From 499e547057f5bba5cd6f87ebe59b05d0c59da905 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 22 Feb 2012 15:50:28 -0500 Subject: tracing/ring-buffer: Only have tracing_on disable tracing buffers As the ring-buffer code is being used by other facilities in the kernel, having tracing_on file disable *all* buffers is not a desired affect. It should only disable the ftrace buffers that are being used. Move the code into the trace.c file and use the buffer disabling for tracing_on() and tracing_off(). This way only the ftrace buffers will be affected by them and other kernel utilities will not be confused to why their output suddenly stopped. Signed-off-by: Steven Rostedt --- include/linux/ring_buffer.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 67be0376d8e3..7be2e88f23fd 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -151,6 +151,9 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_disable(struct ring_buffer *buffer); void ring_buffer_record_enable(struct ring_buffer *buffer); +void ring_buffer_record_off(struct ring_buffer *buffer); +void ring_buffer_record_on(struct ring_buffer *buffer); +int ring_buffer_record_is_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); -- cgit v1.2.3 From 37d73998920859784e6504462a2fd5f52cc08051 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 14 Mar 2012 00:03:02 +0100 Subject: perf: Add ifdef to remove unused enum switch warnings Fix for unused symbols in switch warnings. Link: http://lkml.kernel.org/r/20120313230302.GA1514@m.redhat.com Cc: Mark Brown Cc: Frederic Weisbecker Cc: Ingo Molnar Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt --- include/linux/ftrace_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h index dd478fc8f9f5..5f3f3be5af09 100644 --- a/include/linux/ftrace_event.h +++ b/include/linux/ftrace_event.h @@ -144,12 +144,14 @@ struct event_filter; enum trace_reg { TRACE_REG_REGISTER, TRACE_REG_UNREGISTER, +#ifdef CONFIG_PERF_EVENTS TRACE_REG_PERF_REGISTER, TRACE_REG_PERF_UNREGISTER, TRACE_REG_PERF_OPEN, TRACE_REG_PERF_CLOSE, TRACE_REG_PERF_ADD, TRACE_REG_PERF_DEL, +#endif }; struct ftrace_event_call; -- cgit v1.2.3 From 641cc938815dfd09f8fa1ec72deb814f0938ac33 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 15 Mar 2012 20:09:14 +0100 Subject: perf: Adding sysfs group format attribute for pmu device Adding sysfs group 'format' attribute for pmu device that contains a syntax description on how to construct raw events. The event configuration is described in following struct pefr_event_attr attributes: config config1 config2 Each sysfs attribute within the format attribute group, describes mapping of name and bitfield definition within one of above attributes. eg: "/sys/.../format/event" contains "config:0-7" "/sys/.../format/umask" contains "config:8-15" "/sys/.../format/usr" contains "config:16" the attribute value syntax is: line: config ':' bits config: 'config' | 'config1' | 'config2" bits: bits ',' bit_term | bit_term bit_term: VALUE '-' VALUE | VALUE Adding format attribute definitions for x86 cpu pmus. Acked-by: Peter Zijlstra Signed-off-by: Peter Zijlstra Signed-off-by: Jiri Olsa Link: http://lkml.kernel.org/n/tip-vhdk5y2hyype9j63prymty36@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- include/linux/perf_event.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index bd9f55a5958d..57ae485e80fc 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -550,6 +550,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #include #define PERF_MAX_STACK_DEPTH 255 @@ -1291,5 +1292,18 @@ do { \ register_cpu_notifier(&fn##_nb); \ } while (0) + +#define PMU_FORMAT_ATTR(_name, _format) \ +static ssize_t \ +_name##_show(struct device *dev, \ + struct device_attribute *attr, \ + char *page) \ +{ \ + BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ + return sprintf(page, _format "\n"); \ +} \ + \ +static struct device_attribute format_attr_##_name = __ATTR_RO(_name) + #endif /* __KERNEL__ */ #endif /* _LINUX_PERF_EVENT_H */ -- cgit v1.2.3 From 93d68e52295fb8b65ded6db49e32e63b6a203e0b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 20 Mar 2012 12:28:29 -0400 Subject: tracing: Move the tracing_on/off() declarations into CONFIG_TRACING The tracing_on/off() declarations were under CONFIG_RING_BUFFER, but the functions are now only defined under CONFIG_TRACING as they are specific to ftrace and not the ring buffer. But the declarations were still defined under the ring buffer and this caused the build to fail when CONFIG_RING_BUFFER was set but CONFIG_TRACING was not. Reported-by: Ingo Molnar Signed-off-by: Steven Rostedt --- include/linux/kernel.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e8343422240a..51b9548fd12d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -414,16 +414,10 @@ extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); * Most likely, you want to use tracing_on/tracing_off. */ #ifdef CONFIG_RING_BUFFER -void tracing_on(void); -void tracing_off(void); /* trace_off_permanent stops recording with no way to bring it back */ void tracing_off_permanent(void); -int tracing_is_on(void); #else -static inline void tracing_on(void) { } -static inline void tracing_off(void) { } static inline void tracing_off_permanent(void) { } -static inline int tracing_is_on(void) { return 0; } #endif enum ftrace_dump_mode { @@ -433,6 +427,10 @@ enum ftrace_dump_mode { }; #ifdef CONFIG_TRACING +void tracing_on(void); +void tracing_off(void); +int tracing_is_on(void); + extern void tracing_start(void); extern void tracing_stop(void); extern void ftrace_off_permanent(void); @@ -517,6 +515,11 @@ static inline void tracing_start(void) { } static inline void tracing_stop(void) { } static inline