perf-eh_elf/util/mmap.c
Linus Torvalds 16c00db4bb Merge tag 'afs-fixes-20180514' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
Pull AFS fixes from David Howells:
 "Here's a set of patches that fix a number of bugs in the in-kernel AFS
  client, including:

   - Fix directory locking to not use individual page locks for
     directory reading/scanning but rather to use a semaphore on the
     afs_vnode struct as the directory contents must be read in a single
     blob and data from different reads must not be mixed as the entire
     contents may be shuffled about between reads.

   - Fix address list parsing to handle port specifiers correctly.

   - Only give up callback records on a server if we actually talked to
     that server (we might not be able to access a server).

   - Fix some callback handling bugs, including refcounting,
     whole-volume callbacks and when callbacks actually get broken in
     response to a CB.CallBack op.

   - Fix some server/address rotation bugs, including giving up if we
     can't probe a server; giving up if a server says it doesn't have a
     volume, but there are more servers to try.

   - Fix the decoding of fetched statuses to be OpenAFS compatible.

   - Fix the handling of server lookups in Cache Manager ops (such as
     CB.InitCallBackState3) to use a UUID if possible and to handle no
     server being found.

   - Fix a bug in server lookup where not all addresses are compared.

   - Fix the non-encryption of calls that prevents some servers from
     being accessed (this also requires an AF_RXRPC patch that has
     already gone in through the net tree).

  There's also a patch that adds tracepoints to log Cache Manager ops
  that don't find a matching server, either by UUID or by address"

* tag 'afs-fixes-20180514' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs:
  afs: Fix the non-encryption of calls
  afs: Fix CB.CallBack handling
  afs: Fix whole-volume callback handling
  afs: Fix afs_find_server search loop
  afs: Fix the handling of an unfound server in CM operations
  afs: Add a tracepoint to record callbacks from unlisted servers
  afs: Fix the handling of CB.InitCallBackState3 to find the server by UUID
  afs: Fix VNOVOL handling in address rotation
  afs: Fix AFSFetchStatus decoder to provide OpenAFS compatibility
  afs: Fix server rotation's handling of fileserver probe failure
  afs: Fix refcounting in callback registration
  afs: Fix giving up callbacks on server destruction
  afs: Fix address list parsing
  afs: Fix directory page locking
2018-05-15 10:48:36 -07:00

