linux_dsm_epyc7002/fs/select.c

1422 lines
34 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 21:07:57 +07:00
// SPDX-License-Identifier: GPL-2.0
/*
* This file contains the procedures for the handling of select and poll
*
* Created for Linux based loosely upon Mathius Lattner's minix
* patches by Peter MacDonald. Heavily edited by Linus.
*
* 4 February 1994
* COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS
* flag set in its personality we do *not* modify the given timeout
* parameter to reflect time remaining.
*
* 24 January 2000
* Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation
* of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian).
*/
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/sched/rt.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/fs.h>
#include <linux/rcupdate.h>
#include <linux/hrtimer.h>
#include <linux/freezer.h>
#include <net/busy_poll.h>
fs/select: add vmalloc fallback for select(2) The select(2) syscall performs a kmalloc(size, GFP_KERNEL) where size grows with the number of fds passed. We had a customer report page allocation failures of order-4 for this allocation. This is a costly order, so it might easily fail, as the VM expects such allocation to have a lower-order fallback. Such trivial fallback is vmalloc(), as the memory doesn't have to be physically contiguous and the allocation is temporary for the duration of the syscall only. There were some concerns, whether this would have negative impact on the system by exposing vmalloc() to userspace. Although an excessive use of vmalloc can cause some system wide performance issues - TLB flushes etc. - a large order allocation is not for free either and an excessive reclaim/compaction can have a similar effect. Also note that the size is effectively limited by RLIMIT_NOFILE which defaults to 1024 on the systems I checked. That means the bitmaps will fit well within single page and thus the vmalloc() fallback could be only excercised for processes where root allows a higher limit. Note that the poll(2) syscall seems to use a linked list of order-0 pages, so it doesn't need this kind of fallback. [eric.dumazet@gmail.com: fix failure path logic] [akpm@linux-foundation.org: use proper type for size] Link: http://lkml.kernel.org/r/20160927084536.5923-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Laight <David.Laight@ACULAB.COM> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Jason Baron <jbaron@akamai.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 03:51:14 +07:00
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
/*
* Estimate expected accuracy in ns from a timeval.
*
* After quite a bit of churning around, we've settled on
* a simple thing of taking 0.1% of the timeout as the
* slack, with a cap of 100 msec.
* "nice" tasks get a 0.5% slack instead.
*
* Consider this comment an open invitation to come up with even
* better solutions..
*/
#define MAX_SLACK (100 * NSEC_PER_MSEC)
static long __estimate_accuracy(struct timespec64 *tv)
{
long slack;
int divfactor = 1000;
if (tv->tv_sec < 0)
return 0;
if (task_nice(current) > 0)
divfactor = divfactor / 5;
if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor))
return MAX_SLACK;
slack = tv->tv_nsec / divfactor;
slack += tv->tv_sec * (NSEC_PER_SEC/divfactor);
if (slack > MAX_SLACK)
return MAX_SLACK;
return slack;
}
u64 select_estimate_accuracy(struct timespec64 *tv)
{
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 04:20:51 +07:00
u64 ret;
struct timespec64 now;
/*
* Realtime tasks get a slack of 0 for obvious reasons.
*/
if (rt_task(current))
return 0;
ktime_get_ts64(&now);
now = timespec64_sub(*tv, now);
ret = __estimate_accuracy(&now);
if (ret < current->timer_slack_ns)
return current->timer_slack_ns;
return ret;
}
struct poll_table_page {
struct poll_table_page * next;
struct poll_table_entry * entry;
struct poll_table_entry entries[0];
};
#define POLL_TABLE_FULL(table) \
((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table))
/*
* Ok, Peter made a complicated, but straightforward multiple_wait() function.
* I have rewritten this, taking some shortcuts: This code may not be easy to
* follow, but it should be free of race-conditions, and it's practical. If you
* understand what I'm doing here, then you understand how the linux
* sleep/wakeup mechanism works.
*
* Two very simple procedures, poll_wait() and poll_freewait() make all the
* work. poll_wait() is an inline-function defined in <linux/poll.h>,
* as all select/poll functions have to call it to add an entry to the
* poll table.
*/
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
poll_table *p);
void poll_initwait(struct poll_wqueues *pwq)
{
init_poll_funcptr(&pwq->pt, __pollwait);
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
pwq->polling_task = current;
pwq->triggered = 0;
pwq->error = 0;
pwq->table = NULL;
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
pwq->inline_index = 0;
}
EXPORT_SYMBOL(poll_initwait);
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
static void free_poll_entry(struct poll_table_entry *entry)
{
remove_wait_queue(entry->wait_address, &entry->wait);
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
fput(entry->filp);
}
void poll_freewait(struct poll_wqueues *pwq)
{
struct poll_table_page * p = pwq->table;
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
int i;
for (i = 0; i < pwq->inline_index; i++)
free_poll_entry(pwq->inline_entries + i);
while (p) {
struct poll_table_entry * entry;
struct poll_table_page *old;
entry = p->entry;
do {
entry--;
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
free_poll_entry(entry);
} while (entry > p->entries);
old = p;
p = p->next;
free_page((unsigned long) old);
}
}
EXPORT_SYMBOL(poll_freewait);
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p)
{
struct poll_table_page *table = p->table;
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
if (p->inline_index < N_INLINE_POLL_ENTRIES)
return p->inline_entries + p->inline_index++;
if (!table || POLL_TABLE_FULL(table)) {
struct poll_table_page *new_table;
new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL);
if (!new_table) {
p->error = -ENOMEM;
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
return NULL;
}
new_table->entry = new_table->entries;
new_table->next = table;
p->table = new_table;
table = new_table;
}
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
return table->entry++;
}
static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
{
struct poll_wqueues *pwq = wait->private;
DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task);
/*
* Although this function is called under waitqueue lock, LOCK
* doesn't imply write barrier and the users expect write
* barrier semantics on wakeup functions. The following
* smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
* and is paired with smp_store_mb() in poll_schedule_timeout.
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
*/
smp_wmb();
pwq->triggered = 1;
/*
* Perform the default wake up operation using a dummy
* waitqueue.
*
* TODO: This is hacky but there currently is no interface to
* pass in @sync. @sync is scheduled to be removed and once
* that happens, wake_up_process() can be used directly.
