Add a comment to ep_poll(), rename labels a bit clearly, fix a warning of
unused variable from gcc and optimize the non-blocking path a little.
Hinted-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
hannes@cmpxchg.org:
: The non-blocking ep_poll path optimization introduced skipping over the
: return value setup.
:
: Initialize it properly, my userspace gets upset by epoll_wait() returning
: random things.
:
: In addition, remove the reinitialization at the fetch_events label, the
: return value is garuanteed to be zero when execution reaches there.
[hannes@cmpxchg.org: fix initialization]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Shawn Bohrer <shawn.bohrer@gmail.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (47 commits)
doc: CONFIG_UNEVICTABLE_LRU doesn't exist anymore
Update cpuset info & webiste for cgroups
dcdbas: force SMI to happen when expected
arch/arm/Kconfig: remove one to many l's in the word.
asm-generic/user.h: Fix spelling in comment
drm: fix printk typo 'sracth'
Remove one to many n's in a word
Documentation/filesystems/romfs.txt: fixing link to genromfs
drivers:scsi Change printk typo initate -> initiate
serial, pch uart: Remove duplicate inclusion of linux/pci.h header
fs/eventpoll.c: fix spelling
mm: Fix out-of-date comments which refers non-existent functions
drm: Fix printk typo 'failled'
coh901318.c: Change initate to initiate.
mbox-db5500.c Change initate to initiate.
edac: correct i82975x error-info reported
edac: correct i82975x mci initialisation
edac: correct commented info
fs: update comments to point correct document
target: remove duplicate include of target/target_core_device.h from drivers/target/target_core_hba.c
...
Trivial conflict in fs/eventpoll.c (spelling vs addition)
In several places, an epoll fd can call another file's ->f_op->poll()
method with ep->mtx held. This is in general unsafe, because that other
file could itself be an epoll fd that contains the original epoll fd.
The code defends against this possibility in its own ->poll() method using
ep_call_nested, but there are several other unsafe calls to ->poll
elsewhere that can be made to deadlock. For example, the following simple
program causes the call in ep_insert recursively call the original fd's
->poll, leading to deadlock:
#include <unistd.h>
#include <sys/epoll.h>
int main(void) {
int e1, e2, p[2];
struct epoll_event evt = {
.events = EPOLLIN
};
e1 = epoll_create(1);
e2 = epoll_create(2);
pipe(p);
epoll_ctl(e2, EPOLL_CTL_ADD, e1, &evt);
epoll_ctl(e1, EPOLL_CTL_ADD, p[0], &evt);
write(p[1], p, sizeof p);
epoll_ctl(e1, EPOLL_CTL_ADD, e2, &evt);
return 0;
}
On insertion, check whether the inserted file is itself a struct epoll,
and if so, do a recursive walk to detect whether inserting this file would
create a loop of epoll structures, which could lead to deadlock.
[nelhage@ksplice.com: Use epmutex to serialize concurrent inserts]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Nelson Elhage <nelhage@ksplice.com>
Reported-by: Nelson Elhage <nelhage@ksplice.com>
Tested-by: Nelson Elhage <nelhage@ksplice.com>
Cc: <stable@kernel.org> [2.6.34+, possibly earlier]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
commit 95aac7b1cd ("epoll: make epoll_wait() use the hrtimer range
feature") added a performance regression because it uses timespec_add_ns()
with potential very large 'ns' values.
[akpm@linux-foundation.org: s/epoll_set_mstimeout/ep_set_mstimeout/, per Davide]
Reported-by: Simon Kirby <sim@hostway.ca>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Shawn Bohrer <shawn.bohrer@gmail.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: <stable@kernel.org> [2.6.37.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
It seems a couple places such as arch/ia64/kernel/perfmon.c and
drivers/infiniband/core/uverbs_main.c could use anon_inode_getfile()
instead of a private pseudo-fs + alloc_file(), if only there were a way
to get a read-only file. So provide this by having anon_inode_getfile()
create a read-only file if we pass O_RDONLY in flags.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
For consistency drop & in front of every proc_handler. Explicity
taking the address is unnecessary and it prevents optimizations
like stubbing the proc_handlers to NULL.
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Now that sys_sysctl is a generic wrapper around /proc/sys .ctl_name
and .strategy members of sysctl tables are dead code. Remove them.
Cc: Jan Harkes <jaharkes@cs.cmu.edu>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
This fixes a regression in 2.6.30.
I unfortunately accepted a patch time ago, to drop the "current" usage
from possible IRQ context, w/out proper thought over it. The patch
switched to using the CPU id by bounding the nested call callback with a
get_cpu()/put_cpu().
Unfortunately the ep_call_nested() function can be called with a callback
that grabs sleepy locks (from own f_op->poll()), that results in epic
fails. The following patch uses the proper "context" depending on the
path where it is called, and on the kind of callback.
This has been reported by Stefan Richter, that has also verified the patch
is his previously failing environment.