338 lines
7.9 KiB
C

/*
* Copyright (C) 2011-2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
*
* Parts came from evlist.c builtin-{top,stat,record}.c, see those files for further
* copyright notes.
*
* Released under the GPL v2. (and only v2, not any later version)
*/
#include <sys/mman.h>
#include <inttypes.h>
#include <asm/bug.h>
#include "debug.h"
#include "event.h"
#include "mmap.h"
#include "util.h" /* page_size */
size_t perf_mmap__mmap_len(struct perf_mmap *map)
{
return map->mask + 1 + page_size;
}
/* When check_messup is true, 'end' must points to a good entry */
static union perf_event *perf_mmap__read(struct perf_mmap *map,
u64 *startp, u64 end)
{
unsigned char *data = map->base + page_size;
union perf_event *event = NULL;
int diff = end - *startp;
if (diff >= (int)sizeof(event->header)) {
size_t size;
event = (union perf_event *)&data[*startp & map->mask];
size = event->header.size;
if (size < sizeof(event->header) || diff < (int)size)
return NULL;
/*
* Event straddles the mmap boundary -- header should always
* be inside due to u64 alignment of output.
*/
if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
unsigned int offset = *startp;
unsigned int len = min(sizeof(*event), size), cpy;
void *dst = map->event_copy;
do {
cpy = min(map->mask + 1 - (offset & map->mask), len);
memcpy(dst, &data[offset & map->mask], cpy);
offset += cpy;
dst += cpy;
len -= cpy;
} while (len);
event = (union perf_event *)map->event_copy;
}
*startp += size;
}
return event;
}
/*
* Read event from ring buffer one by one.
* Return one event for each call.
*
* Usage:
* perf_mmap__read_init()
* while(event = perf_mmap__read_event()) {
* //process the event
* perf_mmap__consume()
* }
* perf_mmap__read_done()
*/
union perf_event *perf_mmap__read_event(struct perf_mmap *map)
{
union perf_event *event;
/*
* Check if event was unmapped due to a POLLHUP/POLLERR.
*/
if (!refcount_read(&map->refcnt))
return NULL;
/* non-overwirte doesn't pause the ringbuffer */
if (!map->overwrite)
map->end = perf_mmap__read_head(map);
event = perf_mmap__read(map, &map->start, map->end);
if (!map->overwrite)
map->prev = map->start;
return event;
}
static bool perf_mmap__empty(struct perf_mmap *map)
{
return perf_mmap__read_head(map) == map->prev && !map->auxtrace_mmap.base;
}
void perf_mmap__get(struct perf_mmap *map)
{
refcount_inc(&map->refcnt);
}
void perf_mmap__put(struct perf_mmap *map)
{
BUG_ON(map->base && refcount_read(&map->refcnt) == 0);
if (refcount_dec_and_test(&map->refcnt))
perf_mmap__munmap(map);
}
void perf_mmap__consume(struct perf_mmap *map)
{
if (!map->overwrite) {
u64 old = map->prev;
perf_mmap__write_tail(map, old);
}
if (refcount_read(&map->refcnt) == 1 && perf_mmap__empty(map))
perf_mmap__put(map);
}
int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
struct auxtrace_mmap_params *mp __maybe_unused,
void *userpg __maybe_unused,
int fd __maybe_unused)
{
return 0;
}
void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
{
}
void __weak auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp __maybe_unused,
off_t auxtrace_offset __maybe_unused,
unsigned int auxtrace_pages __maybe_unused,
bool auxtrace_overwrite __maybe_unused)
{
}
void __weak auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp __maybe_unused,
struct perf_evlist *evlist __maybe_unused,
int idx __maybe_unused,
bool per_cpu __maybe_unused)
{
}
void perf_mmap__munmap(struct perf_mmap *map)
{
if (map->base != NULL) {
munmap(map->base, perf_mmap__mmap_len(map));
map->base = NULL;
map->fd = -1;
refcount_set(&map->refcnt, 0);
}
auxtrace_mmap__munmap(&map->auxtrace_mmap);
}
int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
{
/*
* The last one will be done at perf_mmap__consume(), so that we
* make sure we don't prevent tools from consuming every last event in
* the ring buffer.
*
* I.e. we can get the POLLHUP meaning that the fd doesn't exist
* anymore, but the last events for it are still in the ring buffer,
* waiting to be consumed.
*
* Tools can chose to ignore this at their own discretion, but the
* evlist layer can't just drop it when filtering events in
* perf_evlist__filter_pollfd().
*/
refcount_set(&map->refcnt, 2);
map->prev = 0;
map->mask = mp->mask;
map->base = mmap(NULL, perf_mmap__mmap_len(map), mp->prot,
MAP_SHARED, fd, 0);
if (map->base == MAP_FAILED) {
pr_debug2("failed to mmap perf event ring buffer, error %d\n",
errno);
map->base = NULL;
return -1;
}
map->fd = fd;
if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
&mp->auxtrace_mp, map->base, fd))
return -1;
return 0;
}
static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end)
{
struct perf_event_header *pheader;
u64 evt_head = *start;
int size = mask + 1;
pr_debug2("%s: buf=%p, start=%"PRIx64"\n", __func__, buf, *start);
pheader = (struct perf_event_header *)(buf + (*start & mask));
while (true) {
if (evt_head - *start >= (unsigned int)size) {
pr_debug("Finished reading overwrite ring buffer: rewind\n");
if (evt_head - *start > (unsigned int)size)
evt_head -= pheader->size;
*end = evt_head;
return 0;
}
pheader = (struct perf_event_header *)(buf + (evt_head & mask));
if (pheader->size == 0) {
pr_debug("Finished reading overwrite ring buffer: get start\n");
*end = evt_head;
return 0;
}
evt_head += pheader->size;
pr_debug3("move evt_head: %"PRIx64"\n", evt_head);
}
WARN_ONCE(1, "Shouldn't get here\n");
return -1;
}
/*
* Report the start and end of the available data in ringbuffer
*/
static int __perf_mmap__read_init(struct perf_mmap *md)
{
u64 head = perf_mmap__read_head(md);
u64 old = md->prev;
unsigned char *data = md->base + page_size;
unsigned long size;
md->start = md->overwrite ? head : old;
md->end = md->overwrite ? old : head;
if (md->start == md->end)
return -EAGAIN;
size = md->end - md->start;
if (size > (unsigned long)(md->mask) + 1) {
if (!md->overwrite) {
WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
md->prev = head;
perf_mmap__consume(md);
return -EAGAIN;
}
/*
* Backward ring buffer is full. We still have a chance to read
* most of data from it.
*/
if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end))
return -EINVAL;
}
return 0;
}
int perf_mmap__read_init(struct perf_mmap *map)
{
/*
* Check if event was unmapped due to a POLLHUP/POLLERR.
*/
if (!refcount_read(&map->refcnt))
return -ENOENT;
return __perf_mmap__read_init(map);
}
int perf_mmap__push(struct perf_mmap *md, void *to,
int push(void *to, void *buf, size_t size))
{
u64 head = perf_mmap__read_head(md);
unsigned char *data = md->base + page_size;
unsigned long size;
void *buf;
int rc = 0;
rc = perf_mmap__read_init(md);
if (rc < 0)
return (rc == -EAGAIN) ? 0 : -1;
size = md->end - md->start;
if ((md->start & md->mask) + size != (md->end & md->mask)) {
buf = &data[md->start & md->mask];
size = md->mask + 1 - (md->start & md->mask);
md->start += size;
if (push(to, buf, size) < 0) {
rc = -1;
goto out;
}
}
buf = &data[md->start & md->mask];
size = md->end - md->start;
md->start += size;
if (push(to, buf, size) < 0) {
rc = -1;
goto out;
}
md->prev = head;
perf_mmap__consume(md);
out:
return rc;
}
/*
* Mandatory for overwrite mode
* The direction of overwrite mode is backward.
* The last perf_mmap__read() will set tail to map->prev.
* Need to correct the map->prev to head which is the end of next read.
*/
void perf_mmap__read_done(struct perf_mmap *map)
{
/*
* Check if event was unmapped due to a POLLHUP/POLLERR.
*/
if (!refcount_read(&map->refcnt))
return;
map->prev = perf_mmap__read_head(map);
}