*/
return default_wake_function(&dummy_wait, mode, sync, key);
}
static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
{
struct poll_table_entry *entry;
entry = container_of(wait, struct poll_table_entry, wait);
if (key && !(key_to_poll(key) & entry->key))
return 0;
return __pollwake(wait, mode, sync, key);
}
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
/* Add a new entry */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
poll_table *p)
{
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt);
struct poll_table_entry *entry = poll_get_entry(pwq);
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
if (!entry)
return;
entry->filp = get_file(filp);
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
entry->wait_address = wait_address;
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
entry->key = p->_key;
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
init_waitqueue_func_entry(&entry->wait, pollwake);
entry->wait.private = pwq;
add_wait_queue(wait_address, &entry->wait);
}
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
ktime_t *expires, unsigned long slack)
{
int rc = -EINTR;
set_current_state(state);
if (!pwq->triggered)
rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
__set_current_state(TASK_RUNNING);
/*
* Prepare for the next iteration.
*
* The following smp_store_mb() serves two purposes. First, it's
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
* the counterpart rmb of the wmb in pollwake() such that data
* written before wake up is always visible after wake up.
* Second, the full barrier guarantees that triggered clearing
* doesn't pass event check of the next iteration. Note that
* this problem doesn't exist for the first iteration as
* add_wait_queue() has full barrier semantics.
*/
smp_store_mb(pwq->triggered, 0);
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
return rc;
}
EXPORT_SYMBOL(poll_schedule_timeout);
/**
* poll_select_set_timeout - helper function to setup the timeout value
* @to: pointer to timespec64 variable for the final timeout
* @sec: seconds (from user space)
* @nsec: nanoseconds (from user space)
*
* Note, we do not use a timespec for the user space value here, That
* way we can use the function for timeval and compat interfaces as well.
*
* Returns -EINVAL if sec/nsec are not normalized. Otherwise 0.
*/
int poll_select_set_timeout(struct timespec64 *to, time64_t sec, long nsec)
{
struct timespec64 ts = {.tv_sec = sec, .tv_nsec = nsec};
if (!timespec64_valid(&ts))
return -EINVAL;
/* Optimize for the zero timeout value here */
if (!sec && !nsec) {
to->tv_sec = to->tv_nsec = 0;
} else {
ktime_get_ts64(to);
*to = timespec64_add_safe(*to, ts);
}
return 0;
}
static int poll_select_copy_remaining(struct timespec64 *end_time,
void __user *p,
int timeval, int ret)
{
struct timespec64 rts;
struct timeval rtv;
if (!p)
return ret;
if (current->personality & STICKY_TIMEOUTS)
goto sticky;
/* No update for zero timeout */
if (!end_time->tv_sec && !end_time->tv_nsec)
return ret;
ktime_get_ts64(&rts);
rts = timespec64_sub(*end_time, rts);
if (rts.tv_sec < 0)
rts.tv_sec = rts.tv_nsec = 0;
if (timeval) {
if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec))
memset(&rtv, 0, sizeof(rtv));
rtv.tv_sec = rts.tv_sec;
rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC;
if (!copy_to_user(p, &rtv, sizeof(rtv)))
return ret;
} else if (!put_timespec64(&rts, p))
return ret;
/*
* If an application puts its timeval in read-only memory, we
* don't want the Linux-specific update to the timeval to
* cause a fault after the select has completed
* successfully. However, because we're not updating the
* timeval, we can't restart the system call.
*/
sticky:
if (ret == -ERESTARTNOHAND)
ret = -EINTR;
return ret;
}
/*
* Scalable version of the fd_set.
*/
typedef struct {
unsigned long *in, *out, *ex;
unsigned long *res_in, *res_out, *res_ex;
} fd_set_bits;
/*
* How many longwords for "nr" bits?
*/
#define FDS_BITPERLONG (8*sizeof(long))
#define FDS_LONGS(nr) (((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG)
#define FDS_BYTES(nr) (FDS_LONGS(nr)*sizeof(long))
/*
* We do a VERIFY_WRITE here even though we are only reading this time:
* we'll write to it eventually..
*
* Use "unsigned long" accesses to let user-mode fd_set's be long-aligned.
*/
static inline
int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
{
nr = FDS_BYTES(nr);
if (ufdset)
return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0;
memset(fdset, 0, nr);
return 0;
}
static inline unsigned long __must_check
set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
{
if (ufdset)
return __copy_to_user(ufdset, fdset, FDS_BYTES(nr));
return 0;
}
static inline
void zero_fd_set(unsigned long nr, unsigned long *fdset)
{
memset(fdset, 0, FDS_BYTES(nr));
}
#define FDS_IN(fds, n) (fds->in + n)
#define FDS_OUT(fds, n) (fds->out + n)
#define FDS_EX(fds, n) (fds->ex + n)
#define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n))
static int max_select_fd(unsigned long n, fd_set_bits *fds)
{
unsigned long *open_fds;
unsigned long set;
int max;
struct fdtable *fdt;
/* handle last in-complete long-word first */
set = ~(~0UL << (n & (BITS_PER_LONG-1)));
n /= BITS_PER_LONG;
fdt = files_fdtable(current->files);
open_fds = fdt->open_fds + n;
max = 0;
if (set) {
set &= BITS(fds, n);
if (set) {
if (!(set & ~*open_fds))
goto get_max;
return -EBADF;
}
}
while (n) {
open_fds--;
n--;
set = BITS(fds, n);
if (!set)
continue;
if (set & ~*open_fds)
return -EBADF;
if (max)
continue;
get_max:
do {
max++;
set >>= 1;
} while (set);
max += n * BITS_PER_LONG;
}
return max;
}
#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | EPOLLHUP | EPOLLERR)
#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | EPOLLERR)
#define POLLEX_SET (EPOLLPRI)
static inline void wait_key_set(poll_table *wait, unsigned long in,
unsigned long out, unsigned long bit,
__poll_t ll_flag)
{
wait->_key = POLLEX_SET | ll_flag;
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
if (in & bit)
wait->_key |= POLLIN_SET;
if (out & bit)
wait->_key |= POLLOUT_SET;
}
static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
{
ktime_t expire, *to = NULL;
struct poll_wqueues table;
poll_table *wait;
int retval, i, timed_out = 0;
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 04:20:51 +07:00
u64 slack = 0;
__poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
unsigned long busy_start = 0;
rcu_read_lock();
retval = max_select_fd(n, fds);
rcu_read_unlock();
if (retval < 0)
return retval;
n = retval;
poll_initwait(&table);
wait = &table.pt;
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
wait->_qproc = NULL;
timed_out = 1;
}
if (end_time && !timed_out)
slack = select_estimate_accuracy(end_time);
retval = 0;
for (;;) {
unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
bool can_busy_loop = false;
inp = fds->in; outp = fds->out; exp = fds->ex;
rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;
for (i = 0; i < n; ++rinp, ++routp, ++rexp) {
unsigned long in, out, ex, all_bits, bit = 1, j;
unsigned long res_in = 0, res_out = 0, res_ex = 0;
__poll_t mask;
in = *inp++; out = *outp++; ex = *exp++;
all_bits = in | out | ex;
