diff options
| author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2021-02-22 21:21:03 -0800 |
|---|---|---|
| committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2021-02-22 21:21:03 -0800 |
| commit | 415e915fdfc775ad0c6675fde1008f6f43dd6251 (patch) | |
| tree | 429851187c0e85daa78f5d2bb6853959a1f5545b /kernel/trace | |
| parent | e64123949e6c9581c97fc14594f1cf34bf1d87a8 (diff) | |
| parent | f40ddce88593482919761f74910f42f4b84c004b (diff) | |
Merge tag 'v5.11' into next
Merge with mainline to get latest APIs and device tree bindings.
Diffstat (limited to 'kernel/trace')
39 files changed, 1942 insertions, 932 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index a4020c0b4508..c1a62ae7e812 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -31,6 +31,15 @@ config HAVE_DYNAMIC_FTRACE_WITH_REGS config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS bool +config HAVE_DYNAMIC_FTRACE_WITH_ARGS + bool + help + If this is set, then arguments and stack can be found from + the pt_regs passed into the function callback regs parameter + by default, even without setting the REGS flag in the ftrace_ops. + This allows for use of regs_get_kernel_argument() and + kernel_stack_pointer(). + config HAVE_FTRACE_MCOUNT_RECORD bool help @@ -202,7 +211,7 @@ config DYNAMIC_FTRACE_WITH_REGS config DYNAMIC_FTRACE_WITH_DIRECT_CALLS def_bool y - depends on DYNAMIC_FTRACE + depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS config FUNCTION_PROFILER @@ -253,7 +262,6 @@ config IRQSOFF_TRACER bool "Interrupts-off Latency Tracer" default n depends on TRACE_IRQFLAGS_SUPPORT - depends on !ARCH_USES_GETTIMEOFFSET select TRACE_IRQFLAGS select GENERIC_TRACER select TRACER_MAX_TRACE @@ -277,7 +285,6 @@ config IRQSOFF_TRACER config PREEMPT_TRACER bool "Preemption-off Latency Tracer" default n - depends on !ARCH_USES_GETTIMEOFFSET depends on PREEMPTION select GENERIC_TRACER select TRACER_MAX_TRACE @@ -531,7 +538,7 @@ config KPROBE_EVENTS config KPROBE_EVENTS_ON_NOTRACE bool "Do NOT protect notrace function from kprobe events" depends on KPROBE_EVENTS - depends on KPROBES_ON_FTRACE + depends on DYNAMIC_FTRACE default n help This is only for the developers who want to debug ftrace itself @@ -727,6 +734,45 @@ config TRACE_EVAL_MAP_FILE If unsure, say N. +config FTRACE_RECORD_RECURSION + bool "Record functions that recurse in function tracing" + depends on FUNCTION_TRACER + help + All callbacks that attach to the function tracing have some sort + of protection against recursion. Even though the protection exists, + it adds overhead. This option will create a file in the tracefs + file system called "recursed_functions" that will list the functions + that triggered a recursion. + + This will add more overhead to cases that have recursion. + + If unsure, say N + +config FTRACE_RECORD_RECURSION_SIZE + int "Max number of recursed functions to record" + default 128 + depends on FTRACE_RECORD_RECURSION + help + This defines the limit of number of functions that can be + listed in the "recursed_functions" file, that lists all + the functions that caused a recursion to happen. + This file can be reset, but the limit can not change in + size at runtime. + +config RING_BUFFER_RECORD_RECURSION + bool "Record functions that recurse in the ring buffer" + depends on FTRACE_RECORD_RECURSION + # default y, because it is coupled with FTRACE_RECORD_RECURSION + default y + help + The ring buffer has its own internal recursion. Although when + recursion happens it wont cause harm because of the protection, + but it does cause an unwanted overhead. Enabling this option will + place where recursion was detected into the ftrace "recursed_functions" + file. + + This will add more overhead to cases that have recursion. + config GCOV_PROFILE_FTRACE bool "Enable GCOV profiling on ftrace subsystem" depends on GCOV_KERNEL @@ -797,6 +843,26 @@ config RING_BUFFER_STARTUP_TEST If unsure, say N +config RING_BUFFER_VALIDATE_TIME_DELTAS + bool "Verify ring buffer time stamp deltas" + depends on RING_BUFFER + help + This will audit the time stamps on the ring buffer sub + buffer to make sure that all the time deltas for the + events on a sub buffer matches the current time stamp. + This audit is performed for every event that is not + interrupted, or interrupting another event. A check + is also made when traversing sub buffers to make sure + that all the deltas on the previous sub buffer do not + add up to be greater than the current time stamp. + + NOTE: This adds significant overhead to recording of events, + and should only be used to test the logic of the ring buffer. + Do not use it on production systems. + + Only say Y if you understand what this does, and you + still want it enabled. Otherwise say N + config MMIOTRACE_TEST tristate "Test module for mmiotrace" depends on MMIOTRACE && m diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index e153be351548..7e44cea89fdc 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -92,6 +92,7 @@ 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-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 4b3a42fc3b24..fb0fe4c66b84 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -449,7 +449,7 @@ static struct dentry *blk_create_buf_file_callback(const char *filename, &relay_file_operations); } -static struct rchan_callbacks blk_relay_callbacks = { +static const struct rchan_callbacks blk_relay_callbacks = { .subbuf_start = blk_subbuf_start_callback, .create_buf_file = blk_create_buf_file_callback, .remove_buf_file = blk_remove_buf_file_callback, @@ -458,14 +458,9 @@ static struct rchan_callbacks blk_relay_callbacks = { static void blk_trace_setup_lba(struct blk_trace *bt, struct block_device *bdev) { - struct hd_struct *part = NULL; - - if (bdev) - part = bdev->bd_part; - - if (part) { - bt->start_lba = part->start_sect; - bt->end_lba = part->start_sect + part->nr_sects; + if (bdev) { + bt->start_lba = bdev->bd_start_sect; + bt->end_lba = bdev->bd_start_sect + bdev_nr_sectors(bdev); } else { bt->start_lba = 0; bt->end_lba = -1ULL; @@ -527,7 +522,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, * and scsi-generic block devices we create a temporary new debugfs * directory that will be removed once the trace ends. */ - if (bdev && bdev == bdev->bd_contains) + if (bdev && !bdev_is_partition(bdev)) dir = q->debugfs_dir; else bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root); @@ -793,19 +788,19 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) return cgroup_id(bio_blkcg(bio)->css.cgroup); } #else -u64 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) { return 0; } #endif static u64 -blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) +blk_trace_request_get_cgid(struct request *rq) { if (!rq->bio) return 0; /* Use the first bio */ - return blk_trace_bio_get_cgid(q, rq->bio); + return blk_trace_bio_get_cgid(rq->q, rq->bio); } /* @@ -846,40 +841,35 @@ static void blk_add_trace_rq(struct request *rq, int error, rcu_read_unlock(); } -static void blk_add_trace_rq_insert(void *ignore, - struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_insert(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } -static void blk_add_trace_rq_issue(void *ignore, - struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_issue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } -static void blk_add_trace_rq_merge(void *ignore, - struct request_queue *q, struct request *rq) +static void blk_add_trace_rq_merge(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } -static void blk_add_trace_rq_requeue(void *ignore, - struct request_queue *q, - struct request *rq) +static void blk_add_trace_rq_requeue(void *ignore, struct request *rq) { blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); } static void blk_add_trace_rq_complete(void *ignore, struct request *rq, int error, unsigned int nr_bytes) { blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE, - blk_trace_request_get_cgid(rq->q, rq)); + blk_trace_request_get_cgid(rq)); } /** @@ -911,10 +901,9 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, rcu_read_unlock(); } -static void blk_add_trace_bio_bounce(void *ignore, - struct request_queue *q, struct bio *bio) +static void blk_add_trace_bio_bounce(void *ignore, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0); + blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_BOUNCE, 0); } static void blk_add_trace_bio_complete(void *ignore, @@ -924,63 +913,24 @@ static void blk_add_trace_bio_complete(void *ignore, blk_status_to_errno(bio->bi_status)); } -static void blk_add_trace_bio_backmerge(void *ignore, - struct request_queue *q, - struct request *rq, - struct bio *bio) +static void blk_add_trace_bio_backmerge(void *ignore, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0); + blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_BACKMERGE, 0); } -static void blk_add_trace_bio_frontmerge(void *ignore, - struct request_queue *q, - struct request *rq, - struct bio *bio) +static void blk_add_trace_bio_frontmerge(void *ignore, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0); + blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_FRONTMERGE, 0); } -static void blk_add_trace_bio_queue(void *ignore, - struct request_queue *q, struct bio *bio) +static void blk_add_trace_bio_queue(void *ignore, struct bio *bio) { - blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0); + blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_QUEUE, 0); } -static void blk_add_trace_getrq(void *ignore, - struct request_queue *q, - struct bio *bio, int rw) -{ - if (bio) - blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); - else { - struct blk_trace *bt; - - rcu_read_lock(); - bt = rcu_dereference(q->blk_trace); - if (bt) - __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, - NULL, 0); - rcu_read_unlock(); - } -} - - -static void blk_add_trace_sleeprq(void *ignore, - struct request_queue *q, - struct bio *bio, int rw) +static void blk_add_trace_getrq(void *ignore, struct bio *bio) { - if (bio) - blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); - else { - struct blk_trace *bt; - - rcu_read_lock(); - bt = rcu_dereference(q->blk_trace); - if (bt) - __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, - 0, 0, NULL, 0); - rcu_read_unlock(); - } + blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_GETRQ, 0); } static void blk_add_trace_plug(void *ignore, struct request_queue *q) @@ -1015,10 +965,9 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, rcu_read_unlock(); } -static void blk_add_trace_split(void *ignore, - struct request_queue *q, struct bio *bio, - unsigned int pdu) +static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu) { + struct request_queue *q = bio->bi_disk->queue; struct blk_trace *bt; rcu_read_lock(); @@ -1039,20 +988,16 @@ static void blk_add_trace_split(void *ignore, /** * blk_add_trace_bio_remap - Add a trace for a bio-remap operation * @ignore: trace callback data parameter (not used) - * @q: queue the io is for * @bio: the source bio - * @dev: target device + * @dev: source device * @from: source sector * - * Description: - * Device mapper or raid target sometimes need to split a bio because - * it spans a stripe (or similar). Add a trace for that action. - * + * Called after a bio is remapped to a different device and/or sector. **/ -static void blk_add_trace_bio_remap(void *ignore, - struct request_queue *q, struct bio *bio, - dev_t dev, sector_t from) +static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev, + sector_t from) { + struct request_queue *q = bio->bi_disk->queue; struct blk_trace *bt; struct blk_io_trace_remap r; @@ -1077,7 +1022,6 @@ static void blk_add_trace_bio_remap(void *ignore, /** * blk_add_trace_rq_remap - Add a trace for a request-remap operation * @ignore: trace callback data parameter (not used) - * @q: queue the io is for * @rq: the source request * @dev: target device * @from: source sector @@ -1087,16 +1031,14 @@ static void blk_add_trace_bio_remap(void *ignore, * Add a trace for that action. * **/ -static void blk_add_trace_rq_remap(void *ignore, - struct request_queue *q, - struct request *rq, dev_t dev, +static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { struct blk_trace *bt; struct blk_io_trace_remap r; rcu_read_lock(); - bt = rcu_dereference(q->blk_trace); + bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; @@ -1108,13 +1050,12 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, - sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + sizeof(r), &r, blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } /** * blk_add_driver_data - Add binary message with driver-specific data - * @q: queue the io is for * @rq: io request * @data: driver-specific data * @len: length of driver-specific data @@ -1123,14 +1064,12 @@ static void blk_add_trace_rq_remap(void *ignore, * Some drivers might want to write driver-specific data per request. * **/ -void blk_add_driver_data(struct request_queue *q, - struct request *rq, - void *data, size_t len) +void blk_add_driver_data(struct request *rq, void *data, size_t len) { struct blk_trace *bt; rcu_read_lock(); - bt = rcu_dereference(q->blk_trace); + bt = rcu_dereference(rq->q->blk_trace); if (likely(!bt)) { rcu_read_unlock(); return; @@ -1138,7 +1077,7 @@ void blk_add_driver_data(struct request_queue *q, __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, - blk_trace_request_get_cgid(q, rq)); + blk_trace_request_get_cgid(rq)); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1169,8 +1108,6 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_getrq(blk_add_trace_getrq, NULL); WARN_ON(ret); - ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); - WARN_ON(ret); ret = register_trace_block_plug(blk_add_trace_plug, NULL); WARN_ON(ret); ret = register_trace_block_unplug(blk_add_trace_unplug, NULL); @@ -1190,7 +1127,6 @@ static void blk_unregister_tracepoints(void) unregister_trace_block_split(blk_add_trace_split, NULL); unregister_trace_block_unplug(blk_add_trace_unplug, NULL); unregister_trace_block_plug(blk_add_trace_plug, NULL); - unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL); unregister_trace_block_getrq(blk_add_trace_getrq, NULL); unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL); unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL); @@ -1343,7 +1279,7 @@ static void blk_log_action(struct trace_iterator *iter, const char *act, * ones now use the 64bit ino as the whole ID and * no longer use generation. * - * Regarldess of the content, always output + * Regardless 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(). @@ -1385,7 +1321,7 @@ static void blk_log_dump_pdu(struct trace_seq *s, i == 0 ? "" : " ", pdu_buf[i]); /* - * stop when the rest is just zeroes and indicate so + * stop when the rest is just zeros and indicate so * with a ".." appended */ if (i == end && end != pdu_len - 1) { @@ -1815,32 +1751,15 @@ static ssize_t blk_trace_mask2str(char *buf, int mask) return p - buf; } -static struct request_queue *blk_trace_get_queue(struct block_device *bdev) -{ - if (bdev->bd_disk == NULL) - return NULL; - - return bdev_get_queue(bdev); -} - static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct hd_struct *p = dev_to_part(dev); - struct request_queue *q; - struct block_device *bdev; + struct block_device *bdev = dev_to_bdev(dev); + struct request_queue *q = bdev_get_queue(bdev); struct blk_trace *bt; ssize_t ret = -ENXIO; - bdev = bdget(part_devt(p)); - if (bdev == NULL) - goto out; - - q = blk_trace_get_queue(bdev); - if (q == NULL) - goto out_bdput; - mutex_lock(&q->debugfs_mutex); bt = rcu_dereference_protected(q->blk_trace, @@ -1863,9 +1782,6 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); -out_bdput: - bdput(bdev); -out: return ret; } @@ -1873,9 +1789,8 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct block_device *bdev; - struct request_queue *q; - struct hd_struct *p; + struct block_device *bdev = dev_to_bdev(dev); + struct request_queue *q = bdev_get_queue(bdev); struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1891,19 +1806,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, goto out; value = ret; } - } else if (kstrtoull(buf, 0, &value)) - goto out; - - ret = -ENXIO; - - p = dev_to_part(dev); - bdev = bdget(part_devt(p)); - if (bdev == NULL) - goto out; - - q = blk_trace_get_queue(bdev); - if (q == NULL) - goto out_bdput; + } else { + if (kstrtoull(buf, 0, &value)) + goto out; + } mutex_lock(&q->debugfs_mutex); @@ -1941,8 +1847,6 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, out_unlock_bdev: mutex_unlock(&q->debugfs_mutex); -out_bdput: - bdput(bdev); out: return ret ? ret : count; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a8d4f253ed77..764400260eb6 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/bpf.h> #include <linux/bpf_perf_event.h> +#include <linux/btf.h> #include <linux/filter.h> #include <linux/uaccess.h> #include <linux/ctype.h> @@ -15,6 +16,12 @@ #include <linux/syscalls.h> #include <linux/error-injection.h> #include <linux/btf_ids.h> +#include <linux/bpf_lsm.h> + +#include <net/bpf_sk_storage.h> + +#include <uapi/linux/bpf.h> +#include <uapi/linux/btf.h> #include <asm/tlb.h> @@ -67,6 +74,10 @@ static struct bpf_raw_event_map *bpf_get_raw_tracepoint_module(const char *name) u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, + u64 flags, const struct btf **btf, + s32 *btf_id); + /** * trace_call_bpf - invoke BPF program * @call: tracepoint event @@ -85,9 +96,6 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { unsigned int ret; - if (in_nmi()) /* not supported yet */ - return 1; - cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { @@ -105,7 +113,7 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock * to all call sites, we did a bpf_prog_array_valid() there to check * whether call->prog_array is empty or not, which is - * a heurisitc to speed up execution. + * a heuristic to speed up execution. * * If bpf_prog_array_valid() fetched prog_array was * non-NULL, we go into trace_call_bpf() and do the actual @@ -173,6 +181,16 @@ bpf_probe_read_user_str_common(void *dst, u32 size, { int ret; + /* + * NB: We rely on strncpy_from_user() not copying junk past the NUL + * terminator into `dst`. + * + * strncpy_from_user() does long-sized strides in the fast path. If the + * strncpy does not mask out the bytes after the NUL in `unsafe_ptr`, + * then there could be junk after the NUL in `dst`. If user takes `dst` + * and keys a hash map with it, then semantically identical strings can + * occupy multiple entries in the map. + */ ret = strncpy_from_user_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); @@ -743,19 +761,18 @@ out: return err; } -BTF_ID_LIST(bpf_seq_printf_btf_ids) -BTF_ID(struct, seq_file) +BTF_ID_LIST_SINGLE(btf_seq_file_ids, struct, seq_file) static const struct bpf_func_proto bpf_seq_printf_proto = { .func = bpf_seq_printf, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM_OR_NULL, .arg5_type = ARG_CONST_SIZE_OR_ZERO, - .btf_id = bpf_seq_printf_btf_ids, }; BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len) @@ -763,17 +780,39 @@ BPF_CALL_3(bpf_seq_write, struct seq_file *, m, const void *, data, u32, len) return seq_write(m, data, len) ? -EOVERFLOW : 0; } -BTF_ID_LIST(bpf_seq_write_btf_ids) -BTF_ID(struct, seq_file) - static const struct bpf_func_proto bpf_seq_write_proto = { .func = bpf_seq_write, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_seq_file_ids[0], .