From: Fam Zheng <famz@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
x86@kernel.org, Alexander Viro <viro@zeniv.linux.org.uk>,
Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <keescook@chromium.org>,
Andy Lutomirski <luto@amacapital.net>,
David Herrmann <dh.herrmann@gmail.com>,
Alexei Starovoitov <ast@plumgrid.com>,
Miklos Szeredi <mszeredi@suse.cz>,
David Drysdale <drysdale@google.com>,
Oleg Nesterov <oleg@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Vivek Goyal <vgoyal@redhat.com>,
Mike Frysinger <vapier@gentoo.org>,
"Theodore Ts'o" <tytso@mit.edu>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Rasmus Villemoes <linux@rasmusvillemoes.dk>,
Rashika Kheria <rashika.kheria@gmail.com>,
Hugh Dickins <hughd@google.com>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Fam Zheng <famz@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
linux-fsdevel@vger.kernel.org, linux-api@vger.kernel.org,
Josh Triplett <josh@joshtriplett.org>,
"Michael Kerrisk (man-pages)" <mtk.manpages@gmail.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Omar Sandoval <osandov@osandov.com>,
Jonathan Corbet <corbet@lwn.net>,
shane.seymour@hp.com, dan.j.rosenberg@gmail.com
Subject: [PATCH v4 4/9] epoll: Add implementation for epoll_ctl_batch
Date: Tue, 10 Mar 2015 09:49:10 +0800 [thread overview]
Message-ID: <1425952155-27603-5-git-send-email-famz@redhat.com> (raw)
In-Reply-To: <1425952155-27603-1-git-send-email-famz@redhat.com>
This new syscall is a batched version of epoll_ctl. It will execute each
command as specified in cmds in given order, and stop at first failure
or upon completion of all commands.
Signed-off-by: Fam Zheng <famz@redhat.com>
---
fs/eventpoll.c | 50 ++++++++++++++++++++++++++++++++++++++++++
include/linux/syscalls.h | 4 ++++
include/uapi/linux/eventpoll.h | 11 ++++++++++
3 files changed, 65 insertions(+)
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7909c88..54dc63f 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -99,6 +99,8 @@
#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
+#define EP_MAX_BATCH (INT_MAX / sizeof(struct epoll_ctl_cmd))
+
#define EP_UNACTIVE_PTR ((void *) -1L)
#define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry))
@@ -2069,6 +2071,54 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
sigmask ? &ksigmask : NULL);
}
+SYSCALL_DEFINE4(epoll_ctl_batch, int, epfd, int, flags,
+ int, ncmds, struct epoll_ctl_cmd __user *, cmds)
+{
+ struct epoll_ctl_cmd *kcmds = NULL;
+ int i, ret = 0;
+ size_t cmd_size;
+
+ if (flags)
+ return -EINVAL;
+ if (!cmds || ncmds <= 0 || ncmds > EP_MAX_BATCH)
+ return -EINVAL;
+ cmd_size = sizeof(struct epoll_ctl_cmd) * ncmds;
+ /* TODO: optimize for small arguments like select/poll with a stack
+ * allocated buffer */
+
+ kcmds = kmalloc(cmd_size, GFP_KERNEL);
+ if (!kcmds)
+ return -ENOMEM;
+ if (copy_from_user(kcmds, cmds, cmd_size)) {
+ ret = -EFAULT;
+ goto out;
+ }
+ for (i = 0; i < ncmds; i++) {
+ struct epoll_event ev = (struct epoll_event) {
+ .events = kcmds[i].events,
+ .data = kcmds[i].data,
+ };
+ if (kcmds[i].flags) {
+ kcmds[i].result = -EINVAL;
+ goto copy;
+ }
+ kcmds[i].result = ep_ctl_do(epfd, kcmds[i].op,
+ kcmds[i].fd, ev);
+ if (kcmds[i].result)
+ goto copy;
+ ret++;
+ }
+copy:
+ /* We lose the number of succeeded commands in favor of returning
+ * -EFAULT, but in this case the application will want to fix the
+ * memory bug first. */
+ if (copy_to_user(cmds, kcmds, cmd_size))
+ ret = -EFAULT;
+out:
+ kfree(kcmds);
+ return ret;
+}
+
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd,
