OpenCloudOS-Kernel/kernel/events/internal.h

252 lines
5.8 KiB
C
Raw Normal View History

#ifndef _KERNEL_EVENTS_INTERNAL_H
#define _KERNEL_EVENTS_INTERNAL_H
#include <linux/hardirq.h>
#include <linux/uaccess.h>
/* Buffer handling */
#define RING_BUFFER_WRITABLE 0x01
struct ring_buffer {
atomic_t refcount;
struct rcu_head rcu_head;
#ifdef CONFIG_PERF_USE_VMALLOC
struct work_struct work;
int page_order; /* allocation order */
#endif
int nr_pages; /* nr of data pages */
int overwrite; /* can overwrite itself */
perf/ring_buffer: Introduce new ioctl options to pause and resume the ring-buffer Add new ioctl() to pause/resume ring-buffer output. In some situations we want to read from the ring-buffer only when we ensure nothing can write to the ring-buffer during reading. Without this patch we have to turn off all events attached to this ring-buffer to achieve this. This patch is a prerequisite to enable overwrite support for the perf ring-buffer support. Following commits will introduce new methods support reading from overwrite ring buffer. Before reading, caller must ensure the ring buffer is frozen, or the reading is unreliable. Signed-off-by: Wang Nan <wangnan0@huawei.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <pi3orama@163.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1459147292-239310-2-git-send-email-wangnan0@huawei.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-28 14:41:29 +08:00
int paused; /* can write into ring buffer */
atomic_t poll; /* POLL_ for wakeups */
local_t head; /* write position */
local_t nest; /* nested writers */
local_t events; /* event limit */
local_t wakeup; /* wakeup stamp */
local_t lost; /* nr records lost */
long watermark; /* wakeup watermark */
long aux_watermark;
perf: Fix loss of notification with multi-event When you do: $ perf record -e cycles,cycles,cycles noploop 10 You expect about 10,000 samples for each event, i.e., 10s at 1000samples/sec. However, this is not what's happening. You get much fewer samples, maybe 3700 samples/event: $ perf report -D | tail -15 Aggregated stats: TOTAL events: 10998 MMAP events: 66 COMM events: 2 SAMPLE events: 10930 cycles stats: TOTAL events: 3644 SAMPLE events: 3644 cycles stats: TOTAL events: 3642 SAMPLE events: 3642 cycles stats: TOTAL events: 3644 SAMPLE events: 3644 On a Intel Nehalem or even AMD64, there are 4 counters capable of measuring cycles, so there is plenty of space to measure those events without multiplexing (even with the NMI watchdog active). And even with multiplexing, we'd expect roughly the same number of samples per event. The root of the problem was that when the event that caused the buffer to become full was not the first event passed on the cmdline, the user notification would get lost. The notification was sent to the file descriptor of the overflowed event but the perf tool was not polling on it. The perf tool aggregates all samples into a single buffer, i.e., the buffer of the first event. Consequently, it assumes notifications for any event will come via that descriptor. The seemingly straight forward solution of moving the waitq into the ringbuffer object doesn't work because of life-time issues. One could perf_event_set_output() on a fd that you're also blocking on and cause the old rb object to be freed while its waitq would still be referenced by the blocked thread -> FAIL. Therefore link all events to the ringbuffer and broadcast the wakeup from the ringbuffer object to all possible events that could be waited upon. This is rather ugly, and we're open to better solutions but it works for now. Reported-by: Stephane Eranian <eranian@google.com> Finished-by: Stephane Eranian <eranian@google.com> Reviewed-by: Stephane Eranian <eranian@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20111126014731.GA7030@quad Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-11-26 09:47:31 +08:00
/* poll crap */
spinlock_t event_lock;
struct list_head event_list;
atomic_t mmap_count;
unsigned long mmap_locked;
struct user_struct *mmap_user;
perf: Add AUX area to ring buffer for raw data streams This patch introduces "AUX space" in the perf mmap buffer, intended for exporting high bandwidth data streams to userspace, such as instruction flow traces. AUX space is a ring buffer, defined by aux_{offset,size} fields in the user_page structure, and read/write pointers aux_{head,tail}, which abide by the same rules as data_* counterparts of the main perf buffer. In order to allocate/mmap AUX, userspace needs to set up aux_offset to such an offset that will be greater than data_offset+data_size and aux_size to be the desired buffer size. Both need to be page aligned. Then, same aux_offset and aux_size should be passed to mmap() call and if everything adds up, you should have an AUX buffer as a result. Pages that are mapped into this buffer also come out of user's mlock rlimit plus perf_event_mlock_kb allowance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:11 +08:00