if (all_bits == 0) {
i += BITS_PER_LONG;
continue;
}
for (j = 0; j < BITS_PER_LONG; ++j, ++i, bit <<= 1) {
struct fd f;
if (i >= n)
break;
if (!(bit & all_bits))
continue;
f = fdget(i);
if (f.file) {
const struct file_operations *f_op;
f_op = f.file->f_op;
mask = DEFAULT_POLLMASK;
if (f_op->poll) {
wait_key_set(wait, in, out,
bit, busy_flag);
mask = (*f_op->poll)(f.file, wait);
}
fdput(f);
if ((mask & POLLIN_SET) && (in & bit)) {
res_in |= bit;
retval++;
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
wait->_qproc = NULL;
}
if ((mask & POLLOUT_SET) && (out & bit)) {
res_out |= bit;
retval++;
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
wait->_qproc = NULL;
}
if ((mask & POLLEX_SET) && (ex & bit)) {
res_ex |= bit;
retval++;
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
wait->_qproc = NULL;
}
/* got something, stop busy polling */
if (retval) {
can_busy_loop = false;
busy_flag = 0;
/*
* only remember a returned
* POLL_BUSY_LOOP if we asked for it
*/
} else if (busy_flag & mask)
can_busy_loop = true;
}
}
if (res_in)
*rinp = res_in;
if (res_out)
*routp = res_out;
if (res_ex)
*rexp = res_ex;
cond_resched();
}
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
wait->_qproc = NULL;
if (retval || timed_out || signal_pending(current))
break;
if (table.error) {
retval = table.error;
break;
}
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
/* only if found POLL_BUSY_LOOP sockets && not out of time */
if (can_busy_loop && !need_resched()) {
if (!busy_start) {
busy_start = busy_loop_current_time();
continue;
}
if (!busy_loop_timeout(busy_start))
continue;
}
busy_flag = 0;
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to
* pointer to the expiry value.
*/
if (end_time && !to) {
expire = timespec64_to_ktime(*end_time);
to = &expire;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE,
to, slack))
timed_out = 1;
}
poll_freewait(&table);
return retval;
}
/*
* We can actually return ERESTARTSYS instead of EINTR, but I'd
* like to be certain this leads to no problems. So I return
* EINTR just for safety.
*
* Update: ERESTARTSYS breaks at least the xview clock binary, so
* I'm trying ERESTARTNOHAND which restart only when you want to.
*/
int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
fd_set __user *exp, struct timespec64 *end_time)
{
fd_set_bits fds;
void *bits;
int ret, max_fds;
fs/select: add vmalloc fallback for select(2) The select(2) syscall performs a kmalloc(size, GFP_KERNEL) where size grows with the number of fds passed. We had a customer report page allocation failures of order-4 for this allocation. This is a costly order, so it might easily fail, as the VM expects such allocation to have a lower-order fallback. Such trivial fallback is vmalloc(), as the memory doesn't have to be physically contiguous and the allocation is temporary for the duration of the syscall only. There were some concerns, whether this would have negative impact on the system by exposing vmalloc() to userspace. Although an excessive use of vmalloc can cause some system wide performance issues - TLB flushes etc. - a large order allocation is not for free either and an excessive reclaim/compaction can have a similar effect. Also note that the size is effectively limited by RLIMIT_NOFILE which defaults to 1024 on the systems I checked. That means the bitmaps will fit well within single page and thus the vmalloc() fallback could be only excercised for processes where root allows a higher limit. Note that the poll(2) syscall seems to use a linked list of order-0 pages, so it doesn't need this kind of fallback. [eric.dumazet@gmail.com: fix failure path logic] [akpm@linux-foundation.org: use proper type for size] Link: http://lkml.kernel.org/r/20160927084536.5923-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Laight <David.Laight@ACULAB.COM> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Jason Baron <jbaron@akamai.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 03:51:14 +07:00
size_t size, alloc_size;
struct fdtable *fdt;
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
/* Allocate small arguments on the stack to save memory and be faster */
long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
ret = -EINVAL;
if (n < 0)
goto out_nofds;
/* max_fds can increase, so grab it once to avoid race */
rcu_read_lock();
fdt = files_fdtable(current->files);
max_fds = fdt->max_fds;
rcu_read_unlock();
if (n > max_fds)
n = max_fds;
/*
* We need 6 bitmaps (in/out/ex for both incoming and outgoing),
* since we used fdset we need to allocate memory in units of
* long-words.
*/
size = FDS_BYTES(n);
bits = stack_fds;
if (size > sizeof(stack_fds) / 6) {
/* Not enough space in on-stack array; must use kmalloc */
ret = -ENOMEM;
fs/select: add vmalloc fallback for select(2) The select(2) syscall performs a kmalloc(size, GFP_KERNEL) where size grows with the number of fds passed. We had a customer report page allocation failures of order-4 for this allocation. This is a costly order, so it might easily fail, as the VM expects such allocation to have a lower-order fallback. Such trivial fallback is vmalloc(), as the memory doesn't have to be physically contiguous and the allocation is temporary for the duration of the syscall only. There were some concerns, whether this would have negative impact on the system by exposing vmalloc() to userspace. Although an excessive use of vmalloc can cause some system wide performance issues - TLB flushes etc. - a large order allocation is not for free either and an excessive reclaim/compaction can have a similar effect. Also note that the size is effectively limited by RLIMIT_NOFILE which defaults to 1024 on the systems I checked. That means the bitmaps will fit well within single page and thus the vmalloc() fallback could be only excercised for processes where root allows a higher limit. Note that the poll(2) syscall seems to use a linked list of order-0 pages, so it doesn't need this kind of fallback. [eric.dumazet@gmail.com: fix failure path logic] [akpm@linux-foundation.org: use proper type for size] Link: http://lkml.kernel.org/r/20160927084536.5923-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Laight <David.Laight@ACULAB.COM> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Jason Baron <jbaron@akamai.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 03:51:14 +07:00
if (size > (SIZE_MAX / 6))
goto out_nofds;
alloc_size = 6 * size;
