From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755098AbYLMBS0 (ORCPT ); Fri, 12 Dec 2008 20:18:26 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753337AbYLMBSR (ORCPT ); Fri, 12 Dec 2008 20:18:17 -0500 Received: from mail-bw0-f13.google.com ([209.85.218.13]:62853 "EHLO mail-bw0-f13.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752778AbYLMBSQ (ORCPT ); Fri, 12 Dec 2008 20:18:16 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=googlemail.com; s=gamma; h=message-id:date:from:reply-to:to:subject:cc:in-reply-to :mime-version:content-type:content-transfer-encoding :content-disposition:references; b=JAOjV7marN7PCCxivNLVc+mqq68h3v6NfH85sfVTOBZN8iRkuod99LeyR7q3qGE7Nc 3U6ieaH2CJjyvO/cvgq3FCeHisk/MeK9+4NAfqQ3WuPk6WnN8++uB33CjRrbdV7qelLs 379DMRlXXoRcGbZiWuGxSmdrdWe9G58OERvw4= Message-ID: Date: Fri, 12 Dec 2008 20:18:11 -0500 From: "Michael Kerrisk" Reply-To: mtk.manpages@gmail.com To: "Gerd Hoffmann" Subject: Re: [PATCH v2] Add preadv and pwritev system calls. Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, "Linux API" In-Reply-To: <1229090440-32120-1-git-send-email-kraxel@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <1229090440-32120-1-git-send-email-kraxel@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Gerd, Please CC linux-api on patches that change the API! Cheers, Michael On Fri, Dec 12, 2008 at 9:00 AM, Gerd Hoffmann wrote: > This patch adds preadv and pwritev system calls. These syscalls are a > pretty straightforward combination of pread and readv (same for write). > They are quite useful for doing vectored I/O in threaded applications. > Using lseek+readv instead opens race windows you'll have to plug with > locking. > > Other systems have such system calls too, for example NetBSD, check > here: http://www.daemon-systems.org/man/preadv.2.html > > The patch sports the actual system call implementation and the windup in > the x86 system call tables. Other archs are TBD. > > Signed-off-by: Gerd Hoffmann > --- > arch/x86/ia32/ia32entry.S | 2 + > arch/x86/include/asm/unistd_32.h | 2 + > arch/x86/include/asm/unistd_64.h | 4 ++ > arch/x86/kernel/syscall_table_32.S | 2 + > fs/compat.c | 61 ++++++++++++++++++++++++++++++++++++ > fs/read_write.c | 48 ++++++++++++++++++++++++++++ > 6 files changed, 119 insertions(+), 0 deletions(-) > > diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S > index 256b00b..9a8501b 100644 > --- a/arch/x86/ia32/ia32entry.S > +++ b/arch/x86/ia32/ia32entry.S > @@ -826,4 +826,6 @@ ia32_sys_call_table: > .quad sys_dup3 /* 330 */ > .quad sys_pipe2 > .quad sys_inotify_init1 > + .quad compat_sys_preadv > + .quad compat_sys_pwritev > ia32_syscall_end: > diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h > index f2bba78..6e72d74 100644 > --- a/arch/x86/include/asm/unistd_32.h > +++ b/arch/x86/include/asm/unistd_32.h > @@ -338,6 +338,8 @@ > #define __NR_dup3 330 > #define __NR_pipe2 331 > #define __NR_inotify_init1 332 > +#define __NR_preadv 333 > +#define __NR_pwritev 334 > > #ifdef __KERNEL__ > > diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h > index d2e415e..f818294 100644 > --- a/arch/x86/include/asm/unistd_64.h > +++ b/arch/x86/include/asm/unistd_64.h > @@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3) > __SYSCALL(__NR_pipe2, sys_pipe2) > #define __NR_inotify_init1 294 > __SYSCALL(__NR_inotify_init1, sys_inotify_init1) > +#define __NR_preadv 295 > +__SYSCALL(__NR_preadv, sys_preadv) > +#define __NR_pwritev 296 > +__SYSCALL(__NR_pwritev, sys_pwritev) > > > #ifndef __NO_STUBS > diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S > index d44395f..a1a5506 