char *buff) { char *command, *next = buff; struct event_command *p; @@ -292,6 +298,7 @@ event_trigger_write(struct file *filp, const char __user *ubuf, static int event_trigger_open(struct inode *inode, struct file *filp) { + /* Checks for tracefs lockdown */ return event_trigger_regex_open(inode, filp); } @@ -495,7 +502,9 @@ void update_cond_flag(struct trace_event_file *file) struct event_trigger_data *data; bool set_cond = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->filter || event_command_post_trigger(data->cmd_ops) || event_command_needs_rec(data->cmd_ops)) { set_cond = true; @@ -530,7 +539,9 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) { ret = -EEXIST; goto out; @@ -575,7 +586,9 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { unregistered = true; list_del_rcu(&data->list); @@ -1491,7 +1504,9 @@ int event_enable_register_trigger(char *glob, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { test_enable_data = test->private_data; if (test_enable_data && (test->cmd_ops->trigger_type == @@ -1531,7 +1546,9 @@ void event_enable_unregister_trigger(char *glob, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { enable_data = data->private_data; if (enable_data && (data->cmd_ops->trigger_type == diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 45630a76ed3a..77ce5a3b6773 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -29,10 +29,8 @@ static int ftrace_event_register(struct trace_event_call *call, * function and thus become accesible via perf. */ #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) /* not needed for this file */ #undef __field_struct @@ -41,6 +39,9 @@ static int ftrace_event_register(struct trace_event_call *call, #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_desc #define __field_desc(type, container, item) type item; @@ -60,7 +61,7 @@ static int ftrace_event_register(struct trace_event_call *call, #define F_printk(fmt, args...) fmt, args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct ____ftrace_##name { \ tstruct \ }; \ @@ -73,76 +74,46 @@ static void __always_unused ____ftrace_check_##name(void) \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" +#undef __field_ext +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = _filter_type }, + #undef __field -#define __field(type, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER) + +#undef __field_fn +#define __field_fn(_type, _item) __field_ext(_type, _item, FILTER_TRACE_FN) #undef __field_desc -#define __field_desc(type, container, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER) #undef __array -#define __array(type, item, len) \ - do { \ - char *type_str = #type"["__stringify(len)"]"; \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, type_str, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; \ - } while (0); +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef __array_desc -#define __array_desc(type, container, item, len) \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len) #undef __dynamic_array -#define __dynamic_array(type, item) \ - ret = trace_define_field(event_call, #type "[]", #item, \ - offsetof(typeof(field), item), \ - 0, is_signed_type(type), filter_type);\ - if (ret) \ - return ret; +#define __dynamic_array(_type, _item) { \ + .type = #_type "[]", .name = #_item, \ + .size = 0, .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ -static int __init \ -ftrace_define_fields_##name(struct trace_event_call *event_call) \ -{ \ - struct struct_name field; \ - int ret; \ - int filter_type = filter; \ - \ - tstruct; \ - \ - return ret; \ -} +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +static struct trace_event_fields ftrace_event_fields_##name[] = { \ + tstruct \ + {} }; #include "trace_entries.h" @@ -152,6 +123,9 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #undef __field #define __field(type, item) +#undef __field_fn +#define __field_fn(type, item) + #undef __field_desc #define __field_desc(type, container, item) @@ -168,12 +142,10 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ - regfn) \ - \ -struct trace_event_class __refdata event_class_ftrace_##call = { \ +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn) \ +static struct trace_event_class __refdata event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ - .define_fields = ftrace_define_fields_##call, \ + .fields_array = ftrace_event_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ .reg = regfn, \ }; \ @@ -187,13 +159,13 @@ struct trace_event_call __used event_##call = { \ .print_fmt = print, \ .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ }; \ -struct trace_event_call __used \ +static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ FTRACE_ENTRY_REG(call, struct_name, etype, \ - PARAMS(tstruct), PARAMS(print), filter, NULL) + PARAMS(tstruct), PARAMS(print), NULL) bool ftrace_event_is_function(struct trace_event_call *call) { diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index b611cd36e22d..8a4c8d5c2c98 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -101,7 +101,7 @@ static int function_trace_init(struct trace_array *tr) ftrace_init_array_ops(tr, func); - tr->trace_buffer.cpu = get_cpu(); + tr->array_buffer.cpu = get_cpu(); put_cpu(); tracing_start_cmdline_record(); @@ -118,7 +118,7 @@ static void function_trace_reset(struct trace_array *tr) static void function_trace_start(struct trace_array *tr) { - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); } static void @@ -143,7 +143,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, goto out; cpu = smp_processor_id(); - data = per_cpu_ptr(tr->trace_buffer.data, cpu); + data = per_cpu_ptr(tr->array_buffer.data, cpu); if (!atomic_read(&data->disabled)) { local_save_flags(flags); trace_function(tr, ip, parent_ip, flags, pc); @@ -192,7 +192,7 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip, */ local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->trace_buffer.data, cpu); + data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 78af97163147..7d71546ba00a 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -101,7 +101,7 @@ int __trace_graph_entry(struct trace_array *tr, { struct trace_event_call *call = &event_funcgraph_entry; struct ring_buffer_event *event; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ftrace_graph_ent_entry *entry; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, @@ -171,7 +171,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->trace_buffer.data, cpu); + data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); @@ -221,7 +221,7 @@ void __trace_graph_return(struct trace_array *tr, { struct trace_event_call *call = &event_funcgraph_exit; struct ring_buffer_event *event; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ftrace_graph_ret_entry *entry; event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, @@ -252,7 +252,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace) local_irq_save(flags); cpu = raw_smp_processor_id(); - data = per_cpu_ptr(tr->trace_buffer.data, cpu); + data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { pc = preempt_count(); @@ -444,9 +444,9 @@ get_return_for_leaf(struct trace_iterator *iter, * We need to consume the current entry to see * the next one. */ - ring_buffer_consume(iter->trace_buffer->buffer, iter->cpu, + ring_buffer_consume(iter->array_buffer->buffer, iter->cpu, NULL, NULL); - event = ring_buffer_peek(iter->trace_buffer->buffer, iter->cpu, + event = ring_buffer_peek(iter->array_buffer->buffer, iter->cpu, NULL, NULL); } @@ -503,7 +503,7 @@ print_graph_rel_time(struct trace_iterator *iter, struct trace_seq *s) { unsigned long long usecs; - usecs = iter->ts - iter->trace_buffer->time_start; + usecs = iter->ts - iter->array_buffer->time_start; do_div(usecs, NSEC_PER_USEC); trace_seq_printf(s, "%9llu us | ", usecs); diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index fa95139445b2..a48808c43249 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * trace_hwlatdetect.c - A simple Hardware Latency detector. + * trace_hwlat.c - A simple Hardware Latency detector. * * Use this tracer to detect large system latencies induced by the behavior of * certain underlying system hardware or firmware, independent of Linux itself. @@ -104,7 +104,7 @@ static void trace_hwlat_sample(struct hwlat_sample *sample) { struct trace_array *tr = hwlat_trace; struct trace_event_call *call = &event_hwlat; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct hwlat_entry *entry; unsigned long flags; @@ -150,7 +150,7 @@ void trace_hwlat_callback(bool enter) if (enter) nmi_ts_start = time_get(); else - nmi_total_ts = time_get() - nmi_ts_start; + nmi_total_ts += time_get() - nmi_ts_start; } if (enter) @@ -237,6 +237,7 @@ static int get_sample(void) /* If we exceed the threshold value, we have found a hardware latency */ if (sample > thresh || outer_sample > thresh) { struct hwlat_sample s; + u64 latency; ret = 1; @@ -253,9 +254,13 @@ static int get_sample(void) s.nmi_count = nmi_count; trace_hwlat_sample(&s); + latency = max(sample, outer_sample); + /* Keep a running maximum ever recorded hardware latency */ - if (sample > tr->max_latency) - tr->max_latency = sample; + if (latency > tr->max_latency) { + tr->max_latency = latency; + latency_fsnotify(tr); + } } out: @@ -274,7 +279,7 @@ static void move_to_next_cpu(void) return; /* * If for some reason the user modifies the CPU affinity - * of this thread, than stop migrating for the duration + * of this thread, then stop migrating for the duration * of the current test. */ if (!cpumask_equal(current_mask, current->cpus_ptr)) @@ -551,7 +556,7 @@ static int init_tracefs(void) return 0; err: - tracefs_remove_recursive(top_dir); + tracefs_remove(top_dir); return -ENOMEM; } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index a745b0cee5d3..10bbb0f381d5 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -122,7 +122,7 @@ static int func_prolog_dec(struct trace_array *tr, if (!irqs_disabled_flags(*flags) && !preempt_count()) return 0; - *data = per_cpu_ptr(tr->trace_buffer.data, cpu); + *data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (likely(disabled == 1)) @@ -167,7 +167,7 @@ static int irqsoff_display_graph(struct trace_array *tr, int set) per_cpu(tracing_cpu, cpu) = 0; tr->max_latency = 0; - tracing_reset_online_cpus(&irqsoff_trace->trace_buffer); + tracing_reset_online_cpus(&irqsoff_trace->array_buffer); return start_irqsoff_tracer(irqsoff_trace, set); } @@ -382,7 +382,7 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) if (per_cpu(tracing_cpu, cpu)) return; - data = per_cpu_ptr(tr->trace_buffer.data, cpu); + data = per_cpu_ptr(tr->array_buffer.data, cpu); if (unlikely(!data) || atomic_read(&data->disabled)) return; @@ -420,7 +420,7 @@ stop_critical_timing(unsigned long ip, unsigned long parent_ip, int pc) if (!tracer_enabled || !tracing_is_enabled()) return; - data = per_cpu_ptr(tr->trace_buffer.data, cpu); + data = per_cpu_ptr(tr->array_buffer.data, cpu); if (unlikely(!data) || !data->critical_start || atomic_read(&data->disabled)) diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index cca65044c14c..9da76104f7a2 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -43,7 +43,7 @@ static void ftrace_dump_buf(int skip_entries, long cpu_file) if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter.buffer_iter[cpu] = - ring_buffer_read_prepare(iter.trace_buffer->buffer, + ring_buffer_read_prepare(iter.array_buffer->buffer, cpu, GFP_ATOMIC); ring_buffer_read_start(iter.buffer_iter[cpu]); tracing_iter_reset(&iter, cpu); @@ -51,7 +51,7 @@ static void ftrace_dump_buf(int skip_entries, long cpu_file) } else { iter.cpu_file = cpu_file; iter.buffer_iter[cpu_file] = - ring_buffer_read_prepare(iter.trace_buffer->buffer, + ring_buffer_read_prepare(iter.array_buffer->buffer, cpu_file, GFP_ATOMIC); ring_buffer_read_start(iter.buffer_iter[cpu_file]); tracing_iter_reset(&iter, cpu_file); @@ -124,7 +124,7 @@ static int kdb_ftdump(int