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, - .btf_id = bpf_seq_write_btf_ids, +}; + +BPF_CALL_4(bpf_seq_printf_btf, struct seq_file *, m, struct btf_ptr *, ptr, + u32, btf_ptr_size, u64, flags) +{ + const struct btf *btf; + s32 btf_id; + int ret; + + ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id); + if (ret) + return ret; + + return btf_type_seq_show_flags(btf, btf_id, ptr->ptr, m, flags); +} + +static const struct bpf_func_proto bpf_seq_printf_btf_proto = { + .func = bpf_seq_printf_btf, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_seq_file_ids[0], + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, }; static __always_inline int @@ -993,6 +1032,20 @@ const struct bpf_func_proto bpf_get_current_task_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_get_current_task_btf) +{ + return (unsigned long) current; +} + +BTF_ID_LIST_SINGLE(bpf_get_current_btf_ids, struct, task_struct) + +static const struct bpf_func_proto bpf_get_current_task_btf_proto = { + .func = bpf_get_current_task_btf, + .gpl_only = true, + .ret_type = RET_PTR_TO_BTF_ID, + .ret_btf_id = &bpf_get_current_btf_ids[0], +}; + BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); @@ -1057,7 +1110,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) return -EINVAL; work = this_cpu_ptr(&send_signal_work); - if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) + if (irq_work_is_busy(&work->irq_work)) return -EBUSY; /* Add the current task, which is the target of sending signal, @@ -1098,6 +1151,122 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_d_path, struct path *, path, char *, buf, u32, sz) +{ + long len; + char *p; + + if (!sz) + return 0; + + p = d_path(path, buf, sz); + if (IS_ERR(p)) { + len = PTR_ERR(p); + } else { + len = buf + sz - p; + memmove(buf, p, len); + } + + return len; +} + +BTF_SET_START(btf_allowlist_d_path) +#ifdef CONFIG_SECURITY +BTF_ID(func, security_file_permission) +BTF_ID(func, security_inode_getattr) +BTF_ID(func, security_file_open) +#endif +#ifdef CONFIG_SECURITY_PATH +BTF_ID(func, security_path_truncate) +#endif +BTF_ID(func, vfs_truncate) +BTF_ID(func, vfs_fallocate) +BTF_ID(func, dentry_open) +BTF_ID(func, vfs_getattr) +BTF_ID(func, filp_close) +BTF_SET_END(btf_allowlist_d_path) + +static bool bpf_d_path_allowed(const struct bpf_prog *prog) +{ + if (prog->type == BPF_PROG_TYPE_LSM) + return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); + + return btf_id_set_contains(&btf_allowlist_d_path, + prog->aux->attach_btf_id); +} + +BTF_ID_LIST_SINGLE(bpf_d_path_btf_ids, struct, path) + +static const struct bpf_func_proto bpf_d_path_proto = { + .func = bpf_d_path, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_d_path_btf_ids[0], + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .allowed = bpf_d_path_allowed, +}; + +#define BTF_F_ALL (BTF_F_COMPACT | BTF_F_NONAME | \ + BTF_F_PTR_RAW | BTF_F_ZERO) + +static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size, + u64 flags, const struct btf **btf, + s32 *btf_id) +{ + const struct btf_type *t; + + if (unlikely(flags & ~(BTF_F_ALL))) + return -EINVAL; + + if (btf_ptr_size != sizeof(struct btf_ptr)) + return -EINVAL; + + *btf = bpf_get_btf_vmlinux(); + + if (IS_ERR_OR_NULL(*btf)) + return IS_ERR(*btf) ? PTR_ERR(*btf) : -EINVAL; + + if (ptr->type_id > 0) + *btf_id = ptr->type_id; + else + return -EINVAL; + + if (*btf_id > 0) + t = btf_type_by_id(*btf, *btf_id); + if (*btf_id <= 0 || !t) + return -ENOENT; + + return 0; +} + +BPF_CALL_5(bpf_snprintf_btf, char *, str, u32, str_size, struct btf_ptr *, ptr, + u32, btf_ptr_size, u64, flags) +{ + const struct btf *btf; + s32 btf_id; + int ret; + + ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id); + if (ret) + return ret; + + return btf_type_snprintf_show(btf, btf_id, ptr->ptr, str, str_size, + flags); +} + +const struct bpf_func_proto bpf_snprintf_btf_proto = { + .func = bpf_snprintf_btf, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_CONST_SIZE, + .arg5_type = ARG_ANYTHING, +}; + const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1118,12 +1287,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; + case BPF_FUNC_get_current_task_btf: + return &bpf_get_current_task_btf_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: @@ -1182,6 +1355,14 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_jiffies64_proto; case BPF_FUNC_get_task_stack: return &bpf_get_task_stack_proto; + case BPF_FUNC_copy_from_user: + return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL; + case BPF_FUNC_snprintf_btf: + return &bpf_snprintf_btf_proto; + case BPF_FUNC_per_cpu_ptr: + return &bpf_per_cpu_ptr_proto; + case BPF_FUNC_this_cpu_ptr: + return &bpf_this_cpu_ptr_proto; default: return NULL; } @@ -1570,6 +1751,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_tracing_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_tracing_proto; + case BPF_FUNC_sock_from_file: + return &bpf_sock_from_file_proto; #endif case BPF_FUNC_seq_printf: return prog->expected_attach_type == BPF_TRACE_ITER ? @@ -1579,6 +1766,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return prog->expected_attach_type == BPF_TRACE_ITER ? &bpf_seq_write_proto : NULL; + case BPF_FUNC_seq_printf_btf: + return prog->expected_attach_type == BPF_TRACE_ITER ? + &bpf_seq_printf_btf_proto : + NULL; + case BPF_FUNC_d_path: + return &bpf_d_path_proto; default: return raw_tp_prog_func_proto(func_id, prog); } @@ -1625,6 +1818,9 @@ const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { }; const struct bpf_prog_ops raw_tracepoint_prog_ops = { +#ifdef CONFIG_NET + .test_run = bpf_prog_test_run_raw_tp, +#endif }; const struct bpf_verifier_ops tracing_verifier_ops = { @@ -1873,10 +2069,12 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) { - struct module *mod = __module_address((unsigned long)btp); + struct module *mod; - if (mod) - module_put(mod); + preempt_disable(); + mod = __module_address((unsigned long)btp); + module_put(mod); + preempt_enable(); } static __always_inline @@ -2027,10 +2225,11 @@ static int bpf_event_notify(struct notifier_block *nb, unsigned long op, { struct bpf_trace_module *btm, *tmp; struct module *mod = module; + int ret = 0; if (mod->num_bpf_raw_events == 0 || (op != MODULE_STATE_COMING && op != MODULE_STATE_GOING)) - return 0; + goto out; mutex_lock(&bpf_module_mutex); @@ -2040,6 +2239,8 @@ static int bpf_event_notify(struct notifier_block *nb, unsigned long op, if (btm) { btm->module = module; list_add(&btm->list, &bpf_trace_modules); + } else { + ret = -ENOMEM; } break; case MODULE_STATE_GOING: @@ -2055,7 +2256,8 @@ static int bpf_event_notify(struct notifier_block *nb, unsigned long op, mutex_unlock(&bpf_module_mutex); - return 0; +out: + return notifier_from_errno(ret); } static struct notifier_block bpf_module_nb = { diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 1af321dec0f1..29a6ebeebc9e 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -334,8 +334,7 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, static struct ftrace_ops graph_ops = { .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | - FTRACE_OPS_FL_INITIALIZED | + .flags = FTRACE_OPS_FL_INITIALIZED | FTRACE_OPS_FL_PID | FTRACE_OPS_FL_STUB, #ifdef FTRACE_GRAPH_TRAMP_ADDR @@ -387,15 +386,14 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) } } - read_lock(&tasklist_lock); - do_each_thread(g, t) { + rcu_read_lock(); + for_each_process_thread(g, t) { if (start == end) { ret = -EAGAIN; goto unlock; } if (t->ret_stack == NULL) { - atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; t->curr_ret_depth = -1; @@ -403,10 +401,10 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) smp_wmb(); t->ret_stack = ret_stack_list[start++]; } - } while_each_thread(g, t); + } unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); free: for (i = start; i < end; i++) kfree(ret_stack_list[i]); @@ -490,7 +488,6 @@ static DEFINE_PER_CPU(struct ftrace_ret_stack *, idle_ret_stack); static void graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) { - atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->ftrace_timestamp = 0; /* make curr_ret_stack visible before we add the ret_stack */ diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 541453927c82..4d8e35575549 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -80,7 +80,7 @@ enum { struct ftrace_ops ftrace_list_end __read_mostly = { .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_STUB, + .flags = FTRACE_OPS_FL_STUB, INIT_OPS_HASH(ftrace_list_end) }; @@ -121,7 +121,7 @@ struct ftrace_ops global_ops; #if ARCH_SUPPORTS_FTRACE_OPS static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *regs); + struct ftrace_ops *op, struct ftrace_regs *fregs); #else /* See comment below, where ftrace_ops_list_func is defined */ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); @@ -140,7 +140,7 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops) } static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { struct trace_array *tr = op->private; int pid; @@ -154,7 +154,7 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, return; } - op->saved_func(ip, parent_ip, op, regs); + op->saved_func(ip, parent_ip, op, fregs); } static void ftrace_sync_ipi(void *data) @@ -230,7 +230,7 @@ static void update_ftrace_function(void) /* * For static tracing, we need to be a bit more careful. * The function change takes affect immediately. Thus, - * we need to coorditate the setting of the function_trace_ops + * we need to coordinate the setting of the function_trace_ops * with the setting of the ftrace_trace_function. * * Set the function to the list ops, which will call the @@ -754,7 +754,7 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) static void function_profile_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *regs) + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; @@ -866,7 +866,7 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED, + .flags = FTRACE_OPS_FL_INITIALIZED, INIT_OPS_HASH(ftrace_profile_ops) }; @@ -1040,8 +1040,7 @@ struct ftrace_ops global_ops = { .local_hash.notrace_hash = EMPTY_HASH, .local_hash.filter_hash = EMPTY_HASH, INIT_OPS_HASH(global_ops) - .flags = FTRACE_OPS_FL_RECURSION_SAFE | - FTRACE_OPS_FL_INITIALIZED | + .flags = FTRACE_OPS_FL_INITIALIZED | FTRACE_OPS_FL_PID, }; @@ -1368,10 +1367,10 @@ static struct ftrace_hash *dup_hash(struct ftrace_hash *src, int size) int i; /* - * Make the hash size about 1/2 the # found + * Use around half the size (max bit of it), but + * a minimum of 2 is fine (as size of 0 or 1 both give 1 for bits). */ - for (size /= 2; size; size >>= 1) - bits++; + bits = fls(size / 2); /* Don't allocate too much */ if (bits > FTRACE_HASH_MAX_BITS) @@ -1451,7 +1450,7 @@ static bool hash_contains_ip(unsigned long ip, { /* * The function record is a match if it exists in the filter - * hash and not in the notrace hash. Note, an emty hash is + * hash and not in the notrace hash. Note, an empty hash is * considered a match for the filter hash, but an empty * notrace hash is considered not in the notrace hash. */ @@ -1629,6 +1628,8 @@ static bool test_rec_ops_needs_regs(struct dyn_ftrace *rec) static struct ftrace_ops * ftrace_find_tramp_ops_any(struct dyn_ftrace *rec); static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude); +static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops); static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, @@ -1778,7 +1779,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, * to it. */ if (ftrace_rec_count(rec) == 1 && - ftrace_find_tramp_ops_any(rec)) + ftrace_find_tramp_ops_any_other(rec, ops)) rec->flags |= FTRACE_FL_TRAMP; else rec->flags &= ~FTRACE_FL_TRAMP; @@ -2144,6 +2145,7 @@ 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) @@ -2245,6 +2247,24 @@ ftrace_find_tramp_ops_any(struct dyn_ftrace *rec) } static struct ftrace_ops * +ftrace_find_tramp_ops_any_other(struct dyn_ftrace *rec, struct ftrace_ops *op_exclude) +{ + struct ftrace_ops *op; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (op == op_exclude || !op->trampoline) + continue; + + if (hash_contains_ip(ip, op->func_hash)) + return op; + } while_for_each_ftrace_op(op); + + return NULL; +} + +static struct ftrace_ops * ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *op) { @@ -2369,8 +2389,9 @@ unsigned long ftrace_find_rec_direct(unsigned long ip) } static void call_direct_funcs(unsigned long ip, unsigned long pip, - struct ftrace_ops *ops, struct pt_regs *regs) + struct ftrace_ops *ops, struct ftrace_regs *fregs) { + struct pt_regs *regs = ftrace_get_regs(fregs); unsigned long addr; addr = ftrace_find_rec_direct(ip); @@ -2382,7 +2403,7 @@ static void call_direct_funcs(unsigned long ip, unsigned long pip, struct ftrace_ops direct_ops = { .func = call_direct_funcs, - .flags = FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_RECURSION_SAFE + .flags = FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_PERMANENT, /* @@ -2402,7 +2423,7 @@ struct ftrace_ops direct_ops = { * * If the record has the FTRACE_FL_REGS set, that means that it * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS - * is not not set, then it wants to convert to the normal callback. + * is not set, then it wants to convert to the normal callback. * * Returns the address of the trampoline to set to */ @@ -2976,7 +2997,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) synchronize_rcu_tasks_rude(); /* - * When the kernel is preeptive, tasks can be preempted + * When the kernel is preemptive, tasks can be preempted * while on a ftrace trampoline. Just scheduling a task on * a CPU is not good enough to flush them. Calling * synchornize_rcu_tasks() will wait for those tasks to @@ -3129,18 +3150,20 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs) static int ftrace_allocate_records(struct ftrace_page *pg, int count) { int order; + int pages; int cnt; if (WARN_ON(!count)) return -EINVAL; - order = get_count_order(DIV_ROUND_UP(count, ENTRIES_PER_PAGE)); + pages = DIV_ROUND_UP(count, ENTRIES_PER_PAGE); + order = get_count_order(pages); /* * We want to fill as much as possible. No more than a page * may be empty. */ - while ((PAGE_SIZE << order) / ENTRY_SIZE >= count + ENTRIES_PER_PAGE) + if (!is_power_of_2(pages)) order--; again: @@ -4161,7 +4184,6 @@ static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, struct ftrace_hash **orig_hash, *new_hash; LIST_HEAD(process_mods); char *func; - int ret; mutex_lock(&ops->func_hash->regex_lock); @@ -4214,7 +4236,7 @@ static void process_mod_list(struct list_head *head, struct ftrace_ops *ops, mutex_lock(&ftrace_lock); - ret = ftrace_hash_move_and_update_ops(ops, orig_hash, + ftrace_hash_move_and_update_ops(ops, orig_hash, new_hash, enable); mutex_unlock(&ftrace_lock); @@ -4292,7 +4314,7 @@ static int __init ftrace_mod_cmd_init(void) core_initcall(ftrace_mod_cmd_init); static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { struct ftrace_probe_ops *probe_ops; struct ftrace_func_probe *probe; @@ -4368,7 +4390,7 @@ void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper, * @ip: The instruction pointer address to map @data to * @data: The data to map to @ip * - * Returns 0 on succes otherwise an error. + * Returns 0 on success otherwise an error. */ int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper, unsigned long ip, void *data) @@ -4536,7 +4558,7 @@ register_ftrace_function_probe(char *glob, struct trace_array *tr, /* * 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. + * may be NULL or empty. Need to be careful when reading the loop. */ mutex_lock(&probe->ops.func_hash->regex_lock); @@ -5566,7 +5588,6 @@ int ftrace_regex_release(struct inode *inode, struct file *file) struct ftrace_hash **orig_hash; struct trace_parser *parser; int filter_hash; - int ret; if (file->f_mode & FMODE_READ) { iter = m->private; @@ -5594,7 +5615,7 @@ int ftrace_regex_release(struct inode *inode, struct file *file) orig_hash = &iter->ops->func_hash->notrace_hash; mutex_lock(&ftrace_lock); - ret = ftrace_hash_move_and_update_ops(iter->ops, orig_hash, + ftrace_hash_move_and_update_ops(iter->ops, orig_hash, iter->hash, filter_hash); mutex_unlock(&ftrace_lock); } else { @@ -6862,8 +6883,7 @@ void ftrace_init_trace_array(struct trace_array *tr) struct ftrace_ops global_ops = { .func = ftrace_stub, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | - FTRACE_OPS_FL_INITIALIZED | + .flags = FTRACE_OPS_FL_INITIALIZED | FTRACE_OPS_FL_PID, }; @@ -6913,12 +6933,13 @@ void ftrace_reset_array_ops(struct trace_array *tr) static nokprobe_inline void __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ignored, struct pt_regs *regs) + struct ftrace_ops *ignored, struct ftrace_regs *fregs) { + struct pt_regs *regs = ftrace_get_regs(fregs); struct ftrace_ops *op; int bit; - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX); if (bit < 0) return; @@ -6947,7 +6968,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, pr_warn("op=%p %pS\n", op, op); goto out; } - op->func(ip, parent_ip, op, regs); + op->func(ip, parent_ip, op, fregs); } } while_for_each_ftrace_op(op); out: @@ -6970,9 +6991,9 @@ out: */ #if ARCH_SUPPORTS_FTRACE_OPS static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { - __ftrace_ops_list_func(ip, parent_ip, NULL, regs); + __ftrace_ops_list_func(ip, parent_ip, NULL, fregs); } NOKPROBE_SYMBOL(ftrace_ops_list_func); #else @@ -6989,18 +7010,18 @@ NOKPROBE_SYMBOL(ftrace_ops_no_ops); * this function will be called by the mcount trampoline. */ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { int bit; - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); + bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX); if (bit < 0) return; preempt_disable_notrace(); if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) - op->func(ip, parent_ip, op, regs); + op->func(ip, parent_ip, op, fregs); preempt_enable_notrace(); trace_clear_recursion(bit); @@ -7021,11 +7042,11 @@ NOKPROBE_SYMBOL(ftrace_ops_assist_func); ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops) { /* - * If the function does not handle recursion, needs to be RCU safe, - * or does per cpu logic, then we need to call the assist handler. + * If the function does not handle recursion or needs to be RCU safe, + * then we need to call the assist handler. */ - if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE) || - ops->flags & FTRACE_OPS_FL_RCU) + if (ops->flags & (FTRACE_OPS_FL_RECURSION | + FTRACE_OPS_FL_RCU)) return ftrace_ops_assist_func; return ops->func; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 93ef0ab6ea20..ec08f948dd80 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4,6 +4,7 @@ * * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> */ +#include <linux/trace_recursion.h> #include <linux/trace_events.h> #include <linux/ring_buffer.h> #include <linux/trace_clock.h> @@ -129,7 +130,16 @@ int ring_buffer_print_entry_header(struct trace_seq *s) #define RB_ALIGNMENT 4U #define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX) #define RB_EVNT_MIN_SIZE 8U /* two 32bit words */ -#define RB_ALIGN_DATA __aligned(RB_ALIGNMENT) + +#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS +# define RB_FORCE_8BYTE_ALIGNMENT 0 +# define RB_ARCH_ALIGNMENT RB_ALIGNMENT +#else +# define RB_FORCE_8BYTE_ALIGNMENT 1 +# define RB_ARCH_ALIGNMENT 8U +#endif + +#define RB_ALIGN_DATA __aligned(RB_ARCH_ALIGNMENT) /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */ #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX @@ -438,14 +448,16 @@ enum { }; /* * Used for which event context the event is in. - * NMI = 0 - * IRQ = 1 - * SOFTIRQ = 2 - * NORMAL = 3 + * TRANSITION = 0 + * NMI = 1 + * IRQ = 2 + * SOFTIRQ = 3 + * NORMAL = 4 * * See trace_recursive_lock() comment below for more details. */ enum { + RB_CTX_TRANSITION, RB_CTX_NMI, RB_CTX_IRQ, RB_CTX_SOFTIRQ, @@ -793,7 +805,7 @@ static void rb_wake_up_waiters(struct irq_work *work) * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on - * @full: wait until a full page is available, if @cpu != RING_BUFFER_ALL_CPUS + * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise @@ -1420,7 +1432,8 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) return 0; } -static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu) +static int __rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, + long nr_pages, struct list_head *pages) { struct buffer_page *bpage, *tmp; bool