100644 > --- a/arch/x86/kernel/syscall_table_32.S > +++ b/arch/x86/kernel/syscall_table_32.S > @@ -332,3 +332,5 @@ ENTRY(sys_call_table) > .long sys_dup3 /* 330 */ > .long sys_pipe2 > .long sys_inotify_init1 > + .long sys_preadv > + .long sys_pwritev > diff --git a/fs/compat.c b/fs/compat.c > index e5f49f5..3a25cf3 100644 > --- a/fs/compat.c > +++ b/fs/compat.c > @@ -1214,6 +1214,67 @@ out: > return ret; > } > > +asmlinkage ssize_t > +compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, > + unsigned long vlen, loff_t pos) > +{ > + struct file *file; > + ssize_t ret = -EBADF; > + > + if (pos < 0) > + return -EINVAL; > + > + file = fget(fd); > + if (!file) > + return -EBADF; > + > + if (!(file->f_mode & FMODE_READ)) > + goto out; > + > + ret = -EINVAL; > + if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) > + goto out; > + > + ret = compat_do_readv_writev(READ, file, vec, vlen, &pos); > + > +out: > + if (ret > 0) > + add_rchar(current, ret); > + inc_syscr(current); > + fput(file); > + return ret; > +} > + > +asmlinkage ssize_t > +compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, > + unsigned long vlen, loff_t pos) > +{ > + struct file *file; > + ssize_t ret = -EBADF; > + > + if (pos < 0) > + return -EINVAL; > + > + file = fget(fd); > + if (!file) > + return -EBADF; > + if (!(file->f_mode & FMODE_WRITE)) > + goto out; > + > + ret = -EINVAL; > + if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) > + goto out; > + > + ret = compat_do_readv_writev(WRITE, file, vec, vlen, &pos); > + > +out: > + if (ret > 0) > + add_wchar(current, ret); > + inc_syscw(current); > + fput(file); > + return ret; > +} > + > asmlinkage long > compat_sys_vmsplice(int fd, const struct compat_iovec __user *iov32, > unsigned int nr_segs, unsigned int flags) > diff --git a/fs/read_write.c b/fs/read_write.c > index 969a6d9..89f273d 100644 > --- a/fs/read_write.c > +++ b/fs/read_write.c > @@ -701,6 +701,54 @@ sys_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen) > return ret; > } > > +asmlinkage ssize_t sys_preadv(unsigned long fd, const struct iovec __user *vec, > + unsigned long vlen, loff_t pos) > +{ > + struct file *file; > + ssize_t ret = -EBADF; > + int fput_needed; > + > + if (pos < 0) > + return -EINVAL; > + > + file = fget_light(fd, &fput_needed); > + if (file) { > + ret = -ESPIPE; > + if (file->f_mode & FMODE_PREAD) > + ret = vfs_readv(file, vec, vlen, &pos); > + fput_light(file, fput_needed); > + } > + > + if (ret > 0) > + add_rchar(current, ret); > + inc_syscr(current); > + return ret; > +} > + > +asmlinkage ssize_t sys_pwritev(unsigned long fd, const struct iovec __user *vec, > + unsigned long vlen, loff_t pos) > +{ > + struct file *file; > + ssize_t ret = -EBADF; > + int fput_needed; > + > + if (pos < 0) > + return -EINVAL; > + > + file = fget_light(fd, &fput_needed); > + if (file) { > + ret = -ESPIPE; > + if (file->f_mode & FMODE_PWRITE) > + ret = vfs_writev(file, vec, vlen, &pos); > + fput_light(file, fput_needed); > + } > + > + if (ret > 0) > + add_wchar(current, ret); > + inc_syscw(current); > + return ret; > +} > + > static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, > size_t count, loff_t max) > { > -- > 1.5.6.5 > > -- > To unsubscribe from this list: send the line "unsubscribe linux-arch" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- Michael Kerrisk Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/ git://git.kernel.org/pub/scm/docs/man-pages/man-pages.git man-pages online: http://www.kernel.org/doc/man-pages/online_pages.html Found a bug? http://www.kernel.org/doc/man-pages/reporting_bugs.html