/* AUX area */
long aux_head;
perf: Add API for PMUs to write to the AUX area For pmus that wish to write data to ring buffer's AUX area, provide perf_aux_output_{begin,end}() calls to initiate/commit data writes, similarly to perf_output_{begin,end}. These also use the same output handle structure. Also, similarly to software counterparts, these will direct inherited events' output to parents' ring buffers. After the perf_aux_output_begin() returns successfully, handle->size is set to the maximum amount of data that can be written wrt aux_tail pointer, so that no data that the user hasn't seen will be overwritten, therefore this should always be called before hardware writing is enabled. On success, this will return the pointer to pmu driver's private structure allocated for this aux area by pmu::setup_aux. Same pointer can also be retrieved using perf_get_aux() while hardware writing is enabled. PMU driver should pass the actual amount of data written as a parameter to perf_aux_output_end(). All hardware writes should be completed and visible before this one is called. Additionally, perf_aux_output_skip() will adjust output handle and aux_head in case some part of the buffer has to be skipped over to maintain hardware's alignment constraints. Nested writers are forbidden and guards are in place to catch such attempts. Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-8-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:16 +08:00
local_t aux_nest;
perf/aux: Ensure aux_wakeup represents most recent wakeup index The aux_watermark member of struct ring_buffer represents the period (in terms of bytes) at which wakeup events should be generated when data is written to the aux buffer in non-snapshot mode. On hardware that cannot generate an interrupt when the aux_head reaches an arbitrary wakeup index (such as ARM SPE), the aux_head sampled from handle->head in perf_aux_output_{skip,end} may in fact be past the wakeup index. This can lead to wakeup slowly falling behind the head. For example, consider the case where hardware can only generate an interrupt on a page-boundary and the aux buffer is initialised as follows: // Buffer size is 2 * PAGE_SIZE rb->aux_head = rb->aux_wakeup = 0 rb->aux_watermark = PAGE_SIZE / 2 following the first perf_aux_output_begin call, the handle is initialised with: handle->head = 0 handle->size = 2 * PAGE_SIZE handle->wakeup = PAGE_SIZE / 2 and the hardware will be programmed to generate an interrupt at PAGE_SIZE. When the interrupt is raised, the hardware head will be at PAGE_SIZE, so calling perf_aux_output_end(handle, PAGE_SIZE) puts the ring buffer into the following state: rb->aux_head = PAGE_SIZE rb->aux_wakeup = PAGE_SIZE / 2 rb->aux_watermark = PAGE_SIZE / 2 and then the next call to perf_aux_output_begin will result in: handle->head = handle->wakeup = PAGE_SIZE for which the semantics are unclear and, for a smaller aux_watermark (e.g. PAGE_SIZE / 4), then the wakeup would in fact be behind head at this point. This patch fixes the problem by rounding down the aux_head (as sampled from the handle) to the nearest aux_watermark boundary when updating rb->aux_wakeup, therefore taking into account any overruns by the hardware. Reported-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1502900297-21839-2-git-send-email-will.deacon@arm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-17 00:18:17 +08:00
long aux_wakeup; /* last aux_watermark boundary crossed by aux_head */
perf: Add AUX area to ring buffer for raw data streams This patch introduces "AUX space" in the perf mmap buffer, intended for exporting high bandwidth data streams to userspace, such as instruction flow traces. AUX space is a ring buffer, defined by aux_{offset,size} fields in the user_page structure, and read/write pointers aux_{head,tail}, which abide by the same rules as data_* counterparts of the main perf buffer. In order to allocate/mmap AUX, userspace needs to set up aux_offset to such an offset that will be greater than data_offset+data_size and aux_size to be the desired buffer size. Both need to be page aligned. Then, same aux_offset and aux_size should be passed to mmap() call and if everything adds up, you should have an AUX buffer as a result. Pages that are mapped into this buffer also come out of user's mlock rlimit plus perf_event_mlock_kb allowance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:11 +08:00