argc, const char **argv) iter.buffer_iter = buffer_iter; for_each_tracing_cpu(cpu) { - atomic_inc(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); + atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); } /* A negative skip_entries means skip all but the last entries */ @@ -139,7 +139,7 @@ static int kdb_ftdump(int argc, const char **argv) ftrace_dump_buf(skip_entries, cpu_file); for_each_tracing_cpu(cpu) { - atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); } kdb_trap_printk--; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 9d483ad9bb6c..362cca52f5de 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_kprobe: " fmt +#include <linux/security.h> #include <linux/module.h> #include <linux/uaccess.h> #include <linux/rculist.h> @@ -21,7 +22,6 @@ #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; @@ -39,7 +39,7 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_kprobe_release(struct dyn_event *ev); static bool trace_kprobe_is_busy(struct dyn_event *ev); static bool trace_kprobe_match(const char *system, const char *event, - struct dyn_event *ev); + int argc, const char **argv, struct dyn_event *ev); static struct dyn_event_operations trace_kprobe_ops = { .create = trace_kprobe_create, @@ -137,13 +137,36 @@ static bool trace_kprobe_is_busy(struct dyn_event *ev) return trace_probe_is_enabled(&tk->tp); } +static bool trace_kprobe_match_command_head(struct trace_kprobe *tk, + int argc, const char **argv) +{ + char buf[MAX_ARGSTR_LEN + 1]; + + if (!argc) + return true; + + if (!tk->symbol) + snprintf(buf, sizeof(buf), "0x%p", tk->rp.kp.addr); + else if (tk->rp.kp.offset) + snprintf(buf, sizeof(buf), "%s+%u", + trace_kprobe_symbol(tk), tk->rp.kp.offset); + else + snprintf(buf, sizeof(buf), "%s", trace_kprobe_symbol(tk)); + if (strcmp(buf, argv[0])) + return false; + argc--; argv++; + + return trace_probe_match_command_args(&tk->tp, argc, argv); +} + static bool trace_kprobe_match(const char *system, const char *event, - struct dyn_event *ev) + int argc, const char **argv, struct dyn_event *ev) { struct trace_kprobe *tk = to_trace_kprobe(ev); return strcmp(trace_probe_name(&tk->tp), event) == 0 && - (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0); + (!system || strcmp(trace_probe_group_name(&tk->tp), system) == 0) && + trace_kprobe_match_command_head(tk, argc, argv); } static nokprobe_inline unsigned long trace_kprobe_nhit(struct trace_kprobe *tk) @@ -180,20 +203,33 @@ unsigned long trace_kprobe_address(struct trace_kprobe *tk) return addr; } +static nokprobe_inline struct trace_kprobe * +trace_kprobe_primary_from_call(struct trace_event_call *call) +{ + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return NULL; + + return container_of(tp, struct trace_kprobe, tp); +} + bool trace_kprobe_on_func_entry(struct trace_event_call *call) { - struct trace_kprobe *tk = (struct trace_kprobe *)call->data; + struct trace_kprobe *tk = trace_kprobe_primary_from_call(call); - return kprobe_on_func_entry(tk->rp.kp.addr, + return tk ? kprobe_on_func_entry(tk->rp.kp.addr, tk->rp.kp.addr ? NULL : tk->rp.kp.symbol_name, - tk->rp.kp.addr ? 0 : tk->rp.kp.offset); + tk->rp.kp.addr ? 0 : tk->rp.kp.offset) : false; } bool trace_kprobe_error_injectable(struct trace_event_call *call) { - struct trace_kprobe *tk = (struct trace_kprobe *)call->data; + struct trace_kprobe *tk = trace_kprobe_primary_from_call(call); - return within_error_injection_list(trace_kprobe_address(tk)); + return tk ? within_error_injection_list(trace_kprobe_address(tk)) : + false; } static int register_kprobe_event(struct trace_kprobe *tk); @@ -253,7 +289,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group); + ret = trace_probe_init(&tk->tp, event, group, false); if (ret < 0) goto error; @@ -291,32 +327,68 @@ static inline int __enable_trace_kprobe(struct trace_kprobe *tk) return ret; } +static void __disable_trace_kprobe(struct trace_probe *tp) +{ + struct trace_probe *pos; + struct trace_kprobe *tk; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tk = container_of(pos, struct trace_kprobe, tp); + if (!trace_kprobe_is_registered(tk)) + continue; + if (trace_kprobe_is_return(tk)) + disable_kretprobe(&tk->rp); + else + disable_kprobe(&tk->rp.kp); + } +} + /* * Enable trace_probe * if the file is NULL, enable "perf" handler, or enable "trace" handler. */ -static int -enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) +static int enable_trace_kprobe(struct trace_event_call *call, + struct trace_event_file *file) { - bool enabled = trace_probe_is_enabled(&tk->tp); + struct trace_probe *pos, *tp; + struct trace_kprobe *tk; + bool enabled; int ret = 0; + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + enabled = trace_probe_is_enabled(tp); + + /* This also changes "enabled" state */ if (file) { - ret = trace_probe_add_file(&tk->tp, file); + ret = trace_probe_add_file(tp, file); if (ret) return ret; } else - trace_probe_set_flag(&tk->tp, TP_FLAG_PROFILE); + trace_probe_set_flag(tp, TP_FLAG_PROFILE); if (enabled) return 0; - ret = __enable_trace_kprobe(tk); + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tk = container_of(pos, struct trace_kprobe, tp); + if (trace_kprobe_has_gone(tk)) + continue; + ret = __enable_trace_kprobe(tk); + if (ret) + break; + enabled = true; + } + if (ret) { + /* Failed to enable one of them. Roll back all */ + if (enabled) + __disable_trace_kprobe(tp); if (file) - trace_probe_remove_file(&tk->tp, file); + trace_probe_remove_file(tp, file); else - trace_probe_clear_flag(&tk->tp, TP_FLAG_PROFILE); + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); } return ret; @@ -326,11 +398,14 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) * Disable trace_probe * if the file is NULL, disable "perf" handler, or disable "trace" handler. */ -static int -disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) +static int disable_trace_kprobe(struct trace_event_call *call, + struct trace_event_file *file) { - struct trace_probe *tp = &tk->tp; - int ret = 0; + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; if (file) { if (!trace_probe_get_file_link(tp, file)) @@ -341,12 +416,8 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) } else trace_probe_clear_flag(tp, TP_FLAG_PROFILE); - if (!trace_probe_is_enabled(tp) && trace_kprobe_is_registered(tk)) { - if (trace_kprobe_is_return(tk)) - disable_kretprobe(&tk->rp); - else - disable_kprobe(&tk->rp.kp); - } + if (!trace_probe_is_enabled(tp)) + __disable_trace_kprobe(tp); out: if (file) @@ -358,16 +429,15 @@ disable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) */ trace_probe_remove_file(tp, file); - return ret; + return 0; } #if defined(CONFIG_KPROBES_ON_FTRACE) && \ !defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE) -static bool within_notrace_func(struct trace_kprobe *tk) +static bool __within_notrace_func(unsigned long addr) { - unsigned long offset, size, addr; + unsigned long offset, size; - addr = trace_kprobe_address(tk); if (!addr || !kallsyms_lookup_size_offset(addr, &size, &offset)) return false; @@ -380,6 +450,28 @@ static bool within_notrace_func(struct trace_kprobe *tk) */ return !ftrace_location_range(addr, addr + size - 1); } + +static bool within_notrace_func(struct trace_kprobe *tk) +{ + unsigned long addr = addr = trace_kprobe_address(tk); + char symname[KSYM_NAME_LEN], *p; + + if (!__within_notrace_func(addr)) + return false; + + /* Check if the address is on a suffixed-symbol */ + if (!lookup_symbol_name(addr, symname)) { + p = strchr(symname, '.'); + if (!p) + return true; + *p = '\0'; + addr = (unsigned long)kprobe_lookup_name(symname, 0); + if (addr) + return __within_notrace_func(addr); + } + + return true; +} #else #define within_notrace_func(tk) (false) #endif @@ -389,6 +481,10 @@ static int __register_trace_kprobe(struct trace_kprobe *tk) { int i, ret; + ret = security_locked_down(LOCKDOWN_KPROBES); + if (ret) + return ret; + if (trace_kprobe_is_registered(tk)) return -EINVAL; @@ -437,6 +533,10 @@ static void __unregister_trace_kprobe(struct trace_kprobe *tk) /* Unregister a trace_probe and probe_event */ static int unregister_trace_kprobe(struct trace_kprobe *tk) { + /* If other probes are on the event, just unregister kprobe */ + if (trace_probe_has_sibling(&tk->tp)) + goto unreg; + /* Enabled event can not be unregistered */ if (trace_probe_is_enabled(&tk->tp)) return -EBUSY; @@ -445,12 +545,82 @@ static int unregister_trace_kprobe(struct trace_kprobe *tk) if (unregister_kprobe_event(tk)) return -EBUSY; +unreg: __unregister_trace_kprobe(tk); dyn_event_remove(&tk->devent); + trace_probe_unlink(&tk->tp); return 0; } +static bool trace_kprobe_has_same_kprobe(struct trace_kprobe *orig, + struct trace_kprobe *comp) +{ + struct trace_probe_event *tpe = orig->tp.event; + struct trace_probe *pos; + int i; + + list_for_each_entry(pos, &tpe->probes, list) { + orig = container_of(pos, struct trace_kprobe, tp); + if (strcmp(trace_kprobe_symbol(orig), + trace_kprobe_symbol(comp)) || + trace_kprobe_offset(orig) != trace_kprobe_offset(comp)) + continue; + + /* + * trace_probe_compare_arg_type() ensured that nr_args and + * each argument name and type are same. Let's compare comm. + */ + for (i = 0; i < orig->tp.nr_args; i++) { + if (strcmp(orig->tp.args[i].comm, + comp->tp.args[i].comm)) + break; + } + + if (i == orig->tp.nr_args) + return true; + } + + return false; +} + +static int append_trace_kprobe(struct trace_kprobe *tk, struct trace_kprobe *to) +{ + int ret; + + ret = trace_probe_compare_arg_type(&tk->tp, &to->tp); + if (ret) { + /* Note that argument starts index = 2 */ + trace_probe_log_set_index(ret + 1); + trace_probe_log_err(0, DIFF_ARG_TYPE); + return -EEXIST; + } + if (trace_kprobe_has_same_kprobe(to, tk)) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, SAME_PROBE); + return -EEXIST; + } + + /* Append to existing event */ + ret = trace_probe_append(&tk->tp, &to->tp); + if (ret) + return ret; + + /* Register k*probe */ + ret = __register_trace_kprobe(tk); + if (ret == -ENOENT && !trace_kprobe_module_exist(tk)) { + pr_warn("This probe might be able to register after target module is loaded. Continue.\n"); + ret = 0; + } + + if (ret) + trace_probe_unlink(&tk->tp); + else + dyn_event_add(&tk->devent); + + return ret; +} + /* Register a trace_probe and probe_event */ static int register_trace_kprobe(struct trace_kprobe *tk) { @@ -459,14 +629,17 @@ static int register_trace_kprobe(struct trace_kprobe *tk) mutex_lock(&event_mutex); - /* Delete old (same name) event if exist */ old_tk = find_trace_kprobe(trace_probe_name(&tk->tp), trace_probe_group_name(&tk->tp)); if (old_tk) { - ret = unregister_trace_kprobe(old_tk); - if (ret < 0) - goto end; - free_trace_kprobe(old_tk); + if (trace_kprobe_is_return(tk) != trace_kprobe_is_return(old_tk)) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, DIFF_PROBE_TYPE); + ret = -EEXIST; + } else { + ret = append_trace_kprobe(tk, old_tk); + } + goto end; } /* Register new event */ @@ -700,7 +873,7 @@ static int trace_kprobe_create(int argc, const char *argv[]) trace_probe_log_err(0, BAD_INSN_BNDRY); else if (ret == -ENOENT) trace_probe_log_err(0, BAD_PROBE_ADDR); - else if (ret != -ENOMEM) + else if (ret != -ENOMEM && ret != -EEXIST) trace_probe_log_err(0, FAIL_REG_PROBE); goto error; } @@ -728,6 +901,167 @@ static int create_or_delete_trace_kprobe(int argc, char **argv) return ret == -ECANCELED ? -EINVAL : ret; } +static int trace_kprobe_run_command(struct dynevent_cmd *cmd) +{ + return trace_run_command(cmd->seq.buffer, create_or_delete_trace_kprobe); +} + +/** + * kprobe_event_cmd_init - Initialize a kprobe event command object + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @buf: A pointer to the buffer used to build the command + * @maxlen: The length of the buffer passed in @buf + * + * Initialize a synthetic event command object. Use this before + * calling any of the other kprobe_event functions. + */ +void