user_thread = current->mm != NULL; @@ -1460,13 +1473,15 @@ static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu) struct page *page; bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()), - mflags, cpu_to_node(cpu)); + mflags, cpu_to_node(cpu_buffer->cpu)); if (!bpage) goto free_pages; + rb_check_bpage(cpu_buffer, bpage); + list_add(&bpage->list, pages); - page = alloc_pages_node(cpu_to_node(cpu), mflags, 0); + page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu), mflags, 0); if (!page) goto free_pages; bpage->page = page_address(page); @@ -1498,7 +1513,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer, WARN_ON(!nr_pages); - if (__rb_allocate_pages(nr_pages, &pages, cpu_buffer->cpu)) + if (__rb_allocate_pages(cpu_buffer, nr_pages, &pages)) return -ENOMEM; /* @@ -1952,18 +1967,18 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, { struct ring_buffer_per_cpu *cpu_buffer; unsigned long nr_pages; - int cpu, err = 0; + int cpu, err; /* * Always succeed at resizing a non-existent buffer: */ if (!buffer) - return size; + return 0; /* Make sure the requested buffer exists */ if (cpu_id != RING_BUFFER_ALL_CPUS && !cpumask_test_cpu(cpu_id, buffer->cpumask)) - return size; + return 0; nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE); @@ -1971,8 +1986,6 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, if (nr_pages < 2) nr_pages = 2; - size = nr_pages * BUF_PAGE_SIZE; - /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); @@ -2007,8 +2020,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, * allocated without receiving ENOMEM */ INIT_LIST_HEAD(&cpu_buffer->new_pages); - if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update, - &cpu_buffer->new_pages, cpu)) { + if (__rb_allocate_pages(cpu_buffer, cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages)) { /* not enough memory for new pages */ err = -ENOMEM; goto out_err; @@ -2073,8 +2086,8 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, INIT_LIST_HEAD(&cpu_buffer->new_pages); if (cpu_buffer->nr_pages_to_update > 0 && - __rb_allocate_pages(cpu_buffer->nr_pages_to_update, - &cpu_buffer->new_pages, cpu_id)) { + __rb_allocate_pages(cpu_buffer, cpu_buffer->nr_pages_to_update, + &cpu_buffer->new_pages)) { err = -ENOMEM; goto out_err; } @@ -2119,7 +2132,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, } mutex_unlock(&buffer->mutex); - return size; + return 0; out_err: for_each_buffer_cpu(buffer, cpu) { @@ -2626,9 +2639,6 @@ rb_add_time_stamp(struct ring_buffer_event *event, u64 delta, bool abs) return skip_time_extend(event); } -static inline bool rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer, - struct ring_buffer_event *event); - #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK static inline bool sched_clock_stable(void) { @@ -2717,7 +2727,7 @@ rb_update_event(struct ring_buffer_per_cpu *cpu_buffer, event->time_delta = delta; length -= RB_EVNT_HDR_SIZE; - if (length > RB_MAX_SMALL_DATA) { + if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) { event->type_len = 0; event->array[0] = length; } else @@ -2732,11 +2742,11 @@ static unsigned rb_calculate_event_length(unsigned length) if (!length) length++; - if (length > RB_MAX_SMALL_DATA) + if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) length += sizeof(event.array[0]); length += RB_EVNT_HDR_SIZE; - length = ALIGN(length, RB_ALIGNMENT); + length = ALIGN(length, RB_ARCH_ALIGNMENT); /* * In case the time delta is larger than the 27 bits for it @@ -2756,20 +2766,6 @@ static unsigned rb_calculate_event_length(unsigned length) return length; } -static __always_inline bool -rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer, - struct ring_buffer_event *event) -{ - unsigned long addr = (unsigned long)event; - unsigned long index; - - index = rb_event_index(event); - addr &= PAGE_MASK; - - return cpu_buffer->commit_page->page == (void *)addr && - rb_commit_index(cpu_buffer) == index; -} - static u64 rb_time_delta(struct ring_buffer_event *event) { switch (event->type_len) { @@ -3004,6 +3000,13 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) irq_work_queue(&cpu_buffer->irq_work.work); } +#ifdef CONFIG_RING_BUFFER_RECORD_RECURSION +# define do_ring_buffer_record_recursion() \ + do_ftrace_record_recursion(_THIS_IP_, _RET_IP_) +#else +# define do_ring_buffer_record_recursion() do { } while (0) +#endif + /* * The lock and unlock are done within a preempt disable section. * The current_context per_cpu variable can only be modified @@ -3014,10 +3017,10 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * a bit of overhead in something as critical as function tracing, * we use a bitmask trick. * - * bit 0 = NMI context - * bit 1 = IRQ context - * bit 2 = SoftIRQ context - * bit 3 = normal context. + * bit 1 = NMI context + * bit 2 = IRQ context + * bit 3 = SoftIRQ context + * bit 4 = normal context. * * This works because this is the order of contexts that can * preempt other contexts. A SoftIRQ never preempts an IRQ @@ -3040,6 +3043,30 @@ rb_wakeups(struct trace_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The least significant bit can be cleared this way, and it * just so happens that it is the same bit corresponding to * the current context. + * + * Now the TRANSITION bit breaks the above slightly. The TRANSITION bit + * is set when a recursion is detected at the current context, and if + * the TRANSITION bit is already set, it will fail the recursion. + * This is needed because there's a lag between the changing of + * interrupt context and updating the preempt count. In this case, + * a false positive will be found. To handle this, one extra recursion + * is allowed, and this is done by the TRANSITION bit. If the TRANSITION + * bit is already set, then it is considered a recursion and the function + * ends. Otherwise, the TRANSITION bit is set, and that bit is returned. + * + * On the trace_recursive_unlock(), the TRANSITION bit will be the first + * to be cleared. Even if it wasn't the context that set it. That is, + * if an interrupt comes in while NORMAL bit is set and the ring buffer + * is called before preempt_count() is updated, since the check will + * be on the NORMAL bit, the TRANSITION bit will then be set. If an + * NMI then comes in, it will set the NMI bit, but when the NMI code + * does the trace_recursive_unlock() it will clear the TRANSTION bit + * and leave the NMI bit set. But this is fine, because the interrupt + * code that set the TRANSITION bit will then clear the NMI bit when it + * calls trace_recursive_unlock(). If another NMI comes in, it will + * set the TRANSITION bit and continue. + * + * Note: The TRANSITION bit only handles a single transition between context. */ static __always_inline int @@ -3055,8 +3082,18 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) bit = pc & NMI_MASK ? RB_CTX_NMI : pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ; - if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) - return 1; + if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) { + /* + * It is possible that this was called by transitioning + * between interrupt context, and preempt_count() has not + * been updated yet. In this case, use the TRANSITION bit. + */ + bit = RB_CTX_TRANSITION; + if (val & (1 << (bit + cpu_buffer->nest))) { + do_ring_buffer_record_recursion(); + return 1; + } + } val |= (1 << (bit + cpu_buffer->nest)); cpu_buffer->current_context = val; @@ -3071,8 +3108,8 @@ trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->current_context - (1 << cpu_buffer->nest); } -/* The recursive locking above uses 4 bits */ -#define NESTED_BITS 4 +/* The recursive locking above uses 5 bits */ +#define NESTED_BITS 5 /** * ring_buffer_nest_start - Allow to trace while nested @@ -3149,6 +3186,153 @@ int ring_buffer_unlock_commit(struct trace_buffer *buffer, } EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit); +/* Special value to validate all deltas on a page. */ +#define CHECK_FULL_PAGE 1L + +#ifdef CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS +static void dump_buffer_page(struct buffer_data_page *bpage, + struct rb_event_info *info, + unsigned long tail) +{ + struct ring_buffer_event *event; + u64 ts, delta; + int e; + + ts = bpage->time_stamp; + pr_warn(" [%lld] PAGE TIME STAMP\n", ts); + + for (e = 0; e < tail; e += rb_event_length(event)) { + + event = (struct ring_buffer_event *)(bpage->data + e); + + switch (event->type_len) { + + case RINGBUF_TYPE_TIME_EXTEND: + delta = ring_buffer_event_time_stamp(event); + ts += delta; + pr_warn(" [%lld] delta:%lld TIME EXTEND\n", ts, delta); + break; + + case RINGBUF_TYPE_TIME_STAMP: + delta = ring_buffer_event_time_stamp(event); + ts = delta; + pr_warn(" [%lld] absolute:%lld TIME STAMP\n", ts, delta); + break; + + case RINGBUF_TYPE_PADDING: + ts += event->time_delta; + pr_warn(" [%lld] delta:%d PADDING\n", ts, event->time_delta); + break; + + case RINGBUF_TYPE_DATA: + ts += event->time_delta; + pr_warn(" [%lld] delta:%d\n", ts, event->time_delta); + break; + + default: + break; + } + } +} + +static DEFINE_PER_CPU(atomic_t, checking); +static atomic_t ts_dump; + +/* + * Check if the current event time stamp matches the deltas on + * the buffer page. + */ +static void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, + struct rb_event_info *info, + unsigned long tail) +{ + struct ring_buffer_event *event; + struct buffer_data_page *bpage; + u64 ts, delta; + bool full = false; + int e; + + bpage = info->tail_page->page; + + if (tail == CHECK_FULL_PAGE) { + full = true; + tail = local_read(&bpage->commit); + } else if (info->add_timestamp & + (RB_ADD_STAMP_FORCE | RB_ADD_STAMP_ABSOLUTE)) { + /* Ignore events with absolute time stamps */ + return; + } + + /* + * Do not check the first event (skip possible extends too). + * Also do not check if previous events have not been committed. + */ + if (tail <= 8 || tail > local_read(&bpage->commit)) + return; + + /* + * If this interrupted another event, + */ + if (atomic_inc_return(this_cpu_ptr(&checking)) != 1) + goto out; + + ts = bpage->time_stamp; + + for (e = 0; e < tail; e += rb_event_length(event)) { + + event = (struct ring_buffer_event *)(bpage->data + e); + + switch (event->type_len) { + + case RINGBUF_TYPE_TIME_EXTEND: + delta = ring_buffer_event_time_stamp(event); + ts += delta; + break; + + case RINGBUF_TYPE_TIME_STAMP: + delta = ring_buffer_event_time_stamp(event); + ts = delta; + break; + + case RINGBUF_TYPE_PADDING: + if (event->time_delta == 1) + break; + /* fall through */ + case RINGBUF_TYPE_DATA: + ts += event->time_delta; + break; + + default: + RB_WARN_ON(cpu_buffer, 1); + } + } + if ((full && ts > info->ts) || + (!full && ts + info->delta != info->ts)) { + /* If another report is happening, ignore this one */ + if (atomic_inc_return(&ts_dump) != 1) { + atomic_dec(&ts_dump); + goto out; + } + atomic_inc(&cpu_buffer->record_disabled); + pr_warn("[CPU: %d]TIME DOES NOT MATCH expected:%lld actual:%lld delta:%lld after:%lld\n", + cpu_buffer->cpu, + ts + info->delta, info->ts, info->delta, info->after); + dump_buffer_page(bpage, info, tail); + atomic_dec(&ts_dump); + /* Do not re-enable checking */ + return; + } +out: + atomic_dec(this_cpu_ptr(&checking)); +} +#else +static inline void check_buffer(struct ring_buffer_per_cpu *cpu_buffer, + struct rb_event_info *info, + unsigned long tail) +{ +} +#endif /* CONFIG_RING_BUFFER_VALIDATE_TIME_DELTAS */ + static struct ring_buffer_event * __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, struct rb_event_info *info) @@ -3200,14 +3384,14 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* See if we shot pass the end of this buffer page */ if (unlikely(write > BUF_PAGE_SIZE)) { - if (tail != w) { - /* before and after may now different, fix it up*/ - b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); - a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); - if (a_ok && b_ok && info->before != info->after) - (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, - info->before, info->after); - } + /* before and after may now different, fix it up*/ + b_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before); + a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after); + if (a_ok && b_ok && info->before != info->after) + (void)rb_time_cmpxchg(&cpu_buffer->before_stamp, + info->before, info->after); + if (a_ok && b_ok) + check_buffer(cpu_buffer, info, CHECK_FULL_PAGE); return rb_move_tail(cpu_buffer, tail, info); } @@ -3225,9 +3409,10 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, /* This did not interrupt any time update */ info->delta = info->ts - info->after; else - /* Just use full timestamp for inerrupting event */ + /* Just use full timestamp for interrupting event */ info->delta = info->ts; barrier(); + check_buffer(cpu_buffer, info, tail); if (unlikely(info->ts != save_before)) { /* SLOW PATH - Interrupted between C and E */ @@ -3253,15 +3438,15 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer, ts = rb_time_stamp(cpu_buffer->buffer); barrier(); /*E*/ if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) && - info->after < ts) { + info->after < ts && + rb_time_cmpxchg(&cpu_buffer->write_stamp, + info->after, ts)) { /* Nothing came after this event between C and E */ info->delta = ts - info->after; - (void)rb_time_cmpxchg(&cpu_buffer->write_stamp, - info->after, info->ts); info->ts = ts; } else { /* - * Interrupted beween C and E: + * Interrupted between C and E: * Lost the previous events time stamp. Just set the * delta to zero, and this will be the same time as * the event this event interrupted. And the events that @@ -3468,7 +3653,7 @@ rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer, } /** - * ring_buffer_commit_discard - discard an event that has not been committed + * ring_buffer_discard_commit - discard an event that has not been committed * @buffer: the ring buffer * @event: non committed event to discard * @@ -4866,6 +5051,9 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + atomic_inc(&cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); @@ -4876,6 +5064,8 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); + + mutex_unlock(&buffer->mutex); } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); @@ -4889,6 +5079,9 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer) struct ring_buffer_per_cpu *cpu_buffer; int cpu; + /* prevent another thread from changing buffer sizes */ + mutex_lock(&buffer->mutex); + for_each_online_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; @@ -4907,6 +5100,8 @@ void ring_buffer_reset_online_cpus(struct trace_buffer *buffer) atomic_dec(&cpu_buffer->record_disabled); atomic_dec(&cpu_buffer->resize_disabled); } + + mutex_unlock(&buffer->mutex); } /** diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 7d56d621ffea..a4b4bbf8c3bf 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -242,9 +242,11 @@ 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 = "char[]", .name = "dynstring_field_1" }, { .type = "u64", .name = "ts_ms" }, { .type = "unsigned int", .name = "cpu" }, { .type = "char[64]", .name = "my_string_field" }, + { .type = "char[]", .name = "dynstring_field_2" }, { .type = "int", .name = "my_int_field" }, }; @@ -254,7 +256,7 @@ static struct synth_field_desc create_synth_test_fields[] = { */ static int __init test_create_synth_event(void) { - u64 vals[7]; + u64 vals[9]; int ret; /* Create the create_synth_test event with the fields above */ @@ -292,10 +294,12 @@ static int __init test_create_synth_event(void) vals[0] = 777; /* next_pid_field */ vals[1] = (u64)(long)"tiddlywinks"; /* next_comm_field */ vals[2] = 1000000; /* ts_ns */ - vals[3] = 1000; /* ts_ms */ - vals[4] = raw_smp_processor_id(); /* cpu */ - vals[5] = (u64)(long)"thneed"; /* my_string_field */ - vals[6] = 398; /* my_int_field */ + vals[3] = (u64)(long)"xrayspecs"; /* dynstring_field_1 */ + vals[4] = 1000; /* ts_ms */ + vals[5] = raw_smp_processor_id(); /* cpu */ + vals[6] = (u64)(long)"thneed"; /* my_string_field */ + vals[7] = (u64)(long)"kerplunk"; /* dynstring_field_2 */ + vals[8] = 398; /* my_int_field */ /* Now generate a create_synth_test event */ ret = synth_event_trace_array(create_synth_test, vals, ARRAY_SIZE(vals)); @@ -303,7 +307,7 @@ static int __init test_create_synth_event(void) return ret; delete: /* We got an error after creating the event, delete it */ - ret = synth_event_delete("create_synth_test"); + synth_event_delete("create_synth_test"); goto out; } @@ -422,13 +426,15 @@ 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 */ + ret = synth_event_trace(create_synth_test, 9, /* number of values */ (u64)444, /* next_pid_field */ (u64)(long)"clackers", /* next_comm_field */ (u64)1000000, /* ts_ns */ + (u64)(long)"viewmaster",/* dynstring_field_1 */ (u64)1000, /* ts_ms */ (u64)raw_smp_processor_id(), /* cpu */ (u64)(long)"Thneed", /* my_string_field */ + (u64)(long)"yoyos", /* dynstring_field_2 */ (u64)999); /* my_int_field */ return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d3e5de717df2..b5815a022ecc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -68,10 +68,21 @@ bool ring_buffer_expanded; static bool __read_mostly tracing_selftest_running; /* - * If a tracer is running, we do not want to run SELFTEST. + * If boot-time tracing including tracers/events via kernel cmdline + * is running, we do not want to run SELFTEST. */ bool __read_mostly tracing_selftest_disabled; +#ifdef CONFIG_FTRACE_STARTUP_TEST +void __init disable_tracing_selftest(const char *reason) +{ + if (!tracing_selftest_disabled) { + tracing_selftest_disabled = true; + pr_info("Ftrace startup test is disabled due to %s\n", reason); + } +} +#endif + /* Pipe tracepoints to printk */ struct trace_iterator *tracepoint_print_iter; int tracepoint_printk; @@ -163,7 +174,8 @@ static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ int tracing_set_tracer(struct trace_array *tr, const char *buf); -static void ftrace_trace_userstack(struct trace_buffer *buffer, +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc); #define MAX_TRACER_SIZE 100 @@ -251,6 +263,145 @@ unsigned long long ns2usecs(u64 nsec) return nsec; } +static void +trace_process_export(struct trace_export *export, + struct ring_buffer_event *event, int flag) +{ + struct trace_entry *entry; + unsigned int size = 0; + + if (export->flags & flag) { + entry = ring_buffer_event_data(event); + size = ring_buffer_event_length(event); + export->write(export, entry, size); + } +} + +static DEFINE_MUTEX(ftrace_export_lock); + +static struct trace_export __rcu *ftrace_exports_list __read_mostly; + +static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled); +static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled); +static DEFINE_STATIC_KEY_FALSE(trace_marker_exports_enabled); + +static inline void ftrace_exports_enable(struct trace_export *export) +{ + if (export->flags & TRACE_EXPORT_FUNCTION) + static_branch_inc(&trace_function_exports_enabled); + + if (export->flags & TRACE_EXPORT_EVENT) + static_branch_inc(&trace_event_exports_enabled); + + if (export->flags & TRACE_EXPORT_MARKER) + static_branch_inc(&trace_marker_exports_enabled); +} + +static inline void ftrace_exports_disable(struct trace_export *export) +{ + if (export->flags & TRACE_EXPORT_FUNCTION) + static_branch_dec(&trace_function_exports_enabled); + + if (export->flags & TRACE_EXPORT_EVENT) + static_branch_dec(&trace_event_exports_enabled); + + if (export->flags & TRACE_EXPORT_MARKER) + static_branch_dec(&trace_marker_exports_enabled); +} + +static void ftrace_exports(struct ring_buffer_event *event, int flag) +{ + struct trace_export *export; + + preempt_disable_notrace(); + + export = rcu_dereference_raw_check(ftrace_exports_list); + while (export) { + trace_process_export(export, event, flag); + export = rcu_dereference_raw_check(export->next); + } + + preempt_enable_notrace(); +} + +static inline void +add_trace_export(struct