unsigned long aux_pgoff;
int aux_nr_pages;
perf: Support overwrite mode for the AUX area This adds support for overwrite mode in the AUX area, which means "keep collecting data till you're stopped", turning AUX area into a circular buffer, where new data overwrites old data. It does not depend on data buffer's overwrite mode, so that it doesn't lose sideband data that is instrumental for processing AUX data. Overwrite mode is enabled at mapping AUX area read only. Even though aux_tail in the buffer's user page might be user writable, it will be ignored in this mode. A PERF_RECORD_AUX with PERF_AUX_FLAG_OVERWRITE set is written to the perf data stream every time an event writes new data to the AUX area. The pmu driver might not be able to infer the exact beginning of the new data in each snapshot, some drivers will only provide the tail, which is aux_offset + aux_size in the AUX record. Consumer has to be able to tell the new data from the old one, for example, by means of time stamps if such are provided in the trace. Consumer is also responsible for disabling any events that might write to the AUX area (thus potentially racing with the consumer) before collecting the data. Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-9-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:17 +08:00
int aux_overwrite;
perf: Add AUX area to ring buffer for raw data streams This patch introduces "AUX space" in the perf mmap buffer, intended for exporting high bandwidth data streams to userspace, such as instruction flow traces. AUX space is a ring buffer, defined by aux_{offset,size} fields in the user_page structure, and read/write pointers aux_{head,tail}, which abide by the same rules as data_* counterparts of the main perf buffer. In order to allocate/mmap AUX, userspace needs to set up aux_offset to such an offset that will be greater than data_offset+data_size and aux_size to be the desired buffer size. Both need to be page aligned. Then, same aux_offset and aux_size should be passed to mmap() call and if everything adds up, you should have an AUX buffer as a result. Pages that are mapped into this buffer also come out of user's mlock rlimit plus perf_event_mlock_kb allowance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:11 +08:00
atomic_t aux_mmap_count;
unsigned long aux_mmap_locked;
void (*free_aux)(void *);
atomic_t aux_refcount;
void **aux_pages;
void *aux_priv;
struct perf_event_mmap_page *user_page;
void *data_pages[0];
};
extern void rb_free(struct ring_buffer *rb);
static inline void rb_free_rcu(struct rcu_head *rcu_head)
{
struct ring_buffer *rb;
rb = container_of(rcu_head, struct ring_buffer, rcu_head);
rb_free(rb);
}
perf/ring_buffer: Introduce new ioctl options to pause and resume the ring-buffer Add new ioctl() to pause/resume ring-buffer output. In some situations we want to read from the ring-buffer only when we ensure nothing can write to the ring-buffer during reading. Without this patch we have to turn off all events attached to this ring-buffer to achieve this. This patch is a prerequisite to enable overwrite support for the perf ring-buffer support. Following commits will introduce new methods support reading from overwrite ring buffer. Before reading, caller must ensure the ring buffer is frozen, or the reading is unreliable. Signed-off-by: Wang Nan <wangnan0@huawei.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: <pi3orama@163.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1459147292-239310-2-git-send-email-wangnan0@huawei.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-28 14:41:29 +08:00
static inline void rb_toggle_paused(struct ring_buffer *rb, bool pause)
{
if (!pause && rb->nr_pages)
rb->paused = 0;
else
rb->paused = 1;
}
extern struct ring_buffer *
rb_alloc(int nr_pages, long watermark, int cpu, int flags);
extern void perf_event_wakeup(struct perf_event *event);