void ftrace_off_permanent(void) { } static inline void trace_dump_stack(void) { } + +static inline void tracing_on(void) { } +static inline void tracing_off(void) { } +static inline int tracing_is_on(void) { return 0; } + static inline int trace_printk(const char *fmt, ...) { -- cgit v1.2.3 From c7206205d00ab375839bd6c7ddb247d600693c09 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 22 Mar 2012 17:26:36 +0100 Subject: perf: Fix mmap_page capabilities and docs Complete the syscall-less self-profiling feature and address all complaints, namely: - capabilities, so we can detect what is actually available at runtime Add a capabilities field to perf_event_mmap_page to indicate what is actually available for use. - on x86: RDPMC weirdness due to being 40/48 bits and not sign-extending properly. - ABI documentation as to how all this stuff works. Also improve the documentation for the new features. Signed-off-by: Peter Zijlstra Cc: Stephane Eranian Cc: Vince Weaver Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Link: http://lkml.kernel.org/r/1332433596.2487.33.camel@twins Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 83 ++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 73 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 57ae485e80fc..ca9ed4e6a286 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -299,18 +299,31 @@ struct perf_event_mmap_page { /* * Bits needed to read the hw events in user-space. * - * u32 seq; - * s64 count; + * u32 seq, time_mult, time_shift, idx, width; + * u64 count, enabled, running; + * u64 cyc, time_offset; + * s64 pmc = 0; * * do { * seq = pc->lock; - * * barrier() - * if (pc->index) { - * count = pmc_read(pc->index - 1); - * count += pc->offset; - * } else - * goto regular_read; + * + * enabled = pc->time_enabled; + * running = pc->time_running; + * + * if (pc->cap_usr_time && enabled != running) { + * cyc = rdtsc(); + * time_offset = pc->time_offset; + * time_mult = pc->time_mult; + * time_shift = pc->time_shift; + * } + * + * idx = pc->index; + * count = pc->offset; + * if (pc->cap_usr_rdpmc && idx) { + * width = pc->pmc_width; + * pmc = rdpmc(idx - 1); + * } * * barrier(); * } while (pc->lock != seq); @@ -323,14 +336,57 @@ struct perf_event_mmap_page { __s64 offset; /* add to hardware event value */ __u64 time_enabled; /* time event active */ __u64 time_running; /* time event on cpu */ - __u32 time_mult, time_shift; + union { + __u64 capabilities; + __u64 cap_usr_time : 1, + cap_usr_rdpmc : 1, + cap_____res : 62; + }; + + /* + * If cap_usr_rdpmc this field provides the bit-width of the value + * read using the rdpmc() or equivalent instruction. This can be used + * to sign extend the result like: + * + * pmc <<= 64 - width; + * pmc >>= 64 - width; // signed shift right + * count += pmc; + */ + __u16 pmc_width; + + /* + * If cap_usr_time the below fields can be used to compute the time + * delta since time_enabled (in ns) using rdtsc or similar. + * + * u64 quot, rem; + * u64 delta; + * + * quot = (cyc >> time_shift); + * rem = cyc & ((1 << time_shift) - 1); + * delta = time_offset + quot * time_mult + + * ((rem * time_mult) >> time_shift); + * + * Where time_offset,time_mult,time_shift and cyc are read in the + * seqcount loop described above. This delta can then be added to + * enabled and possible running (if idx), improving the scaling: + * + * enabled += delta; + * if (idx) + * running += delta; + * + * quot = count / running; + * rem = count % running; + * count = quot * enabled + (rem * enabled) / running; + */ + __u16 time_shift; + __u32 time_mult; __u64 time_offset; /* * Hole for extension of the self monitor capabilities */ - __u64 __reserved[121]; /* align to 1k */ + __u64 __reserved[120]; /* align to 1k */ /* * Control data for the mmap() data buffer. @@ -347,6 +403,13 @@ struct perf_event_mmap_page { __u64 data_tail; /* user-space written tail */ }; +/* + * Build time assertion that we keep the data_head at the intended location. + * IOW, validation we got the __reserved[] size right. + */ +extern char __assert_mmap_data_head_offset + [1 - 2*!!(offsetof(struct perf_event_mmap_page, data_head) != 1024)]; + #define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) -- cgit v1.2.3 From b01c3a0010aabadf745f3e7fdb9cab682e0a28a2 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 23 Mar 2012 15:41:20 +0100 Subject: perf: Move mmap page data_head offset assertion out of header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Having the build time assertion in header is making the perf build fail on x86 with: ../../include/linux/perf_event.h:411:32: error: variably modified \ ‘__assert_mmap_data_head_offset’ at file scope [-Werror] I'm moving the build time validation out of the header, because I think it's better than to lessen the perf build warn/error check. Signed-off-by: Jiri Olsa Cc: acme@redhat.com Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org Cc: cjashfor@linux.vnet.ibm.com Cc: fweisbec@gmail.com Link: http://lkml.kernel.org/r/1332513680-7870-1-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ca9ed4e6a286..ddbb6a901f65 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -403,13 +403,6 @@ struct perf_event_mmap_page { __u64 data_tail; /* user-space written tail */ }; -/* - * Build time assertion that we keep the data_head at the intended location. - * IOW, validation we got the __reserved[] size right. - */ -extern char __assert_mmap_data_head_offset - [1 - 2*!!(offsetof(struct perf_event_mmap_page, data_head) != 1024)]; - #define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0) #define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0) #define PERF_RECORD_MISC_KERNEL (1 << 0) -- cgit v1.2.3