treewide: use kv[mz]alloc* rather than opencoded variants There are many code paths opencoding kvmalloc. Let's use the helper instead. The main difference to kvmalloc is that those users are usually not considering all the aspects of the memory allocator. E.g. allocation requests <= 32kB (with 4kB pages) are basically never failing and invoke OOM killer to satisfy the allocation. This sounds too disruptive for something that has a reasonable fallback - the vmalloc. On the other hand those requests might fallback to vmalloc even when the memory allocator would succeed after several more reclaim/compaction attempts previously. There is no guarantee something like that happens though. This patch converts many of those places to kv[mz]alloc* helpers because they are more conservative. Link: http://lkml.kernel.org/r/20170306103327.2766-2-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> # Xen bits Acked-by: Kees Cook <keescook@chromium.org> Acked-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Andreas Dilger <andreas.dilger@intel.com> # Lustre Acked-by: Christian Borntraeger <borntraeger@de.ibm.com> # KVM/s390 Acked-by: Dan Williams <dan.j.williams@intel.com> # nvdim Acked-by: David Sterba <dsterba@suse.com> # btrfs Acked-by: Ilya Dryomov <idryomov@gmail.com> # Ceph Acked-by: Tariq Toukan <tariqt@mellanox.com> # mlx4 Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx5 Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Colin Cross <ccross@android.com> Cc: Tony Luck <tony.luck@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: Kent Overstreet <kent.overstreet@gmail.com> Cc: Santosh Raspatur <santosh@chelsio.com> Cc: Hariprasad S <hariprasad@chelsio.com> Cc: Yishai Hadas <yishaih@mellanox.com> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: "Yan, Zheng" <zyan@redhat.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-09 05:57:27 +07:00
bits = kvmalloc(alloc_size, GFP_KERNEL);
if (!bits)
goto out_nofds;
}
fds.in = bits;
fds.out = bits + size;
fds.ex = bits + 2*size;
fds.res_in = bits + 3*size;
fds.res_out = bits + 4*size;
fds.res_ex = bits + 5*size;
if ((ret = get_fd_set(n, inp, fds.in)) ||
(ret = get_fd_set(n, outp, fds.out)) ||
(ret = get_fd_set(n, exp, fds.ex)))
goto out;
zero_fd_set(n, fds.res_in);
zero_fd_set(n, fds.res_out);
zero_fd_set(n, fds.res_ex);
ret = do_select(n, &fds, end_time);
if (ret < 0)
goto out;
if (!ret) {
ret = -ERESTARTNOHAND;
if (signal_pending(current))
goto out;
ret = 0;
}
if (set_fd_set(n, inp, fds.res_in) ||
set_fd_set(n, outp, fds.res_out) ||
set_fd_set(n, exp, fds.res_ex))
ret = -EFAULT;
out:
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
if (bits != stack_fds)
fs/select: add vmalloc fallback for select(2) The select(2) syscall performs a kmalloc(size, GFP_KERNEL) where size grows with the number of fds passed. We had a customer report page allocation failures of order-4 for this allocation. This is a costly order, so it might easily fail, as the VM expects such allocation to have a lower-order fallback. Such trivial fallback is vmalloc(), as the memory doesn't have to be physically contiguous and the allocation is temporary for the duration of the syscall only. There were some concerns, whether this would have negative impact on the system by exposing vmalloc() to userspace. Although an excessive use of vmalloc can cause some system wide performance issues - TLB flushes etc. - a large order allocation is not for free either and an excessive reclaim/compaction can have a similar effect. Also note that the size is effectively limited by RLIMIT_NOFILE which defaults to 1024 on the systems I checked. That means the bitmaps will fit well within single page and thus the vmalloc() fallback could be only excercised for processes where root allows a higher limit. Note that the poll(2) syscall seems to use a linked list of order-0 pages, so it doesn't need this kind of fallback. [eric.dumazet@gmail.com: fix failure path logic] [akpm@linux-foundation.org: use proper type for size] Link: http://lkml.kernel.org/r/20160927084536.5923-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Laight <David.Laight@ACULAB.COM> Cc: Hillf Danton <hillf.zj@alibaba-inc.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Jason Baron <jbaron@akamai.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 03:51:14 +07:00
kvfree(bits);
out_nofds:
return ret;
}
SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
fd_set __user *, exp, struct timeval __user *, tvp)
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
{
struct timespec64 end_time, *to = NULL;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
struct timeval tv;
int ret;
if (tvp) {
if (copy_from_user(&tv, tvp, sizeof(tv)))
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to,
tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
return -EINVAL;
}
ret = core_sys_select(n, inp, outp, exp, to);
ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
return ret;
}
static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp,
fd_set __user *exp, struct timespec __user *tsp,
const sigset_t __user *sigmask, size_t sigsetsize)
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
{
sigset_t ksigmask, sigsaved;
struct timespec64 ts, end_time, *to = NULL;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
int ret;
if (tsp) {
if (get_timespec64(&ts, tsp))
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
return -EINVAL;
}
if (sigmask) {
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
return -EFAULT;
sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
ret = core_sys_select(n, inp, outp, exp, to);
ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
if (ret == -ERESTARTNOHAND) {
/*
* Don't restore the signal mask yet. Let do_signal() deliver
* the signal on the way back to userspace, before the signal
* mask is restored.
*/
if (sigmask) {
memcpy(&current->saved_sigmask, &sigsaved,
sizeof(sigsaved));
set_restore_sigmask();
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
} else if (sigmask)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
return ret;
}
/*
* Most architectures can't handle 7-argument syscalls. So we provide a
* 6-argument version where the sixth argument is a pointer to a structure
* which has a pointer to the sigset_t itself followed by a size_t containing
* the sigset size.
*/
SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp,
fd_set __user *, exp, struct timespec __user *, tsp,
void __user *, sig)
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
{
size_t sigsetsize = 0;
sigset_t __user *up = NULL;
if (sig) {
if (!access_ok(VERIFY_READ, sig, sizeof(void *)+sizeof(size_t))
|| __get_user(up, (sigset_t __user * __user *)sig)
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
|| __get_user(sigsetsize,
(size_t __user *)(sig+sizeof(void *))))
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
return -EFAULT;
}
return do_pselect(n, inp, outp, exp, tsp, up, sigsetsize);
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
#ifdef __ARCH_WANT_SYS_OLD_SELECT
struct sel_arg_struct {
unsigned long n;
fd_set __user *inp, *outp, *exp;
struct timeval __user *tvp;
};
SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
{
struct sel_arg_struct a;
if (copy_from_user(&a, arg, sizeof(a)))
return -EFAULT;
return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
}
#endif
struct poll_list {
struct poll_list *next;
int len;
struct pollfd entries[0];
};
#define POLLFD_PER_PAGE ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd))
/*
* Fish for pollable events on the pollfd->fd file descriptor. We're only
* interested in events matching the pollfd->events mask, and the result
* matching that mask is both recorded in pollfd->revents and returned. The
* pwait poll_table will be used by the fd-provided poll handler for waiting,
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
* if pwait->_qproc is non-NULL.
