From 7d9dbca34240ebb6ff88d8a29c6c7bffd098f0c1 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:22 -0700 Subject: flag parameters: anon_inode_getfd extension This patch just extends the anon_inode_getfd interface to take an additional parameter with a flag value. The flag value is passed on to get_unused_fd_flags in anticipation for a use with the O_CLOEXEC flag. No actual semantic changes here, the changed callers all pass 0 for now. [akpm@linux-foundation.org: KVM fix] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/eventpoll.c') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 990c01d2d66..9392dd96812 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1068,7 +1068,7 @@ asmlinkage long sys_epoll_create(int size) * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ - fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep); + fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep, 0); if (fd < 0) ep_free(ep); -- cgit v1.2.3-70-g09d2 From a0998b50c3f0b8fdd265c63e0032f86ebe377dbf Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:27 -0700 Subject: flag parameters: epoll_create This patch adds the new epoll_create2 syscall. It extends the old epoll_create syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EPOLL_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EPOLL_CLOEXEC is introduced which in this implementation must have the same value as O_CLOEXEC. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 1, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, 1, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 1 + arch/x86/kernel/syscall_table_32.S | 1 + fs/eventpoll.c | 13 +++++++++++-- include/asm-x86/unistd_32.h | 1 + include/asm-x86/unistd_64.h | 2 ++ include/linux/eventpoll.h | 4 ++++ include/linux/syscalls.h | 1 + 7 files changed, 21 insertions(+), 2 deletions(-) (limited to 'fs/eventpoll.c') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index cf0eb31745c..04366f08f42 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -828,4 +828,5 @@ ia32_sys_call_table: .quad compat_sys_timerfd_gettime .quad compat_sys_signalfd4 .quad sys_eventfd2 + .quad sys_epoll_create2 ia32_syscall_end: diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index cf112cb11c3..4d7007ca263 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -328,3 +328,4 @@ ENTRY(sys_call_table) .long sys_timerfd_gettime .long sys_signalfd4 .long sys_eventfd2 + .long sys_epoll_create2 diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 9392dd96812..3fd4014f3c5 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1046,11 +1046,14 @@ retry: * RB tree. With the current implementation, the "size" parameter is ignored * (besides sanity checks). */ -asmlinkage long sys_epoll_create(int size) +asmlinkage long sys_epoll_create2(int size, int flags) { int error, fd = -1; struct eventpoll *ep; + if (flags & ~EPOLL_CLOEXEC) + return -EINVAL; + DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n", current, size)); @@ -1068,7 +1071,8 @@ asmlinkage long sys_epoll_create(int size) * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ - fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep, 0); + fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep, + flags & O_CLOEXEC); if (fd < 0) ep_free(ep); @@ -1079,6 +1083,11 @@ error_return: return fd; } +asmlinkage long sys_epoll_create(int size) +{ + return sys_epoll_create2(size, 0); +} + /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index edbd8723c93..a37d6b0c4e1 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -334,6 +334,7 @@ #define __NR_timerfd_gettime 326 #define __NR_signalfd4 327 #define __NR_eventfd2 328 +#define __NR_epoll_create2 329 #ifdef __KERNEL__ diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index fb059a6feeb..a1a4a5b6e5e 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -645,6 +645,8 @@ __SYSCALL(__NR_paccept, sys_paccept) __SYSCALL(__NR_signalfd4, sys_signalfd4) #define __NR_eventfd2 290 __SYSCALL(__NR_eventfd2, sys_eventfd2) +#define __NR_epoll_create2 291 +__SYSCALL(__NR_epoll_create2, sys_epoll_create2) #ifndef __NO_STUBS diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index cf79853967f..1cfaa40059c 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,8 +14,12 @@ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H +/* For O_CLOEXEC */ +#include #include +/* Flags for epoll_create2. */ +#define EPOLL_CLOEXEC O_CLOEXEC /* Valid opcodes to issue to sys_epoll_ctl() */ #define EPOLL_CTL_ADD 1 diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 9ab09926a7f..85953240f28 