trace_export **list, struct trace_export *export) +{ + rcu_assign_pointer(export->next, *list); + /* + * We are entering export into the list but another + * CPU might be walking that list. We need to make sure + * the export->next pointer is valid before another CPU sees + * the export pointer included into the list. + */ + rcu_assign_pointer(*list, export); +} + +static inline int +rm_trace_export(struct trace_export **list, struct trace_export *export) +{ + struct trace_export **p; + + for (p = list; *p != NULL; p = &(*p)->next) + if (*p == export) + break; + + if (*p != export) + return -1; + + rcu_assign_pointer(*p, (*p)->next); + + return 0; +} + +static inline void +add_ftrace_export(struct trace_export **list, struct trace_export *export) +{ + ftrace_exports_enable(export); + + add_trace_export(list, export); +} + +static inline int +rm_ftrace_export(struct trace_export **list, struct trace_export *export) +{ + int ret; + + ret = rm_trace_export(list, export); + ftrace_exports_disable(export); + + return ret; +} + +int register_ftrace_export(struct trace_export *export) +{ + if (WARN_ON_ONCE(!export->write)) + return -1; + + mutex_lock(&ftrace_export_lock); + + add_ftrace_export(&ftrace_exports_list, export); + + mutex_unlock(&ftrace_export_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(register_ftrace_export); + +int unregister_ftrace_export(struct trace_export *export) +{ + int ret; + + mutex_lock(&ftrace_export_lock); + + ret = rm_ftrace_export(&ftrace_exports_list, export); + + mutex_unlock(&ftrace_export_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(unregister_ftrace_export); + /* trace_flags holds trace_options default values */ #define TRACE_DEFAULT_FLAGS \ (FUNCTION_DEFAULT_FLAGS | \ @@ -1973,11 +2124,7 @@ int __init register_tracer(struct tracer *type) apply_trace_boot_options(); /* disable other selftests, since this will break it. */ - tracing_selftest_disabled = true; -#ifdef CONFIG_FTRACE_STARTUP_TEST - printk(KERN_INFO "Disabling FTRACE selftests due to running tracer '%s'\n", - type->name); -#endif + disable_tracing_selftest("running a tracer"); out_unlock: return ret; @@ -2511,7 +2658,7 @@ void trace_buffered_event_enable(void) preempt_disable(); if (cpu == smp_processor_id() && - this_cpu_read(trace_buffered_event) != + __this_cpu_read(trace_buffered_event) != per_cpu(trace_buffered_event, cpu)) WARN_ON_ONCE(1); preempt_enable(); @@ -2598,7 +2745,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, (entry = this_cpu_read(trace_buffered_event))) { /* Try to use the per cpu buffer first */ val = this_cpu_inc_return(trace_buffered_event_cnt); - if (val == 1) { + if ((len < (PAGE_SIZE - sizeof(*entry))) && val == 1) { trace_event_setup(entry, type, flags, pc); entry->array[0] = len; return entry; @@ -2611,7 +2758,7 @@ trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, /* * If tracing is off, but we have triggers enabled * we still need to look at the event data. Use the temp_buffer - * to store the trace event for the tigger to use. It's recusive + * to store the trace event for the trigger to use. It's recursive * safe and will not be recorded anywhere. */ if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) { @@ -2699,6 +2846,8 @@ void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); + if (static_branch_unlikely(&trace_event_exports_enabled)) + ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer, fbuffer->event, fbuffer->entry, fbuffer->flags, fbuffer->pc, fbuffer->regs); @@ -2729,7 +2878,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, * two. They are not that meaningful. */ ftrace_trace_stack(tr, buffer, flags, regs ? 0 : STACK_SKIP, pc, regs); - ftrace_trace_userstack(buffer, flags, pc); + ftrace_trace_userstack(tr, buffer, flags, pc); } /* @@ -2742,129 +2891,6 @@ trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, __buffer_unlock_commit(buffer, event); } -static void -trace_process_export(struct trace_export *export, - struct ring_buffer_event *event) -{ - struct trace_entry *entry; - unsigned int size = 0; - - entry = ring_buffer_event_data(event); - size = ring_buffer_event_length(event); - export->write(export, entry, size); -} - -static DEFINE_MUTEX(ftrace_export_lock); - -static struct trace_export __rcu *ftrace_exports_list __read_mostly; - -static DEFINE_STATIC_KEY_FALSE(ftrace_exports_enabled); - -static inline void ftrace_exports_enable(void) -{ - static_branch_enable(&ftrace_exports_enabled); -} - -static inline void ftrace_exports_disable(void) -{ - static_branch_disable(&ftrace_exports_enabled); -} - -static void ftrace_exports(struct ring_buffer_event *event) -{ - struct trace_export *export; - - preempt_disable_notrace(); - - export = rcu_dereference_raw_check(ftrace_exports_list); - while (export) { - trace_process_export(export, event); - export = rcu_dereference_raw_check(export->next); - } - - preempt_enable_notrace(); -} - -static inline void -add_trace_export(struct trace_export **list, struct trace_export *export) -{ - rcu_assign_pointer(export->next, *list); - /* - * We are entering export into the list but another - * CPU might be walking that list. We need to make sure - * the export->next pointer is valid before another CPU sees - * the export pointer included into the list. - */ - rcu_assign_pointer(*list, export); -} - -static inline int -rm_trace_export(struct trace_export **list, struct trace_export *export) -{ - struct trace_export **p; - - for (p = list; *p != NULL; p = &(*p)->next) - if (*p == export) - break; - - if (*p != export) - return -1; - - rcu_assign_pointer(*p, (*p)->next); - - return 0; -} - -static inline void -add_ftrace_export(struct trace_export **list, struct trace_export *export) -{ - if (*list == NULL) - ftrace_exports_enable(); - - add_trace_export(list, export); -} - -static inline int -rm_ftrace_export(struct trace_export **list, struct trace_export *export) -{ - int ret; - - ret = rm_trace_export(list, export); - if (*list == NULL) - ftrace_exports_disable(); - - return ret; -} - -int register_ftrace_export(struct trace_export *export) -{ - if (WARN_ON_ONCE(!export->write)) - return -1; - - mutex_lock(&ftrace_export_lock); - - add_ftrace_export(&ftrace_exports_list, export); - - mutex_unlock(&ftrace_export_lock); - - return 0; -} -EXPORT_SYMBOL_GPL(register_ftrace_export); - -int unregister_ftrace_export(struct trace_export *export) -{ - int ret; - - mutex_lock(&ftrace_export_lock); - - ret = rm_ftrace_export(&ftrace_exports_list, export); - - mutex_unlock(&ftrace_export_lock); - - return ret; -} -EXPORT_SYMBOL_GPL(unregister_ftrace_export); - void trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, unsigned long flags, @@ -2884,8 +2910,8 @@ trace_function(struct trace_array *tr, entry->parent_ip = parent_ip; if (!call_filter_check_discard(call, entry, buffer, event)) { - if (static_branch_unlikely(&ftrace_exports_enabled)) - ftrace_exports(event); + if (static_branch_unlikely(&trace_function_exports_enabled)) + ftrace_exports(event, TRACE_EXPORT_FUNCTION); __buffer_unlock_commit(buffer, event); } } @@ -2934,7 +2960,7 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; /* This should never happen. If it does, yell once and skip */ - if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING)) + if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING)) goto out; /* @@ -3038,13 +3064,14 @@ EXPORT_SYMBOL_GPL(trace_dump_stack); static DEFINE_PER_CPU(int, user_stack_count); static void -ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) +ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc) { struct trace_event_call *call = &event_user_stack; struct ring_buffer_event *event; struct userstack_entry *entry; - if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE)) + if (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE)) return; /* @@ -3083,7 +3110,8 @@ ftrace_trace_userstack(struct trace_buffer *buffer, unsigned long flags, int pc) preempt_enable(); } #else /* CONFIG_USER_STACKTRACE_SUPPORT */ -static void ftrace_trace_userstack(struct trace_buffer *buffer, +static void ftrace_trace_userstack(struct trace_array *tr, + struct trace_buffer *buffer, unsigned long flags, int pc) { } @@ -3100,7 +3128,7 @@ struct trace_buffer_struct { static struct trace_buffer_struct *trace_percpu_buffer; /* - * Thise allows for lockless recording. If we're nested too deeply, then + * This allows for lockless recording. If we're nested too deeply, then * this returns NULL. */ static char *get_trace_buf(void) @@ -3114,7 +3142,7 @@ static char *get_trace_buf(void) /* Interrupts must see nesting incremented before we use the buffer */ barrier(); - return &buffer->buffer[buffer->nesting][0]; + return &buffer->buffer[buffer->nesting - 1][0]; } static void put_trace_buf(void) @@ -3516,7 +3544,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, } #define STATIC_TEMP_BUF_SIZE 128 -static char static_temp_buf[STATIC_TEMP_BUF_SIZE]; +static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4); /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, @@ -5124,10 +5152,10 @@ static const char readme_msg[] = "\t -:[<group>/]<event>\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" - "place (kretprobe): [<module>:]<symbol>[+<offset>]|<memaddr>\n" + "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n" #endif #ifdef CONFIG_UPROBE_EVENTS - " place (uprobe): <path>:<offset>[(ref_ctr_offset)]\n" + " place (uprobe): <path>:<offset>[%return][(ref_ctr_offset)]\n" #endif "\t args: <name>=fetcharg[:type]\n" "\t fetcharg: %<register>, @<address>, @<symbol>[+|-<offset>],\n" @@ -5251,7 +5279,12 @@ static const char readme_msg[] = "\t trace(<synthetic_event>,param list) - generate synthetic event\n" "\t save(field,...) - save current event fields\n" #ifdef CONFIG_TRACER_SNAPSHOT - "\t snapshot() - snapshot the trace buffer\n" + "\t snapshot() - snapshot the trace buffer\n\n" +#endif +#ifdef CONFIG_SYNTH_EVENTS + " events/synthetic_events\t- Create/append/remove/show synthetic events\n" + "\t Write into this file to define/undefine new synthetic events.\n" + "\t example: echo 'myevent u64 lat; char name[]' >> synthetic_events\n" #endif #endif ; @@ -6664,7 +6697,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, written = -EFAULT; } else written = cnt; - len = cnt; if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { /* do not add \n before testing triggers, but add \0 */ @@ -6678,6 +6710,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, } else entry->buf[cnt] = '\0'; + if (static_branch_unlikely(&trace_marker_exports_enabled)) + ftrace_exports(event, TRACE_EXPORT_MARKER); __buffer_unlock_commit(buffer, event); if (tt) @@ -8638,6 +8672,24 @@ struct trace_array *trace_array_find_get(const char *instance) return tr; } +static int trace_array_create_dir(struct trace_array *tr) +{ + int ret; + + tr->dir = tracefs_create_dir(tr->name, trace_instance_dir); + if (!tr->dir) + return -EINVAL; + + ret = event_trace_add_tracer(tr->dir, tr); + if (ret) + tracefs_remove(tr->dir); + + init_tracer_tracefs(tr, tr->dir); + __update_tracer_options(tr); + + return ret; +} + static struct trace_array *trace_array_create(const char *name) { struct trace_array *tr; @@ -8673,30 +8725,28 @@ static struct trace_array *trace_array_create(const char *name) if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; - tr->dir = tracefs_create_dir(name, trace_instance_dir); - if (!tr->dir) - goto out_free_tr; - - ret = event_trace_add_tracer(tr->dir, tr); - if (ret) { - tracefs_remove(tr->dir); + if (ftrace_allocate_ftrace_ops(tr) < 0) goto out_free_tr; - } ftrace_init_trace_array(tr); - init_tracer_tracefs(tr, tr->dir); init_trace_flags_index(tr); - __update_tracer_options(tr); + + if (trace_instance_dir) { + ret = trace_array_create_dir(tr); + if (ret) + goto out_free_tr; + } else + __trace_early_add_events(tr); list_add(&tr->list, &ftrace_trace_arrays); tr->ref++; - return tr; out_free_tr: + ftrace_free_ftrace_ops(tr); free_trace_buffers(tr); free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); @@ -8801,7 +8851,6 @@ static int __remove_instance(struct trace_array *tr) free_cpumask_var(tr->tracing_cpumask); kfree(tr->name); kfree(tr); - tr = NULL; return 0; } @@ -8855,11 +8904,27 @@ static int instance_rmdir(const char *name) static __init void create_trace_instances(struct dentry *d_tracer) { + struct trace_array *tr; + trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer, instance_mkdir, instance_rmdir); if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n")) return; + + mutex_lock(&event_mutex); + mutex_lock(&trace_types_lock); + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (!tr->name) + continue; + if (MEM_FAIL(trace_array_create_dir(tr) < 0, + "Failed to create instance directory\n")) + break; + } + + mutex_unlock(&trace_types_lock); + mutex_unlock(&event_mutex); } static void @@ -8973,21 +9038,21 @@ static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) * directory. It is called via fs_initcall() by any of the boot up code * and expects to return the dentry of the top level tracing directory. */ -struct dentry *tracing_init_dentry(void) +int 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); + return -EPERM; } /* The top level trace array uses NULL as parent */ if (tr->dir) - return NULL; + return 0; if (WARN_ON(!tracefs_initialized())) - return ERR_PTR(-ENODEV); + return -ENODEV; /* * As there may still be users that expect the tracing @@ -8998,13 +9063,16 @@ struct dentry *tracing_init_dentry(void) tr->dir = debugfs_create_automount("tracing", NULL, trace_automount, NULL); - return NULL; + return 0; } extern struct trace_eval_map *__start_ftrace_eval_maps[]; extern struct trace_eval_map *__stop_ftrace_eval_maps[]; -static void __init trace_eval_init(void) +static struct workqueue_struct *eval_map_wq __initdata; +static struct work_struct eval_map_work __initdata; + +static void __init eval_map_work_func(struct work_struct *work) { int len; @@ -9012,6 +9080,33 @@ static void __init trace_eval_init(void) trace_insert_eval_map(NULL, __start_ftrace_eval_maps, len); } +static int __init trace_eval_init(void) +{ + INIT_WORK(&eval_map_work, eval_map_work_func); + + eval_map_wq = alloc_workqueue("eval_map_wq", WQ_UNBOUND, 0); + if (!eval_map_wq) { + pr_err("Unable to allocate eval_map_wq\n"); + /* Do work here */ + eval_map_work_func(&eval_map_work); + return -ENOMEM; + } + + queue_work(eval_map_wq, &eval_map_work); + return 0; +} + +static int __init trace_eval_sync(void) +{ + /* Make sure the eval map updates are finished */ + if (eval_map_wq) + destroy_workqueue(eval_map_wq); + return 0; +} + +late_initcall_sync(trace_eval_sync); + + #ifdef CONFIG_MODULES static void trace_module_add_evals(struct module *mod) { @@ -9074,7 +9169,7 @@ static int trace_module_notify(struct notifier_block *self, break; } - return 0; + return NOTIFY_OK; } static struct notifier_block trace_module_nb = { @@ -9085,48 +9180,48 @@ static struct notifier_block trace_module_nb = { static __init int tracer_init_tracefs(void) { - struct dentry *d_tracer; + int ret; trace_access_lock_init(); - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return 0; event_trace_init(); - init_tracer_tracefs(&global_trace, d_tracer); - ftrace_init_tracefs_toplevel(&global_trace, d_tracer); + init_tracer_tracefs(&global_trace, NULL); + ftrace_init_tracefs_toplevel(&global_trace, NULL); - trace_create_file("tracing_thresh", 0644, d_tracer, + trace_create_file("tracing_thresh", 0644, NULL, &global_trace, &tracing_thresh_fops); - trace_create_file("README", 0444, d_tracer, + trace_create_file("README", 0444, NULL, NULL, &tracing_readme_fops); - trace_create_file("saved_cmdlines", 0444, d_tracer, + trace_create_file("saved_cmdlines", 0444, NULL, NULL, &tracing_saved_cmdlines_fops); - trace_create_file("saved_cmdlines_size", 0644, d_tracer, + trace_create_file("saved_cmdlines_size", 0644, NULL, NULL, &tracing_saved_cmdlines_size_fops); - trace_create_file("saved_tgids", 0444, d_tracer, + trace_create_file("saved_tgids", 0444, NULL, NULL, &tracing_saved_tgids_fops); trace_eval_init(); - trace_create_eval_file(d_tracer); + trace_create_eval_file(NULL); #ifdef CONFIG_MODULES register_module_notifier(&trace_module_nb); #endif #ifdef CONFIG_DYNAMIC_FTRACE - trace_create_file("dyn_ftrace_total_info", 0444, d_tracer, + trace_create_file("dyn_ftrace_total_info", 0444, NULL, NULL, &tracing_dyn_info_fops); #endif - create_trace_instances(d_tracer); + create_trace_instances(NULL); update_tracer_options(&global_trace); @@ -9289,7 +9384,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) } /* - * We need to stop all tracing on all CPUS to read the + * We need to stop all tracing on all CPUS to read * the next buffer. This is a bit expensive, but is * not done often. We fill all what we can read, * and then release the locks again. @@ -9432,7 +9527,7 @@ __init static int tracer_alloc_buffers(void) } /* - * Make sure we don't accidently add more trace options + * Make sure we don't accidentally add more trace options * than we have bits for. */ BUILD_BUG_ON(TRACE_ITER_LAST_BIT > TRACE_FLAGS_MAX_SIZE); @@ -9461,7 +9556,7 @@ __init static int tracer_alloc_buffers(void) /* * The prepare callbacks allocates some memory for the ring buffer. We - * don't free the buffer if the if the CPU goes down. If we were to free + * don't free the buffer if the CPU goes down. If we were to free * the buffer, then the user would lose any trace that was in the * buffer. The memory will be removed once the "instance" is removed. */ diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 610d21355526..e448d2da0b99 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -19,6 +19,7 @@ #include <linux/glob.h> #include <linux/irq_work.h> #include <linux/workqueue.h> +#include <linux/ctype.h> #ifdef CONFIG_FTRACE_SYSCALLS #include <asm/unistd.h> /* For NR_SYSCALLS */ @@ -98,7 +99,7 @@ enum trace_type { /* Use this for memory failure errors */ #define MEM_FAIL(condition, fmt, ...) ({ \ - static bool __section(.data.once) __warned; \ + static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(condition); \ \ if (unlikely(__ret_warn_once && !