*/
static inline __poll_t do_pollfd(struct pollfd *pollfd, poll_table *pwait,
bool *can_busy_poll,
__poll_t busy_flag)
{
__poll_t mask;
int fd;
mask = 0;
fd = pollfd->fd;
if (fd >= 0) {
struct fd f = fdget(fd);
mask = EPOLLNVAL;
if (f.file) {
/* userland u16 ->events contains POLL... bitmap */
__poll_t filter = demangle_poll(pollfd->events) |
EPOLLERR | EPOLLHUP;
mask = DEFAULT_POLLMASK;
if (f.file->f_op->poll) {
pwait->_key = filter;
pwait->_key |= busy_flag;
mask = f.file->f_op->poll(f.file, pwait);
if (mask & busy_flag)
*can_busy_poll = true;
}
/* Mask out unneeded events. */
mask &= filter;
fdput(f);
}
}
/* ... and so does ->revents */
pollfd->revents = mangle_poll(mask);
return mask;
}
static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
struct timespec64 *end_time)
{
poll_table* pt = &wait->pt;
ktime_t expire, *to = NULL;
int timed_out = 0, count = 0;
timer: convert timer_slack_ns from unsigned long to u64 This patchset introduces a /proc/<pid>/timerslack_ns interface which would allow controlling processes to be able to set the timerslack value on other processes in order to save power by avoiding wakeups (Something Android currently does via out-of-tree patches). The first patch tries to fix the internal timer_slack_ns usage which was defined as a long, which limits the slack range to ~4 seconds on 32bit systems. It converts it to a u64, which provides the same basically unlimited slack (500 years) on both 32bit and 64bit machines. The second patch introduces the /proc/<pid>/timerslack_ns interface which allows the full 64bit slack range for a task to be read or set on both 32bit and 64bit machines. With these two patches, on a 32bit machine, after setting the slack on bash to 10 seconds: $ time sleep 1 real 0m10.747s user 0m0.001s sys 0m0.005s The first patch is a little ugly, since I had to chase the slack delta arguments through a number of functions converting them to u64s. Let me know if it makes sense to break that up more or not. Other than that things are fairly straightforward. This patch (of 2): The timer_slack_ns value in the task struct is currently a unsigned long. This means that on 32bit applications, the maximum slack is just over 4 seconds. However, on 64bit machines, its much much larger (~500 years). This disparity could make application development a little (as well as the default_slack) to a u64. This means both 32bit and 64bit systems have the same effective internal slack range. Now the existing ABI via PR_GET_TIMERSLACK and PR_SET_TIMERSLACK specify the interface as a unsigned long, so we preserve that limitation on 32bit systems, where SET_TIMERSLACK can only set the slack to a unsigned long value, and GET_TIMERSLACK will return ULONG_MAX if the slack is actually larger then what can be stored by an unsigned long. This patch also modifies hrtimer functions which specified the slack delta as a unsigned long. Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Oren Laadan <orenl@cellrox.com> Cc: Ruchi Kandoi <kandoiruchi@google.com> Cc: Rom Lemarchand <romlem@android.com> Cc: Kees Cook <keescook@chromium.org> Cc: Android Kernel Team <kernel-team@android.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-03-18 04:20:51 +07:00
u64 slack = 0;
__poll_t busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
unsigned long busy_start = 0;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
/* Optimise the no-wait case */
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
pt->_qproc = NULL;
timed_out = 1;
}
if (end_time && !timed_out)
slack = select_estimate_accuracy(end_time);
for (;;) {
struct poll_list *walk;
bool can_busy_loop = false;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
for (walk = list; walk != NULL; walk = walk->next) {
struct pollfd * pfd, * pfd_end;
pfd = walk->entries;
pfd_end = pfd + walk->len;
for (; pfd != pfd_end; pfd++) {
/*
* Fish for events. If we found one, record it
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
* and kill poll_table->_qproc, so we don't
* needlessly register any other waiters after
* this. They'll get immediately deregistered
* when we break out and return.
*/
if (do_pollfd(pfd, pt, &can_busy_loop,
busy_flag)) {
count++;
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
pt->_qproc = NULL;
/* found something, stop busy polling */
busy_flag = 0;
can_busy_loop = false;
}
}
}
/*
* All waiters have already been registered, so don't provide
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
* a poll_table->_qproc to them on the next loop iteration.
*/
poll: add poll_requested_events() and poll_does_not_wait() functions In some cases the poll() implementation in a driver has to do different things depending on the events the caller wants to poll for. An example is when a driver needs to start a DMA engine if the caller polls for POLLIN, but doesn't want to do that if POLLIN is not requested but instead only POLLOUT or POLLPRI is requested. This is something that can happen in the video4linux subsystem among others. Unfortunately, the current epoll/poll/select implementation doesn't provide that information reliably. The poll_table_struct does have it: it has a key field with the event mask. But once a poll() call matches one or more bits of that mask any following poll() calls are passed a NULL poll_table pointer. Also, the eventpoll implementation always left the key field at ~0 instead of using the requested events mask. This was changed in eventpoll.c so the key field now contains the actual events that should be polled for as set by the caller. The solution to the NULL poll_table pointer is to set the qproc field to NULL in poll_table once poll() matches the events, not the poll_table pointer itself. That way drivers can obtain the mask through a new poll_requested_events inline. The poll_table_struct can still be NULL since some kernel code calls it internally (netfs_state_poll() in ./drivers/staging/pohmelfs/netfs.h). In that case poll_requested_events() returns ~0 (i.e. all events). Very rarely drivers might want to know whether poll_wait will actually wait. If another earlier file descriptor in the set already matched the events the caller wanted to wait for, then the kernel will return from the select() call without waiting. This might be useful information in order to avoid doing expensive work. A new helper function poll_does_not_wait() is added that drivers can use to detect this situation. This is now used in sock_poll_wait() in include/net/sock.h. This was the only place in the kernel that needed this information. Drivers should no longer access any of the poll_table internals, but use the poll_requested_events() and poll_does_not_wait() access functions instead. In order to enforce that the poll_table fields are now prepended with an underscore and a comment was added warning against using them directly. This required a change in unix_dgram_poll() in unix/af_unix.c which used the key field to get the requested events. It's been replaced by a call to poll_requested_events(). For qproc it was especially important to change its name since the behavior of that field changes with this patch since this function pointer can now be NULL when that wasn't possible in the past. Any driver accessing the qproc or key fields directly will now fail to compile. Some notes regarding the correctness of this patch: the driver's poll() function is called with a 'struct poll_table_struct *wait' argument. This pointer may or may not be NULL, drivers can never rely on it being one or the other as that depends on whether or not an earlier file descriptor in the select()'s fdset matched the requested events. There are only three things a driver can do with the wait argument: 1) obtain the key field: events = wait ? wait->key : ~0; This will still work although it should be replaced with the new poll_requested_events() function (which does exactly the same). This will now even work better, since wait is no longer set to NULL unnecessarily. 