struct epoll_event __user *, events,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 76d1e38..7d784e3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -12,6 +12,7 @@
#define _LINUX_SYSCALLS_H
struct epoll_event;
+struct epoll_ctl_cmd;
struct iattr;
struct inode;
struct iocb;
@@ -634,6 +635,9 @@ asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
int maxevents, int timeout,
const sigset_t __user *sigmask,
size_t sigsetsize);
+asmlinkage long sys_epoll_ctl_batch(int epfd, int flags,
+ int ncmds,
+ struct epoll_ctl_cmd __user *cmds);
asmlinkage long sys_gethostname(char __user *name, int len);
asmlinkage long sys_sethostname(char __user *name, int len);
asmlinkage long sys_setdomainname(char __user *name, int len);
diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h
index bc81fb2..4e18b17 100644
--- a/include/uapi/linux/eventpoll.h
+++ b/include/uapi/linux/eventpoll.h
@@ -18,6 +18,8 @@
#include <linux/fcntl.h>
#include <linux/types.h>
+#include <linux/signal.h>
+
/* Flags for epoll_create1. */
#define EPOLL_CLOEXEC O_CLOEXEC
@@ -61,6 +63,15 @@ struct epoll_event {
__u64 data;
} EPOLL_PACKED;
+struct epoll_ctl_cmd {
+ int flags;
+ int op;
+ int fd;
+ __u32 events;
+ __u64 data;
+ int result;
+} EPOLL_PACKED;
+
#ifdef CONFIG_PM_SLEEP
static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev)
{
--
1.9.3
next prev parent reply other threads:[~2015-03-10 1:51 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-03-10 1:49 [PATCH v4 0/9] epoll: Introduce new syscalls, epoll_ctl_batch and epoll_pwait1 Fam Zheng
2015-03-10 1:49 ` [PATCH v4 1/9] epoll: Extract epoll_wait_do and epoll_pwait_do Fam Zheng
2015-03-10 1:49 ` [PATCH v4 2/9] epoll: Specify clockid explicitly Fam Zheng
2015-03-10 1:49 ` [PATCH v4 3/9] epoll: Extract ep_ctl_do Fam Zheng
2015-03-10 1:49 ` Fam Zheng [this message]
2015-03-10 13:59 ` [PATCH v4 4/9] epoll: Add implementation for epoll_ctl_batch Dan Rosenberg
2015-03-11 2:23 ` Fam Zheng
2015-03-10 1:49 ` [PATCH v4 5/9] x86: Hook up epoll_ctl_batch syscall Fam Zheng
2015-03-10 1:49 ` [PATCH v4 6/9] epoll: Add implementation for epoll_pwait1 Fam Zheng
2015-03-10 1:49 ` [PATCH v4 7/9] x86: Hook up epoll_pwait1 syscall Fam Zheng
2015-03-10 1:49 ` [PATCH v4 8/9] epoll: Add compat version implementation of epoll_pwait1 Fam Zheng
2015-03-10 1:49 ` [PATCH v4 9/9] x86: Hook up 32 bit compat epoll_pwait1 syscall Fam Zheng
2015-03-12 15:02 ` [PATCH v4 0/9] epoll: Introduce new syscalls, epoll_ctl_batch and epoll_pwait1 Jason Baron
2015-03-13 11:31 ` Fam Zheng
2015-03-13 14:46 ` Jason Baron
2015-03-13 14:56 ` Paolo Bonzini
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1425952155-27603-5-git-send-email-famz@redhat.com \
--to=famz@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=ast@plumgrid.com \
--cc=corbet@lwn.net \
--cc=dan.j.rosenberg@gmail.com \
--cc=davem@davemloft.net \
--cc=dh.herrmann@gmail.com \
--cc=drysdale@google.com \
--cc=heiko.carstens@de.ibm.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=josh@joshtriplett.org \
--cc=keescook@chromium.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@rasmusvillemoes.dk \
--cc=luto@amacapital.net \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@redhat.com \
--cc=mszeredi@suse.cz \
--cc=mtk.manpages@gmail.com \
--cc=oleg@redhat.com \
--cc=osandov@osandov.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=rashika.kheria@gmail.com \
--cc=shane.seymour@hp.com \
--cc=tglx@linutronix.de \
--cc=tytso@mit.edu \
--cc=vapier@gentoo.org \
--cc=vgoyal@redhat.com \
--cc=viro@zeniv.linux.org.uk \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).