__warned)) { \ @@ -246,7 +247,7 @@ typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data); * tracing_snapshot_cond(tr, cond_data), the cond_data passed in is * passed in turn to the cond_snapshot.update() function. That data * can be compared by the update() implementation with the cond_data - * contained wihin the struct cond_snapshot instance associated with + * contained within the struct cond_snapshot instance associated with * the trace_array. Because the tr->max_lock is held throughout the * update() call, the update() function can directly retrieve the * cond_snapshot and cond_data associated with the per-instance @@ -271,7 +272,7 @@ typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data); * take the snapshot, by returning 'true' if so, 'false' if no * snapshot should be taken. Because the max_lock is held for * the duration of update(), the implementation is safe to - * directly retrieven and save any implementation data it needs + * directly retrieved and save any implementation data it needs * to in association with the snapshot. */ struct cond_snapshot { @@ -557,163 +558,6 @@ struct tracer { bool noboot; }; - -/* Only current can touch trace_recursion */ - -/* - * For function tracing recursion: - * The order of these bits are important. - * - * When function tracing occurs, the following steps are made: - * If arch does not support a ftrace feature: - * call internal function (uses INTERNAL bits) which calls... - * If callback is registered to the "global" list, the list - * function is called and recursion checks the GLOBAL bits. - * then this function calls... - * The function callback, which can use the FTRACE bits to - * check for recursion. - * - * Now if the arch does not suppport a feature, and it calls - * the global list function which calls the ftrace callback - * all three of these steps will do a recursion protection. - * There's no reason to do one if the previous caller already - * did. The recursion that we are protecting against will - * go through the same steps again. - * - * To prevent the multiple recursion checks, if a recursion - * bit is set that is higher than the MAX bit of the current - * check, then we know that the check was made by the previous - * caller, and we can skip the current check. - */ -enum { - /* Function recursion bits */ - TRACE_FTRACE_BIT, - TRACE_FTRACE_NMI_BIT, - TRACE_FTRACE_IRQ_BIT, - TRACE_FTRACE_SIRQ_BIT, - - /* INTERNAL_BITs must be greater than FTRACE_BITs */ - TRACE_INTERNAL_BIT, - TRACE_INTERNAL_NMI_BIT, - TRACE_INTERNAL_IRQ_BIT, - TRACE_INTERNAL_SIRQ_BIT, - - TRACE_BRANCH_BIT, -/* - * Abuse of the trace_recursion. - * As we need a way to maintain state if we are tracing the function - * graph in irq because we want to trace a particular function that - * was called in irq context but we have irq tracing off. Since this - * can only be modified by current, we can reuse trace_recursion. - */ - TRACE_IRQ_BIT, - - /* Set if the function is in the set_graph_function file */ - TRACE_GRAPH_BIT, - - /* - * In the very unlikely case that an interrupt came in - * at a start of graph tracing, and we want to trace - * the function in that interrupt, the depth can be greater - * than zero, because of the preempted start of a previous - * trace. In an even more unlikely case, depth could be 2 - * if a softirq interrupted the start of graph tracing, - * followed by an interrupt preempting a start of graph - * tracing in the softirq, and depth can even be 3 - * if an NMI came in at the start of an interrupt function - * that preempted a softirq start of a function that - * preempted normal context!!!! Luckily, it can't be - * greater than 3, so the next two bits are a mask - * of what the depth is when we set TRACE_GRAPH_BIT - */ - - TRACE_GRAPH_DEPTH_START_BIT, - TRACE_GRAPH_DEPTH_END_BIT, - - /* - * To implement set_graph_notrace, if this bit is set, we ignore - * function graph tracing of called functions, until the return - * function is called to clear it. - */ - TRACE_GRAPH_NOTRACE_BIT, -}; - -#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) -#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) -#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) - -#define trace_recursion_depth() \ - (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) -#define trace_recursion_set_depth(depth) \ - do { \ - current->trace_recursion &= \ - ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ - current->trace_recursion |= \ - ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ - } while (0) - -#define TRACE_CONTEXT_BITS 4 - -#define TRACE_FTRACE_START TRACE_FTRACE_BIT -#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1) - -#define TRACE_LIST_START TRACE_INTERNAL_BIT -#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1) - -#define TRACE_CONTEXT_MASK TRACE_LIST_MAX - -static __always_inline int trace_get_context_bit(void) -{ - int bit; - - if (in_interrupt()) { - if (in_nmi()) - bit = 0; - - else if (in_irq()) - bit = 1; - else - bit = 2; - } else - bit = 3; - - return bit; -} - -static __always_inline int trace_test_and_set_recursion(int start, int max) -{ - unsigned int val = current->trace_recursion; - int bit; - - /* A previous recursion check was made */ - if ((val & TRACE_CONTEXT_MASK) > max) - return 0; - - bit = trace_get_context_bit() + start; - if (unlikely(val & (1 << bit))) - return -1; - - val |= 1 << bit; - current->trace_recursion = val; - barrier(); - - return bit; -} - -static __always_inline void trace_clear_recursion(int bit) -{ - unsigned int val = current->trace_recursion; - - if (!bit) - return; - - bit = 1 << bit; - val &= ~bit; - - barrier(); - current->trace_recursion = val; -} - static inline struct ring_buffer_iter * trace_buffer_iter(struct trace_iterator *iter, int cpu) { @@ -737,7 +581,7 @@ struct dentry *trace_create_file(const char *name, void *data, const struct file_operations *fops); -struct dentry *tracing_init_dentry(void); +int tracing_init_dentry(void); struct ring_buffer_event; @@ -875,6 +719,8 @@ extern bool ring_buffer_expanded; extern bool tracing_selftest_disabled; #ifdef CONFIG_FTRACE_STARTUP_TEST +extern void __init disable_tracing_selftest(const char *reason); + extern int trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr); extern int trace_selftest_startup_function_graph(struct tracer *trace, @@ -898,6 +744,9 @@ extern int trace_selftest_startup_branch(struct tracer *trace, */ #define __tracer_data __refdata #else +static inline void __init disable_tracing_selftest(const char *reason) +{ +} /* Tracers are seldom changed. Optimize when selftests are disabled. */ #define __tracer_data __read_mostly #endif /* CONFIG_FTRACE_STARTUP_TEST */ @@ -1125,6 +974,8 @@ extern int ftrace_is_dead(void); int ftrace_create_function_files(struct trace_array *tr, struct dentry *parent); void ftrace_destroy_function_files(struct trace_array *tr); +int ftrace_allocate_ftrace_ops(struct trace_array *tr); +void ftrace_free_ftrace_ops(struct trace_array *tr); void ftrace_init_global_array_ops(struct trace_array *tr); void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func); void ftrace_reset_array_ops(struct trace_array *tr); @@ -1146,6 +997,11 @@ ftrace_create_function_files(struct trace_array *tr, { return 0; } +static inline int ftrace_allocate_ftrace_ops(struct trace_array *tr) +{ + return 0; +} +static inline void ftrace_free_ftrace_ops(struct trace_array *tr) { } static inline void ftrace_destroy_function_files(struct trace_array *tr) { } static inline __init void ftrace_init_global_array_ops(struct trace_array *tr) { } @@ -1472,7 +1328,7 @@ __trace_event_discard_commit(struct trace_buffer *buffer, /* * Helper function for event_trigger_unlock_commit{_regs}(). * If there are event triggers attached to this event that requires - * filtering against its fields, then they wil be called as the + * filtering against its fields, then they will be called as the * entry already holds the field information of the current event. * * It also checks if the event should be discarded or not. @@ -1651,6 +1507,7 @@ extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); +extern void __trace_early_add_events(struct trace_array *tr); extern struct trace_event_file *__find_event_file(struct trace_array *tr, const char *system, @@ -2082,4 +1939,16 @@ static __always_inline void trace_iterator_reset(struct trace_iterator *iter) iter->pos = -1; } +/* Check the name is good for event/group/fields */ +static inline bool is_good_name(const char *name) +{ + if (!isalpha(*name) && *name != '_') + return false; + while (*++name != '\0') { + if (!isalpha(*name) && !isdigit(*name) && *name != '_') + return false; + } + return true; +} + #endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 2e9a4746ea85..801c2a7f7605 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -31,7 +31,7 @@ static bool ok_to_run; * it simply writes "START". As the first write is cold cache and * the rest is hot, we save off that time in bm_first and it is * reported as "first", which is shown in the second write to the - * tracepoint. The "first" field is writen within the statics from + * tracepoint. The "first" field is written within the statics from * then on but never changes. */ static void trace_do_benchmark(void) @@ -112,7 +112,7 @@ static void trace_do_benchmark(void) int i = 0; /* * stddev is the square of standard deviation but - * we want the actualy number. Use the average + * we want the actually number. Use the average * as our seed to find the std. * * The next try is: @@ -155,7 +155,7 @@ static int benchmark_event_kthread(void *arg) /* * We don't go to sleep, but let others run as well. - * This is bascially a "yield()" to let any task that + * This is basically a "yield()" to let any task that * wants to run, schedule in, but if the CPU is idle, * we'll keep burning cycles. * diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index fa0fc08c6ef8..a82f03f385f8 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -40,6 +40,16 @@ trace_boot_set_instance_options(struct trace_array *tr, struct xbc_node *node) pr_err("Failed to set option: %s\n", buf); } + p = xbc_node_find_value(node, "tracing_on", NULL); + if (p && *p != '\0') { + if (kstrtoul(p, 10, &v)) + pr_err("Failed to set tracing on: %s\n", p); + if (v) + tracer_tracing_on(tr); + else + tracer_tracing_off(tr); + } + p = xbc_node_find_value(node, "trace_clock", NULL); if (p && *p != '\0') { if (tracing_set_clock(tr, p) < 0) @@ -274,6 +284,12 @@ trace_boot_enable_tracer(struct trace_array *tr, struct xbc_node *node) if (tracing_set_tracer(tr, p) < 0) pr_err("Failed to set given tracer: %s\n", p); } + + /* Since tracer can free snapshot buffer, allocate snapshot here.*/ + if (xbc_node_find_value(node, "alloc_snapshot", NULL)) { + if (tracing_alloc_snapshot_instance(tr) < 0) + pr_err("Failed to allocate snapshot buffer\n"); + } } static void __init @@ -328,7 +344,12 @@ static int __init trace_boot_init(void) trace_boot_init_one_instance(tr, trace_node); trace_boot_init_instances(trace_node); + disable_tracing_selftest("running boot-time tracing"); + return 0; } - -fs_initcall(trace_boot_init); +/* + * Start tracing at the end of core-initcall, so that it starts tracing + * from the beginning of postcore_initcall. + */ +core_initcall_sync(trace_boot_init); diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index 9f2e8520b748..4f967d5cd917 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -206,14 +206,14 @@ static const struct file_operations dynamic_events_ops = { /* Make a tracefs interface for controlling dynamic events */ static __init int init_dynamic_event(void) { - struct dentry *d_tracer; struct dentry *entry; + int ret; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return 0; - entry = tracefs_create_file("dynamic_events", 0644, d_tracer, + entry = tracefs_create_file("dynamic_events", 0644, NULL, NULL, &dynamic_events_ops); /* Event list interface */ @@ -276,7 +276,7 @@ int dynevent_arg_add(struct dynevent_cmd *cmd, * 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 by an operator, if applicable, followed 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. @@ -402,7 +402,7 @@ void dynevent_arg_init(struct dynevent_arg *arg, * 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 + * 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, diff --git a/kernel/trace/trace_dynevent.h b/kernel/trace/trace_dynevent.h index d6857a254ede..d6f72dcb7269 100644 --- a/kernel/trace/trace_dynevent.h +++ b/kernel/trace/trace_dynevent.h @@ -29,10 +29,10 @@ struct dyn_event; * @show: Showing method. This is invoked when user reads the event definitions * via dynamic_events interface. * @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. + * Return true if it is busy, otherwise false. + * @free: Delete the given event. Return 0 if success, otherwise error. * @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 + * and argv is used for exact match. Return true if it matches, otherwise * false. * * Except for @create, these methods are called under holding event_mutex. diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 18c4a58aff79..4547ac59da61 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -32,7 +32,7 @@ * to be deciphered for the format file. Although these macros * may become out of sync with the internal structure, they * will create a compile error if it happens. Since the - * internel structures are just tracing helpers, this is not + * internal structures are just tracing helpers, this is not * an issue. * * When an internal structure is used, it should use: @@ -93,10 +93,10 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, F_STRUCT( __field_struct( struct ftrace_graph_ret, ret ) __field_packed( unsigned long, ret, func ) - __field_packed( unsigned long, ret, overrun ) + __field_packed( int, ret, depth ) + __field_packed( unsigned int, ret, overrun ) __field_packed( unsigned long long, ret, calltime) __field_packed( unsigned long long, ret, rettime ) - __field_packed( int, ret, depth ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d", diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 643e0b19920d..a71181655958 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -432,17 +432,25 @@ NOKPROBE_SYMBOL(perf_trace_buf_update); #ifdef CONFIG_FUNCTION_TRACER static void perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *pt_regs) + struct ftrace_ops *ops, struct ftrace_regs *fregs) { struct ftrace_entry *entry; struct perf_event *event; struct hlist_head head; struct pt_regs regs; int rctx; + int bit; + + if (!rcu_is_watching()) + return; if ((unsigned long)ops->private != smp_processor_id()) return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + event = container_of(ops, struct perf_event, ftrace_ops); /* @@ -463,13 +471,15 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, entry = perf_trace_buf_alloc(ENTRY_SIZE, NULL, &rctx); if (!entry) - return; + goto out; entry->ip = ip; entry->parent_ip = parent_ip; perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN, 1, ®s, &head, NULL); +out: + ftrace_test_recursion_unlock(bit); #undef ENTRY_SIZE } @@ -477,7 +487,6 @@ static int perf_ftrace_function_register(struct perf_event *event) { struct ftrace_ops *ops = &event->ftrace_ops; - ops->flags = FTRACE_OPS_FL_RCU; ops->func = perf_ftrace_function_call; ops->private = (void *)(unsigned long)nr_cpu_ids; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index a85effb2373b..d387b774ceeb 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -38,6 +38,7 @@ DEFINE_MUTEX(event_mutex); LIST_HEAD(ftrace_events); static LIST_HEAD(ftrace_generic_fields); static LIST_HEAD(ftrace_common_fields); +static bool eventdir_initialized; #define GFP_TRACE (GFP_KERNEL | __GFP_ZERO) @@ -1211,7 +1212,8 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt, mutex_lock(&event_mutex); list_for_each_entry(file, &tr->events, list) { call = file->event_call; - if (!trace_event_name(call) || !call->class || !call->class->reg) + if ((call->flags & TRACE_EVENT_FL_IGNORE_ENABLE) || + !trace_event_name(call) || !call->class || !call->class->reg) continue; if (system && strcmp(call->class->system, system->name) != 0) @@ -2124,11 +2126,47 @@ event_subsystem_dir(struct trace_array *tr, const char *name, } static int +event_define_fields(struct trace_event_call *call) +{ + struct list_head *head; + int ret = 0; + + /* + * Other events may have the same class. Only update + * the fields if they are not already defined. + */ + head = trace_get_fields(call); + if (list_empty(head)) { + 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) { + 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 (WARN_ON_ONCE(ret)) { + pr_err("error code is %d\n", ret); + break; + } + + offset += field->size; + } + } + + return ret; +} + +static int event_create_dir(struct dentry *parent, struct trace_event_file *file) { struct trace_event_call *call = file->event_call; struct trace_array *tr = file->tr; - struct list_head *head; struct dentry *d_events; const char *name; int ret; @@ -2162,35 +2200,10 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) &ftrace_event_id_fops); #endif - /* - * Other events may have the same class. Only update - * the fields if they are not already defined. - */ - head = trace_get_fields(call); - if (list_empty(head)) { - 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); - return -1; - } + ret = event_define_fields(call); + if (ret < 0) { + pr_warn("Could not initialize trace point events/%s\n", name); + return ret; } /* @@ -2424,7 +2437,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) /* * Since calls are grouped by systems, the likelyhood that the * next call in the iteration belongs to the same system as the - * previous call is high. As an optimization, we skip seaching + * previous call is high. As an optimization, we skip searching * for a map[] that matches the call's system if the last call * was from the same system. That's what last_i is for. If the * call has the same system as the previous call, then last_i @@ -2475,7 +2488,10 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr) if (!file) return -ENOMEM; - return event_create_dir(tr->event_dir, file); + if (eventdir_initialized) + return event_create_dir(tr->event_dir, file); + else + return event_define_fields(call); } /* @@ -2483,7 +2499,7 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr) * for enabling events at boot. We want to enable events before * the filesystem is initialized. */ -static __init int +static int __trace_early_add_new_event(struct trace_event_call *call, struct trace_array *tr) { @@ -2493,7 +2509,7 @@ __trace_early_add_new_event(struct trace_event_call *call, if (!file) return -ENOMEM; - return 0; + return event_define_fields(call); } struct ftrace_module_file_ops; @@ -2646,7 +2662,7 @@ static int trace_module_notify(struct notifier_block *self, mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); - return 0; + return NOTIFY_OK; } static struct notifier_block trace_module_nb = { @@ -3116,14 +3132,13 @@ static inline int register_event_cmds(void) { return 0; } #endif /* CONFIG_DYNAMIC_FTRACE */ /* - * The top level array has already had its trace_event_file - * descriptors created in order to allow for early events to - * be recorded. This function is called after the tracefs has been - * initialized, and we now have to create the files associated - * to the events. + * The top level array and trace arrays created by boot-time tracing + * have already had its trace_event_file descriptors created in order + * to allow for early events to be recorded. + * This function is called after the tracefs has been initialized, + * and we now have to create the files associated to the events. */ -static __init void -__trace_early_add_event_dirs(struct trace_array *tr) +static void __trace_early_add_event_dirs(struct trace_array *tr) { struct trace_event_file *file; int ret; @@ -3138,13 +3153,12 @@ __trace_early_add_event_dirs(struct trace_array *tr) } /* - * For early boot up, the top trace array requires to have - * a list of events that can be enabled. This must be done before - * the filesystem is set up in order to allow events to be traced - * early. + * For early boot up, the top trace array and the trace arrays created + * by boot-time tracing require to have a list of events that can be + * enabled. This must be done before the filesystem is set up in order + * to allow events to be traced early. */ -static __init void -__trace_early_add_events(struct trace_array *tr) +void __trace_early_add_events(struct trace_array *tr) { struct trace_event_call *call; int ret; @@ -3188,7 +3202,7 @@ static __init int setup_trace_event(char *str) { strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE); ring_buffer_expanded = true; - tracing_selftest_disabled = true; + disable_tracing_selftest("running event tracing"); return 1; } @@ -3258,7 +3272,7 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) * * When a new instance is created, it needs to set up its events * directory, as well as other files associated with events. It also - * creates the event hierachry in the @parent/events directory. + * creates the event hierarchy in the @parent/events directory. * * Returns 0 on success. * @@ -3275,7 +3289,11 @@ int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr) goto out; down_write(&trace_event_sem); - __trace_add_event_dirs(tr); + /* If tr already has the event list, it is initialized in early boot. */ + if (unlikely(!list_empty(&tr->events))) + __trace_early_add_event_dirs(tr); + else + __trace_add_event_dirs(tr); up_write(&trace_event_sem); out: @@ -3411,10 +3429,10 @@ static __init int event_trace_enable(void) * initialize events and