linux/kernel/events/internal.h
Elena Reshetova ca3bb3d027 perf/ring_buffer: Convert ring_buffer.aux_refcount to refcount_t
atomic_t variables are currently used to implement reference
counters with the following properties:

 - counter is initialized to 1 using atomic_set()
 - a resource is freed upon counter reaching zero
 - once counter reaches zero, its further
   increments aren't allowed
 - counter schema uses basic atomic operations
   (set, inc, inc_not_zero, dec_and_test, etc.)

Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.

The variable ring_buffer.aux_refcount is used as pure reference counter.
Convert it to refcount_t and fix up the operations.

** Important note for maintainers:

Some functions from refcount_t API defined in lib/refcount.c
have different memory ordering guarantees than their atomic
counterparts. Please check Documentation/core-api/refcount-vs-atomic.rst
for more information.

Normally the differences should not matter since refcount_t provides
enough guarantees to satisfy the refcounting use cases, but in
some rare cases it might matter.
Please double check that you don't have some undocumented
memory guarantees for this variable usage.

For the ring_buffer.aux_refcount it might make a difference
in following places:

 - perf_aux_output_begin(): increment in refcount_inc_not_zero() only
   guarantees control dependency on success vs. fully ordered
   atomic counterpart
 - rb_free_aux(): decrement in refcount_dec_and_test() only
   provides RELEASE ordering and ACQUIRE ordering + control dependency
   on success vs. fully ordered atomic counterpart

Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: namhyung@kernel.org
Link: https://lkml.kernel.org/r/1548678448-24458-4-git-send-email-elena.reshetova@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-02-04 08:46:17 +01:00

250 lines
5.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _KERNEL_EVENTS_INTERNAL_H
#define _KERNEL_EVENTS_INTERNAL_H
#include <linux/hardirq.h>
#include <linux/uaccess.h>
#include <linux/refcount.h>
/* Buffer handling */
#define RING_BUFFER_WRITABLE 0x01
struct ring_buffer {
refcount_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 */
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;
/* 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 */
long aux_head;
local_t aux_nest;
long aux_wakeup; /* last aux_watermark boundary crossed by aux_head */
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 *);
refcount_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);
}
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);
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_BODY(advance_buf, memcpy_func, ...) \
{ \
unsigned long size, written; \
\
do { \
size = min(handle->size, len); \
written = memcpy_func(__VA_ARGS__); \
written = size - written; \
\
len -= written; \
handle->addr += written; \
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; \
}
#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) \
__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size)
static inline unsigned long
__output_custom(struct perf_output_handle *handle, perf_copy_f copy_func,
const void *buf, unsigned long len)
{
unsigned long orig_len = len;
__DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf,
orig_len - len, size)
}
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)
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]--;
}
#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 */