kprobe_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen) +{ + dynevent_cmd_init(cmd, buf, maxlen, DYNEVENT_TYPE_KPROBE, + trace_kprobe_run_command); +} +EXPORT_SYMBOL_GPL(kprobe_event_cmd_init); + +/** + * __kprobe_event_gen_cmd_start - Generate a kprobe event command from arg list + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @name: The name of the kprobe event + * @loc: The location of the kprobe event + * @kretprobe: Is this a return probe? + * @args: Variable number of arg (pairs), one pair for each field + * + * NOTE: Users normally won't want to call this function directly, but + * rather use the kprobe_event_gen_cmd_start() wrapper, which automatically + * adds a NULL to the end of the arg list. If this function is used + * directly, make sure the last arg in the variable arg list is NULL. + * + * Generate a kprobe event command to be executed by + * kprobe_event_gen_cmd_end(). This function can be used to generate the + * complete command or only the first part of it; in the latter case, + * kprobe_event_add_fields() can be used to add more fields following this. + * + * Return: 0 if successful, error otherwise. + */ +int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, + const char *name, const char *loc, ...) +{ + char buf[MAX_EVENT_NAME_LEN]; + struct dynevent_arg arg; + va_list args; + int ret; + + if (cmd->type != DYNEVENT_TYPE_KPROBE) + return -EINVAL; + + if (kretprobe) + snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name); + else + snprintf(buf, MAX_EVENT_NAME_LEN, "p:kprobes/%s", name); + + ret = dynevent_str_add(cmd, buf); + if (ret) + return ret; + + dynevent_arg_init(&arg, 0); + arg.str = loc; + ret = dynevent_arg_add(cmd, &arg, NULL); + if (ret) + return ret; + + va_start(args, loc); + for (;;) { + const char *field; + + field = va_arg(args, const char *); + if (!field) + break; + + if (++cmd->n_fields > MAX_TRACE_ARGS) { + ret = -EINVAL; + break; + } + + arg.str = field; + ret = dynevent_arg_add(cmd, &arg, NULL); + if (ret) + break; + } + va_end(args); + + return ret; +} +EXPORT_SYMBOL_GPL(__kprobe_event_gen_cmd_start); + +/** + * __kprobe_event_add_fields - Add probe fields to a kprobe command from arg list + * @cmd: A pointer to the dynevent_cmd struct representing the new event + * @args: Variable number of arg (pairs), one pair for each field + * + * NOTE: Users normally won't want to call this function directly, but + * rather use the kprobe_event_add_fields() wrapper, which + * automatically adds a NULL to the end of the arg list. If this + * function is used directly, make sure the last arg in the variable + * arg list is NULL. + * + * Add probe fields to an existing kprobe command using a variable + * list of args. Fields are added in the same order they're listed. + * + * Return: 0 if successful, error otherwise. + */ +int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...) +{ + struct dynevent_arg arg; + va_list args; + int ret = 0; + + if (cmd->type != DYNEVENT_TYPE_KPROBE) + return -EINVAL; + + dynevent_arg_init(&arg, 0); + + va_start(args, cmd); + for (;;) { + const char *field; + + field = va_arg(args, const char *); + if (!field) + break; + + if (++cmd->n_fields > MAX_TRACE_ARGS) { + ret = -EINVAL; + break; + } + + arg.str = field; + ret = dynevent_arg_add(cmd, &arg, NULL); + if (ret) + break; + } + va_end(args); + + return ret; +} +EXPORT_SYMBOL_GPL(__kprobe_event_add_fields); + +/** + * kprobe_event_delete - Delete a kprobe event + * @name: The name of the kprobe event to delete + * + * Delete a kprobe event with the give @name from kernel code rather + * than directly from the command line. + * + * Return: 0 if successful, error otherwise. + */ +int kprobe_event_delete(const char *name) +{ + char buf[MAX_EVENT_NAME_LEN]; + + snprintf(buf, MAX_EVENT_NAME_LEN, "-:%s", name); + + return trace_run_command(buf, create_or_delete_trace_kprobe); +} +EXPORT_SYMBOL_GPL(kprobe_event_delete); + static int trace_kprobe_release(struct dyn_event *ev) { struct trace_kprobe *tk = to_trace_kprobe(ev); @@ -783,6 +1117,10 @@ static int probes_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_kprobe_ops); if (ret < 0) @@ -835,6 +1173,12 @@ static const struct seq_operations profile_seq_op = { static int profile_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &profile_seq_op); } @@ -965,6 +1309,9 @@ retry: case FETCH_OP_COMM: val = (unsigned long)current->comm; break; + case FETCH_OP_DATA: + val = (unsigned long)code->data; + break; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API case FETCH_OP_ARG: val = regs_get_kernel_argument(regs, code->param); @@ -988,35 +1335,35 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, struct trace_event_file *trace_file) { struct kprobe_trace_entry_head *entry; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - int size, dsize, pc; - unsigned long irq_flags; struct trace_event_call *call = trace_probe_event_call(&tk->tp); + struct trace_event_buffer fbuffer; + int dsize; WARN_ON(call != trace_file->event_call); if (trace_trigger_soft_disabled(trace_file)) return; - local_save_flags(irq_flags); - pc = preempt_count(); + local_save_flags(fbuffer.flags); + fbuffer.pc = preempt_count(); + fbuffer.trace_file = trace_file; dsize = __get_data_size(&tk->tp, regs); - size = sizeof(*entry) + tk->tp.size + dsize; - event = trace_event_buffer_lock_reserve(&buffer, trace_file, - call->event.type, - size, irq_flags, pc); - if (!event) + fbuffer.event = + trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file, + call->event.type, + sizeof(*entry) + tk->tp.size + dsize, + fbuffer.flags, fbuffer.pc); + if (!fbuffer.event) return; - entry = ring_buffer_event_data(event); + fbuffer.regs = regs; + entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->ip = (unsigned long)tk->rp.kp.addr; store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); - event_trigger_unlock_commit_regs(trace_file, buffer, event, - entry, irq_flags, pc, regs); + trace_event_buffer_commit(&fbuffer); } static void @@ -1036,36 +1383,35 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct trace_event_file *trace_file) { struct kretprobe_trace_entry_head *entry; - struct ring_buffer_event *event; - struct ring_buffer *buffer; - int size, pc, dsize; - unsigned long irq_flags; + struct trace_event_buffer fbuffer; struct trace_event_call *call = trace_probe_event_call(&tk->tp); + int dsize; WARN_ON(call != trace_file->event_call); if (trace_trigger_soft_disabled(trace_file)) return; - local_save_flags(irq_flags); - pc = preempt_count(); + local_save_flags(fbuffer.flags); + fbuffer.pc = preempt_count(); + fbuffer.trace_file = trace_file; dsize = __get_data_size(&tk->tp, regs); - size = sizeof(*entry) + tk->tp.size + dsize; - - event = trace_event_buffer_lock_reserve(&buffer, trace_file, - call->event.type, - size, irq_flags, pc); - if (!event) + fbuffer.event = + trace_event_buffer_lock_reserve(&fbuffer.buffer, trace_file, + call->event.type, + sizeof(*entry) + tk->tp.size + dsize, + fbuffer.flags, fbuffer.pc); + if (!fbuffer.event) return; - entry = ring_buffer_event_data(event); + fbuffer.regs = regs; + entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = (unsigned long)ri->ret_addr; store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); - event_trigger_unlock_commit_regs(trace_file, buffer, event, - entry, irq_flags, pc, regs); + trace_event_buffer_commit(&fbuffer); } static void @@ -1089,7 +1435,10 @@ print_kprobe_event(struct trace_iterator *iter, int flags, struct trace_probe *tp; field = (struct kprobe_trace_entry_head *)iter->ent; - tp = container_of(event, struct trace_probe, call.event); + tp = trace_probe_primary_from_call( + container_of(event, struct trace_event_call, event)); + if (WARN_ON_ONCE(!tp)) + goto out; trace_seq_printf(s, "%s: (", trace_probe_name(tp)); @@ -1116,7 +1465,10 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, struct trace_probe *tp; field = (struct kretprobe_trace_entry_head *)iter->ent; - tp = container_of(event, struct trace_probe, call.event); + tp = trace_probe_primary_from_call( + container_of(event, struct trace_event_call, event)); + if (WARN_ON_ONCE(!tp)) + goto out; trace_seq_printf(s, "%s: (", trace_probe_name(tp)); @@ -1145,23 +1497,31 @@ static int kprobe_event_define_fields(struct trace_event_call *event_call) { int ret; struct kprobe_trace_entry_head field; - struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data; + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(event_call); + if (WARN_ON_ONCE(!tp)) + return -ENOENT; DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0); - return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp); + return traceprobe_define_arg_fields(event_call, sizeof(field), tp); } static int kretprobe_event_define_fields(struct trace_event_call *event_call) { int ret; struct kretprobe_trace_entry_head field; - struct trace_kprobe *tk = (struct trace_kprobe *)event_call->data; + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(event_call); + if (WARN_ON_ONCE(!tp)) + return -ENOENT; DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0); DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0); - return traceprobe_define_arg_fields(event_call, sizeof(field), &tk->tp); + return traceprobe_define_arg_fields(event_call, sizeof(field), tp); } #ifdef CONFIG_PERF_EVENTS @@ -1289,20 +1649,19 @@ int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, static int kprobe_register(struct trace_event_call *event, enum trace_reg type, void *data) { - struct trace_kprobe *tk = (struct trace_kprobe *)event->data; struct trace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: - return enable_trace_kprobe(tk, file); + return enable_trace_kprobe(event, file); case TRACE_REG_UNREGISTER: - return disable_trace_kprobe(tk, file); + return disable_trace_kprobe(event, file); #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return enable_trace_kprobe(tk, NULL); + return enable_trace_kprobe(event, NULL); case TRACE_REG_PERF_UNREGISTER: - return disable_trace_kprobe(tk, NULL); + return disable_trace_kprobe(event, NULL); case TRACE_REG_PERF_OPEN: case TRACE_REG_PERF_CLOSE: case TRACE_REG_PERF_ADD: @@ -1355,21 +1714,32 @@ static struct trace_event_functions kprobe_funcs = { .trace = print_kprobe_event }; +static struct trace_event_fields kretprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kretprobe_event_define_fields }, + {} +}; + +static struct trace_event_fields kprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_kprobe *tk) { struct trace_event_call *call = trace_probe_event_call(&tk->tp); if (trace_kprobe_is_return(tk)) { call->event.funcs = &kretprobe_funcs; - call->class->define_fields = kretprobe_event_define_fields; + call->class->fields_array = kretprobe_fields_array; } else { call->event.funcs = &kprobe_funcs; - call->class->define_fields = kprobe_event_define_fields; + call->class->fields_array = kprobe_fields_array; } call->flags = TRACE_EVENT_FL_KPROBE; call->class->reg = kprobe_register; - call->data = tk; } static int register_kprobe_event(struct trace_kprobe *tk) @@ -1432,7 +1802,9 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call) { struct trace_kprobe *tk; - tk = container_of(event_call, struct trace_kprobe, tp.call); + tk = trace_kprobe_primary_from_call(event_call); + if (unlikely(!tk)) + return; if (trace_probe_is_enabled(&tk->tp)) { WARN_ON(1); @@ -1485,11 +1857,12 @@ static __init void setup_boot_kprobe_events(void) enable_boot_kprobe_events(); } -/* Make a tracefs interface for controlling probe points */ -static __init int init_kprobe_trace(void) +/* + * Register dynevent at subsys_initcall. This allows kernel to setup kprobe + * events in fs_initcall without tracefs. + */ +static __init int init_kprobe_trace_early(void) { - struct dentry *d_tracer; - struct dentry *entry; int ret; ret = dyn_event_register(&trace_kprobe_ops); @@ -1499,6 +1872,16 @@ static __init int init_kprobe_trace(void) if (register_module_notifier(&trace_kprobe_module_nb)) return -EINVAL; + return 0; +} +subsys_initcall(init_kprobe_trace_early); + +/* Make a tracefs interface for controlling probe points */ +static __init int init_kprobe_trace(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + d_tracer = tracing_init_dentry(); if (IS_ERR(d_tracer)) return 0; @@ -1577,7 +1960,8 @@ static __init int kprobe_trace_self_tests_init(void) pr_warn("error on getting probe file.