From d23569979ca1cd139a42c410e0c7b9e6014c3b3a Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Wed, 13 Dec 2023 09:37:01 -0500 Subject: tracing: Allow creating instances with specified system events A trace instance may only need to enable specific events. As the eventfs directory of an instance currently creates all events which adds overhead, allow internal instances to be created with just the events in systems that they care about. This currently only deals with systems and not individual events, but this should bring down the overhead of creating instances for specific use cases quite bit. The trace_array_get_by_name() now has another parameter "systems". This parameter is a const string pointer of a comma/space separated list of event systems that should be created by the trace_array. (Note if the trace_array already exists, this parameter is ignored). The list of systems is saved and if a module is loaded, its events will not be added unless the system for those events also match the systems string. Link: https://lore.kernel.org/linux-trace-kernel/20231213093701.03fddec0@gandalf.local.home Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Sean Paul Cc: Arun Easi Cc: Daniel Wagner Tested-by: Dmytro Maluka Signed-off-by: Steven Rostedt (Google) --- include/linux/trace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/trace.h b/include/linux/trace.h index 2a70a447184c..fdcd76b7be83 100644 --- a/include/linux/trace.h +++ b/include/linux/trace.h @@ -51,7 +51,7 @@ int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...); int trace_array_init_printk(struct trace_array *tr); void trace_array_put(struct trace_array *tr); -struct trace_array *trace_array_get_by_name(const char *name); +struct trace_array *trace_array_get_by_name(const char *name, const char *systems); int trace_array_destroy(struct trace_array *tr); /* For osnoise tracer */ @@ -84,7 +84,7 @@ static inline int trace_array_init_printk(struct trace_array *tr) static inline void trace_array_put(struct trace_array *tr) { } -static inline struct trace_array *trace_array_get_by_name(const char *name) +static inline struct trace_array *trace_array_get_by_name(const char *name, const char *systems) { return NULL; } -- cgit From 8ec90be7f15fac42992ea821be929d3b06cd0fd9 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Tue, 12 Dec 2023 13:19:01 -0500 Subject: tracing: Allow for max buffer data size trace_marker writes Allow a trace write to be as big as the ring buffer tracing data will allow. Currently, it only allows writes of 1KB in size, but there's no reason that it cannot allow what the ring buffer can hold. Link: https://lore.kernel.org/linux-trace-kernel/20231212131901.5f501e72@gandalf.local.home Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 782e14f62201..b1b03b2c0f08 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -141,6 +141,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter); bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter); unsigned long ring_buffer_size(struct trace_buffer *buffer, int cpu); +unsigned long ring_buffer_max_event_size(struct trace_buffer *buffer); void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu); void ring_buffer_reset_online_cpus(struct trace_buffer *buffer); -- cgit From 40fc60e36c60ba85b2974e507b67df40c94e9578 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Sat, 9 Dec 2023 17:52:20 -0500 Subject: trace_seq: Increase the buffer size to almost two pages Now that trace_marker can hold more than 1KB string, and can write as much as the ring buffer can hold, the trace_seq is not big enough to hold writes: ~# a="1234567890" ~# cnt=4080 ~# s="" ~# while [ $cnt -gt 10 ]; do ~# s="${s}${a}" ~# cnt=$((cnt-10)) ~# done ~# echo $s > trace_marker ~# cat trace # tracer: nop # # entries-in-buffer/entries-written: 2/2 #P:8 # # _-----=> irqs-off/BH-disabled # / _----=> need-resched # | / _---=> hardirq/softirq # || / _--=> preempt-depth # ||| / _-=> migrate-disable # |||| / delay # TASK-PID CPU# ||||| TIMESTAMP FUNCTION # | | | ||||| | | <...>-860 [002] ..... 105.543465: tracing_mark_write[LINE TOO BIG] <...>-860 [002] ..... 105.543496: tracing_mark_write: 789012345678901234567890 By increasing the trace_seq buffer to almost two pages, it can now print out the first line. This also subtracts the rest of the trace_seq fields from the buffer, so that the entire trace_seq is now PAGE_SIZE aligned. Link: https://lore.kernel.org/linux-trace-kernel/20231209175220.19867af4@gandalf.local.home Cc: Mark Rutland Cc: Mathieu Desnoyers Reviewed-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- include/linux/trace_seq.