perhaps start any events that are on the * command line. Unfortunately, there are some events that will not * start this early, like the system call tracepoints that need - * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable() - * is called before pid 1 starts, and this flag is never set, making - * the syscall tracepoint never get reached, but the event is enabled - * regardless (and not doing anything). + * to set the %SYSCALL_WORK_SYSCALL_TRACEPOINT flag of pid 1. But + * event_trace_enable() is called before pid 1 starts, and this flag + * is never set, making the syscall tracepoint never get reached, but + * the event is enabled regardless (and not doing anything). */ static __init int event_trace_enable_again(void) { @@ -3431,10 +3449,21 @@ static __init int event_trace_enable_again(void) early_initcall(event_trace_enable_again); +/* Init fields which doesn't related to the tracefs */ +static __init int event_trace_init_fields(void) +{ + if (trace_define_generic_fields()) + pr_warn("tracing: Failed to allocated generic fields"); + + if (trace_define_common_fields()) + pr_warn("tracing: Failed to allocate common fields"); + + return 0; +} + __init int event_trace_init(void) { struct trace_array *tr; - struct dentry *d_tracer; struct dentry *entry; int ret; @@ -3442,22 +3471,12 @@ __init int event_trace_init(void) if (!tr) return -ENODEV; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) - return 0; - - entry = tracefs_create_file("available_events", 0444, d_tracer, + entry = tracefs_create_file("available_events", 0444, NULL, tr, &ftrace_avail_fops); if (!entry) pr_warn("Could not create tracefs 'available_events' entry\n"); - if (trace_define_generic_fields()) - pr_warn("tracing: Failed to allocated generic fields"); - - if (trace_define_common_fields()) - pr_warn("tracing: Failed to allocate common fields"); - - ret = early_event_add_tracer(d_tracer, tr); + ret = early_event_add_tracer(NULL, tr); if (ret) return ret; @@ -3466,6 +3485,9 @@ __init int event_trace_init(void) if (ret) pr_warn("Failed to register trace events module notifier\n"); #endif + + eventdir_initialized = true; + return 0; } @@ -3474,6 +3496,7 @@ void __init trace_event_init(void) event_trace_memsetup(); init_ftrace_syscalls(); event_trace_enable(); + event_trace_init_fields(); } #ifdef CONFIG_EVENT_TRACE_STARTUP_TEST @@ -3651,7 +3674,7 @@ static struct trace_event_file event_trace_file __initdata; static void __init function_test_events_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) + struct ftrace_ops *op, struct ftrace_regs *regs) { struct trace_buffer *buffer; struct ring_buffer_event *event; @@ -3690,7 +3713,6 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops trace_ops __initdata = { .func = function_test_events_call, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static __init void event_trace_self_test_with_function(void) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 78a678eeb140..e91259f6a722 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1561,27 +1561,6 @@ static inline void event_clear_filter(struct trace_event_file *file) RCU_INIT_POINTER(file->filter, NULL); } -static inline void -event_set_no_set_filter_flag(struct trace_event_file *file) -{ - file->flags |= EVENT_FILE_FL_NO_SET_FILTER; -} - -static inline void -event_clear_no_set_filter_flag(struct trace_event_file *file) -{ - file->flags &= ~EVENT_FILE_FL_NO_SET_FILTER; -} - -static inline bool -event_no_set_filter_flag(struct trace_event_file *file) -{ - if (file->flags & EVENT_FILE_FL_NO_SET_FILTER) - return true; - - return false; -} - struct filter_list { struct list_head list; struct event_filter *filter; @@ -1950,7 +1929,7 @@ static int __ftrace_function_set_filter(int filter, char *buf, int len, /* * The 'ip' field could have multiple filters set, separated * either by space or comma. We first cut the filter and apply - * all pieces separatelly. + * all pieces separately. */ re = ftrace_function_filter_re(buf, len, &re_cnt); if (!re) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 1b2ef6490229..39ebe1826fc3 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -147,6 +147,8 @@ struct hist_field { */ unsigned int var_ref_idx; bool read_once; + + unsigned int var_str_idx; }; static u64 hist_field_none(struct hist_field *field, @@ -349,6 +351,7 @@ struct hist_trigger_data { unsigned int n_keys; unsigned int n_fields; unsigned int n_vars; + unsigned int n_var_str; unsigned int key_size; struct tracing_map_sort_key sort_keys[TRACING_MAP_SORT_KEYS_MAX]; unsigned int n_sort_keys; @@ -1396,7 +1399,14 @@ static int hist_trigger_elt_data_alloc(struct tracing_map_elt *elt) } } - n_str = hist_data->n_field_var_str + hist_data->n_save_var_str; + n_str = hist_data->n_field_var_str + hist_data->n_save_var_str + + hist_data->n_var_str; + if (n_str > SYNTH_FIELDS_MAX) { + hist_elt_data_free(elt_data); + return -EINVAL; + } + + BUILD_BUG_ON(STR_VAR_LEN_MAX & (sizeof(u64) - 1)); size = STR_VAR_LEN_MAX; @@ -3279,6 +3289,15 @@ static int check_synth_field(struct synth_event *event, field = event->fields[field_pos]; + /* + * A dynamic string synth field can accept static or + * dynamic. A static string synth field can only accept a + * same-sized static string, which is checked for later. + */ + if (strstr(hist_field->type, "char[") && field->is_string + && field->is_dynamic) + return 0; + if (strcmp(field->type, hist_field->type) != 0) { if (field->size != hist_field->size || field->is_signed != hist_field->is_signed) @@ -3336,7 +3355,7 @@ trace_action_create_field_var(struct hist_trigger_data *hist_data, } else { field_var = NULL; /* - * If no explicit system.event is specfied, default to + * If no explicit system.event is specified, default to * looking for fields on the onmatch(system.event.xxx) * event. */ @@ -3651,6 +3670,7 @@ static int create_var_field(struct hist_trigger_data *hist_data, { struct trace_array *tr = hist_data->event_file->tr; unsigned long flags = 0; + int ret; if (WARN_ON(val_idx >= TRACING_MAP_VALS_MAX + TRACING_MAP_VARS_MAX)) return -EINVAL; @@ -3665,7 +3685,12 @@ static int create_var_field(struct hist_trigger_data *hist_data, if (WARN_ON(hist_data->n_vars > TRACING_MAP_VARS_MAX)) return -EINVAL; - return __create_val_field(hist_data, val_idx, file, var_name, expr_str, flags); + ret = __create_val_field(hist_data, val_idx, file, var_name, expr_str, flags); + + if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_STRING) + hist_data->fields[val_idx]->var_str_idx = hist_data->n_var_str++; + + return ret; } static int create_val_fields(struct hist_trigger_data *hist_data, @@ -4392,6 +4417,22 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, hist_val = hist_field->fn(hist_field, elt, rbe, rec); if (hist_field->flags & HIST_FIELD_FL_VAR) { var_idx = hist_field->var.idx; + + if (hist_field->flags & HIST_FIELD_FL_STRING) { + unsigned int str_start, var_str_idx, idx; + char *str, *val_str; + + str_start = hist_data->n_field_var_str + + hist_data->n_save_var_str; + var_str_idx = hist_field->var_str_idx; + idx = str_start + var_str_idx; + + str = elt_data->field_var_str[idx]; + val_str = (char *)(uintptr_t)hist_val; + strscpy(str, val_str, STR_VAR_LEN_MAX); + + hist_val = (u64)(uintptr_t)str; + } tracing_map_set_var(elt, var_idx, hist_val); continue; } diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index c6cca0d1d584..5a8bc0b421f1 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -20,6 +20,48 @@ #include "trace_synth.h" +#undef ERRORS +#define ERRORS \ + C(BAD_NAME, "Illegal name"), \ + C(CMD_INCOMPLETE, "Incomplete command"), \ + C(EVENT_EXISTS, "Event already exists"), \ + C(TOO_MANY_FIELDS, "Too many fields"), \ + C(INCOMPLETE_TYPE, "Incomplete type"), \ + C(INVALID_TYPE, "Invalid type"), \ + C(INVALID_FIELD, "Invalid field"), \ + C(CMD_TOO_LONG, "Command too long"), + +#undef C +#define C(a, b) SYNTH_ERR_##a + +enum { ERRORS }; + +#undef C +#define C(a, b) b + +static const char *err_text[] = { ERRORS }; + +static char last_cmd[MAX_FILTER_STR_VAL]; + +static int errpos(const char *str) +{ + return err_pos(last_cmd, str); +} + +static void last_cmd_set(char *str) +{ + if (!str) + return; + + strncpy(last_cmd, str, MAX_FILTER_STR_VAL - 1); +} + +static void synth_err(u8 err_type, u8 err_pos) +{ + tracing_log_err(NULL, "synthetic_events", last_cmd, err_text, + err_type, err_pos); +} + 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); @@ -88,7 +130,7 @@ static int synth_event_define_fields(struct trace_event_call *call) event->fields[i]->offset = n_u64; - if (event->fields[i]->is_string) { + if (event->fields[i]->is_string && !event->fields[i]->is_dynamic) { offset += STR_VAR_LEN_MAX; n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } else { @@ -132,13 +174,16 @@ static int synth_field_string_size(char *type) start += sizeof("char[") - 1; end = strchr(type, ']'); - if (!end || end < start) + if (!end || end < start || type + strlen(type) > end + 1) return -EINVAL; len = end - start; if (len > 3) return -EINVAL; + if (len == 0) + return 0; /* variable-length string */ + strncpy(buf, start, len); buf[len] = '\0'; @@ -184,6 +229,8 @@ static int synth_field_size(char *type) size = sizeof(long); else if (strcmp(type, "unsigned long") == 0) size = sizeof(unsigned long); + else if (strcmp(type, "bool") == 0) + size = sizeof(bool); else if (strcmp(type, "pid_t") == 0) size = sizeof(pid_t); else if (strcmp(type, "gfp_t") == 0) @@ -226,12 +273,14 @@ static const char *synth_field_fmt(char *type) fmt = "%ld"; else if (strcmp(type, "unsigned long") == 0) fmt = "%lu"; + else if (strcmp(type, "bool") == 0) + fmt = "%d"; 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"; + fmt = "%.*s"; return fmt; } @@ -290,10 +339,27 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, /* parameter values */ if (se->fields[i]->is_string) { - trace_seq_printf(s, print_fmt, se->fields[i]->name, - (char *)&entry->fields[n_u64], - i == se->n_fields - 1 ? "" : " "); - n_u64 += STR_VAR_LEN_MAX / sizeof(u64); + if (se->fields[i]->is_dynamic) { + u32 offset, data_offset; + char *str_field; + + offset = (u32)entry->fields[n_u64]; + data_offset = offset & 0xffff; + + str_field = (char *)entry + data_offset; + + trace_seq_printf(s, print_fmt, se->fields[i]->name, + STR_VAR_LEN_MAX, + str_field, + i == se->n_fields - 1 ? "" : " "); + n_u64++; + } else { + trace_seq_printf(s, print_fmt, se->fields[i]->name, + STR_VAR_LEN_MAX, + (char *)&entry->fields[n_u64], + i == se->n_fields - 1 ? "" : " "); + n_u64 += STR_VAR_LEN_MAX / sizeof(u64); + } } else { struct trace_print_flags __flags[] = { __def_gfpflag_names, {-1, NULL} }; @@ -325,16 +391,52 @@ static struct trace_event_functions synth_event_funcs = { .trace = print_synth_event }; +static unsigned int trace_string(struct synth_trace_event *entry, + struct synth_event *event, + char *str_val, + bool is_dynamic, + unsigned int data_size, + unsigned int *n_u64) +{ + unsigned int len = 0; + char *str_field; + + if (is_dynamic) { + u32 data_offset; + + data_offset = offsetof(typeof(*entry), fields); + data_offset += event->n_u64 * sizeof(u64); + data_offset += data_size; + + str_field = (char *)entry + data_offset; + + len = strlen(str_val) + 1; + strscpy(str_field, str_val, len); + + data_offset |= len << 16; + *(u32 *)&entry->fields[*n_u64] = data_offset; + + (*n_u64)++; + } else { + str_field = (char *)&entry->fields[*n_u64]; + + strscpy(str_field, str_val, STR_VAR_LEN_MAX); + (*n_u64) += STR_VAR_LEN_MAX / sizeof(u64); + } + + return len; +} + static notrace void trace_event_raw_event_synth(void *__data, u64 *var_ref_vals, unsigned int *var_ref_idx) { + unsigned int i, n_u64, val_idx, len, data_size = 0; struct trace_event_file *trace_file = __data; struct synth_trace_event *entry; struct trace_event_buffer fbuffer; struct trace_buffer *buffer; struct synth_event *event; - unsigned int i, n_u64, val_idx; int fields_size = 0; event = trace_file->event_call->data; @@ -344,6 +446,18 @@ static notrace void trace_event_raw_event_synth(void *__data, fields_size = event->n_u64 * sizeof(u64); + for (i = 0; i < event->n_dynamic_fields; i++) { + unsigned int field_pos = event->dynamic_fields[i]->field_pos; + char *str_val; + + val_idx = var_ref_idx[field_pos]; + str_val = (char *)(long)var_ref_vals[val_idx]; + + len = strlen(str_val) + 1; + + fields_size += len; + } + /* * Avoid ring buffer recursion detection, as this event * is being performed within another event. @@ -360,10 +474,11 @@ static notrace void trace_event_raw_event_synth(void *__data, val_idx = var_ref_idx[i]; if (event->fields[i]->is_string) { 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); + len = trace_string(entry, event, str_val, + event->fields[i]->is_dynamic, + data_size, &n_u64); + data_size += len; /* only dynamic string increments */ } else { struct synth_field *field = event->fields[i]; u64 val = var_ref_vals[val_idx]; @@ -422,8 +537,13 @@ static int __set_synth_event_print_fmt(struct synth_event *event, pos += snprintf(buf + pos, LEN_OR_ZERO, "\""); for (i = 0; i < event->n_fields; i++) { - pos += snprintf(buf + pos, LEN_OR_ZERO, - ", REC->%s", event->fields[i]->name); + if (event->fields[i]->is_string && + event->fields[i]->is_dynamic) + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", __get_str(%s)", event->fields[i]->name); + else + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", REC->%s", event->fields[i]->name); } #undef LEN_OR_ZERO @@ -464,14 +584,18 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, { struct synth_field *field; const char *prefix = NULL, *field_type = argv[0], *field_name, *array; - int len, ret = 0; + int len, ret = -ENOMEM; + struct seq_buf s; + ssize_t size; if (field_type[0] == ';') field_type++; if (!strcmp(field_type, "unsigned")) { - if (argc < 3) + if (argc < 3) { + synth_err(SYNTH_ERR_INCOMPLETE_TYPE, errpos(field_type)); return ERR_PTR(-EINVAL); + } prefix = "unsigned "; field_type = argv[1]; field_name = argv[2]; @@ -493,44 +617,82 @@ static struct synth_field *parse_synth_field(int argc, const char **argv, len--; field->name = kmemdup_nul(field_name, len, GFP_KERNEL); - if (!field->name) { - ret = -ENOMEM; + if (!field->name) + goto free; + + if (!is_good_name(field->name)) { + synth_err(SYNTH_ERR_BAD_NAME, errpos(field_name)); + ret = -EINVAL; goto free; } if (field_type[0] == ';') field_type++; len = strlen(field_type) + 1; + if (array) len += strlen(array); + if (prefix) len += strlen(prefix); field->type = kzalloc(len, GFP_KERNEL); - if (!field->type) { - ret = -ENOMEM; + if (!field->type) goto free; - } + + seq_buf_init(&s, field->type, len); if (prefix) - strcat(field->type, prefix); - strcat(field->type, field_type); + seq_buf_puts(&s, prefix); + seq_buf_puts(&s, field_type); if (array) { - strcat(field->type, array); - if (field->type[len - 1] == ';') - field->type[len - 1] = '\0'; + seq_buf_puts(&s, array); + if (s.buffer[s.len - 1] == ';') + s.len--; } + if (WARN_ON_ONCE(!seq_buf_buffer_left(&s))) + goto free; - field->size = synth_field_size(field->type); - if (!field->size) { + s.buffer[s.len] = '\0'; + + size = synth_field_size(field->type); + if (size < 0) { + synth_err(SYNTH_ERR_INVALID_TYPE, errpos(field_type)); ret = -EINVAL; goto free; + } else if (size == 0) { + if (synth_field_is_string(field->type)) { + char *type; + + len = sizeof("__data_loc ") + strlen(field->type) + 1; + type = kzalloc(len, GFP_KERNEL); + if (!type) + goto free; + + seq_buf_init(&s, type, len); + seq_buf_puts(&s, "__data_loc "); + seq_buf_puts(&s, field->type); + + if (WARN_ON_ONCE(!seq_buf_buffer_left(&s))) + goto free; + s.buffer[s.len] = '\0'; + + kfree(field->type); + field->type = type; + + field->is_dynamic = true; + size = sizeof(u64); + } else { + synth_err(SYNTH_ERR_INVALID_TYPE, errpos(field_type)); + ret = -EINVAL; + goto free; + } } + field->size = size; if (synth_field_is_string(field->type)) field->is_string = true; field->is_signed = synth_field_signed(field->type); - out: return field; free: @@ -661,6 +823,7 @@ static void free_synth_event(struct synth_event *event) free_synth_field(event->fields[i]); kfree(event->fields); + kfree(event->dynamic_fields); kfree(event->name); kfree(event->class.system); free_synth_tracepoint(event->tp); @@ -671,8 +834,8 @@ static void free_synth_event(struct synth_event *event) static struct synth_event *alloc_synth_event(const char *name, int n_fields, struct synth_field **fields) { + unsigned int i, j, n_dynamic_fields = 0; struct synth_event *event; - unsigned int i; event = kzalloc(sizeof(*event), GFP_KERNEL); if (!event) { @@ -694,11 +857,33 @@ static struct synth_event *alloc_synth_event(const char *name, int n_fields, goto out; } + for (i = 0; i < n_fields; i++) + if (fields[i]->is_dynamic) + n_dynamic_fields++; + + if (n_dynamic_fields) { + event->dynamic_fields = kcalloc(n_dynamic_fields, + sizeof(*event->dynamic_fields), + GFP_KERNEL); + if (!event->dynamic_fields) { + free_synth_event(event); + event = ERR_PTR(-ENOMEM); + goto out; + } + } + dyn_event_init(&event->devent, &synth_event_ops); - for (i = 0; i < n_fields; i++) + for (i = 0, j = 0; i < n_fields; i++) { event->fields[i] = fields[i]; + if (fields[i]->is_dynamic) { + event->dynamic_fields[j] = fields[i]; + event->dynamic_fields[j]->field_pos = i; + event->dynamic_fields[j++] = fields[i]; + event->n_dynamic_fields++; + } + } event->n_fields = n_fields; out: return event; @@ -710,6 +895,10 @@ static int synth_event_check_arg_fn(void *data) int size; size = synth_field_size((char *)arg_pair->lhs); + if (size == 0) { + if (strstr((char *)arg_pair->lhs, "[")) + return 0; + } return size ? 0 : -EINVAL; } @@ -971,12 +1160,47 @@ int synth_event_gen_cmd_array_start(struct dynevent_cmd *cmd, const char *name, } EXPORT_SYMBOL_GPL(synth_event_gen_cmd_array_start); +static int save_cmdstr(int argc, const char *name, const char **argv) +{ + struct seq_buf s; + char *buf; + int i; + + buf = kzalloc(MAX_DYNEVENT_CMD_LEN, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + seq_buf_init(&s, buf, MAX_DYNEVENT_CMD_LEN); + + seq_buf_puts(&s, name); + + for (i = 0; i < argc; i++) { + seq_buf_putc(&s, ' '); + seq_buf_puts(&s, argv[i]); + } + + if (!seq_buf_buffer_left(&s)) { + synth_err(SYNTH_ERR_CMD_TOO_LONG, 0); + kfree(buf); + return -EINVAL; + } + buf[s.len] = 0; + last_cmd_set(buf); + + kfree(buf); + return 0; +} + static int __create_synth_event(int argc, const char *name, const char **argv) { struct synth_field *field, *fields[SYNTH_FIELDS_MAX]; struct synth_event *event = NULL; int i, consumed = 0, n_fields = 0, ret = 0; + ret = save_cmdstr(argc, name, argv); + if (ret) + return ret; + /* * Argument syntax: * - Add synthetic event: <event_name> field[;field] ... @@ -984,13 +1208,22 @@ static int __create_synth_event(int argc, const char *name, const char **argv) * where 'field' = type field_name */ - if (name[0] == '\0' || argc < 1) + if (name[0] == '\0' || argc < 1) { + synth_err(SYNTH_ERR_CMD_INCOMPLETE, 0); return -EINVAL; + } mutex_lock(&event_mutex); + if (!is_good_name(name)) { + synth_err(SYNTH_ERR_BAD_NAME, errpos(name)); + ret = -EINVAL; + goto out; + } + event = find_synth_event(name); if (event) { + synth_err(SYNTH_ERR_EVENT_EXISTS, errpos(name)); ret = -EEXIST; goto out; } @@ -999,6 +1232,7 @@ static int __create_synth_event(int argc, const char *name, const char **argv) if (strcmp(argv[i], ";") == 0) continue; if (n_fields == SYNTH_FIELDS_MAX) { + synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0); ret = -EINVAL; goto err; } @@ -1013,6 +1247,7 @@ static int __create_synth_event(int argc, const char *name, const char **argv) } if (i < argc && strcmp(argv[i], ";") != 0) { + synth_err(SYNTH_ERR_INVALID_FIELD, errpos(argv[i])); ret = -EINVAL; goto err; } @@ -1041,7 +1276,7 @@ static int __create_synth_event(int argc, const char *name, const char **argv) /** * synth_event_create - Create a new synthetic event - * @name: The name of the new sythetic event + * @name: The name of the new synthetic 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 @@ -1198,10 +1433,9 @@ void synth_event_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen) 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) +__synth_event_trace_init(struct trace_event_file *file, + struct synth_event_trace_state *trace_state) { - int entry_size, fields_size = 0; int ret = 0; memset(trace_state, '\0', sizeof(*trace_state)); @@ -1211,8 +1445,8 @@ __synth_event_trace_start(struct trace_event_file *file, * 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 + * to honor not logging when disabled. For the iterated + * trace case, we save the enabled state upon start and just * ignore the following data calls. */ if (!