\n"); warn++; } else - enable_trace_kprobe(tk, file); + enable_trace_kprobe( + trace_probe_event_call(&tk->tp), file); } } @@ -1598,7 +1982,8 @@ static __init int kprobe_trace_self_tests_init(void) pr_warn("error on getting probe file.\n"); warn++; } else - enable_trace_kprobe(tk, file); + enable_trace_kprobe( + trace_probe_event_call(&tk->tp), file); } } @@ -1631,7 +2016,8 @@ static __init int kprobe_trace_self_tests_init(void) pr_warn("error on getting probe file.\n"); warn++; } else - disable_trace_kprobe(tk, file); + disable_trace_kprobe( + trace_probe_event_call(&tk->tp), file); } tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM); @@ -1649,7 +2035,8 @@ static __init int kprobe_trace_self_tests_init(void) pr_warn("error on getting probe file.\n"); warn++; } else - disable_trace_kprobe(tk, file); + disable_trace_kprobe( + trace_probe_event_call(&tk->tp), file); } ret = trace_run_command("-:testprobe", create_or_delete_trace_kprobe); diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index b0388016b687..84582bf1ed5f 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -32,7 +32,7 @@ static void mmio_reset_data(struct trace_array *tr) overrun_detected = false; prev_overruns = 0; - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); } static int mmio_trace_init(struct trace_array *tr) @@ -122,7 +122,7 @@ static void mmio_close(struct trace_iterator *iter) static unsigned long count_overruns(struct trace_iterator *iter) { unsigned long cnt = atomic_xchg(&dropped_count, 0); - unsigned long over = ring_buffer_overruns(iter->trace_buffer->buffer); + unsigned long over = ring_buffer_overruns(iter->array_buffer->buffer); if (over > prev_overruns) cnt += over - prev_overruns; @@ -297,7 +297,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, struct mmiotrace_rw *rw) { struct trace_event_call *call = &event_mmiotrace_rw; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_rw *entry; int pc = preempt_count(); @@ -318,7 +318,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr, void mmio_trace_rw(struct mmiotrace_rw *rw) { struct trace_array *tr = mmio_trace_array; - struct trace_array_cpu *data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); + struct trace_array_cpu *data = per_cpu_ptr(tr->array_buffer.data, smp_processor_id()); __trace_mmiotrace_rw(tr, data, rw); } @@ -327,7 +327,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr, struct mmiotrace_map *map) { struct trace_event_call *call = &event_mmiotrace_map; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct trace_mmiotrace_map *entry; int pc = preempt_count(); @@ -351,7 +351,7 @@ void mmio_trace_mapping(struct mmiotrace_map *map) struct trace_array_cpu *data; preempt_disable(); - data = per_cpu_ptr(tr->trace_buffer.data, smp_processor_id()); + data = per_cpu_ptr(tr->array_buffer.data, smp_processor_id()); __trace_mmiotrace_map(tr, data, map); preempt_enable(); } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index cab4a5398f1d..b4909082f6a4 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -219,10 +219,10 @@ trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len, { int i; const char *ret = trace_seq_buffer_ptr(p); + const char *fmt = concatenate ? "%*phN" : "%*ph"; - for (i = 0; i < buf_len; i++) - trace_seq_printf(p, "%s%2.2x", concatenate || i == 0 ? "" : " ", - buf[i]); + for (i = 0; i < buf_len; i += 16) + trace_seq_printf(p, fmt, min(buf_len - i, 16), &buf[i]); trace_seq_putc(p, 0); return ret; @@ -274,6 +274,21 @@ trace_print_array_seq(struct trace_seq *p, const void *buf, int count, } EXPORT_SYMBOL(trace_print_array_seq); +const char * +trace_print_hex_dump_seq(struct trace_seq *p, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ + const char *ret = trace_seq_buffer_ptr(p); + + trace_seq_putc(p, '\n'); + trace_seq_hex_dump(p, prefix_str, prefix_type, + rowsize, groupsize, buf, len, ascii); + trace_seq_putc(p, 0); + return ret; +} +EXPORT_SYMBOL(trace_print_hex_dump_seq); + int trace_raw_output_prep(struct trace_iterator *iter, struct trace_event *trace_event) { @@ -523,7 +538,7 @@ lat_print_timestamp(struct trace_iterator *iter, u64 next_ts) struct trace_array *tr = iter->tr; unsigned long verbose = tr->trace_flags & TRACE_ITER_VERBOSE; unsigned long in_ns = iter->iter_flags & TRACE_FILE_TIME_IN_NS; - unsigned long long abs_ts = iter->ts - iter->trace_buffer->time_start; + unsigned long long abs_ts = iter->ts - iter->array_buffer->time_start; unsigned long long rel_ts = next_ts - iter->ts; struct trace_seq *s = &iter->seq; diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index c3fd849d4a8f..d4e31e969206 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -6,6 +6,7 @@ * */ #include <linux/seq_file.h> +#include <linux/security.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/ftrace.h> @@ -348,6 +349,12 @@ static const struct seq_operations show_format_seq_ops = { static int ftrace_formats_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &show_format_seq_ops); } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index dbef0d135075..ab8b6436d53f 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -178,6 +178,16 @@ void __trace_probe_log_err(int offset, int err_type) if (!command) return; + if (trace_probe_log.index >= trace_probe_log.argc) { + /** + * Set the error position is next to the last arg + space. + * Note that len includes the terminal null and the cursor + * appaers at pos + 1. + */ + pos = len; + offset = 0; + } + /* And make a command string from argv array */ p = command; for (i = 0; i < trace_probe_log.argc; i++) { @@ -316,6 +326,29 @@ inval_var: return -EINVAL; } +static int str_to_immediate(char *str, unsigned long *imm) +{ + if (isdigit(str[0])) + return kstrtoul(str, 0, imm); + else if (str[0] == '-') + return kstrtol(str, 0, (long *)imm); + else if (str[0] == '+') + return kstrtol(str + 1, 0, (long *)imm); + return -EINVAL; +} + +static int __parse_imm_string(char *str, char **pbuf, int offs) +{ + size_t len = strlen(str); + + if (str[len - 1] != '"') { + trace_probe_log_err(offs + len, IMMSTR_NO_CLOSE); + return -EINVAL; + } + *pbuf = kstrndup(str, len - 1, GFP_KERNEL); + return 0; +} + /* Recursive argument parser */ static int parse_probe_arg(char *arg, const struct fetch_type *type, @@ -430,7 +463,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type, ret = parse_probe_arg(arg, t2, &code, end, flags, offs); if (ret) break; - if (code->op == FETCH_OP_COMM) { + if (code->op == FETCH_OP_COMM || + code->op == FETCH_OP_DATA) { trace_probe_log_err(offs, COMM_CANT_DEREF); return -EINVAL; } @@ -444,6 +478,21 @@ parse_probe_arg(char *arg, const struct fetch_type *type, code->offset = offset; } break; + case '\\': /* Immediate value */ + if (arg[1] == '"') { /* Immediate string */ + ret = __parse_imm_string(arg + 2, &tmp, offs + 2); + if (ret) + break; + code->op = FETCH_OP_DATA; + code->data = tmp; + } else { + ret = str_to_immediate(arg + 1, &code->immediate); + if (ret) + trace_probe_log_err(offs + 1, BAD_IMM); + else + code->op = FETCH_OP_IMM; + } + break; } if (!ret && code->op == FETCH_OP_NOP) { /* Parsed, but do not find fetch method */ @@ -542,8 +591,11 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, } } - /* Since $comm can not be dereferred, we can find $comm by strcmp */ - if (strcmp(arg, "$comm") == 0) { + /* + * Since $comm and immediate string can not be dereferred, + * we can find those by strcmp. + */ + if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) { /* The type of $comm must be "string", and not an array. */ if (parg->count || (t && strcmp(t, "string"))) return -EINVAL; @@ -580,7 +632,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, if (!strcmp(parg->type->name, "string") || !strcmp(parg->type->name, "ustring")) { if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF && - code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM) { + code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM && + code->op != FETCH_OP_DATA) { trace_probe_log_err(offset + (t ? (t - arg) : 0), BAD_STRING); ret = -EINVAL; @@ -589,9 +642,10 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) || parg->count) { /* - * IMM and COMM is pointing actual address, those must - * be kept, and if parg->count != 0, this is an array - * of string pointers instead of string address itself. + * IMM, DATA and COMM is pointing actual address, those + * must be kept, and if parg->count != 0, this is an + * array of string pointers instead of string address + * itself. */ code++; if (code->op != FETCH_OP_NOP) { @@ -665,7 +719,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size, fail: if (ret) { for (code = tmp; code < tmp + FETCH_INSN_MAX; code++) - if (code->op == FETCH_NOP_SYMBOL) + if (code->op == FETCH_NOP_SYMBOL || + code->op == FETCH_OP_DATA) kfree(code->data); } kfree(tmp); @@ -736,7 +791,8 @@ void traceprobe_free_probe_arg(struct probe_arg *arg) struct fetch_insn *code = arg->code; while (code && code->op != FETCH_OP_END) { - if (code->op == FETCH_NOP_SYMBOL) + if (code->op == FETCH_NOP_SYMBOL || + code->op == FETCH_OP_DATA) kfree(code->data); code++; } @@ -820,7 +876,8 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, for (i = 0; i < tp->nr_args; i++) { parg = tp->args + i; if (parg->count) { - if (strcmp(parg->type->name, "string") == 0) + if ((strcmp(parg->type->name, "string") == 0) || + (strcmp(parg->type->name, "ustring") == 0)) fmt = ", __get_str(%s[%d])"; else fmt = ", REC->%s[%d]"; @@ -828,7 +885,8 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, pos += snprintf(buf + pos, LEN_OR_ZERO, fmt, parg->name, j); } else { - if (strcmp(parg->type->name, "string") == 0) + if ((strcmp(parg->type->name, "string") == 0) || + (strcmp(parg->type->name, "ustring") == 0)) fmt = ", __get_str(%s)"; else fmt = ", REC->%s"; @@ -886,43 +944,89 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call, return 0; } +static void trace_probe_event_free(struct trace_probe_event *tpe) +{ + kfree(tpe->class.system); + kfree(tpe->call.name); + kfree(tpe->call.print_fmt); + kfree(tpe); +} + +int trace_probe_append(struct trace_probe *tp, struct trace_probe *to) +{ + if (trace_probe_has_sibling(tp)) + return -EBUSY; + + list_del_init(&tp->list); + trace_probe_event_free(tp->event); + + tp->event = to->event; + list_add_tail(&tp->list, trace_probe_probe_list(to)); + + return 0; +} + +void trace_probe_unlink(struct trace_probe *tp) +{ + list_del_init(&tp->list); + if (list_empty(trace_probe_probe_list(tp))) + trace_probe_event_free(tp->event); + tp->event = NULL; +} void trace_probe_cleanup(struct trace_probe *tp) { - struct trace_event_call *call = trace_probe_event_call(tp); int i; for (i = 0; i < tp->nr_args; i++) traceprobe_free_probe_arg(&tp->args[i]); - kfree(call->class->system); - kfree(call->name); - kfree(call->print_fmt); + if (tp->event) + trace_probe_unlink(tp); } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group) + const char *group, bool alloc_filter) { - struct trace_event_call *call = trace_probe_event_call(tp); + struct trace_event_call *call; + size_t size = sizeof(struct trace_probe_event); + int ret = 0; if (!event || !group) return -EINVAL; - call->class = &tp->class; - call->name = kstrdup(event, GFP_KERNEL); - if (!call->name) - return -ENOMEM; + if (alloc_filter) + size += sizeof(struct trace_uprobe_filter); - tp->class.system = kstrdup(group, GFP_KERNEL); - if (!tp->class.system) { - kfree(call->name); - call->name = NULL; + tp->event = kzalloc(size, GFP_KERNEL); + if (!tp->event) return -ENOMEM; + + INIT_LIST_HEAD(&tp->event->files); + INIT_LIST_HEAD(&tp->event->class.fields); + INIT_LIST_HEAD(&tp->event->probes); + INIT_LIST_HEAD(&tp->list); + list_add(&tp->event->probes, &tp->list); + + call = trace_probe_event_call(tp); + call->class = &tp->event->class; + call->name = kstrdup(event, GFP_KERNEL); + if (!call->name) { + ret = -ENOMEM; + goto error; + } + + tp->event->class.system = kstrdup(group, GFP_KERNEL); + if (!tp->event->class.system) { + ret = -ENOMEM; + goto error; } - INIT_LIST_HEAD(&tp->files); - INIT_LIST_HEAD(&tp->class.fields); return 0; + +error: + trace_probe_cleanup(tp); + return ret; } int trace_probe_register_event_call(struct trace_probe *tp) @@ -951,7 +1055,7 @@ int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file) link->file = file; INIT_LIST_HEAD(&link->list); - list_add_tail_rcu(&link->list, &tp->files); + list_add_tail_rcu(&link->list, &tp->event->files); trace_probe_set_flag(tp, TP_FLAG_TRACE); return 0; } @@ -982,8 +1086,51 @@ int trace_probe_remove_file(struct trace_probe *tp, synchronize_rcu(); kfree(link); - if (list_empty(&tp->files)) + if (list_empty(&tp->event->files)) trace_probe_clear_flag(tp, TP_FLAG_TRACE); return 0; } + +/* + * Return the smallest index of different type argument (start from 1). + * If all argument types and name are same, return 0. + */ +int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b) +{ + int i; + + /* In case of more arguments */ + if (a->nr_args < b->nr_args) + return a->nr_args + 1; + if (a->nr_args > b->nr_args) + return b->nr_args + 1; + + for (i = 0; i < a->nr_args; i++) { + if ((b->nr_args <= i) || + ((a->args[i].type != b->args[i].type) || + (a->args[i].count != b->args[i].count) || + strcmp(a->args[i].name, b->args[i].name))) + return i + 1; + } + + return 0; +} + +bool trace_probe_match_command_args(struct trace_probe *tp, + int argc, const char **argv) +{ + char buf[MAX_ARGSTR_LEN + 1]; + int i; + + if (tp->nr_args < argc) + return false; + + for (i = 0; i < argc; i++) { + snprintf(buf, sizeof(buf), "%s=%s", + tp->args[i].name, tp->args[i].comm); + if (strcmp(buf, argv[i])) + return false; + } + return true; +} diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index d1714820efe1..a0ff9e200ef6 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -89,6 +89,7 @@ enum fetch_op { FETCH_OP_COMM, /* Current comm */ FETCH_OP_ARG, /* Function argument : .param */ FETCH_OP_FOFFS, /* File offset: .immediate */ + FETCH_OP_DATA, /* Allocated data: .data */ // Stage 2 (dereference) op FETCH_OP_DEREF, /* Dereference: .offset */ FETCH_OP_UDEREF, /* User-space Dereference: .offset */ @@ -222,11 +223,25 @@ struct probe_arg { const struct fetch_type *type; /* Type of this argument */ }; -struct trace_probe { +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + +/* Event call and class holder */ +struct trace_probe_event { unsigned int flags; /* For TP_FLAG_* */ struct trace_event_class class; struct trace_event_call call; struct list_head files; + struct list_head probes; + struct trace_uprobe_filter filter[0]; +}; + +struct trace_probe { + struct list_head list; + struct trace_probe_event *event; ssize_t size; /* trace entry size */ unsigned int nr_args; struct probe_arg args[]; @@ -240,19 +255,19 @@ struct event_file_link { static inline bool trace_probe_test_flag(struct trace_probe *tp, unsigned int flag) { - return !!(tp->flags & flag); + return !!(tp->event->flags & flag); } static inline void trace_probe_set_flag(struct trace_probe *tp, unsigned int flag) { - tp->flags |= flag; + tp->event->flags |= flag; } static inline void trace_probe_clear_flag(struct trace_probe *tp, unsigned int flag) { - tp->flags &= ~flag; + tp->event->flags &= ~flag; } static inline bool trace_probe_is_enabled(struct trace_probe *tp) @@ -262,45 +277,76 @@ static inline bool trace_probe_is_enabled(struct trace_probe *tp) static inline const char *trace_probe_name(struct trace_probe *tp) { - return trace_event_name(&tp->call); + return trace_event_name(&tp->event->call); } static inline const char *trace_probe_group_name(struct trace_probe *tp) { - return tp->call.class->system; + return tp->event->call.class->system; } static inline struct trace_event_call * trace_probe_event_call(struct trace_probe *tp) { - return &tp->call; + return &tp->event->call; +} + +static inline struct trace_probe_event * +trace_probe_event_from_call(struct trace_event_call *event_call) +{ + return container_of(event_call, struct trace_probe_event, call); +} + +static inline struct trace_probe * +trace_probe_primary_from_call(struct trace_event_call *call) +{ + struct trace_probe_event *tpe = trace_probe_event_from_call(call); + + return list_first_entry(&tpe->probes, struct trace_probe, list); +} + +static inline struct list_head *trace_probe_probe_list(struct trace_probe *tp) +{ + return &tp->event->probes; +} + +static inline bool trace_probe_has_sibling(struct trace_probe *tp) +{ + struct list_head *list = trace_probe_probe_list(tp); + + return !list_empty(list) && !list_is_singular(list); } static inline int trace_probe_unregister_event_call(struct trace_probe *tp) { /* tp->event is unregistered in trace_remove_event_call() */ - return trace_remove_event_call(&tp->call); + return trace_remove_event_call(&tp->event->call); } static inline bool trace_probe_has_single_file(struct trace_probe *tp) { - return !!list_is_singular(&tp->files); + return !!list_is_singular(&tp->event->files); } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group); + const char *group, bool alloc_filter); void trace_probe_cleanup(struct trace_probe *tp); +int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); +void trace_probe_unlink(struct trace_probe *tp); int trace_probe_register_event_call(struct trace_probe *tp); int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file); int trace_probe_remove_file(struct trace_probe *tp, struct trace_event_file *file); struct event_file_link *trace_probe_get_file_link(struct trace_probe *tp, struct trace_event_file *file); +int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b); +bool trace_probe_match_command_args(struct trace_probe *tp, + int argc, const char **argv); #define trace_probe_for_each_link(pos, tp) \ - list_for_each_entry(pos, &(tp)->files, list) + list_for_each_entry(pos, &(tp)->event->files, list) #define trace_probe_for_each_link_rcu(pos, tp) \ - list_for_each_entry_rcu(pos, &(tp)->files, list) + list_for_each_entry_rcu(pos, &(tp)->event->files, list) /* Check the name is good for event/group/fields */ static inline bool is_good_name(const char *name) @@ -370,6 +416,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(BAD_VAR, "Invalid $-valiable specified"), \ C(BAD_REG_NAME, "Invalid register name"), \ C(BAD_MEM_ADDR, "Invalid memory address"), \ + C(BAD_IMM, "Invalid immediate value"), \ + C(IMMSTR_NO_CLOSE, "String is not closed with '\"'"), \ C(FILE_ON_KPROBE, "File offset is not available with kprobe"), \ C(BAD_FILE_OFFS, "Invalid file offset value"), \ C(SYM_ON_UPROBE, "Symbol is not available with uprobe"), \ @@ -393,7 +441,10 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(ARG_TOO_LONG, "Argument expression is too long"), \ C(NO_ARG_BODY, "No argument expression"), \ C(BAD_INSN_BNDRY, "Probe point is not an instruction boundary"),\ - C(FAIL_REG_PROBE, "Failed to register probe event"), + C(FAIL_REG_PROBE, "Failed to register probe event"),\ + C(DIFF_PROBE_TYPE, "Probe type is different from existing probe"),\ + C(DIFF_ARG_TYPE, "Argument type or name is different from existing probe"),\ + C(SAME_PROBE, "There is already the exact same probe event"), #undef C #define C(a, b) TP_ERR_##a diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index e288168661e1..e304196d7c28 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -89,8 +89,10 @@ static void tracing_sched_unregister(void) static void tracing_start_sched_switch(int ops) { - bool sched_register = (!sched_cmdline_ref && !sched_tgid_ref); + bool sched_register; + mutex_lock(&sched_register_mutex); + sched_register = (!sched_cmdline_ref && !sched_tgid_ref); switch (ops) { case RECORD_CMDLINE: diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 743b2b520d34..97b10bb31a1f 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -82,7 +82,7 @@ func_prolog_preempt_disable(struct trace_array *tr, if (cpu != wakeup_current_cpu) goto out_enable; - *data = per_cpu_ptr(tr->trace_buffer.data, cpu); + *data = per_cpu_ptr(tr->array_buffer.data, cpu); disabled = atomic_inc_return(&(*data)->disabled); if (unlikely(disabled != 1)) goto out; @@ -378,7 +378,7 @@ tracing_sched_switch_trace(struct trace_array *tr, unsigned long flags, int pc) { struct trace_event_call *call = &event_context_switch; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct ctx_switch_entry *entry; @@ -408,7 +408,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, struct trace_event_call *call = &event_wakeup; struct ring_buffer_event *event; struct ctx_switch_entry *entry; - struct ring_buffer *buffer = tr->trace_buffer.buffer; + struct trace_buffer *buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, TRACE_WAKE, sizeof(*entry), flags, pc); @@ -459,7 +459,7 @@ probe_wakeup_sched_switch(void *ignore, bool preempt, /* disable local data, not wakeup_cpu data */ cpu = raw_smp_processor_id(); - disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled); if (likely(disabled != 1)) goto out; @@ -471,7 +471,7 @@ probe_wakeup_sched_switch(void *ignore, bool preempt, goto out_unlock; /* The task we are waiting for is waking up */ - data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); + data = per_cpu_ptr(wakeup_trace->array_buffer.data, wakeup_cpu); __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc); tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc); @@ -494,7 +494,7 @@ out_unlock: arch_spin_unlock(&wakeup_lock); local_irq_restore(flags); out: - atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled); } static void __wakeup_reset(struct trace_array *tr) @@ -513,7 +513,7 @@ static void wakeup_reset(struct trace_array *tr) { unsigned long flags; - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); local_irq_save(flags); arch_spin_lock(&wakeup_lock); @@ -551,7 +551,7 @@ probe_wakeup(void *ignore, struct task_struct *p) return; pc = preempt_count(); - disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); + disabled = atomic_inc_return(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled); if (unlikely(disabled != 1)) goto out; @@ -579,12 +579,11 @@ probe_wakeup(void *ignore, struct task_struct *p) else tracing_dl = 0; - wakeup_task = p; - get_task_struct(wakeup_task); + wakeup_task = get_task_struct(p); local_save_flags(flags); - data = per_cpu_ptr(wakeup_trace->trace_buffer.data, wakeup_cpu); + data = per_cpu_ptr(wakeup_trace->array_buffer.data, wakeup_cpu); data->preempt_timestamp = ftrace_now(cpu); tracing_sched_wakeup_trace(wakeup_trace, p, current, flags, pc); __trace_stack(wakeup_trace, flags, 0, pc); @@ -599,7 +598,7 @@ probe_wakeup(void *ignore, struct task_struct *p) out_locked: arch_spin_unlock(&wakeup_lock); out: - atomic_dec(&per_cpu_ptr(wakeup_trace->trace_buffer.data, cpu)->disabled); + atomic_dec(&per_cpu_ptr(wakeup_trace->array_buffer.data, cpu)->disabled); } static void start_wakeup_tracer(struct trace_array *tr) @@ -631,7 +630,7 @@ static void start_wakeup_tracer(struct trace_array *tr) if (ret) { pr_info("wakeup trace: Couldn't activate tracepoint" " probe to kernel_sched_migrate_task\n"); - return; + goto fail_deprobe_sched_switch; } wakeup_reset(tr); @@ -649,6 +648,8 @@ static void start_wakeup_tracer(struct trace_array *tr) printk(KERN_ERR "failed to start wakeup tracer\n"); return; +fail_deprobe_sched_switch: + unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL); fail_deprobe_wake_new: unregister_trace_sched_wakeup_new(probe_wakeup, NULL); fail_deprobe: diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 69ee8ef12cee..b5e3496cf803 