perf: Add AUX area to ring buffer for raw data streams This patch introduces "AUX space" in the perf mmap buffer, intended for exporting high bandwidth data streams to userspace, such as instruction flow traces. AUX space is a ring buffer, defined by aux_{offset,size} fields in the user_page structure, and read/write pointers aux_{head,tail}, which abide by the same rules as data_* counterparts of the main perf buffer. In order to allocate/mmap AUX, userspace needs to set up aux_offset to such an offset that will be greater than data_offset+data_size and aux_size to be the desired buffer size. Both need to be page aligned. Then, same aux_offset and aux_size should be passed to mmap() call and if everything adds up, you should have an AUX buffer as a result. Pages that are mapped into this buffer also come out of user's mlock rlimit plus perf_event_mlock_kb allowance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:11 +08:00
extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
pgoff_t pgoff, int nr_pages, long watermark, int flags);
perf: Add AUX area to ring buffer for raw data streams This patch introduces "AUX space" in the perf mmap buffer, intended for exporting high bandwidth data streams to userspace, such as instruction flow traces. AUX space is a ring buffer, defined by aux_{offset,size} fields in the user_page structure, and read/write pointers aux_{head,tail}, which abide by the same rules as data_* counterparts of the main perf buffer. In order to allocate/mmap AUX, userspace needs to set up aux_offset to such an offset that will be greater than data_offset+data_size and aux_size to be the desired buffer size. Both need to be page aligned. Then, same aux_offset and aux_size should be passed to mmap() call and if everything adds up, you should have an AUX buffer as a result. Pages that are mapped into this buffer also come out of user's mlock rlimit plus perf_event_mlock_kb allowance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:11 +08:00
extern void rb_free_aux(struct ring_buffer *rb);
perf: Add API for PMUs to write to the AUX area For pmus that wish to write data to ring buffer's AUX area, provide perf_aux_output_{begin,end}() calls to initiate/commit data writes, similarly to perf_output_{begin,end}. These also use the same output handle structure. Also, similarly to software counterparts, these will direct inherited events' output to parents' ring buffers. After the perf_aux_output_begin() returns successfully, handle->size is set to the maximum amount of data that can be written wrt aux_tail pointer, so that no data that the user hasn't seen will be overwritten, therefore this should always be called before hardware writing is enabled. On success, this will return the pointer to pmu driver's private structure allocated for this aux area by pmu::setup_aux. Same pointer can also be retrieved using perf_get_aux() while hardware writing is enabled. PMU driver should pass the actual amount of data written as a parameter to perf_aux_output_end(). All hardware writes should be completed and visible before this one is called. Additionally, perf_aux_output_skip() will adjust output handle and aux_head in case some part of the buffer has to be skipped over to maintain hardware's alignment constraints. Nested writers are forbidden and guards are in place to catch such attempts. Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-8-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:16 +08:00
extern struct ring_buffer *ring_buffer_get(struct perf_event *event);
extern void ring_buffer_put(struct ring_buffer *rb);
perf: Add AUX area to ring buffer for raw data streams This patch introduces "AUX space" in the perf mmap buffer, intended for exporting high bandwidth data streams to userspace, such as instruction flow traces. AUX space is a ring buffer, defined by aux_{offset,size} fields in the user_page structure, and read/write pointers aux_{head,tail}, which abide by the same rules as data_* counterparts of the main perf buffer. In order to allocate/mmap AUX, userspace needs to set up aux_offset to such an offset that will be greater than data_offset+data_size and aux_size to be the desired buffer size. Both need to be page aligned. Then, same aux_offset and aux_size should be passed to mmap() call and if everything adds up, you should have an AUX buffer as a result. Pages that are mapped into this buffer also come out of user's mlock rlimit plus perf_event_mlock_kb allowance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:11 +08:00
static inline bool rb_has_aux(struct ring_buffer *rb)
{
return !!rb->aux_nr_pages;
}
void perf_event_aux_event(struct perf_event *event, unsigned long head,
unsigned long size, u64 flags);
extern struct page *
perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff);
#ifdef CONFIG_PERF_USE_VMALLOC
/*
* Back perf_mmap() with vmalloc memory.
*
* Required for architectures that have d-cache aliasing issues.