(file->flags & EVENT_FILE_FL_ENABLED) || @@ -1223,8 +1457,20 @@ __synth_event_trace_start(struct trace_event_file *file, } trace_state->event = file->event_call->data; +out: + return ret; +} + +static inline int +__synth_event_trace_start(struct trace_event_file *file, + struct synth_event_trace_state *trace_state, + int dynamic_fields_size) +{ + int entry_size, fields_size = 0; + int ret = 0; fields_size = trace_state->event->n_u64 * sizeof(u64); + fields_size += dynamic_fields_size; /* * Avoid ring buffer recursion detection, as this event @@ -1241,7 +1487,7 @@ __synth_event_trace_start(struct trace_event_file *file, ring_buffer_nest_end(trace_state->buffer); ret = -EINVAL; } -out: + return ret; } @@ -1274,23 +1520,46 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state) */ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) { + unsigned int i, n_u64, len, data_size = 0; struct synth_event_trace_state state; - unsigned int i, n_u64; va_list args; int ret; - ret = __synth_event_trace_start(file, &state); + ret = __synth_event_trace_init(file, &state); if (ret) { if (ret == -ENOENT) ret = 0; /* just disabled, not really an error */ return ret; } + if (state.event->n_dynamic_fields) { + va_start(args, n_vals); + + for (i = 0; i < state.event->n_fields; i++) { + u64 val = va_arg(args, u64); + + if (state.event->fields[i]->is_string && + state.event->fields[i]->is_dynamic) { + char *str_val = (char *)(long)val; + + data_size += strlen(str_val) + 1; + } + } + + va_end(args); + } + + ret = __synth_event_trace_start(file, &state, data_size); + if (ret) + return ret; + if (n_vals != state.event->n_fields) { ret = -EINVAL; goto out; } + data_size = 0; + va_start(args, n_vals); for (i = 0, n_u64 = 0; i < state.event->n_fields; i++) { u64 val; @@ -1299,10 +1568,11 @@ int synth_event_trace(struct trace_event_file *file, unsigned int n_vals, ...) 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); + len = trace_string(state.entry, state.event, str_val, + state.event->fields[i]->is_dynamic, + data_size, &n_u64); + data_size += len; /* only dynamic string increments */ } else { struct synth_field *field = state.event->fields[i]; @@ -1355,29 +1625,46 @@ EXPORT_SYMBOL_GPL(synth_event_trace); int synth_event_trace_array(struct trace_event_file *file, u64 *vals, unsigned int n_vals) { + unsigned int i, n_u64, field_pos, len, data_size = 0; struct synth_event_trace_state state; - unsigned int i, n_u64; + char *str_val; int ret; - ret = __synth_event_trace_start(file, &state); + ret = __synth_event_trace_init(file, &state); if (ret) { if (ret == -ENOENT) ret = 0; /* just disabled, not really an error */ return ret; } + if (state.event->n_dynamic_fields) { + for (i = 0; i < state.event->n_dynamic_fields; i++) { + field_pos = state.event->dynamic_fields[i]->field_pos; + str_val = (char *)(long)vals[field_pos]; + len = strlen(str_val) + 1; + data_size += len; + } + } + + ret = __synth_event_trace_start(file, &state, data_size); + if (ret) + return ret; + if (n_vals != state.event->n_fields) { ret = -EINVAL; goto out; } + data_size = 0; + 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); + len = trace_string(state.entry, state.event, str_val, + state.event->fields[i]->is_dynamic, + data_size, &n_u64); + data_size += len; /* only dynamic string increments */ } else { struct synth_field *field = state.event->fields[i]; u64 val = vals[i]; @@ -1445,9 +1732,17 @@ int synth_event_trace_start(struct trace_event_file *file, if (!trace_state) return -EINVAL; - ret = __synth_event_trace_start(file, trace_state); - if (ret == -ENOENT) - ret = 0; /* just disabled, not really an error */ + ret = __synth_event_trace_init(file, trace_state); + if (ret) { + if (ret == -ENOENT) + ret = 0; /* just disabled, not really an error */ + return ret; + } + + if (trace_state->event->n_dynamic_fields) + return -ENOTSUPP; + + ret = __synth_event_trace_start(file, trace_state, 0); return ret; } @@ -1508,6 +1803,11 @@ static int __synth_event_add_val(const char *field_name, u64 val, char *str_val = (char *)(long)val; char *str_field; + if (field->is_dynamic) { /* add_val can't do dynamic strings */ + ret = -EINVAL; + goto out; + } + if (!str_val) { ret = -EINVAL; goto out; @@ -1679,14 +1979,22 @@ static int __synth_event_show(struct seq_file *m, struct synth_event *event) { struct synth_field *field; unsigned int i; + char *type, *t; seq_printf(m, "%s\t", event->name); for (i = 0; i < event->n_fields; i++) { field = event->fields[i]; + type = field->type; + t = strstr(type, "__data_loc"); + if (t) { /* __data_loc belongs in format but not event desc */ + t += sizeof("__data_loc"); + type = t; + } + /* parameter values */ - seq_printf(m, "%s %s%s", field->type, field->name, + seq_printf(m, "%s %s%s", type, field->name, i == event->n_fields - 1 ? "" : "; "); } @@ -1754,25 +2062,31 @@ static const struct file_operations synth_events_fops = { .release = seq_release, }; -static __init int trace_events_synth_init(void) +/* + * Register dynevent at core_initcall. This allows kernel to setup kprobe + * events in postcore_initcall without tracefs. + */ +static __init int trace_events_synth_init_early(void) { - struct dentry *entry = NULL; - struct dentry *d_tracer; int err = 0; err = dyn_event_register(&synth_event_ops); - if (err) { + if (err) pr_warn("Could not register synth_event_ops\n"); - return err; - } - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) { - err = PTR_ERR(d_tracer); + return err; +} +core_initcall(trace_events_synth_init_early); + +static __init int trace_events_synth_init(void) +{ + struct dentry *entry = NULL; + int err = 0; + err = tracing_init_dentry(); + if (err) goto err; - } - entry = tracefs_create_file("synthetic_events", 0644, d_tracer, + entry = tracefs_create_file("synthetic_events", 0644, NULL, NULL, &synth_events_fops); if (!entry) { err = -ENODEV; diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 70d3d0a09053..d960f6b11b5e 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -26,7 +26,7 @@ static int ftrace_event_register(struct trace_event_call *call, /* * The FTRACE_ENTRY_REG macro allows ftrace entry to define register - * function and thus become accesible via perf. + * function and thus become accessible via perf. */ #undef FTRACE_ENTRY_REG #define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ @@ -176,7 +176,7 @@ struct trace_event_call __used event_##call = { \ .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \ }; \ static struct trace_event_call __used \ -__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; +__section("_ftrace_events") *__event_##call = &event_##call; #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index dd4dff71d89a..c5095dd28e20 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -23,10 +23,10 @@ static void tracing_start_function_trace(struct trace_array *tr); static void tracing_stop_function_trace(struct trace_array *tr); static void function_trace_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs); + struct ftrace_ops *op, struct ftrace_regs *fregs); static void function_stack_trace_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs); + struct ftrace_ops *op, struct ftrace_regs *fregs); static struct tracer_flags func_flags; /* Our option */ @@ -34,29 +34,37 @@ enum { TRACE_FUNC_OPT_STACK = 0x1, }; -static int allocate_ftrace_ops(struct trace_array *tr) +int ftrace_allocate_ftrace_ops(struct trace_array *tr) { struct ftrace_ops *ops; + /* The top level array uses the "global_ops" */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return 0; + ops = kzalloc(sizeof(*ops), GFP_KERNEL); if (!ops) return -ENOMEM; /* Currently only the non stack version is supported */ ops->func = function_trace_call; - ops->flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_PID; + ops->flags = FTRACE_OPS_FL_PID; tr->ops = ops; ops->private = tr; + return 0; } +void ftrace_free_ftrace_ops(struct trace_array *tr) +{ + kfree(tr->ops); + tr->ops = NULL; +} int ftrace_create_function_files(struct trace_array *tr, struct dentry *parent) { - int ret; - /* * The top level array uses the "global_ops", and the files are * created on boot up. @@ -64,9 +72,8 @@ int ftrace_create_function_files(struct trace_array *tr, if (tr->flags & TRACE_ARRAY_FL_GLOBAL) return 0; - ret = allocate_ftrace_ops(tr); - if (ret) - return ret; + if (!tr->ops) + return -EINVAL; ftrace_create_filter_files(tr->ops, parent); @@ -76,14 +83,12 @@ int ftrace_create_function_files(struct trace_array *tr, void ftrace_destroy_function_files(struct trace_array *tr) { ftrace_destroy_filter_files(tr->ops); - kfree(tr->ops); - tr->ops = NULL; + ftrace_free_ftrace_ops(tr); } static int function_trace_init(struct trace_array *tr) { ftrace_func_t func; - /* * Instance trace_arrays get their ops allocated * at instance creation. Unless it failed @@ -123,7 +128,7 @@ static void function_trace_start(struct trace_array *tr) static void function_trace_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { struct trace_array *tr = op->private; struct trace_array_cpu *data; @@ -135,22 +140,20 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, if (unlikely(!tr->function_enabled)) return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + pc = preempt_count(); preempt_disable_notrace(); - bit = trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX); - if (bit < 0) - goto out; - cpu = smp_processor_id(); 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); } - trace_clear_recursion(bit); - - out: + ftrace_test_recursion_unlock(bit); preempt_enable_notrace(); } @@ -174,7 +177,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, static void function_stack_trace_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { struct trace_array *tr = op->private; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 4a9c49c08ec9..d874dec87131 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -957,7 +957,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s, /* Overrun */ if (flags & TRACE_GRAPH_PRINT_OVERRUN) - trace_seq_printf(s, " (Overruns: %lu)\n", + trace_seq_printf(s, " (Overruns: %u)\n", trace->overrun); print_graph_irq(iter, trace->func, TRACE_GRAPH_RET, @@ -1336,13 +1336,13 @@ static const struct file_operations graph_depth_fops = { static __init int init_graph_tracefs(void) { - struct dentry *d_tracer; + int ret; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return 0; - trace_create_file("max_graph_depth", 0644, d_tracer, + trace_create_file("max_graph_depth", 0644, NULL, NULL, &graph_depth_fops); return 0; diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 17873e5d0353..c0df9b97f147 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -368,7 +368,7 @@ static int start_kthread(struct trace_array *tr) struct task_struct *kthread; int next_cpu; - if (WARN_ON(hwlat_kthread)) + if (hwlat_kthread) return 0; /* Just pick the first CPU on first iteration */ @@ -485,11 +485,11 @@ hwlat_width_write(struct file *filp, const char __user *ubuf, * @ppos: The current position in @file * * This function provides a write implementation for the "window" interface - * to the hardware latency detetector. The window is the total time + * to the hardware latency detector. The window is the total time * in us that will be considered one sample period. Conceptually, windows * occur back-to-back and contain a sample width period during which * actual sampling occurs. Can be used to write a new total window size. It - * is enfoced that any value written must be greater than the sample width + * is enforced that any value written must be greater than the sample width * size, or an error results. */ static ssize_t @@ -538,14 +538,14 @@ static const struct file_operations window_fops = { */ static int init_tracefs(void) { - struct dentry *d_tracer; + int ret; struct dentry *top_dir; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return -ENOMEM; - top_dir = tracefs_create_dir("hwlat_detector", d_tracer); + top_dir = tracefs_create_dir("hwlat_detector", NULL); if (!top_dir) return -ENOMEM; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 10bbb0f381d5..6756379b661f 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -138,7 +138,7 @@ static int func_prolog_dec(struct trace_array *tr, */ static void irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; @@ -562,6 +562,8 @@ static int __irqsoff_tracer_init(struct trace_array *tr) /* non overwrite screws up the latency tracers */ set_tracer_flag(tr, TRACE_ITER_OVERWRITE, 1); set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, 1); + /* without pause, we will produce garbage if another latency occurs */ + set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, 1); tr->max_latency = 0; irqsoff_trace = tr; @@ -583,11 +585,13 @@ static void __irqsoff_tracer_reset(struct trace_array *tr) { int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + int pause_flag = save_flags & TRACE_ITER_PAUSE_ON_TRACE; stop_irqsoff_tracer(tr, is_graph(tr)); set_tracer_flag(tr, TRACE_ITER_LATENCY_FMT, lat_flag); set_tracer_flag(tr, TRACE_ITER_OVERWRITE, overwrite_flag); + set_tracer_flag(tr, TRACE_ITER_PAUSE_ON_TRACE, pause_flag); ftrace_reset_array_ops(tr); irqsoff_busy = false; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index aefb6065b508..56c7fbff7bd7 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -25,11 +25,12 @@ /* Kprobe early definition from command line */ static char kprobe_boot_events_buf[COMMAND_LINE_SIZE] __initdata; -static bool kprobe_boot_events_enabled __initdata; static int __init set_kprobe_boot_events(char *str) { strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE); + disable_tracing_selftest("running kprobe events"); + return 0; } __setup("kprobe_event=", set_kprobe_boot_events); @@ -106,9 +107,10 @@ static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk) static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk, struct module *mod) { - int len = strlen(mod->name); + int len = strlen(module_name(mod)); const char *name = trace_kprobe_symbol(tk); - return strncmp(mod->name, name, len) == 0 && name[len] == ':'; + + return strncmp(module_name(mod), name, len) == 0 && name[len] == ':'; } static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk) @@ -219,9 +221,9 @@ bool trace_kprobe_on_func_entry(struct trace_event_call *call) { struct trace_kprobe *tk = trace_kprobe_primary_from_call(call); - return tk ? 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) : false; + tk->rp.kp.addr ? 0 : tk->rp.kp.offset) == 0) : false; } bool trace_kprobe_error_injectable(struct trace_event_call *call) @@ -432,7 +434,7 @@ static int disable_trace_kprobe(struct trace_event_call *call, return 0; } -#if defined(CONFIG_KPROBES_ON_FTRACE) && \ +#if defined(CONFIG_DYNAMIC_FTRACE) && \ !defined(CONFIG_KPROBE_EVENTS_ON_NOTRACE) static bool __within_notrace_func(unsigned long addr) { @@ -688,7 +690,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb, if (ret) pr_warn("Failed to re-register probe %s on %s: %d\n", trace_probe_name(&tk->tp), - mod->name, ret); + module_name(mod), ret); } } mutex_unlock(&event_mutex); @@ -717,6 +719,9 @@ static int trace_kprobe_create(int argc, const char *argv[]) * p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS] * - Add kretprobe: * r[MAXACTIVE][:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS] + * Or + * p:[GRP/]EVENT] [MOD:]KSYM[+0]%return [FETCHARGS] + * * Fetch args: * $retval : fetch return value * $stack : fetch stack address @@ -746,7 +751,6 @@ static int trace_kprobe_create(int argc, const char *argv[]) switch (argv[0][0]) { case 'r': is_return = true; - flags |= TPARG_FL_RETURN; break; case 'p': break; @@ -804,15 +808,31 @@ static int trace_kprobe_create(int argc, const char *argv[]) symbol = kstrdup(argv[1], GFP_KERNEL); if (!symbol) return -ENOMEM; + + tmp = strchr(symbol, '%'); + if (tmp) { + if (!strcmp(tmp, "%return")) { + *tmp = '\0'; + is_return = true; + } else { + trace_probe_log_err(tmp - symbol, BAD_ADDR_SUFFIX); + goto parse_error; + } + } + /* TODO: support .init module functions */ ret = traceprobe_split_symbol_offset(symbol, &offset); if (ret || offset < 0 || offset > UINT_MAX) { trace_probe_log_err(0, BAD_PROBE_ADDR); goto parse_error; } - if (kprobe_on_func_entry(NULL, symbol, offset)) + if (is_return) + flags |= TPARG_FL_RETURN; + ret = kprobe_on_func_entry(NULL, symbol, offset); + if (ret == 0) flags |= TPARG_FL_FENTRY; - if (offset && is_return && !