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -23,7 +23,7 @@ static inline int trace_valid_entry(struct trace_entry *entry) return 0; } -static int trace_test_buffer_cpu(struct trace_buffer *buf, int cpu) +static int trace_test_buffer_cpu(struct array_buffer *buf, int cpu) { struct ring_buffer_event *event; struct trace_entry *entry; @@ -60,7 +60,7 @@ static int trace_test_buffer_cpu(struct trace_buffer *buf, int cpu) * Test the trace buffer to see if all the elements * are still sane. */ -static int __maybe_unused trace_test_buffer(struct trace_buffer *buf, unsigned long *count) +static int __maybe_unused trace_test_buffer(struct array_buffer *buf, unsigned long *count) { unsigned long flags, cnt = 0; int cpu, ret = 0; @@ -362,7 +362,7 @@ static int trace_selftest_startup_dynamic_tracing(struct tracer *trace, msleep(100); /* we should have nothing in the buffer */ - ret = trace_test_buffer(&tr->trace_buffer, &count); + ret = trace_test_buffer(&tr->array_buffer, &count); if (ret) goto out; @@ -383,7 +383,7 @@ static int trace_selftest_startup_dynamic_tracing(struct tracer *trace, ftrace_enabled = 0; /* check the trace buffer */ - ret = trace_test_buffer(&tr->trace_buffer, &count); + ret = trace_test_buffer(&tr->array_buffer, &count); ftrace_enabled = 1; tracing_start(); @@ -682,7 +682,7 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ftrace_enabled = 0; /* check the trace buffer */ - ret = trace_test_buffer(&tr->trace_buffer, &count); + ret = trace_test_buffer(&tr->array_buffer, &count); ftrace_enabled = 1; trace->reset(tr); @@ -768,7 +768,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, * Simulate the init() callback but we attach a watchdog callback * to detect and recover from possible hangs */ - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(&tr->array_buffer); set_graph_array(tr); ret = register_ftrace_graph(&fgraph_ops); if (ret) { @@ -790,7 +790,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(&tr->trace_buffer, &count); + ret = trace_test_buffer(&tr->array_buffer, &count); /* Need to also simulate the tr->reset to remove this fgraph_ops */ tracing_stop_cmdline_record(); @@ -848,7 +848,7 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(&tr->trace_buffer, NULL); + ret = trace_test_buffer(&tr->array_buffer, NULL); if (!ret) ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); @@ -910,7 +910,7 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(&tr->trace_buffer, NULL); + ret = trace_test_buffer(&tr->array_buffer, NULL); if (!ret) ret = trace_test_buffer(&tr->max_buffer, &count); trace->reset(tr); @@ -976,7 +976,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(&tr->trace_buffer, NULL); + ret = trace_test_buffer(&tr->array_buffer, NULL); if (ret) goto out; @@ -1006,7 +1006,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array * /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(&tr->trace_buffer, NULL); + ret = trace_test_buffer(&tr->array_buffer, NULL); if (ret) goto out; @@ -1136,7 +1136,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check both trace buffers */ - ret = trace_test_buffer(&tr->trace_buffer, NULL); + ret = trace_test_buffer(&tr->array_buffer, NULL); if (!ret) ret = trace_test_buffer(&tr->max_buffer, &count); @@ -1177,7 +1177,7 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(&tr->trace_buffer, &count); + ret = trace_test_buffer(&tr->array_buffer, &count); trace->reset(tr); tracing_start(); diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 6b1c562ffdaf..1d84fcc78e3e 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -30,9 +30,6 @@ /* How much buffer is left on the trace_seq? */ #define TRACE_SEQ_BUF_LEFT(s) seq_buf_buffer_left(&(s)->seq) -/* How much buffer is written? */ -#define TRACE_SEQ_BUF_USED(s) seq_buf_used(&(s)->seq) - /* * trace_seq should work with being initialized with 0s. */ @@ -376,3 +373,33 @@ int trace_seq_to_user(struct trace_seq *s, char __user *ubuf, int cnt) return seq_buf_to_user(&s->seq, ubuf, cnt); } EXPORT_SYMBOL_GPL(trace_seq_to_user); + +int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, + int prefix_type, int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ + unsigned int save_len = s->seq.len; + + if (s->full) + return 0; + + __trace_seq_init(s); + + if (TRACE_SEQ_BUF_LEFT(s) < 1) { + s->full = 1; + return 0; + } + + seq_buf_hex_dump(&(s->seq), prefix_str, + prefix_type, rowsize, groupsize, + buf, len, ascii); + + if (unlikely(seq_buf_has_overflowed(&s->seq))) { + s->seq.len = save_len; + s->full = 1; + return 0; + } + + return 1; +} +EXPORT_SYMBOL(trace_seq_hex_dump); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 5d16f73898db..c557f42a9397 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -5,6 +5,7 @@ */ #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <linux/security.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> #include <linux/spinlock.h> @@ -53,6 +54,104 @@ static void print_max_stack(void) } } +/* + * The stack tracer looks for a maximum stack at each call from a function. It + * registers a callback from ftrace, and in that callback it examines the stack + * size. It determines the stack size from the variable passed in, which is the + * address of a local variable in the stack_trace_call() callback function. + * The stack size is calculated by the address of the local variable to the top + * of the current stack. If that size is smaller than the currently saved max + * stack size, nothing more is done. + * + * If the size of the stack is greater than the maximum recorded size, then the + * following algorithm takes place. + * + * For architectures (like x86) that store the function's return address before + * saving the function's local variables, the stack will look something like + * this: + * + * [ top of stack ] + * 0: sys call entry frame + * 10: return addr to entry code + * 11: start of sys_foo frame + * 20: return addr to sys_foo + * 21: start of kernel_func_bar frame + * 30: return addr to kernel_func_bar + * 31: [ do trace stack here ] + * + * The save_stack_trace() is called returning all the functions it finds in the + * current stack. Which would be (from the bottom of the stack to the top): + * + * return addr to kernel_func_bar + * return addr to sys_foo + * return addr to entry code + * + * Now to figure out how much each of these functions' local variable size is, + * a search of the stack is made to find these values. When a match is made, it + * is added to the stack_dump_trace[] array. The offset into the stack is saved + * in the stack_trace_index[] array. The above example would show: + * + * stack_dump_trace[] | stack_trace_index[] + * ------------------ + ------------------- + * return addr to kernel_func_bar | 30 + * return addr to sys_foo | 20 + * return addr to entry | 10 + * + * The print_max_stack() function above, uses these values to print the size of + * each function's portion of the stack. + * + * for (i = 0; i < nr_entries; i++) { + * size = i == nr_entries - 1 ? stack_trace_index[i] : + * stack_trace_index[i] - stack_trace_index[i+1] + * print "%d %d %d %s\n", i, stack_trace_index[i], size, stack_dump_trace[i]); + * } + * + * The above shows + * + * depth size location + * ----- ---- -------- + * 0 30 10 kernel_func_bar + * 1 20 10 sys_foo + * 2 10 10 entry code + * + * Now for architectures that might save the return address after the functions + * local variables (saving the link register before calling nested functions), + * this will cause the stack to look a little different: + * + * [ top of stack ] + * 0: sys call entry frame + * 10: start of sys_foo_frame + * 19: return addr to entry code << lr saved before calling kernel_func_bar + * 20: start of kernel_func_bar frame + * 29: return addr to sys_foo_frame << lr saved before calling next function + * 30: [ do trace stack here ] + * + * Although the functions returned by save_stack_trace() may be the same, the + * placement in the stack will be different. Using the same algorithm as above + * would yield: + * + * stack_dump_trace[] | stack_trace_index[] + * ------------------ + ------------------- + * return addr to kernel_func_bar | 30 + * return addr to sys_foo | 29 + * return addr to entry | 19 + * + * Where the mapping is off by one: + * + * kernel_func_bar stack frame size is 29 - 19 not 30 - 29! + * + * To fix this, if the architecture sets ARCH_RET_ADDR_AFTER_LOCAL_VARS the + * values in stack_trace_index[] are shifted by one to and the number of + * stack trace entries is decremented by one. + * + * stack_dump_trace[] | stack_trace_index[] + * ------------------ + ------------------- + * return addr to kernel_func_bar | 29 + * return addr to sys_foo | 19 + * + * Although the entry function is not displayed, the first function (sys_foo) + * will still include the stack size of it. + */ static void check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; @@ -158,6 +257,20 @@ static void check_stack(unsigned long ip, unsigned long *stack) i++; } +#ifdef ARCH_FTRACE_SHIFT_STACK_TRACER + /* + * Some archs will store the link register before calling + * nested functions. This means the saved return address + * comes after the local storage, and we need to shift + * for that. + */ + if (x > 1) { + memmove(&stack_trace_index[0], &stack_trace_index[1], + sizeof(stack_trace_index[0]) * (x - 1)); + x--; + } +#endif + stack_trace_nr_entries = x; if (task_stack_end_corrupted(current)) { @@ -170,6 +283,11 @@ static void check_stack(unsigned long ip, unsigned long *stack) local_irq_restore(flags); } +/* Some archs may not define MCOUNT_INSN_SIZE */ +#ifndef MCOUNT_INSN_SIZE +# define MCOUNT_INSN_SIZE 0 +#endif + static void stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *pt_regs) @@ -358,6 +476,12 @@ static const struct seq_operations stack_trace_seq_ops = { static int stack_trace_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &stack_trace_seq_ops); } @@ -375,6 +499,7 @@ stack_trace_filter_open(struct inode *inode, struct file *file) { struct ftrace_ops *ops = inode->i_private; + /* Checks for tracefs lockdown */ return ftrace_regex_open(ops, FTRACE_ITER_FILTER, inode, file); } diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 75bf1bcb4a8a..d1fa19773cc8 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -9,7 +9,7 @@ * */ - +#include <linux/security.