2) use the qproc callback. This could be deadly since qproc can now be NULL. Renaming qproc should prevent this from happening. There are no kernel drivers that actually access this callback directly, BTW. 3) test whether wait == NULL to determine whether poll would return without waiting. This is no longer sufficient as the correct test is now wait == NULL || wait->_qproc == NULL. However, the worst that can happen here is a slight performance hit in the case where wait != NULL and wait->_qproc == NULL. In that case the driver will assume that poll_wait() will actually add the fd to the set of waiting file descriptors. Of course, poll_wait() will not do that since it tests for wait->_qproc. This will not break anything, though. There is only one place in the whole kernel where this happens (sock_poll_wait() in include/net/sock.h) and that code will be replaced by a call to poll_does_not_wait() in the next patch. Note that even if wait->_qproc != NULL drivers cannot rely on poll_wait() actually waiting. The next file descriptor from the set might match the event mask and thus any possible waits will never happen. Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com> Reviewed-by: Jonathan Corbet <corbet@lwn.net> Reviewed-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Hans de Goede <hdegoede@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Cc: David Miller <davem@davemloft.net> Cc: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-24 05:02:27 +07:00
pt->_qproc = NULL;
if (!count) {
count = wait->error;
if (signal_pending(current))
count = -EINTR;
}
if (count || timed_out)
break;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
/* only if found POLL_BUSY_LOOP sockets && not out of time */
if (can_busy_loop && !need_resched()) {
if (!busy_start) {
busy_start = busy_loop_current_time();
continue;
}
if (!busy_loop_timeout(busy_start))
continue;
}
busy_flag = 0;
/*
* If this is the first loop and we have a timeout
* given, then we convert to ktime_t and set the to
* pointer to the expiry value.
*/
if (end_time && !to) {
expire = timespec64_to_ktime(*end_time);
to = &expire;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
poll: allow f_op->poll to sleep f_op->poll is the only vfs operation which is not allowed to sleep. It's because poll and select implementation used task state to synchronize against wake ups, which doesn't have to be the case anymore as wait/wake interface can now use custom wake up functions. The non-sleep restriction can be a bit tricky because ->poll is not called from an atomic context and the result of accidentally sleeping in ->poll only shows up as temporary busy looping when the timing is right or rather wrong. This patch converts poll/select to use custom wake up function and use separate triggered variable to synchronize against wake up events. The only added overhead is an extra function call during wake up and negligible. This patch removes the one non-sleep exception from vfs locking rules and is beneficial to userland filesystem implementations like FUSE, 9p or peculiar fs like spufs as it's very difficult for those to implement non-sleeping poll method. While at it, make the following cosmetic changes to make poll.h and select.c checkpatch friendly. * s/type * symbol/type *symbol/ : three places in poll.h * remove blank line before EXPORT_SYMBOL() : two places in select.c Oleg: spotted missing barrier in poll_schedule_timeout() Davide: spotted missing write barrier in pollwake() Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Eric Van Hensbergen <ericvh@gmail.com> Cc: Ron Minnich <rminnich@sandia.gov> Cc: Ingo Molnar <mingo@elte.hu> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Miklos Szeredi <mszeredi@suse.cz> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Brad Boyer <flar@allandria.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Roland McGrath <roland@redhat.com> Cc: Mauro Carvalho Chehab <mchehab@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-07 05:40:59 +07:00
if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack))
timed_out = 1;
}
return count;
}
[PATCH] Optimize select/poll by putting small data sets on the stack Optimize select and poll by a using stack space for small fd sets This brings back an old optimization from Linux 2.0. Using the stack is faster than kmalloc. On a Intel P4 system it speeds up a select of a single pty fd by about 13% (~4000 cycles -> ~3500) It also saves memory because a daemon hanging in select or poll will usually save one or two less pages. This can add up - e.g. if you have 10 daemons blocking in poll/select you save 40KB of memory. I did a patch for this long ago, but it was never applied. This version is a reimplementation of the old patch that tries to be less intrusive. I only did the minimal changes needed for the stack allocation. The cut off point before external memory is allocated is currently at 832bytes. The system calls always allocate this much memory on the stack. These 832 bytes are divided into 256 bytes frontend data (for the select bitmaps of the pollfds) and the rest of the space for the wait queues used by the low level drivers. There are some extreme cases where this won't work out for select and it falls back to allocating memory too early - especially with very sparse large select bitmaps - but the majority of processes who only have a small number of file descriptors should be ok. [TBD: 832/256 might not be the best split for select or poll] I suspect more optimizations might be possible, but they would be more complicated. One way would be to cache the select/poll context over multiple system calls because typically the input values should be similar. Problem is when to flush the file descriptors out though. Signed-off-by: Andi Kleen <ak@suse.de> Cc: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-28 16:56:33 +07:00
#define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \
sizeof(struct pollfd))
static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
struct timespec64 *end_time)
{
struct poll_wqueues table;
int err = -EFAULT, fdcount, len, size;
/* Allocate small arguments on the stack to save memory and be
faster - use long to make sure the buffer is aligned properly
on 64 bit archs to avoid unaligned access */
long stack_pps[POLL_STACK_ALLOC/sizeof(long)];
struct poll_list *const head = (struct poll_list *)stack_pps;
struct poll_list *walk = head;
unsigned long todo = nfds;
if (nfds > rlimit(RLIMIT_NOFILE))
return -EINVAL;
len = min_t(unsigned int, nfds, N_STACK_PPS);
for (;;) {
walk->next = NULL;
walk->len = len;
if (!len)
break;
if (copy_from_user(walk->entries, ufds + nfds-todo,
sizeof(struct pollfd) * walk->len))
goto out_fds;
todo -= walk->len;
if (!todo)
break;
len = min(todo, POLLFD_PER_PAGE);
size = sizeof(struct poll_list) + sizeof(struct pollfd) * len;
walk = walk->next = kmalloc(size, GFP_KERNEL);
if (!walk) {
err = -ENOMEM;
goto out_fds;
}
}
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
poll_initwait(&table);
fdcount = do_poll(head, &table, end_time);
poll_freewait(&table);
for (walk = head; walk; walk = walk->next) {
struct pollfd *fds = walk->entries;
int j;
for (j = 0; j < walk->len; j++, ufds++)
if (__put_user(fds[j].revents, &ufds->revents))