*/
static inline int page_order(struct ring_buffer *rb)
{
return rb->page_order;
}
#else
static inline int page_order(struct ring_buffer *rb)
{
return 0;
}
#endif
static inline unsigned long perf_data_size(struct ring_buffer *rb)
{
return rb->nr_pages << (PAGE_SHIFT + page_order(rb));
}
perf: Add AUX area to ring buffer for raw data streams This patch introduces "AUX space" in the perf mmap buffer, intended for exporting high bandwidth data streams to userspace, such as instruction flow traces. AUX space is a ring buffer, defined by aux_{offset,size} fields in the user_page structure, and read/write pointers aux_{head,tail}, which abide by the same rules as data_* counterparts of the main perf buffer. In order to allocate/mmap AUX, userspace needs to set up aux_offset to such an offset that will be greater than data_offset+data_size and aux_size to be the desired buffer size. Both need to be page aligned. Then, same aux_offset and aux_size should be passed to mmap() call and if everything adds up, you should have an AUX buffer as a result. Pages that are mapped into this buffer also come out of user's mlock rlimit plus perf_event_mlock_kb allowance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Kaixu Xia <kaixu.xia@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Robert Richter <rric@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@infradead.org Cc: adrian.hunter@intel.com Cc: kan.liang@intel.com Cc: markus.t.metzger@intel.com Cc: mathieu.poirier@linaro.org Link: http://lkml.kernel.org/r/1421237903-181015-3-git-send-email-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-01-14 20:18:11 +08:00
static inline unsigned long perf_aux_size(struct ring_buffer *rb)
{
return rb->aux_nr_pages << PAGE_SHIFT;
}
bpf, events: fix offset in skb copy handler This patch fixes the __output_custom() routine we currently use with bpf_skb_copy(). I missed that when len is larger than the size of the current handle, we can issue multiple invocations of copy_func, and __output_custom() advances destination but also source buffer by the written amount of bytes. When we have __output_custom(), this is actually wrong since in that case the source buffer points to a non-linear object, in our case an skb, which the copy_func helper is supposed to walk. Therefore, since this is non-linear we thus need to pass the offset into the helper, so that copy_func can use it for extracting the data from the source object. Therefore, adjust the callback signatures properly and pass offset into the skb_header_pointer() invoked from bpf_skb_copy() callback. The __DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things: i) to pass in whether we should advance source buffer or not; this is a compile-time constant condition, ii) to pass in the offset for __output_custom(), which we do with help of __VA_ARGS__, so everything can stay inlined as is currently. Both changes allow for adapting the __output_* fast-path helpers w/o extra overhead. Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-22 07:19:42 +08:00
#define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...) \
{ \
unsigned long size, written; \
\
do { \
size = min(handle->size, len); \
bpf, events: fix offset in skb copy handler This patch fixes the __output_custom() routine we currently use with bpf_skb_copy(). I missed that when len is larger than the size of the current handle, we can issue multiple invocations of copy_func, and __output_custom() advances destination but also source buffer by the written amount of bytes. When we have __output_custom(), this is actually wrong since in that case the source buffer points to a non-linear object, in our case an skb, which the copy_func helper is supposed to walk. Therefore, since this is non-linear we thus need to pass the offset into the helper, so that copy_func can use it for extracting the data from the source object. Therefore, adjust the callback signatures properly and pass offset into the skb_header_pointer() invoked from bpf_skb_copy() callback. The __DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things: i) to pass in whether we should advance source buffer or not; this is a compile-time constant condition, ii) to pass in the offset for __output_custom(), which we do with help of __VA_ARGS__, so everything can stay inlined as is currently. Both changes allow for adapting the __output_* fast-path helpers w/o extra overhead. Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-22 07:19:42 +08:00
written = memcpy_func(__VA_ARGS__); \
written = size - written; \
\
len -= written; \
handle->addr += written; \
bpf, events: fix offset in skb copy handler This patch fixes the __output_custom() routine we currently use with bpf_skb_copy(). I missed that when len is larger than the size of the current handle, we can issue multiple invocations of copy_func, and __output_custom() advances destination but also source buffer by the written amount of bytes. When we have __output_custom(), this is actually wrong since in that case the source buffer points to a non-linear object, in our case an skb, which the copy_func helper is supposed to walk. Therefore, since this is non-linear we thus need to pass the offset into the helper, so that copy_func can use it for extracting the data from the source object. Therefore, adjust the callback signatures properly and pass offset into the skb_header_pointer() invoked from bpf_skb_copy() callback. The __DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things: i) to pass in whether we should advance source buffer or not; this is a compile-time constant condition, ii) to pass in the offset for __output_custom(), which we do with help of __VA_ARGS__, so everything can stay inlined as is currently. Both changes allow for adapting the __output_* fast-path helpers w/o extra overhead. Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-22 07:19:42 +08:00