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h index 3691e0e76a1a..9ec229dfddaa 100644 --- a/include/linux/trace_seq.h +++ b/include/linux/trace_seq.h @@ -8,11 +8,14 @@ /* * Trace sequences are used to allow a function to call several other functions - * to create a string of data to use (up to a max of PAGE_SIZE). + * to create a string of data to use. */ +#define TRACE_SEQ_BUFFER_SIZE (PAGE_SIZE * 2 - \ + (sizeof(struct seq_buf) + sizeof(size_t) + sizeof(int))) + struct trace_seq { - char buffer[PAGE_SIZE]; + char buffer[TRACE_SEQ_BUFFER_SIZE]; struct seq_buf seq; size_t readpos; int full; @@ -21,7 +24,7 @@ struct trace_seq { static inline void trace_seq_init(struct trace_seq *s) { - seq_buf_init(&s->seq, s->buffer, PAGE_SIZE); + seq_buf_init(&s->seq, s->buffer, TRACE_SEQ_BUFFER_SIZE); s->full = 0; s->readpos = 0; } -- cgit From 139f84002145d8624f0195fb090b3a7670744a13 Mon Sep 17 00:00:00 2001 From: "Tzvetomir Stoyanov (VMware)" Date: Tue, 19 Dec 2023 13:54:16 -0500 Subject: ring-buffer: Page size per ring buffer Currently the size of one sub buffer page is global for all buffers and it is hard coded to one system page. In order to introduce configurable ring buffer sub page size, the internal logic should be refactored to work with sub page size per ring buffer. Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-3-tz.stoyanov@gmail.com Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.009147038@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Vincent Donnefort Cc: Kent Overstreet Signed-off-by: Tzvetomir Stoyanov (VMware) Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b1b03b2c0f08..ce46218ce46d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -200,7 +200,7 @@ int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page, struct trace_seq; int ring_buffer_print_entry_header(struct trace_seq *s); -int ring_buffer_print_page_header(struct trace_seq *s); +int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s); enum ring_buffer_flags { RB_FL_OVERWRITE = 1 << 0, -- cgit From 2808e31ec12e5fbe2ae25acc027fcdc67b1fb7f0 Mon Sep 17 00:00:00 2001 From: "Tzvetomir Stoyanov (VMware)" Date: Tue, 19 Dec 2023 13:54:17 -0500 Subject: ring-buffer: Add interface for configuring trace sub buffer size The trace ring buffer sub page size can be configured, per trace instance. A new ftrace file "buffer_subbuf_order" is added to get and set the size of the ring buffer sub page for current trace instance. The size must be an order of system page size, that's why the new interface works with system page order, instead of absolute page size: 0 means the ring buffer sub page is equal to 1 system page and so forth: 0 - 1 system page 1 - 2 system pages 2 - 4 system pages ... The ring buffer sub page size is limited between 1 and 128 system pages. The default value is 1 system page. New ring buffer APIs are introduced: ring_buffer_subbuf_order_set() ring_buffer_subbuf_order_get() ring_buffer_subbuf_size_get() Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-4-tz.stoyanov@gmail.com Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.298324722@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Vincent Donnefort Cc: Kent Overstreet Signed-off-by: Tzvetomir Stoyanov (VMware) Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index ce46218ce46d..12573306b889 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -202,6 +202,10 @@ struct trace_seq; int ring_buffer_print_entry_header(struct trace_seq *s); int ring_buffer_print_page_header(struct trace_buffer *buffer, struct trace_seq *s); +int ring_buffer_subbuf_order_get(struct trace_buffer *buffer); +int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order); +int ring_buffer_subbuf_size_get(struct trace_buffer *buffer); + enum ring_buffer_flags { RB_FL_OVERWRITE = 1 << 0, }; -- cgit From bce761d757452ba5eb77e11fecc37a04b67494e7 Mon Sep 17 00:00:00 2001 From: "Tzvetomir Stoyanov (VMware)" Date: Tue, 19 Dec 2023 13:54:19 -0500 Subject: ring-buffer: Read and write to ring buffers with custom sub buffer size As the size of the ring sub buffer page can be changed dynamically, the logic that reads and writes to the buffer should be fixed to take that into account. Some internal ring buffer APIs are changed: ring_buffer_alloc_read_page() ring_buffer_free_read_page() ring_buffer_read_page() A new API is introduced: ring_buffer_read_page_data() Link: https://lore.kernel.org/linux-trace-devel/20211213094825.61876-6-tz.stoyanov@gmail.com Link: https://lore.kernel.org/linux-trace-kernel/20231219185628.875145995@goodmis.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Vincent Donnefort Cc: Kent Overstreet Signed-off-by: Tzvetomir Stoyanov (VMware) [ Fixed kerneldoc on data_page parameter in ring_buffer_free_read_page() ] Signed-off-by: Steven Rostedt (Google) --- include/linux/ring_buffer.h | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 12573306b889..fa802db216f9 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -192,10 +192,15 @@ bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); -void *ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu); -void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data); -int ring_buffer_read_page(struct trace_buffer *buffer, void **data_page, +struct buffer_data_read_page; +struct buffer_data_read_page * +ring_buffer_alloc_read_page(struct trace_buffer *buffer, int cpu); +void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, + struct buffer_data_read_page *page); +int ring_buffer_read_page(struct trace_buffer *buffer, + struct buffer_data_read_page *data_page, size_t len, int cpu, int full); +void *ring_buffer_read_page_data(struct buffer_data_read_page *page); struct trace_seq; -- cgit