goto out_fds;
}
err = fdcount;
out_fds:
walk = head->next;
while (walk) {
struct poll_list *pos = walk;
walk = walk->next;
kfree(pos);
}
return err;
}
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
static long do_restart_poll(struct restart_block *restart_block)
{
struct pollfd __user *ufds = restart_block->poll.ufds;
int nfds = restart_block->poll.nfds;
struct timespec64 *to = NULL, end_time;
int ret;
if (restart_block->poll.has_timeout) {
end_time.tv_sec = restart_block->poll.tv_sec;
end_time.tv_nsec = restart_block->poll.tv_nsec;
to = &end_time;
}
ret = do_sys_poll(ufds, nfds, to);
if (ret == -EINTR) {
restart_block->fn = do_restart_poll;
ret = -ERESTART_RESTARTBLOCK;
}
return ret;
}
SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
int, timeout_msecs)
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
{
struct timespec64 end_time, *to = NULL;
int ret;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
if (timeout_msecs >= 0) {
to = &end_time;
poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC,
NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC));
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
ret = do_sys_poll(ufds, nfds, to);
if (ret == -EINTR) {
struct restart_block *restart_block;
all arches, signal: move restart_block to struct task_struct If an attacker can cause a controlled kernel stack overflow, overwriting the restart block is a very juicy exploit target. This is because the restart_block is held in the same memory allocation as the kernel stack. Moving the restart block to struct task_struct prevents this exploit by making the restart_block harder to locate. Note that there are other fields in thread_info that are also easy targets, at least on some architectures. It's also a decent simplification, since the restart code is more or less identical on all architectures. [james.hogan@imgtec.com: metag: align thread_info::supervisor_stack] Signed-off-by: Andy Lutomirski <luto@amacapital.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: David Miller <davem@davemloft.net> Acked-by: Richard Weinberger <richard@nod.at> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Haavard Skinnemoen <hskinnemoen@gmail.com> Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no> Cc: Steven Miao <realmz6@gmail.com> Cc: Mark Salter <msalter@redhat.com> Cc: Aurelien Jacquiot <a-jacquiot@ti.com> Cc: Mikael Starvik <starvik@axis.com> Cc: Jesper Nilsson <jesper.nilsson@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Helge Deller <deller@gmx.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Tested-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Chen Liqin <liqin.linux@gmail.com> Cc: Lennox Wu <lennox.wu@gmail.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: Chris Zankel <chris@zankel.net> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Guenter Roeck <linux@roeck-us.net> Signed-off-by: James Hogan <james.hogan@imgtec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 06:01:14 +07:00
restart_block = &current->restart_block;
restart_block->fn = do_restart_poll;
restart_block->poll.ufds = ufds;
restart_block->poll.nfds = nfds;
if (timeout_msecs >= 0) {
restart_block->poll.tv_sec = end_time.tv_sec;
restart_block->poll.tv_nsec = end_time.tv_nsec;
restart_block->poll.has_timeout = 1;
} else
restart_block->poll.has_timeout = 0;
ret = -ERESTART_RESTARTBLOCK;
}
return ret;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
struct timespec __user *, tsp, const sigset_t __user *, sigmask,
size_t, sigsetsize)
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
{
sigset_t ksigmask, sigsaved;
struct timespec64 ts, end_time, *to = NULL;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
int ret;
if (tsp) {
if (get_timespec64(&ts, tsp))
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
if (sigmask) {
/* XXX: Don't preclude handling different sized sigset_t's. */
if (sigsetsize != sizeof(sigset_t))
return -EINVAL;
if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
return -EFAULT;
sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
ret = do_sys_poll(ufds, nfds, to);
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
/* We can restart this syscall, usually */
if (ret == -EINTR) {
/*
* Don't restore the signal mask yet. Let do_signal() deliver
* the signal on the way back to userspace, before the signal
* mask is restored.
*/
if (sigmask) {
memcpy(&current->saved_sigmask, &sigsaved,
sizeof(sigsaved));
set_restore_sigmask();
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
}
ret = -ERESTARTNOHAND;
} else if (sigmask)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
[PATCH] Add pselect/ppoll system call implementation The following implementation of ppoll() and pselect() system calls depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the thread_info. These system calls have to change the signal mask during their operation, and signal handlers must be invoked using the new, temporary signal mask. The old signal mask must be restored either upon successful exit from the system call, or upon returning from the invoked signal handler if the system call is interrupted. We can't simply restore the original signal mask and return to userspace, since the restored signal mask may actually block the signal which interrupted the system call. The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit path to trap into do_signal() just as TIF_SIGPENDING does, and by causing do_signal() to use the saved signal mask instead of the current signal mask when setting up the stack frame for the signal handler -- or by causing do_signal() to simply restore the saved signal mask in the case where there is no handler to be invoked. The first patch implements the sys_pselect() and sys_ppoll() system calls, which are present only if TIF_RESTORE_SIGMASK is defined. That #ifdef should go away in time when all architectures have implemented it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC kernel (in the -mm tree), and the third patch then removes the arch-specific implementations of sys_rt_sigsuspend() and replaces them with generic versions using the same trick. The fourth and fifth patches, provided by David Howells, implement TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch adds the syscalls to the i386 syscall table. This patch: Add the pselect() and ppoll() system calls, providing core routines usable by the original select() and poll() system calls and also the new calls (with their semantics w.r.t timeouts). Signed-off-by: David Woodhouse <dwmw2@infradead.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 08:44:05 +07:00
return ret;
}
#ifdef CONFIG_COMPAT
#define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t))
static
int compat_poll_select_copy_remaining(struct timespec64 *end_time, void __user *p,
int timeval, int ret)
{
struct timespec64 ts;
if (!p)
return ret;
if (current->personality & STICKY_TIMEOUTS)
goto sticky;
/* No update for zero timeout */
if (!end_time->tv_sec && !end_time->tv_nsec)
return ret;
ktime_get_ts64(&ts);
ts = timespec64_sub(*end_time, ts);
if (ts.tv_sec < 0)
ts.tv_sec = ts.tv_nsec = 0;
if (timeval) {
struct compat_timeval rtv;
rtv.tv_sec = ts.tv_sec;
rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
if (!copy_to_user(p, &rtv, sizeof(rtv)))
return ret;
} else {
if (!compat_put_timespec64(&ts, p))
return ret;
}
/*
* If an application puts its timeval in read-only memory, we
* don't want the Linux-specific update to the timeval to
* cause a fault after the select has completed
* successfully. However, because we're not updating the
* timeval, we can't restart the system call.