if (advance_buf) \
buf += written; \
handle->size -= written; \
if (!handle->size) { \
struct ring_buffer *rb = handle->rb; \
\
handle->page++; \
handle->page &= rb->nr_pages - 1; \
handle->addr = rb->data_pages[handle->page]; \
handle->size = PAGE_SIZE << page_order(rb); \
} \
} while (len && written == size); \
\
return len; \
}
perf, events: add non-linear data support for raw records This patch adds support for non-linear data on raw records. It extends raw records to have one or multiple fragments that will be written linearly into the ring slot, where each fragment can optionally have a custom callback handler to walk and extract complex, possibly non-linear data. If a callback handler is provided for a fragment, then the new __output_custom() will be used instead of __output_copy() for the perf_output_sample() part. perf_prepare_sample() does all the size calculation only once, so perf_output_sample() doesn't need to redo the same work anymore, meaning real_size and padding will be cached in the raw record. The raw record becomes 32 bytes in size without holes; to not increase it further and to avoid doing unnecessary recalculations in fast-path, we can reuse next pointer of the last fragment, idea here is borrowed from ZERO_OR_NULL_PTR(), which should keep the perf_output_sample() path for PERF_SAMPLE_RAW minimal. This facility is needed for BPF's event output helper as a first user that will, in a follow-up, add an additional perf_raw_frag to its perf_raw_record in order to be able to more efficiently dump skb context after a linear head meta data related to it. skbs can be non-linear and thus need a custom output function to dump buffers. Currently, the skb data needs to be copied twice; with the help of __output_custom() this work only needs to be done once. Future users could be things like XDP/BPF programs that work on different context though and would thus also have a different callback function. The few users of raw records are adapted to initialize their frag data from the raw record itself, no change in behavior for them. The code is based upon a PoC diff provided by Peter Zijlstra [1]. [1] http://thread.gmane.org/gmane.linux.network/421294 Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-15 00:08:03 +08:00
#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \
static inline unsigned long \
func_name(struct perf_output_handle *handle, \
const void *buf, unsigned long len) \
bpf, events: fix offset in skb copy handler This patch fixes the __output_custom() routine we currently use with bpf_skb_copy(). I missed that when len is larger than the size of the current handle, we can issue multiple invocations of copy_func, and __output_custom() advances destination but also source buffer by the written amount of bytes. When we have __output_custom(), this is actually wrong since in that case the source buffer points to a non-linear object, in our case an skb, which the copy_func helper is supposed to walk. Therefore, since this is non-linear we thus need to pass the offset into the helper, so that copy_func can use it for extracting the data from the source object. Therefore, adjust the callback signatures properly and pass offset into the skb_header_pointer() invoked from bpf_skb_copy() callback. The __DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things: i) to pass in whether we should advance source buffer or not; this is a compile-time constant condition, ii) to pass in the offset for __output_custom(), which we do with help of __VA_ARGS__, so everything can stay inlined as is currently. Both changes allow for adapting the __output_* fast-path helpers w/o extra overhead. Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-22 07:19:42 +08:00
__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size)
perf, events: add non-linear data support for raw records This patch adds support for non-linear data on raw records. It extends raw records to have one or multiple fragments that will be written linearly into the ring slot, where each fragment can optionally have a custom callback handler to walk and extract complex, possibly non-linear data. If a callback handler is provided for a fragment, then the new __output_custom() will be used instead of __output_copy() for the perf_output_sample() part. perf_prepare_sample() does all the size calculation only once, so perf_output_sample() doesn't need to redo the same work anymore, meaning real_size and padding will be cached in the raw record. The raw record becomes 32 bytes in size without holes; to not increase it further and to avoid doing unnecessary recalculations in fast-path, we can reuse next pointer of the last fragment, idea here is borrowed from ZERO_OR_NULL_PTR(), which should keep the perf_output_sample() path for PERF_SAMPLE_RAW minimal. This facility is needed for BPF's event output helper as a first user that will, in a follow-up, add an additional perf_raw_frag to its perf_raw_record in order to be able to more efficiently dump skb context after a linear head meta data related to it. skbs can be non-linear and thus need a custom output function to dump buffers. Currently, the skb data needs to be copied twice; with the help of __output_custom() this work only needs to be done once. Future users could be things like XDP/BPF programs that work on different context though and would thus also have a different callback function. The few users of raw records are adapted to initialize their frag data from the raw record itself, no change in behavior for them. The code is based upon a PoC diff provided by Peter Zijlstra [1]. [1] http://thread.gmane.org/gmane.linux.network/421294 Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-15 00:08:03 +08:00