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Reported-by: Stefan Richter <stefanr@s5r6.in-berlin.de>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use the events hint now sent by some devices, to avoid unnecessary wakeups
for events that are of no interest for the caller. This code handles both
devices that are sending keyed events, and the ones that are not (and
event the ones that sometimes send events, and sometimes don't).
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>
Cc: William Lee Irwin III <wli@movementarian.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
ep_modify() doesn't need to set event.data from within the ep->lock
spinlock as the comment suggests. The only place event.data is used is
ep_send_events_proc(), and this is protected by ep->mtx instead of
ep->lock. Also update the comment for mutex_lock() at the top of
ep_scan_ready_list(), which mentions epoll_ctl(EPOLL_CTL_DEL) but not
epoll_ctl(EPOLL_CTL_MOD).
ep_modify() can also use spin_lock_irq() instead of spin_lock_irqsave().
Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
xchg in ep_unregister_pollwait() is unnecessary because it is protected by
either epmutex or ep->mtx (the same protection as ep_remove()).
If xchg was necessary, it would be insufficient to protect against
problems: if multiple concurrent calls to ep_unregister_pollwait() were
possible then a second caller that returns without doing anything because
nwait == 0 could return before the waitqueues are removed by the first
caller, which looks like it could lead to problematic races with
ep_poll_callback().
So remove xchg and add comments about the locking.
Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If epoll_wait returns -EFAULT, the event that was being returned when the
fault was encountered will be forgotten. This is not a big deal since
EFAULT will happen only if a buggy userspace program passes in a bad
address, in which case what happens later usually doesn't matter.
However, it is easy to remember the event for later, and this patch makes
a simple change to do that.
Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
ep_call_nested() (formerly ep_poll_safewake()) uses "current" (without
dereferencing it) to detect callback recursion, but it may be called from
irq context where the use of current is generally discouraged. It would
be better to use get_cpu() and put_cpu() to detect the callback recursion.
Signed-off-by: Tony Battersby <tonyb@cybernetics.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix a bug inside the epoll's f_op->poll() code, that returns POLLIN even
though there are no actual ready monitored fds. The bug shows up if you
add an epoll fd inside another fd container (poll, select, epoll).
The problem is that callback-based wake ups used by epoll does not carry
(patches will follow, to fix this) any information about the events that
actually happened. So the callback code, since it can't call the file*
->poll() inside the callback, chains the file* into a ready-list.
So, suppose you added an fd with EPOLLOUT only, and some data shows up on
the fd, the file* mapped by the fd will be added into the ready-list (via
wakeup callback). During normal epoll_wait() use, this condition is
sorted out at the time we're actually able to call the file*'s
f_op->poll().
Inside the old epoll's f_op->poll() though, only a quick check
!list_empty(ready-list) was performed, and this could have led to
reporting POLLIN even though no ready fds would show up at a following
epoll_wait(). In order to correctly report the ready status for an epoll
fd, the ready-list must be checked to see if any really available fd+event
would be ready in a following epoll_wait().
Operation (calling f_op->poll() from inside f_op->poll()) that, like wake
ups, must be handled with care because of the fact that epoll fds can be
added to other epoll fds.
Test code:
/*
* epoll_test by Davide Libenzi (Simple code to test epoll internals)
* Copyright (C) 2008 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <sys/types.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <signal.h>
#include <limits.h>
#include <poll.h>
#include <sys/epoll.h>
#include <sys/wait.h>
#define EPWAIT_TIMEO (1 * 1000)
#ifndef POLLRDHUP
#define POLLRDHUP 0x2000
#endif
#define EPOLL_MAX_CHAIN 100L
#define EPOLL_TF_LOOP (1 << 0)
struct epoll_test_cfg {
long size;
long flags;
};
static int xepoll_create(int n) {
int epfd;
if ((epfd = epoll_create(n)) == -1) {
perror("epoll_create");
exit(2);
}
return epfd;
}
static void xepoll_ctl(int epfd, int cmd, int fd, struct epoll_event *evt) {
if (epoll_ctl(epfd, cmd, fd, evt) < 0) {
perror("epoll_ctl");
exit(3);
}
}
static void xpipe(int *fds) {
if (pipe(fds)) {
perror("pipe");
exit(4);
}
}
static pid_t xfork(void) {