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/rbtree.h> @@ -72,9 +72,7 @@ static void destroy_session(struct stat_session *session) kfree(session); } -typedef int (*cmp_stat_t)(void *, void *); - -static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp) +static int insert_stat(struct rb_root *root, void *stat, cmp_func_t cmp) { struct rb_node **new = &(root->rb_node), *parent = NULL; struct stat_node *data; @@ -112,7 +110,7 @@ static int insert_stat(struct rb_root *root, void *stat, cmp_stat_t cmp) * This one will force an insertion as right-most node * in the rbtree. */ -static int dummy_cmp(void *p1, void *p2) +static int dummy_cmp(const void *p1, const void *p2) { return -1; } @@ -238,6 +236,10 @@ static int tracing_stat_open(struct inode *inode, struct file *file) struct seq_file *m; struct stat_session *session = inode->i_private; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + ret = stat_seq_init(session); if (ret) return ret; @@ -278,18 +280,22 @@ static int tracing_stat_init(void) d_tracing = tracing_init_dentry(); if (IS_ERR(d_tracing)) - return 0; + return -ENODEV; stat_dir = tracefs_create_dir("trace_stat", d_tracing); - if (!stat_dir) + if (!stat_dir) { pr_warn("Could not create tracefs 'trace_stat' entry\n"); + return -ENOMEM; + } return 0; } static int init_stat_file(struct stat_session *session) { - if (!stat_dir && tracing_stat_init()) - return -ENODEV; + int ret; + + if (!stat_dir && (ret = tracing_stat_init())) + return ret; session->file = tracefs_create_file(session->ts->name, 0644, stat_dir, @@ -302,7 +308,7 @@ static int init_stat_file(struct stat_session *session) int register_stat_tracer(struct tracer_stat *trace) { struct stat_session *session, *node; - int ret; + int ret = -EINVAL; if (!trace) return -EINVAL; @@ -313,17 +319,15 @@ int register_stat_tracer(struct tracer_stat *trace) /* Already registered? */ mutex_lock(&all_stat_sessions_mutex); list_for_each_entry(node, &all_stat_sessions, session_list) { - if (node->ts == trace) { - mutex_unlock(&all_stat_sessions_mutex); - return -EINVAL; - } + if (node->ts == trace) + goto out; } - mutex_unlock(&all_stat_sessions_mutex); + ret = -ENOMEM; /* Init the session */ session = kzalloc(sizeof(*session), GFP_KERNEL); if (!session) - return -ENOMEM; + goto out; session->ts = trace; INIT_LIST_HEAD(&session->session_list); @@ -332,15 +336,16 @@ int register_stat_tracer(struct tracer_stat *trace) ret = init_stat_file(session); if (ret) { destroy_session(session); - return ret; + goto out; } + ret = 0; /* Register */ - mutex_lock(&all_stat_sessions_mutex); list_add_tail(&session->session_list, &all_stat_sessions); + out: mutex_unlock(&all_stat_sessions_mutex); - return 0; + return ret; } void unregister_stat_tracer(struct tracer_stat *trace) diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h index 8786d17caf49..31d7dc5bf1db 100644 --- a/kernel/trace/trace_stat.h +++ b/kernel/trace/trace_stat.h @@ -16,7 +16,7 @@ struct tracer_stat { void *(*stat_start)(struct tracer_stat *trace); void *(*stat_next)(void *prev, int idx); /* Compare two entries for stats sorting */ - int (*stat_cmp)(void *p1, void *p2); + cmp_func_t stat_cmp; /* Print a stat entry */ int (*stat_show)(struct seq_file *s, void *p); /* Release an entry */ diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index fa8fbff736d6..d85a2f0f316b 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -7,6 +7,7 @@ #include <linux/module.h> /* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */ #include <linux/ftrace.h> #include <linux/perf_event.h> +#include <linux/xarray.h> #include <asm/syscall.h> #include "trace_output.h" @@ -30,6 +31,7 @@ syscall_get_enter_fields(struct trace_event_call *call) extern struct syscall_metadata *__start_syscalls_metadata[]; extern struct syscall_metadata *__stop_syscalls_metadata[]; +static DEFINE_XARRAY(syscalls_metadata_sparse); static struct syscall_metadata **syscalls_metadata; #ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME @@ -101,6 +103,9 @@ find_syscall_meta(unsigned long syscall) static struct syscall_metadata *syscall_nr_to_meta(int nr) { + if (IS_ENABLED(CONFIG_HAVE_SPARSE_SYSCALL_NR)) + return xa_load(&syscalls_metadata_sparse, (unsigned long)nr); + if (!syscalls_metadata || nr >= NR_syscalls || nr < 0) return NULL; @@ -198,11 +203,10 @@ print_syscall_exit(struct trace_iterator *iter, int flags, extern char *__bad_type_size(void); -#define SYSCALL_FIELD(type, field, name) \ - sizeof(type) != sizeof(trace.field) ? \ - __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), field), \ - sizeof(trace.field), is_signed_type(type) +#define SYSCALL_FIELD(_type, _name) { \ + .type = #_type, .name = #_name, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER } static int __init __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) @@ -269,42 +273,23 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call) { struct syscall_trace_enter trace; struct syscall_metadata *meta = call->data; - int ret; - int i; int offset = offsetof(typeof(trace), args); - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; + int ret = 0; + int i; for (i = 0; i < meta->nb_args; i++) { ret = trace_define_field(call, meta->types[i], meta->args[i], offset, sizeof(unsigned long), 0, FILTER_OTHER); + if (ret) + break; offset += sizeof(unsigned long); } return ret; } -static int __init syscall_exit_define_fields(struct trace_event_call *call) -{ - struct syscall_trace_exit trace; - int ret; - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; - - ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret), - FILTER_OTHER); - - return ret; -} - static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) { struct trace_array *tr = data; @@ -312,7 +297,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) struct syscall_trace_enter *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; unsigned long irq_flags; unsigned long args[6]; int pc; @@ -340,7 +325,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) local_save_flags(irq_flags); pc = preempt_count(); - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, sys_data->enter_event->event.type, size, irq_flags, pc); if (!event) @@ -362,7 +347,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) struct syscall_trace_exit *entry; struct syscall_metadata *sys_data; struct ring_buffer_event *event; - struct ring_buffer *buffer; + struct trace_buffer *buffer; unsigned long irq_flags; int pc; int syscall_nr; @@ -386,7 +371,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret) local_save_flags(irq_flags); pc = preempt_count(); - buffer = tr->trace_buffer.buffer; + buffer = tr->array_buffer.buffer; event = trace_buffer_lock_reserve(buffer, sys_data->exit_event->event.type, sizeof(*entry), irq_flags, pc); @@ -502,6 +487,13 @@ static int __init init_syscall_trace(struct trace_event_call *call) return id; } +static struct trace_event_fields __refdata syscall_enter_fields_array[] = { + SYSCALL_FIELD(int, __syscall_nr), + { .type = TRACE_FUNCTION_TYPE, + .define_fields = syscall_enter_define_fields }, + {} +}; + struct trace_event_functions enter_syscall_print_funcs = { .trace = print_syscall_enter, }; @@ -513,7 +505,7 @@ struct trace_event_functions exit_syscall_print_funcs = { struct trace_event_class __refdata event_class_syscall_enter = { .system = "syscalls", .reg = syscall_enter_register, - .define_fields = syscall_enter_define_fields, + .fields_array = syscall_enter_fields_array, .get_fields = syscall_get_enter_fields, .raw_init = init_syscall_trace, }; @@ -521,7 +513,11 @@ struct trace_event_class __refdata event_class_syscall_enter = { struct trace_event_class __refdata event_class_syscall_exit = { .system = "syscalls", .reg = syscall_exit_register, - .define_fields = syscall_exit_define_fields, + .fields_array = (struct trace_event_fields[]){ + SYSCALL_FIELD(int, __syscall_nr), + SYSCALL_FIELD(long, ret), + {} + }, .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), .raw_init = init_syscall_trace, }; @@ -536,12 +532,16 @@ void __init init_ftrace_syscalls(void) struct syscall_metadata *meta; unsigned long addr; int i; - - syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata), - GFP_KERNEL); - if (!syscalls_metadata) { - WARN_ON(1); - return; + void *ret; + + if (!IS_ENABLED(CONFIG_HAVE_SPARSE_SYSCALL_NR)) { + syscalls_metadata = kcalloc(NR_syscalls, + sizeof(*syscalls_metadata), + GFP_KERNEL); + if (!syscalls_metadata) { + WARN_ON(1); + return; + } } for (i = 0; i < NR_syscalls; i++) { @@ -551,7 +551,16 @@ void __init init_ftrace_syscalls(void) continue; meta->syscall_nr = i; - syscalls_metadata[i] = meta; + + if (!IS_ENABLED(CONFIG_HAVE_SPARSE_SYSCALL_NR)) { + syscalls_metadata[i] = meta; + } else { + ret = xa_store(&syscalls_metadata_sparse, i, meta, + GFP_KERNEL); + WARN(xa_is_err(ret), + "Syscall memory allocation failed\n"); + } + } } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 1ceedb9146b1..18d16f3ef980 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "trace_uprobe: " fmt +#include <linux/security.h> #include <linux/ctype.h> #include <linux/module.h> #include <linux/uaccess.h> @@ -33,18 +34,12 @@ struct uprobe_trace_entry_head { #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) -struct trace_uprobe_filter { - rwlock_t rwlock; - int nr_systemwide; - struct list_head perf_events; -}; - static int trace_uprobe_create(int argc, const char **argv); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); static bool trace_uprobe_is_busy(struct dyn_event *ev); static bool trace_uprobe_match(const char *system, const char *event, - struct dyn_event *ev); + int argc, const char **argv, struct dyn_event *ev); static struct dyn_event_operations trace_uprobe_ops = { .create = trace_uprobe_create, @@ -59,7 +54,6 @@ static struct dyn_event_operations trace_uprobe_ops = { */ struct trace_uprobe { struct dyn_event devent; - struct trace_uprobe_filter filter; struct uprobe_consumer consumer; struct path path; struct inode *inode; @@ -248,6 +242,9 @@ process_fetch_insn(struct fetch_insn *code, struct pt_regs *regs, void *dest, case FETCH_OP_COMM: val = FETCH_TOKEN_COMM; break; + case FETCH_OP_DATA: + val = (unsigned long)code->data; + break; case FETCH_OP_FOFFS: val = translate_user_vaddr(code->immediate); break; @@ -284,13 +281,54 @@ static bool trace_uprobe_is_busy(struct dyn_event *ev) return trace_probe_is_enabled(&tu->tp); } +static bool trace_uprobe_match_command_head(struct trace_uprobe *tu, + int argc, const char **argv) +{ + char buf[MAX_ARGSTR_LEN + 1]; + int len; + + if (!argc) + return true; + + len = strlen(tu->filename); + if (strncmp(tu->filename, argv[0], len) || argv[0][len] != ':') + return false; + + if (tu->ref_ctr_offset == 0) + snprintf(buf, sizeof(buf), "0x%0*lx", + (int)(sizeof(void *) * 2), tu->offset); + else + snprintf(buf, sizeof(buf), "0x%0*lx(0x%lx)", + (int)(sizeof(void *) * 2), tu->offset, + tu->ref_ctr_offset); + if (strcmp(buf, &argv[0][len + 1])) + return false; + + argc--; argv++; + + return trace_probe_match_command_args(&tu->tp, argc, argv); +} + static bool trace_uprobe_match(const char *system, const char *event, - struct dyn_event *ev) + int argc, const char **argv, struct dyn_event *ev) { struct trace_uprobe *tu = to_trace_uprobe(ev); return strcmp(trace_probe_name(&tu->tp), event) == 0 && - (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0); + (!system || strcmp(trace_probe_group_name(&tu->tp), system) == 0) && + trace_uprobe_match_command_head(tu, argc, argv); +} + +static nokprobe_inline struct trace_uprobe * +trace_uprobe_primary_from_call(struct trace_event_call *call) +{ + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return NULL; + + return container_of(tp, struct trace_uprobe, tp); } /* @@ -306,7 +344,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group); + ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; @@ -314,7 +352,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; - init_trace_uprobe_filter(&tu->filter); + init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: @@ -352,15 +390,76 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu) { int ret; + if (trace_probe_has_sibling(&tu->tp)) + goto unreg; + ret = unregister_uprobe_event(tu); if (ret) return ret; +unreg: dyn_event_remove(&tu->devent); + trace_probe_unlink(&tu->tp); free_trace_uprobe(tu); return 0; } +static bool trace_uprobe_has_same_uprobe(struct trace_uprobe *orig, + struct trace_uprobe *comp) +{ + struct trace_probe_event *tpe = orig->tp.event; + struct trace_probe *pos; + struct inode *comp_inode = d_real_inode(comp->path.dentry); + int i; + + list_for_each_entry(pos, &tpe->probes, list) { + orig = container_of(pos, struct trace_uprobe, tp); + if (comp_inode != d_real_inode(orig->path.dentry) || + comp->offset != orig->offset) + continue; + + /* + * trace_probe_compare_arg_type() ensured that nr_args and + * each argument name and type are same. Let's compare comm. + */ + for (i = 0; i < orig->tp.nr_args; i++) { + if (strcmp(orig->tp.args[i].comm, + comp->tp.args[i].comm)) + break; + } + + if (i == orig->tp.nr_args) + return true; + } + + return false; +} + +static int append_trace_uprobe(struct trace_uprobe *tu, struct trace_uprobe *to) +{ + int ret; + + ret = trace_probe_compare_arg_type(&tu->tp, &to->tp); + if (ret) { + /* Note that argument starts index = 2 */ + trace_probe_log_set_index(ret + 1); + trace_probe_log_err(0, DIFF_ARG_TYPE); + return -EEXIST; + } + if (trace_uprobe_has_same_uprobe(to, tu)) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, SAME_PROBE); + return -EEXIST; + } + + /* Append