static inline unsigned long
__output_custom(struct perf_output_handle *handle, perf_copy_f copy_func,
const void *buf, unsigned long len)
bpf, events: fix offset in skb copy handler This patch fixes the __output_custom() routine we currently use with bpf_skb_copy(). I missed that when len is larger than the size of the current handle, we can issue multiple invocations of copy_func, and __output_custom() advances destination but also source buffer by the written amount of bytes. When we have __output_custom(), this is actually wrong since in that case the source buffer points to a non-linear object, in our case an skb, which the copy_func helper is supposed to walk. Therefore, since this is non-linear we thus need to pass the offset into the helper, so that copy_func can use it for extracting the data from the source object. Therefore, adjust the callback signatures properly and pass offset into the skb_header_pointer() invoked from bpf_skb_copy() callback. The __DEFINE_OUTPUT_COPY_BODY() is adjusted to accommodate for two things: i) to pass in whether we should advance source buffer or not; this is a compile-time constant condition, ii) to pass in the offset for __output_custom(), which we do with help of __VA_ARGS__, so everything can stay inlined as is currently. Both changes allow for adapting the __output_* fast-path helpers w/o extra overhead. Fixes: 555c8a8623a3 ("bpf: avoid stack copy and use skb ctx for event output") Fixes: 7e3f977edd0b ("perf, events: add non-linear data support for raw records") Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-22 07:19:42 +08:00
{
unsigned long orig_len = len;
__DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf,
orig_len - len, size)
}
perf, events: add non-linear data support for raw records This patch adds support for non-linear data on raw records. It extends raw records to have one or multiple fragments that will be written linearly into the ring slot, where each fragment can optionally have a custom callback handler to walk and extract complex, possibly non-linear data. If a callback handler is provided for a fragment, then the new __output_custom() will be used instead of __output_copy() for the perf_output_sample() part. perf_prepare_sample() does all the size calculation only once, so perf_output_sample() doesn't need to redo the same work anymore, meaning real_size and padding will be cached in the raw record. The raw record becomes 32 bytes in size without holes; to not increase it further and to avoid doing unnecessary recalculations in fast-path, we can reuse next pointer of the last fragment, idea here is borrowed from ZERO_OR_NULL_PTR(), which should keep the perf_output_sample() path for PERF_SAMPLE_RAW minimal. This facility is needed for BPF's event output helper as a first user that will, in a follow-up, add an additional perf_raw_frag to its perf_raw_record in order to be able to more efficiently dump skb context after a linear head meta data related to it. skbs can be non-linear and thus need a custom output function to dump buffers. Currently, the skb data needs to be copied twice; with the help of __output_custom() this work only needs to be done once. Future users could be things like XDP/BPF programs that work on different context though and would thus also have a different callback function. The few users of raw records are adapted to initialize their frag data from the raw record itself, no change in behavior for them. The code is based upon a PoC diff provided by Peter Zijlstra [1]. [1] http://thread.gmane.org/gmane.linux.network/421294 Suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-07-15 00:08:03 +08:00
static inline unsigned long
memcpy_common(void *dst, const void *src, unsigned long n)
{
memcpy(dst, src, n);
return 0;
}
DEFINE_OUTPUT_COPY(__output_copy, memcpy_common)
static inline unsigned long
memcpy_skip(void *dst, const void *src, unsigned long n)
{
return 0;
}
DEFINE_OUTPUT_COPY(__output_skip, memcpy_skip)
#ifndef arch_perf_out_copy_user
#define arch_perf_out_copy_user arch_perf_out_copy_user
static inline unsigned long
arch_perf_out_copy_user(void *dst, const void *src, unsigned long n)
{
unsigned long ret;
pagefault_disable();
ret = __copy_from_user_inatomic(dst, src, n);
pagefault_enable();
return ret;
}
#endif
DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
/* Callchain handling */
extern struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs);
static inline int get_recursion_context(int *recursion)
{
int rctx;
if (unlikely(in_nmi()))
rctx = 3;
else if (in_irq())
rctx = 2;
else if (in_softirq())
rctx = 1;
else
rctx = 0;
if (recursion[rctx])
return -1;
recursion[rctx]++;
barrier();
return rctx;
}
static inline void put_recursion_context(int *recursion, int rctx)
{
barrier();
recursion[rctx]--;
}
2012-08-07 21:20:40 +08:00
#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP
static inline bool arch_perf_have_user_stack_dump(void)
{
return true;
}
#define perf_user_stack_pointer(regs) user_stack_pointer(regs)
#else
static inline bool arch_perf_have_user_stack_dump(void)
{
return false;
}
#define perf_user_stack_pointer(regs) 0
#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */
#endif /* _KERNEL_EVENTS_INTERNAL_H */