pid_t pid;
if ((pid = fork()) == (pid_t) -1) {
perror("pipe");
exit(5);
}
return pid;
}
static int run_forked_proc(int (*proc)(void *), void *data) {
int status;
pid_t pid;
if ((pid = xfork()) == 0)
exit((*proc)(data));
if (waitpid(pid, &status, 0) != pid) {
perror("waitpid");
return -1;
}
return WIFEXITED(status) ? WEXITSTATUS(status): -2;
}
static int check_events(int fd, int timeo) {
struct pollfd pfd;
fprintf(stdout, "Checking events for fd %d\n", fd);
memset(&pfd, 0, sizeof(pfd));
pfd.fd = fd;
pfd.events = POLLIN | POLLOUT;
if (poll(&pfd, 1, timeo) < 0) {
perror("poll()");
return 0;
}
if (pfd.revents & POLLIN)
fprintf(stdout, "\tPOLLIN\n");
if (pfd.revents & POLLOUT)
fprintf(stdout, "\tPOLLOUT\n");
if (pfd.revents & POLLERR)
fprintf(stdout, "\tPOLLERR\n");
if (pfd.revents & POLLHUP)
fprintf(stdout, "\tPOLLHUP\n");
if (pfd.revents & POLLRDHUP)
fprintf(stdout, "\tPOLLRDHUP\n");
return pfd.revents;
}
static int epoll_test_tty(void *data) {
int epfd, ifd = fileno(stdin), res;
struct epoll_event evt;
if (check_events(ifd, 0) != POLLOUT) {
fprintf(stderr, "Something is cooking on STDIN (%d)\n", ifd);
return 1;
}
epfd = xepoll_create(1);
fprintf(stdout, "Created epoll fd (%d)\n", epfd);
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
xepoll_ctl(epfd, EPOLL_CTL_ADD, ifd, &evt);
if (check_events(epfd, 0) & POLLIN) {
res = epoll_wait(epfd, &evt, 1, 0);
if (res == 0) {
fprintf(stderr, "Epoll fd (%d) is ready when it shouldn't!\n",
epfd);
return 2;
}
}
return 0;
}
static int epoll_wakeup_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write must come after the poll(2) call inside
* check_events(). This tests the nested wakeup code in
* fs/eventpoll.c:ep_poll_safewake()
* By having the check_events() (hence poll(2)) happens first,
* we have poll wait queue filled up, and the write(2) in the
* child will trigger the wakeup chain.
*/
if ((pid = xfork()) == 0) {
sleep(1);
write(pfds[1], "w", 1);
exit(0);
}
res = check_events(epfd, 2000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
static int epoll_poll_chain(void *data) {
struct epoll_test_cfg *tcfg = data;
int i, res, epfd, bfd, nfd, pfds[2];
pid_t pid;
struct epoll_event evt;
memset(&evt, 0, sizeof(evt));
evt.events = EPOLLIN;
epfd = bfd = xepoll_create(1);
for (i = 0; i < tcfg->size; i++) {
nfd = xepoll_create(1);
xepoll_ctl(bfd, EPOLL_CTL_ADD, nfd, &evt);
bfd = nfd;
}
xpipe(pfds);
if (tcfg->flags & EPOLL_TF_LOOP)
{
xepoll_ctl(bfd, EPOLL_CTL_ADD, epfd, &evt);
/*
* If we're testing for loop, we want that the wakeup
* triggered by the write to the pipe done in the child
* process, triggers a fake event. So we add the pipe
* read size with EPOLLOUT events. This will trigger
* an addition to the ready-list, but no real events
* will be there. The the epoll kernel code will proceed
* in calling f_op->poll() of the epfd, triggering the
* loop we want to test.
*/
evt.events = EPOLLOUT;
}
xepoll_ctl(bfd, EPOLL_CTL_ADD, pfds[0], &evt);
/*
* The pipe write mush come before the poll(2) call inside
* check_events(). This tests the nested f_op->poll calls code in
* fs/eventpoll.c:ep_eventpoll_poll()
* By having the pipe write(2) happen first, we make the kernel
* epoll code to load the ready lists, and the following poll(2)
* done inside check_events() will test nested poll code in
* ep_eventpoll_poll().
*/
if ((pid = xfork()) == 0) {
write(pfds[1], "w", 1);
exit(0);
}
sleep(1);
res = check_events(epfd, 1000) & POLLIN;
if (waitpid(pid, NULL, 0) != pid) {
perror("waitpid");
return -1;
}
return res;
}
int main(int ac, char **av) {
int error;
struct epoll_test_cfg tcfg;
fprintf(stdout, "\n********** Testing TTY events\n");
error = run_forked_proc(epoll_test_tty, NULL);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short wakeup chain\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing short poll chain\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == POLLIN ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = EPOLL_MAX_CHAIN;
tcfg.flags = 0;
fprintf(stdout, "\n********** Testing long poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy wakeup chain (HOLD ON)\n");
error = run_forked_proc(epoll_wakeup_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
tcfg.size = 3;
tcfg.flags = EPOLL_TF_LOOP;
fprintf(stdout, "\n********** Testing loopy poll chain (HOLD ON)\n");
error = run_forked_proc(epoll_poll_chain, &tcfg);
fprintf(stdout, error == 0 ?
"********** OK\n": "********** FAIL (%d)\n", error);
return 0;
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Pavel Pisa <pisa@cmp.felk.cvut.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Lucas De Marchi
Shawn Bohrer
Davide Libenzi
Linus Torvalds
Daniel Baluta
Eric Dumazet
Robin Holt
Arnd Bergmann
Changli Gao
Roland Dreier
Eric W. Biederman
Tony Battersby