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -430,6 +430,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_epoll_create(int size); +asmlinkage long sys_epoll_create2(int size, int flags); asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, -- cgit v1.2.3-70-g09d2 From e38b36f325153eaadd1c2a7abc5762079233e540 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:42 -0700 Subject: flag parameters: check magic constants This patch adds test that ensure the boundary conditions for the various constants introduced in the previous patches is met. No code is generated. [akpm@linux-foundation.org: fix alpha] Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventfd.c | 4 ++++ fs/eventpoll.c | 3 +++ fs/inotify_user.c | 4 ++++ fs/signalfd.c | 4 ++++ fs/timerfd.c | 4 ++++ net/socket.c | 6 ++++++ 6 files changed, 25 insertions(+) (limited to 'fs/eventpoll.c') diff --git a/fs/eventfd.c b/fs/eventfd.c index 3ed4466177a..08bf558d040 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -203,6 +203,10 @@ asmlinkage long sys_eventfd2(unsigned int count, int flags) int fd; struct eventfd_ctx *ctx; + /* Check the EFD_* constants for consistency. */ + BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC); + BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK); + if (flags & ~(EFD_CLOEXEC | EFD_NONBLOCK)) return -EINVAL; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3fd4014f3c5..2fdad420404 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1051,6 +1051,9 @@ asmlinkage long sys_epoll_create2(int size, int flags) int error, fd = -1; struct eventpoll *ep; + /* Check the EPOLL_* constant for consistency. */ + BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); + if (flags & ~EPOLL_CLOEXEC) return -EINVAL; diff --git a/fs/inotify_user.c b/fs/inotify_user.c index dc7e1f61974..fe79c25d95d 100644 --- a/fs/inotify_user.c +++ b/fs/inotify_user.c @@ -574,6 +574,10 @@ asmlinkage long sys_inotify_init1(int flags) struct file *filp; int fd, ret; + /* Check the IN_* constants for consistency. */ + BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC); + BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK); + if (flags & ~(IN_CLOEXEC | IN_NONBLOCK)) return -EINVAL; diff --git a/fs/signalfd.c b/fs/signalfd.c index 5441a4bca77..9c39bc7f843 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -211,6 +211,10 @@ asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask, sigset_t sigmask; struct signalfd_ctx *ctx; + /* Check the SFD_* constants for consistency. */ + BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC); + BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK); + if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK)) return -EINVAL; diff --git a/fs/timerfd.c b/fs/timerfd.c index 75d44efe346..c502c60e4f5 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -184,6 +184,10 @@ asmlinkage long sys_timerfd_create(int clockid, int flags) int ufd; struct timerfd_ctx *ctx; + /* Check the TFD_* constants for consistency. */ + BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC); + BUILD_BUG_ON(TFD_NONBLOCK != O_NONBLOCK); + if (flags & ~(TFD_CLOEXEC | TFD_NONBLOCK)) return -EINVAL; if (clockid != CLOCK_MONOTONIC && diff --git a/net/socket.c b/net/socket.c index 31105f9048a..1310a82cbba 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1222,6 +1222,12 @@ asmlinkage long sys_socket(int family, int type, int protocol) struct socket *sock; int flags; + /* Check the SOCK_* constants for consistency. */ + BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); + BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); + BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); + BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); + flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; -- cgit v1.2.3-70-g09d2 From 9fe5ad9c8cef9ad5873d8ee55d1cf00d9b607df0 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 23 Jul 2008 21:29:43 -0700 Subject: flag parameters add-on: remove epoll_create size param Remove the size parameter from the new epoll_create syscall and renames the syscall itself. The updated test program follows. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include #include #include #include #include #ifndef __NR_epoll_create2 # ifdef __x86_64__ # define __NR_epoll_create2 291 # elif defined __i386__ # define __NR_epoll_create2 329 # else # error "need __NR_epoll_create2" # endif #endif #define EPOLL_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_epoll_create2, 0); if (fd == -1) { puts ("epoll_create2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("epoll_create2(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_epoll_create2, EPOLL_CLOEXEC); if (fd == -1) { puts ("epoll_create2(EPOLL_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("epoll_create2(EPOLL_CLOEXEC) set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper Acked-by: Davide Libenzi Cc: Michael Kerrisk Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/ia32/ia32entry.S | 2 +- arch/x86/kernel/syscall_table_32.S | 2 +- fs/eventpoll.c | 18 ++++++++++-------- include/asm-x86/unistd_32.h | 2 +- include/asm-x86/unistd_64.h | 4 ++-- include/linux/eventpoll.h | 2 +- include/linux/syscalls.h | 2 +- 7 files changed, 17 insertions(+), 15 deletions(-) (limited to 'fs/eventpoll.c') diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 4541073dd83..e4bd1793a5e 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -828,7 +828,7 @@ ia32_sys_call_table: .quad compat_sys_timerfd_gettime .quad compat_sys_signalfd4 .quad sys_eventfd2 - .quad sys_epoll_create2 + .quad sys_epoll_create1 .quad sys_dup3 /* 330 */ .quad sys_pipe2 .quad sys_inotify_init1 diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S index f59aba5ff0f..d44395ff34c 100644 --- a/arch/x86/kernel/syscall_table_32.S +++ b/arch/x86/kernel/syscall_table_32.S @@ -328,7 +328,7 @@ ENTRY(sys_call_table) .long sys_timerfd_gettime .long sys_signalfd4 .long sys_eventfd2 - .long sys_epoll_create2 + .long sys_epoll_create1 .long sys_dup3 /* 330 */ .long sys_pipe2 .long sys_inotify_init1 diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 2fdad420404..0c87474f791 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1046,7 +1046,7 @@ retry: * RB tree. With the current implementation, the "size" parameter is ignored * (besides sanity checks). */ -asmlinkage long sys_epoll_create2(int size, int flags) +asmlinkage long sys_epoll_create1(int flags) { int error, fd = -1; struct eventpoll *ep; @@ -1058,14 +1058,13 @@ asmlinkage long sys_epoll_create2(int size, int flags) return -EINVAL; DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n", - current, size)); + current, flags)); /* - * Sanity check on the size parameter, and create the internal data - * structure ( "struct eventpoll" ). + * Create the internal data structure ( "struct eventpoll" ). */ - error = -EINVAL; - if (size <= 0 || (error = ep_alloc(&ep)) < 0) { + error = ep_alloc(&ep); + if (error < 0) { fd = error; goto error_return; } @@ -1081,14 +1080,17 @@ asmlinkage long sys_epoll_create2(int size, int flags) error_return: DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n", - current, size, fd)); + current, flags, fd)); return fd; } asmlinkage long sys_epoll_create(int size) { - return sys_epoll_create2(size, 0); + if (size < 0) + return -EINVAL; + + return sys_epoll_create1(0); } /* diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h index b3daf503ab9..d7394673b77 100644 --- a/include/asm-x86/unistd_32.h +++ b/include/asm-x86/unistd_32.h @@ -334,7 +334,7 @@ #define __NR_timerfd_gettime 326 #define __NR_signalfd4 327 #define __NR_eventfd2 328 -#define __NR_epoll_create2 329 +#define __NR_epoll_create1 329 #define __NR_dup3 330 #define __NR_pipe2 331 #define __NR_inotify_init1 332 diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h index c8cb88d70c6..3a341d79179 100644 --- a/include/asm-x86/unistd_64.h +++ b/include/asm-x86/unistd_64.h @@ -645,8 +645,8 @@ __SYSCALL(__NR_paccept, sys_paccept) __SYSCALL(__NR_signalfd4, sys_signalfd4) #define __NR_eventfd2 290 __SYSCALL(__NR_eventfd2, sys_eventfd2) -#define __NR_epoll_create2 291 -__SYSCALL(__NR_epoll_create2, sys_epoll_create2) +#define __NR_epoll_create1 291 +__SYSCALL(__NR_epoll_create1, sys_epoll_create1) #define __NR_dup3 292 __SYSCALL(__NR_dup3, sys_dup3) #define __NR_pipe2 293 diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 1cfaa40059c..f1e1d3c4712 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -18,7 +18,7 @@ #include #include -/* Flags for epoll_create2. */ +/* Flags for epoll_create1. */ #define EPOLL_CLOEXEC O_CLOEXEC /* Valid opcodes to issue to sys_epoll_ctl() */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 93a7e7f017a..06f2bf76c03 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -431,7 +431,7 @@ asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp); asmlinkage long sys_epoll_create(int size); -asmlinkage long sys_epoll_create2(int size, int flags); +asmlinkage long sys_epoll_create1(int flags); asmlinkage long sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event); asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events, -- cgit v1.2.3-70-g09d2