linux_dsm_epyc7002/kernel/events/internal.h
Yan, Zheng 21509084f9 perf/x86/intel: Handle multiple records in the PEBS buffer
When the PEBS interrupt threshold is larger than one record and the
machine supports multiple PEBS events, the records of these events are
mixed up and we need to demultiplex them.

Demuxing the records is hard because the hardware is deficient. The
hardware has two issues that, when combined, create impossible
scenarios to demux.

The first issue is that the 'status' field of the PEBS record is a copy
of the GLOBAL_STATUS MSR at PEBS assist time. To see why this is a
problem let us first describe the regular PEBS cycle:

A) the CTRn value reaches 0:
  - the corresponding bit in GLOBAL_STATUS gets set
  - we start arming the hardware assist
  < some unspecified amount of time later -- this could cover multiple
    events of interest >

B) the hardware assist is armed, any next event will trigger it

C) a matching event happens:
  - the hardware assist triggers and generates a PEBS record
    this includes a copy of GLOBAL_STATUS at this moment
  - if we auto-reload we (re)set CTRn
  - we clear the relevant bit in GLOBAL_STATUS

Now consider the following chain of events:

  A0, B0, A1, C0

The event generated for counter 0 will include a status with counter 1
set, even though its not at all related to the record. A similar thing
can happen with a !PEBS event if it just happens to overflow at the
right moment.

The second issue is that the hardware will only emit one record for two
or more counters if the event that triggers the assist is 'close'. The
'close' can be several cycles. In some cases even the complete assist,
if the event is something that doesn't need retirement.

For instance, consider this chain of events:

  A0, B0, A1, B1, C01

Where C01 is an event that triggers both hardware assists, we will
generate but a single record, but again with both counters listed in the
status field.

This time the record pertains to both events.

Note that these two cases are different but undistinguishable with the
data as generated. Therefore demuxing records with multiple PEBS bits
(we can safely ignore status bits for !PEBS counters) is impossible.

Furthermore we cannot emit the record to both events because that might
cause a data leak -- the events might not have the same privileges -- so
what this patch does is discard such events.

The assumption/hope is that such discards will be rare.

Here lists some possible ways you may get high discard rate.

  - when you count the same thing multiple times. But it is not a useful
    configuration.
  - you can be unfortunate if you measure with a userspace only PEBS
    event along with either a kernel or unrestricted PEBS event. Imagine
    the event triggering and setting the overflow flag right before
    entering the kernel. Then all kernel side events will end up with
    multiple bits set.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
[ Changelog improvements. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@infradead.org
Cc: eranian@google.com
Link: http://lkml.kernel.org/r/1430940834-8964-4-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-06-07 16:08:45 +02:00

223 lines
5.1 KiB
C

#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 */
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;
/* poll crap */
spinlock_t event_lock;
struct list_head event_list;
atomic_t mmap_count;
unsigned long mmap_locked;
struct user_struct *mmap_user;
/* AUX area */
local_t aux_head;
local_t aux_nest;
local_t aux_wakeup;
unsigned long aux_pgoff;
int aux_nr_pages;
int aux_overwrite;
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);
extern struct ring_buffer *
rb_alloc(int nr_pages, long watermark, int cpu, int flags);
extern void perf_event_wakeup(struct perf_event *event);
extern int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
pgoff_t pgoff, int nr_pages, long watermark, int flags);
extern void rb_free_aux(struct ring_buffer *rb);
extern struct ring_buffer *ring_buffer_get(struct perf_event *event);
extern void ring_buffer_put(struct ring_buffer *rb);
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));
}
static inline unsigned long perf_aux_size(struct ring_buffer *rb)
{
return rb->aux_nr_pages << PAGE_SHIFT;
}
#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) \
{ \
unsigned long size, written; \
\
do { \
size = min(handle->size, len); \
written = memcpy_func(handle->addr, buf, size); \
written = size - written; \
\
len -= written; \
handle->addr += written; \
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; \
}
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);
extern int get_callchain_buffers(void);
extern void put_callchain_buffers(void);
static inline int get_recursion_context(int *recursion)
{
int rctx;
if (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]--;
}
#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 */