to existing event */ + ret = trace_probe_append(&tu->tp, &to->tp); + if (!ret) + dyn_event_add(&tu->devent); + + return ret; +} + /* * Uprobe with multiple reference counter is not allowed. i.e. * If inode and offset matches, reference counter offset *must* @@ -370,25 +469,21 @@ static int unregister_trace_uprobe(struct trace_uprobe *tu) * as the new one does not conflict with any other existing * ones. */ -static struct trace_uprobe *find_old_trace_uprobe(struct trace_uprobe *new) +static int validate_ref_ctr_offset(struct trace_uprobe *new) { struct dyn_event *pos; - struct trace_uprobe *tmp, *old = NULL; + struct trace_uprobe *tmp; struct inode *new_inode = d_real_inode(new->path.dentry); - old = find_probe_event(trace_probe_name(&new->tp), - trace_probe_group_name(&new->tp)); - for_each_trace_uprobe(tmp, pos) { - if ((old ? old != tmp : true) && - new_inode == d_real_inode(tmp->path.dentry) && + if (new_inode == d_real_inode(tmp->path.dentry) && new->offset == tmp->offset && new->ref_ctr_offset != tmp->ref_ctr_offset) { pr_warn("Reference counter offset mismatch."); - return ERR_PTR(-EINVAL); + return -EINVAL; } } - return old; + return 0; } /* Register a trace_uprobe and probe_event */ @@ -399,18 +494,22 @@ static int register_trace_uprobe(struct trace_uprobe *tu) mutex_lock(&event_mutex); - /* register as an event */ - old_tu = find_old_trace_uprobe(tu); - if (IS_ERR(old_tu)) { - ret = PTR_ERR(old_tu); + ret = validate_ref_ctr_offset(tu); + if (ret) goto end; - } + /* register as an event */ + old_tu = find_probe_event(trace_probe_name(&tu->tp), + trace_probe_group_name(&tu->tp)); if (old_tu) { - /* delete old event */ - ret = unregister_trace_uprobe(old_tu); - if (ret) - goto end; + if (is_ret_probe(tu) != is_ret_probe(old_tu)) { + trace_probe_log_set_index(0); + trace_probe_log_err(0, DIFF_PROBE_TYPE); + ret = -EEXIST; + } else { + ret = append_trace_uprobe(tu, old_tu); + } + goto end; } ret = register_uprobe_event(tu); @@ -664,6 +763,10 @@ static int probes_open(struct inode *inode, struct file *file) { int ret; + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { ret = dyn_events_release_all(&trace_uprobe_ops); if (ret) @@ -713,6 +816,12 @@ static const struct seq_operations profile_seq_op = { static int profile_open(struct inode *inode, struct file *file) { + int ret; + + ret = security_locked_down(LOCKDOWN_TRACEFS); + if (ret) + return ret; + return seq_open(file, &profile_seq_op); } @@ -822,8 +931,8 @@ static void __uprobe_trace_func(struct trace_uprobe *tu, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; + struct trace_buffer *buffer; struct ring_buffer_event *event; - struct ring_buffer *buffer; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); @@ -897,7 +1006,10 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e u8 *data; entry = (struct uprobe_trace_entry_head *)iter->ent; - tu = container_of(event, struct trace_uprobe, tp.call.event); + tu = trace_uprobe_primary_from_call( + container_of(event, struct trace_event_call, event)); + if (unlikely(!tu)) + goto out; if (is_ret_probe(tu)) { trace_seq_printf(s, "%s: (0x%lx <- 0x%lx)", @@ -924,28 +1036,73 @@ typedef bool (*filter_func_t)(struct uprobe_consumer *self, enum uprobe_filter_ctx ctx, struct mm_struct *mm); -static int -probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, - filter_func_t filter) +static int trace_uprobe_enable(struct trace_uprobe *tu, filter_func_t filter) +{ + int ret; + + tu->consumer.filter = filter; + tu->inode = d_real_inode(tu->path.dentry); + + if (tu->ref_ctr_offset) + ret = uprobe_register_refctr(tu->inode, tu->offset, + tu->ref_ctr_offset, &tu->consumer); + else + ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + + if (ret) + tu->inode = NULL; + + return ret; +} + +static void __probe_event_disable(struct trace_probe *tp) { - bool enabled = trace_probe_is_enabled(&tu->tp); + struct trace_probe *pos; + struct trace_uprobe *tu; + + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tu = container_of(pos, struct trace_uprobe, tp); + if (!tu->inode) + continue; + + uprobe_unregister(tu->inode, tu->offset, &tu->consumer); + tu->inode = NULL; + } +} + +static int probe_event_enable(struct trace_event_call *call, + struct trace_event_file *file, filter_func_t filter) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + bool enabled; int ret; + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + enabled = trace_probe_is_enabled(tp); + + /* This may also change "enabled" state */ if (file) { - if (trace_probe_test_flag(&tu->tp, TP_FLAG_PROFILE)) + if (trace_probe_test_flag(tp, TP_FLAG_PROFILE)) return -EINTR; - ret = trace_probe_add_file(&tu->tp, file); + ret = trace_probe_add_file(tp, file); if (ret < 0) return ret; } else { - if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) + if (trace_probe_test_flag(tp, TP_FLAG_TRACE)) return -EINTR; - trace_probe_set_flag(&tu->tp, TP_FLAG_PROFILE); + trace_probe_set_flag(tp, TP_FLAG_PROFILE); } - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; @@ -954,18 +1111,15 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, if (ret) goto err_flags; - tu->consumer.filter = filter; - tu->inode = d_real_inode(tu->path.dentry); - if (tu->ref_ctr_offset) { - ret = uprobe_register_refctr(tu->inode, tu->offset, - tu->ref_ctr_offset, &tu->consumer); - } else { - ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tu = container_of(pos, struct trace_uprobe, tp); + ret = trace_uprobe_enable(tu, filter); + if (ret) { + __probe_event_disable(tp); + goto err_buffer; + } } - if (ret) - goto err_buffer; - return 0; err_buffer: @@ -973,33 +1127,35 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, err_flags: if (file) - trace_probe_remove_file(&tu->tp, file); + trace_probe_remove_file(tp, file); else - trace_probe_clear_flag(&tu->tp, TP_FLAG_PROFILE); + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); return ret; } -static void -probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file) +static void probe_event_disable(struct trace_event_call *call, + struct trace_event_file *file) { - if (!trace_probe_is_enabled(&tu->tp)) + struct trace_probe *tp; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return; + + if (!trace_probe_is_enabled(tp)) return; if (file) { - if (trace_probe_remove_file(&tu->tp, file) < 0) + if (trace_probe_remove_file(tp, file) < 0) return; - if (trace_probe_is_enabled(&tu->tp)) + if (trace_probe_is_enabled(tp)) return; } else - trace_probe_clear_flag(&tu->tp, TP_FLAG_PROFILE); - - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); - tu->inode = NULL; + trace_probe_clear_flag(tp, TP_FLAG_PROFILE); + __probe_event_disable(tp); uprobe_buffer_disable(); } @@ -1007,7 +1163,11 @@ static int uprobe_event_define_fields(struct trace_event_call *event_call) { int ret, size; struct uprobe_trace_entry_head field; - struct trace_uprobe *tu = event_call->data; + struct trace_uprobe *tu; + + tu = trace_uprobe_primary_from_call(event_call); + if (unlikely(!tu)) + return -ENODEV; if (is_ret_probe(tu)) { DEFINE_FIELD(unsigned long, vaddr[0], FIELD_STRING_FUNC, 0); @@ -1039,39 +1199,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) } static inline bool -uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +trace_uprobe_filter_event(struct trace_uprobe_filter *filter, + struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); + return __uprobe_perf_filter(filter, event->hw.target->mm); } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || - uprobe_filter_event(tu, event); + trace_uprobe_filter_event(filter, event); } else { - tu->filter.nr_systemwide--; - done = tu->filter.nr_systemwide; + filter->nr_systemwide--; + done = filter->nr_systemwide; } - write_unlock(&tu->filter.rwlock); - - if (!done) - return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + write_unlock(&filter->rwlock); - return 0; + return done; } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +/* This returns true if the filter always covers target mm */ +static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - int err; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid @@ -1081,35 +1241,83 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || - uprobe_filter_event(tu, event); - list_add(&event->hw.tp_list, &tu->filter.perf_events); + trace_uprobe_filter_event(filter, event); + list_add(&event->hw.tp_list, &filter->perf_events); } else { - done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; + done = filter->nr_systemwide; + filter->nr_systemwide++; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); + + return done; +} + +static int uprobe_perf_close(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + int ret = 0; - err = 0; - if (!done) { + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + tu = container_of(pos, struct trace_uprobe, tp); + ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); + if (ret) + break; + } + + return ret; +} + +static int uprobe_perf_open(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + int err = 0; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_add(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); - if (err) - uprobe_perf_close(tu, event); + if (err) { + uprobe_perf_close(call, event); + break; + } } + return err; } static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { + struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); - read_lock(&tu->filter.rwlock); - ret = __uprobe_perf_filter(&tu->filter, mm); - read_unlock(&tu->filter.rwlock); + filter = tu->tp.event->filter; + + read_lock(&filter->rwlock); + ret = __uprobe_perf_filter(filter, mm); + read_unlock(&filter->rwlock); return ret; } @@ -1213,30 +1421,29 @@ static int trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, void *data) { - struct trace_uprobe *tu = event->data; struct trace_event_file *file = data; switch (type) { case TRACE_REG_REGISTER: - return probe_event_enable(tu, file, NULL); + return probe_event_enable(event, file, NULL); case TRACE_REG_UNREGISTER: - probe_event_disable(tu, file); + probe_event_disable(event, file); return 0; #ifdef CONFIG_PERF_EVENTS case TRACE_REG_PERF_REGISTER: - return probe_event_enable(tu, NULL, uprobe_perf_filter); + return probe_event_enable(event, NULL, uprobe_perf_filter); case TRACE_REG_PERF_UNREGISTER: - probe_event_disable(tu, NULL); + probe_event_disable(event, NULL); return 0; case TRACE_REG_PERF_OPEN: - return uprobe_perf_open(tu, data); + return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: - return uprobe_perf_close(tu, data); + return uprobe_perf_close(event, data); #endif default: @@ -1321,16 +1528,20 @@ static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; +static struct trace_event_fields uprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = uprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_uprobe *tu) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); - call->event.funcs = &uprobe_funcs; - call->class->define_fields = uprobe_event_define_fields; + call->class->fields_array = uprobe_fields_array; call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; call->class->reg = trace_uprobe_register; - call->data = tu; } static int register_uprobe_event(struct trace_uprobe *tu) @@ -1399,7 +1610,7 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call) { struct trace_uprobe *tu; - tu = container_of(event_call, struct trace_uprobe, tp.call); + tu = trace_uprobe_primary_from_call(event_call); free_trace_uprobe(tu); } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 9a1c22310323..9e31bfc818ff 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -148,8 +148,8 @@ static int tracing_map_cmp_atomic64(void *val_a, void *val_b) #define DEFINE_TRACING_MAP_CMP_FN(type) \ static int tracing_map_cmp_##type(void *val_a, void *val_b) \ { \ - type a = *(type *)val_a; \ - type b = *(type *)val_b; \ + type a = (type)(*(u64 *)val_a); \ + type b = (type)(*(u64 *)val_b); \ \ return (a > b) ? 1 : ((a < b) ? -1 : 0); \ } |