*/
sticky:
if (ret == -ERESTARTNOHAND)
ret = -EINTR;
return ret;
}
/*
* Ooo, nasty. We need here to frob 32-bit unsigned longs to
* 64-bit unsigned longs.
*/
static
int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
unsigned long *fdset)
{
if (ufdset) {
return compat_get_bitmap(fdset, ufdset, nr);
} else {
zero_fd_set(nr, fdset);
return 0;
}
}
static
int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
unsigned long *fdset)
{
if (!ufdset)
return 0;
return compat_put_bitmap(ufdset, fdset, nr);
}
/*
* This is a virtual copy of sys_select from fs/select.c and probably
* should be compared to it from time to time
*/
/*
* We can actually return ERESTARTSYS instead of EINTR, but I'd
* like to be certain this leads to no problems. So I return
* EINTR just for safety.
*
* Update: ERESTARTSYS breaks at least the xview clock binary, so
* I'm trying ERESTARTNOHAND which restart only when you want to.
*/
static int compat_core_sys_select(int n, compat_ulong_t __user *inp,
compat_ulong_t __user *outp, compat_ulong_t __user *exp,
struct timespec64 *end_time)
{
fd_set_bits fds;
void *bits;
int size, max_fds, ret = -EINVAL;
struct fdtable *fdt;
long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
if (n < 0)
goto out_nofds;
/* max_fds can increase, so grab it once to avoid race */
rcu_read_lock();
fdt = files_fdtable(current->files);
max_fds = fdt->max_fds;
rcu_read_unlock();
if (n > max_fds)
n = max_fds;
/*
* We need 6 bitmaps (in/out/ex for both incoming and outgoing),
* since we used fdset we need to allocate memory in units of
* long-words.
*/
size = FDS_BYTES(n);
bits = stack_fds;
if (size > sizeof(stack_fds) / 6) {
bits = kmalloc(6 * size, GFP_KERNEL);
ret = -ENOMEM;
if (!bits)
goto out_nofds;
}
fds.in = (unsigned long *) bits;
fds.out = (unsigned long *) (bits + size);
fds.ex = (unsigned long *) (bits + 2*size);
fds.res_in = (unsigned long *) (bits + 3*size);
fds.res_out = (unsigned long *) (bits + 4*size);
fds.res_ex = (unsigned long *) (bits + 5*size);
if ((ret = compat_get_fd_set(n, inp, fds.in)) ||
(ret = compat_get_fd_set(n, outp, fds.out)) ||
(ret = compat_get_fd_set(n, exp, fds.ex)))
goto out;
zero_fd_set(n, fds.res_in);
zero_fd_set(n, fds.res_out);
zero_fd_set(n, fds.res_ex);
ret = do_select(n, &fds, end_time);
if (ret < 0)
goto out;
if (!ret) {
ret = -ERESTARTNOHAND;
if (signal_pending(current))
goto out;
ret = 0;
}
if (compat_set_fd_set(n, inp, fds.res_in) ||
compat_set_fd_set(n, outp, fds.res_out) ||
compat_set_fd_set(n, exp, fds.res_ex))
ret = -EFAULT;
out:
if (bits != stack_fds)
kfree(bits);
out_nofds:
return ret;
}
COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
struct compat_timeval __user *, tvp)
{
struct timespec64 end_time, *to = NULL;
struct compat_timeval tv;
int ret;
if (tvp) {
if (copy_from_user(&tv, tvp, sizeof(tv)))
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to,
tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
return -EINVAL;
}
ret = compat_core_sys_select(n, inp, outp, exp, to);
ret = compat_poll_select_copy_remaining(&end_time, tvp, 1, ret);
return ret;
}
struct compat_sel_arg_struct {
compat_ulong_t n;
compat_uptr_t inp;
compat_uptr_t outp;
compat_uptr_t exp;
compat_uptr_t tvp;
};
COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
{
struct compat_sel_arg_struct a;
if (copy_from_user(&a, arg, sizeof(a)))
return -EFAULT;
return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp),
compat_ptr(a.exp), compat_ptr(a.tvp));
}
static long do_compat_pselect(int n, compat_ulong_t __user *inp,
compat_ulong_t __user *outp, compat_ulong_t __user *exp,
struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
compat_size_t sigsetsize)
{
sigset_t ksigmask, sigsaved;
struct timespec64 ts, end_time, *to = NULL;
int ret;
if (tsp) {
if (compat_get_timespec64(&ts, tsp))
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
}
if (sigmask) {
if (sigsetsize != sizeof(compat_sigset_t))
return -EINVAL;
if (get_compat_sigset(&ksigmask, sigmask))
return -EFAULT;
sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
ret = compat_core_sys_select(n, inp, outp, exp, to);
ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
if (ret == -ERESTARTNOHAND) {
/*
* Don't restore the signal mask yet. Let do_signal() deliver
* the signal on the way back to userspace, before the signal
* mask is restored.
*/
if (sigmask) {
memcpy(&current->saved_sigmask, &sigsaved,
sizeof(sigsaved));
set_restore_sigmask();
}
} else if (sigmask)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
return ret;
}
COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
struct compat_timespec __user *, tsp, void __user *, sig)
{
compat_size_t sigsetsize = 0;
compat_uptr_t up = 0;
if (sig) {
if (!access_ok(VERIFY_READ, sig,
sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
__get_user(up, (compat_uptr_t __user *)sig) ||
__get_user(sigsetsize,
(compat_size_t __user *)(sig+sizeof(up))))
return -EFAULT;
}
return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up),
sigsetsize);
}
COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
unsigned int, nfds, struct compat_timespec __user *, tsp,
const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
{
sigset_t ksigmask, sigsaved;
struct timespec64 ts, end_time, *to = NULL;
int ret;
if (tsp) {
if (compat_get_timespec64(&ts, tsp))
return -EFAULT;
to = &end_time;
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
return -EINVAL;
}
if (sigmask) {
if (sigsetsize != sizeof(compat_sigset_t))
return -EINVAL;
if (get_compat_sigset(&ksigmask, sigmask))
return -EFAULT;
sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
}
ret = do_sys_poll(ufds, nfds, to);
/* We can restart this syscall, usually */
if (ret == -EINTR) {
/*
* Don't restore the signal mask yet. Let do_signal() deliver
* the signal on the way back to userspace, before the signal
* mask is restored.
*/
if (sigmask) {
memcpy(&current->saved_sigmask, &sigsaved,
sizeof(sigsaved));
set_restore_sigmask();
}
ret = -ERESTARTNOHAND;
} else if (sigmask)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
return ret;
}
#endif