(flags & TPARG_FL_FENTRY)) { + /* Defer the ENOENT case until register kprobe */ + if (ret == -EINVAL && is_return) { trace_probe_log_err(0, BAD_RETPROBE); goto parse_error; } @@ -1714,7 +1734,8 @@ NOKPROBE_SYMBOL(kprobe_dispatcher); static int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) { - struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp); + struct kretprobe *rp = get_kretprobe(ri); + struct trace_kprobe *tk = container_of(rp, struct trace_kprobe, rp); raw_cpu_inc(*tk->nhit); @@ -1870,8 +1891,6 @@ static __init void setup_boot_kprobe_events(void) ret = trace_run_command(cmd, create_or_delete_trace_kprobe); if (ret) pr_warn("Failed to add event(%d): %s\n", ret, cmd); - else - kprobe_boot_events_enabled = true; cmd = p; } @@ -1880,8 +1899,8 @@ static __init void setup_boot_kprobe_events(void) } /* - * Register dynevent at subsys_initcall. This allows kernel to setup kprobe - * events in fs_initcall without tracefs. + * Register dynevent at core_initcall. This allows kernel to setup kprobe + * events in postcore_initcall without tracefs. */ static __init int init_kprobe_trace_early(void) { @@ -1896,19 +1915,19 @@ static __init int init_kprobe_trace_early(void) return 0; } -subsys_initcall(init_kprobe_trace_early); +core_initcall(init_kprobe_trace_early); /* Make a tracefs interface for controlling probe points */ static __init int init_kprobe_trace(void) { - struct dentry *d_tracer; + int ret; struct dentry *entry; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return 0; - entry = tracefs_create_file("kprobe_events", 0644, d_tracer, + entry = tracefs_create_file("kprobe_events", 0644, NULL, NULL, &kprobe_events_ops); /* Event list interface */ @@ -1916,7 +1935,7 @@ static __init int init_kprobe_trace(void) pr_warn("Could not create tracefs 'kprobe_events' entry\n"); /* Profile interface */ - entry = tracefs_create_file("kprobe_profile", 0444, d_tracer, + entry = tracefs_create_file("kprobe_profile", 0444, NULL, NULL, &kprobe_profile_ops); if (!entry) @@ -1956,10 +1975,8 @@ static __init int kprobe_trace_self_tests_init(void) if (tracing_is_disabled()) return -ENODEV; - if (kprobe_boot_events_enabled) { - pr_info("Skipping kprobe tests due to kprobe_event on cmdline\n"); + if (tracing_selftest_disabled) return 0; - } target = kprobe_trace_selftest_target; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 000e9dc224c6..92b1575ae0ca 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -353,8 +353,8 @@ static inline const char *kretprobed(const char *name) } #endif /* CONFIG_KRETPROBES */ -static void -seq_print_sym(struct trace_seq *s, unsigned long address, bool offset) +void +trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset) { #ifdef CONFIG_KALLSYMS char str[KSYM_SYMBOL_LEN]; @@ -420,7 +420,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) goto out; } - seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET); + trace_seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET); if (sym_flags & TRACE_ITER_SYM_ADDR) trace_seq_printf(s, " <" IP_FMT ">", ip); diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index 2f742b74e7e6..4c954636caf0 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -16,6 +16,7 @@ extern int seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags); +extern void trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset); extern int trace_print_context(struct trace_iterator *iter); extern int trace_print_lat_context(struct trace_iterator *iter); diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index d4e31e969206..ff32476df072 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -96,7 +96,7 @@ static int module_trace_bprintk_format_notify(struct notifier_block *self, if (val == MODULE_STATE_COMING) hold_module_trace_bprintk_format(start, end); } - return 0; + return NOTIFY_OK; } /* @@ -174,7 +174,7 @@ __init static int module_trace_bprintk_format_notify(struct notifier_block *self, unsigned long val, void *data) { - return 0; + return NOTIFY_OK; } static inline const char ** find_next_mod_format(int start_index, void *v, const char **fmt, loff_t *pos) @@ -367,13 +367,13 @@ static const struct file_operations ftrace_formats_fops = { static __init int init_trace_printk_function_export(void) { - struct dentry *d_tracer; + int ret; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return 0; - trace_create_file("printk_formats", 0444, d_tracer, + trace_create_file("printk_formats", 0444, NULL, NULL, &ftrace_formats_fops); return 0; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index a22b62813f8c..2f703a20c724 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -16,7 +16,6 @@ #include <linux/tracefs.h> #include <linux/types.h> #include <linux/string.h> -#include <linux/ctype.h> #include <linux/ptrace.h> #include <linux/perf_event.h> #include <linux/kprobes.h> @@ -348,18 +347,6 @@ bool trace_probe_match_command_args(struct trace_probe *tp, #define trace_probe_for_each_link_rcu(pos, tp) \ 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) -{ - if (!isalpha(*name) && *name != '_') - return false; - while (*++name != '\0') { - if (!isalpha(*name) && !isdigit(*name) && *name != '_') - return false; - } - return true; -} - #define TPARG_FL_RETURN BIT(0) #define TPARG_FL_KERNEL BIT(1) #define TPARG_FL_FENTRY BIT(2) @@ -404,6 +391,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(MAXACT_TOO_BIG, "Maxactive is too big"), \ C(BAD_PROBE_ADDR, "Invalid probed address or symbol"), \ C(BAD_RETPROBE, "Retprobe address must be an function entry"), \ + C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \ C(NO_GROUP_NAME, "Group name is not specified"), \ C(GROUP_TOO_LONG, "Group name is too long"), \ C(BAD_GROUP_NAME, "Group name must follow the same rules as C identifiers"), \ diff --git a/kernel/trace/trace_recursion_record.c b/kernel/trace/trace_recursion_record.c new file mode 100644 index 000000000000..b2edac1fe156 --- /dev/null +++ b/kernel/trace/trace_recursion_record.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/seq_file.h> +#include <linux/kallsyms.h> +#include <linux/module.h> +#include <linux/ftrace.h> +#include <linux/fs.h> + +#include "trace_output.h" + +struct recursed_functions { + unsigned long ip; + unsigned long parent_ip; +}; + +static struct recursed_functions recursed_functions[CONFIG_FTRACE_RECORD_RECURSION_SIZE]; +static atomic_t nr_records; + +/* + * Cache the last found function. Yes, updates to this is racey, but + * so is memory cache ;-) + */ +static unsigned long cached_function; + +void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip) +{ + int index = 0; + int i; + unsigned long old; + + again: + /* First check the last one recorded */ + if (ip == cached_function) + return; + + i = atomic_read(&nr_records); + /* nr_records is -1 when clearing records */ + smp_mb__after_atomic(); + if (i < 0) + return; + + /* + * If there's two writers and this writer comes in second, + * the cmpxchg() below to update the ip will fail. Then this + * writer will try again. It is possible that index will now + * be greater than nr_records. This is because the writer + * that succeeded has not updated the nr_records yet. + * This writer could keep trying again until the other writer + * updates nr_records. But if the other writer takes an + * interrupt, and that interrupt locks up that CPU, we do + * not want this CPU to lock up due to the recursion protection, + * and have a bug report showing this CPU as the cause of + * locking up the computer. To not lose this record, this + * writer will simply use the next position to update the + * recursed_functions, and it will update the nr_records + * accordingly. + */ + if (index < i) + index = i; + if (index >= CONFIG_FTRACE_RECORD_RECURSION_SIZE) + return; + + for (i = index - 1; i >= 0; i--) { + if (recursed_functions[i].ip == ip) { + cached_function = ip; + return; + } + } + + cached_function = ip; + + /* + * We only want to add a function if it hasn't been added before. + * Add to the current location before incrementing the count. + * If it fails to add, then increment the index (save in i) + * and try again. + */ + old = cmpxchg(&recursed_functions[index].ip, 0, ip); + if (old != 0) { + /* Did something else already added this for us? */ + if (old == ip) + return; + /* Try the next location (use i for the next index) */ + index++; + goto again; + } + + recursed_functions[index].parent_ip = parent_ip; + + /* + * It's still possible that we could race with the clearing + * CPU0 CPU1 + * ---- ---- + * ip = func + * nr_records = -1; + * recursed_functions[0] = 0; + * i = -1 + * if (i < 0) + * nr_records = 0; + * (new recursion detected) + * recursed_functions[0] = func + * cmpxchg(recursed_functions[0], + * func, 0) + * + * But the worse that could happen is that we get a zero in + * the recursed_functions array, and it's likely that "func" will + * be recorded again. + */ + i = atomic_read(&nr_records); + smp_mb__after_atomic(); + if (i < 0) + cmpxchg(&recursed_functions[index].ip, ip, 0); + else if (i <= index) + atomic_cmpxchg(&nr_records, i, index + 1); +} +EXPORT_SYMBOL_GPL(ftrace_record_recursion); + +static DEFINE_MUTEX(recursed_function_lock); +static struct trace_seq *tseq; + +static void *recursed_function_seq_start(struct seq_file *m, loff_t *pos) +{ + void *ret = NULL; + int index; + + mutex_lock(&recursed_function_lock); + index = atomic_read(&nr_records); + if (*pos < index) { + ret = &recursed_functions[*pos]; + } + + tseq = kzalloc(sizeof(*tseq), GFP_KERNEL); + if (!tseq) + return ERR_PTR(-ENOMEM); + + trace_seq_init(tseq); + + return ret; +} + +static void *recursed_function_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + int index; + int p; + + index = atomic_read(&nr_records); + p = ++(*pos); + + return p < index ? &recursed_functions[p] : NULL; +} + +static void recursed_function_seq_stop(struct seq_file *m, void *v) +{ + kfree(tseq); + mutex_unlock(&recursed_function_lock); +} + +static int recursed_function_seq_show(struct seq_file *m, void *v) +{ + struct recursed_functions *record = v; + int ret = 0; + + if (record) { + trace_seq_print_sym(tseq, record->parent_ip, true); + trace_seq_puts(tseq, ":\t"); + trace_seq_print_sym(tseq, record->ip, true); + trace_seq_putc(tseq, '\n'); + ret = trace_print_seq(m, tseq); + } + + return ret; +} + +static const struct seq_operations recursed_function_seq_ops = { + .start = recursed_function_seq_start, + .next = recursed_function_seq_next, + .stop = recursed_function_seq_stop, + .show = recursed_function_seq_show +}; + +static int recursed_function_open(struct inode *inode, struct file *file) +{ + int ret = 0; + + mutex_lock(&recursed_function_lock); + /* If this file was opened for write, then erase contents */ + if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { + /* disable updating records */ + atomic_set(&nr_records, -1); + smp_mb__after_atomic(); + memset(recursed_functions, 0, sizeof(recursed_functions)); + smp_wmb(); + /* enable them again */ + atomic_set(&nr_records, 0); + } + if (file->f_mode & FMODE_READ) + ret = seq_open(file, &recursed_function_seq_ops); + mutex_unlock(&recursed_function_lock); + + return ret; +} + +static ssize_t recursed_function_write(struct file *file, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + return count; +} + +static int recursed_function_release(struct inode *inode, struct file *file) +{ + if (file->f_mode & FMODE_READ) + seq_release(inode, file); + return 0; +} + +static const struct file_operations recursed_functions_fops = { + .open = recursed_function_open, + .write = recursed_function_write, + .read = seq_read, + .llseek = seq_lseek, + .release = recursed_function_release, +}; + +__init static int create_recursed_functions(void) +{ + struct dentry *dentry; + + dentry = trace_create_file("recursed_functions", 0644, NULL, NULL, + &recursed_functions_fops); + if (!dentry) + pr_warn("WARNING: Failed to create recursed_functions\n"); + return 0; +} + +fs_initcall(create_recursed_functions); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 97b10bb31a1f..c0181066dbe9 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -212,7 +212,7 @@ static void wakeup_print_header(struct seq_file *s) */ static void wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index b5e3496cf803..73ef12092250 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -107,7 +107,7 @@ static int trace_selftest_test_probe1_cnt; static void trace_selftest_test_probe1_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { trace_selftest_test_probe1_cnt++; } @@ -116,7 +116,7 @@ static int trace_selftest_test_probe2_cnt; static void trace_selftest_test_probe2_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { trace_selftest_test_probe2_cnt++; } @@ -125,7 +125,7 @@ static int trace_selftest_test_probe3_cnt; static void trace_selftest_test_probe3_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { trace_selftest_test_probe3_cnt++; } @@ -134,7 +134,7 @@ static int trace_selftest_test_global_cnt; static void trace_selftest_test_global_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { trace_selftest_test_global_cnt++; } @@ -143,24 +143,21 @@ static int trace_selftest_test_dyn_cnt; static void trace_selftest_test_dyn_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { trace_selftest_test_dyn_cnt++; } static struct ftrace_ops test_probe1 = { .func = trace_selftest_test_probe1_func, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe2 = { .func = trace_selftest_test_probe2_func, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe3 = { .func = trace_selftest_test_probe3_func, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static void print_counts(void) @@ -417,7 +414,7 @@ static int trace_selftest_recursion_cnt; static void trace_selftest_test_recursion_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { /* * This function is registered without the recursion safe flag. @@ -432,7 +429,7 @@ static void trace_selftest_test_recursion_func(unsigned long ip, static void trace_selftest_test_recursion_safe_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { /* * We said we would provide our own recursion. By calling @@ -448,11 +445,11 @@ static void trace_selftest_test_recursion_safe_func(unsigned long ip, static struct ftrace_ops test_rec_probe = { .func = trace_selftest_test_recursion_func, + .flags = FTRACE_OPS_FL_RECURSION, }; static struct ftrace_ops test_recsafe_probe = { .func = trace_selftest_test_recursion_safe_func, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int @@ -492,8 +489,13 @@ trace_selftest_function_recursion(void) unregister_ftrace_function(&test_rec_probe); ret = -1; - if (trace_selftest_recursion_cnt != 1) { - pr_cont("*callback not called once (%d)* ", + /* + * Recursion allows for transitions between context, + * and may call the callback twice. + */ + if (trace_selftest_recursion_cnt != 1 && + trace_selftest_recursion_cnt != 2) { + pr_cont("*callback not called once (or twice) (%d)* ", trace_selftest_recursion_cnt); goto out; } @@ -546,9 +548,11 @@ static enum { static void trace_selftest_test_regs_func(unsigned long ip, unsigned long pip, struct ftrace_ops *op, - struct pt_regs *pt_regs) + struct ftrace_regs *fregs) { - if (pt_regs) + struct pt_regs *regs = ftrace_get_regs(fregs); + + if (regs) trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND; else trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND; @@ -556,7 +560,7 @@ static void trace_selftest_test_regs_func(unsigned long ip, static struct ftrace_ops test_regs_probe = { .func = trace_selftest_test_regs_func, - .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS, + .flags = FTRACE_OPS_FL_SAVE_REGS, }; static int @@ -782,7 +786,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, /* Have we just recovered from a hang? */ if (graph_hang_thresh > GRAPH_MAX_FUNC_TEST) { - tracing_selftest_disabled = true; + disable_tracing_selftest("recovering from a hang"); ret = -1; goto out; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 98bba4764c52..63c285042051 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -290,7 +290,7 @@ static void check_stack(unsigned long ip, unsigned long *stack) static void stack_trace_call(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct pt_regs *pt_regs) + struct ftrace_ops *op, struct ftrace_regs *fregs) { unsigned long stack; @@ -318,7 +318,6 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip, static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, - .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static ssize_t @@ -554,20 +553,20 @@ __setup("stacktrace", enable_stacktrace); static __init int stack_trace_init(void) { - struct dentry *d_tracer; + int ret; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return 0; - trace_create_file("stack_max_size", 0644, d_tracer, + trace_create_file("stack_max_size", 0644, NULL, &stack_trace_max_size, &stack_max_size_fops); - trace_create_file("stack_trace", 0444, d_tracer, + trace_create_file("stack_trace", 0444, NULL, NULL, &stack_trace_fops); #ifdef CONFIG_DYNAMIC_FTRACE - trace_create_file("stack_trace_filter", 0644, d_tracer, + trace_create_file("stack_trace_filter", 0644, NULL, &trace_ops, &stack_trace_filter_fops); #endif diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index d1fa19773cc8..8d141c3825a9 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -276,13 +276,13 @@ static const struct file_operations tracing_stat_fops = { static int tracing_stat_init(void) { - struct dentry *d_tracing; + int ret; - d_tracing = tracing_init_dentry(); - if (IS_ERR(d_tracing)) + ret = tracing_init_dentry(); + if (ret) return -ENODEV; - stat_dir = tracefs_create_dir("trace_stat", d_tracing); + stat_dir = tracefs_create_dir("trace_stat", NULL); if (!stat_dir) { pr_warn("Could not create tracefs 'trace_stat' entry\n"); return -ENOMEM; diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h index ac35c45207c4..6e146b959dcd 100644 --- a/kernel/trace/trace_synth.h +++ b/kernel/trace/trace_synth.h @@ -7,7 +7,7 @@ #define SYNTH_SYSTEM "synthetic" #define SYNTH_FIELDS_MAX 32 -#define STR_VAR_LEN_MAX 32 /* must be multiple of sizeof(u64) */ +#define STR_VAR_LEN_MAX MAX_FILTER_STR_VAL /* must be multiple of sizeof(u64) */ struct synth_field { char *type; @@ -16,6 +16,8 @@ struct synth_field { unsigned int offset; bool is_signed; bool is_string; + bool is_dynamic; + bool field_pos; }; struct synth_event { @@ -24,6 +26,8 @@ struct synth_event { char *name; struct synth_field **fields; unsigned int n_fields; + struct synth_field **dynamic_fields; + unsigned int n_dynamic_fields; unsigned int n_u64; struct trace_event_class class; struct trace_event_call call; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index f4286c9bdeb4..3cf7128e1ad3 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -528,7 +528,7 @@ end: /* * Argument syntax: - * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET [FETCHARGS] + * - Add uprobe: p|r[:[GRP/]EVENT] PATH:OFFSET[%return][(REF)] [FETCHARGS] */ static int trace_uprobe_create(int argc, const char **argv) { @@ -617,6 +617,19 @@ static int trace_uprobe_create(int argc, const char **argv) } } + /* Check if there is %return suffix */ + tmp = strchr(arg, '%'); + if (tmp) { + if (!strcmp(tmp, "%return")) { + *tmp = '\0'; + is_return = true; + } else { + trace_probe_log_err(tmp - filename, BAD_ADDR_SUFFIX); + ret = -EINVAL; + goto fail_address_parse; + } + } + /* Parse uprobe offset. */ ret = kstrtoul(arg, 0, &offset); if (ret) { @@ -1625,21 +1638,20 @@ void destroy_local_trace_uprobe(struct trace_event_call *event_call) /* Make a trace interface for controling probe points */ static __init int init_uprobe_trace(void) { - struct dentry *d_tracer; int ret; ret = dyn_event_register(&trace_uprobe_ops); if (ret) return ret; - d_tracer = tracing_init_dentry(); - if (IS_ERR(d_tracer)) + ret = tracing_init_dentry(); + if (ret) return 0; - trace_create_file("uprobe_events", 0644, d_tracer, + trace_create_file("uprobe_events", 0644, NULL, NULL, &uprobe_events_ops); /* Profile interface */ - trace_create_file("uprobe_profile", 0444, d_tracer, + trace_create_file("uprobe_profile", 0444, NULL, NULL, &uprobe_profile_ops); return 0; } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 74738c9856f1..d6bddb157ef2 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -260,7 +260,7 @@ int tracing_map_add_var(struct tracing_map *map) * to use cmp_fn. * * A key can be a subset of a compound key; for that purpose, the - * offset param is used to describe where within the the compound key + * offset param is used to describe where within the compound key * the key referenced by this key field resides. * * Return: The index identifying the field in the map and associated @@ -609,7 +609,7 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only) * signal that state. There are two user-visible tracing_map * variables, 'hits' and 'drops', which are updated by this function. * Every time an element is either successfully inserted or retrieved, - * the 'hits' value is incrememented. Every time an element insertion + * the 'hits' value is incremented. Every time an element insertion * fails, the 'drops' value is incremented. * * This is a lock-free tracing map insertion function implementing a @@ -642,9 +642,9 @@ struct tracing_map_elt *tracing_map_insert(struct tracing_map *map, void *key) * tracing_map_elt. This is a lock-free lookup; see * tracing_map_insert() for details on tracing_map and how it works. * Every time an element is retrieved, the 'hits' value is - * incrememented. There is one user-visible tracing_map variable, + * incremented. There is one user-visible tracing_map variable, * 'hits', which is updated by this function. Every time an element - * is successfully retrieved, the 'hits' value is incrememented. The + * is successfully retrieved, the 'hits' value is incremented. The * 'drops' value is never updated by this function. * * Return: the tracing_map_elt pointer val associated with the key. diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h index a6de61fc22de..2c765ee2a4d4 100644 --- a/kernel/trace/tracing_map.h +++ b/kernel/trace/tracing_map.h @@ -50,7 +50,7 @@ typedef int (*tracing_map_cmp_fn_t) (void *val_a, void *val_b); * an instance of tracing_map_elt, where 'elt' in the latter part of * that variable name is short for 'element'. The purpose of a * tracing_map_elt is to hold values specific to the particular - * 32-bit hashed key it's assocated with. Things such as the unique + * 32-bit hashed key it's associated with. Things such as the unique * set of aggregated sums associated with the 32-bit hashed key, along * with a copy of the full key associated with the entry, and which * was used to produce the 32-bit hashed key. |