linux/kernel/sys_ni.c

178 lines
5.0 KiB
C
Raw Normal View History

#include <linux/linkage.h>
#include <linux/errno.h>
#include <asm/unistd.h>
/* we can't #include <linux/syscalls.h> here,
but tell gcc to not warn with -Wmissing-prototypes */
asmlinkage long sys_ni_syscall(void);
/*
* Non-implemented system calls get redirected here.
*/
asmlinkage long sys_ni_syscall(void)
{
return -ENOSYS;
}
cond_syscall(sys_nfsservctl);
cond_syscall(sys_quotactl);
cond_syscall(sys32_quotactl);
cond_syscall(sys_acct);
cond_syscall(sys_lookup_dcookie);
cond_syscall(sys_swapon);
cond_syscall(sys_swapoff);
cond_syscall(sys_kexec_load);
cond_syscall(compat_sys_kexec_load);
cond_syscall(sys_init_module);
cond_syscall(sys_delete_module);
cond_syscall(sys_socketpair);
cond_syscall(sys_bind);
cond_syscall(sys_listen);
cond_syscall(sys_accept);
reintroduce accept4 Introduce a new accept4() system call. The addition of this system call matches analogous changes in 2.6.27 (dup3(), evenfd2(), signalfd4(), inotify_init1(), epoll_create1(), pipe2()) which added new system calls that differed from analogous traditional system calls in adding a flags argument that can be used to access additional functionality. The accept4() system call is exactly the same as accept(), except that it adds a flags bit-mask argument. Two flags are initially implemented. (Most of the new system calls in 2.6.27 also had both of these flags.) SOCK_CLOEXEC causes the close-on-exec (FD_CLOEXEC) flag to be enabled for the new file descriptor returned by accept4(). This is a useful security feature to avoid leaking information in a multithreaded program where one thread is doing an accept() at the same time as another thread is doing a fork() plus exec(). More details here: http://udrepper.livejournal.com/20407.html "Secure File Descriptor Handling", Ulrich Drepper). The other flag is SOCK_NONBLOCK, which causes the O_NONBLOCK flag to be enabled on the new open file description created by accept4(). (This flag is merely a convenience, saving the use of additional calls fcntl(F_GETFL) and fcntl (F_SETFL) to achieve the same result. Here's a test program. Works on x86-32. Should work on x86-64, but I (mtk) don't have a system to hand to test with. It tests accept4() with each of the four possible combinations of SOCK_CLOEXEC and SOCK_NONBLOCK set/clear in 'flags', and verifies that the appropriate flags are set on the file descriptor/open file description returned by accept4(). I tested Ulrich's patch in this thread by applying against 2.6.28-rc2, and it passes according to my test program. /* test_accept4.c Copyright (C) 2008, Linux Foundation, written by Michael Kerrisk <mtk.manpages@gmail.com> Licensed under the GNU GPLv2 or later. */ #define _GNU_SOURCE #include <unistd.h> #include <sys/syscall.h> #include <sys/socket.h> #include <netinet/in.h> #include <stdlib.h> #include <fcntl.h> #include <stdio.h> #include <string.h> #define PORT_NUM 33333 #define die(msg) do { perror(msg); exit(EXIT_FAILURE); } while (0) /**********************************************************************/ /* The following is what we need until glibc gets a wrapper for accept4() */ /* Flags for socket(), socketpair(), accept4() */ #ifndef SOCK_CLOEXEC #define SOCK_CLOEXEC O_CLOEXEC #endif #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif #ifdef __x86_64__ #define SYS_accept4 288 #elif __i386__ #define USE_SOCKETCALL 1 #define SYS_ACCEPT4 18 #else #error "Sorry -- don't know the syscall # on this architecture" #endif static int accept4(int fd, struct sockaddr *sockaddr, socklen_t *addrlen, int flags) { printf("Calling accept4(): flags = %x", flags); if (flags != 0) { printf(" ("); if (flags & SOCK_CLOEXEC) printf("SOCK_CLOEXEC"); if ((flags & SOCK_CLOEXEC) && (flags & SOCK_NONBLOCK)) printf(" "); if (flags & SOCK_NONBLOCK) printf("SOCK_NONBLOCK"); printf(")"); } printf("\n"); #if USE_SOCKETCALL long args[6]; args[0] = fd; args[1] = (long) sockaddr; args[2] = (long) addrlen; args[3] = flags; return syscall(SYS_socketcall, SYS_ACCEPT4, args); #else return syscall(SYS_accept4, fd, sockaddr, addrlen, flags); #endif } /**********************************************************************/ static int do_test(int lfd, struct sockaddr_in *conn_addr, int closeonexec_flag, int nonblock_flag) { int connfd, acceptfd; int fdf, flf, fdf_pass, flf_pass; struct sockaddr_in claddr; socklen_t addrlen; printf("=======================================\n"); connfd = socket(AF_INET, SOCK_STREAM, 0); if (connfd == -1) die("socket"); if (connect(connfd, (struct sockaddr *) conn_addr, sizeof(struct sockaddr_in)) == -1) die("connect"); addrlen = sizeof(struct sockaddr_in); acceptfd = accept4(lfd, (struct sockaddr *) &claddr, &addrlen, closeonexec_flag | nonblock_flag); if (acceptfd == -1) { perror("accept4()"); close(connfd); return 0; } fdf = fcntl(acceptfd, F_GETFD); if (fdf == -1) die("fcntl:F_GETFD"); fdf_pass = ((fdf & FD_CLOEXEC) != 0) == ((closeonexec_flag & SOCK_CLOEXEC) != 0); printf("Close-on-exec flag is %sset (%s); ", (fdf & FD_CLOEXEC) ? "" : "not ", fdf_pass ? "OK" : "failed"); flf = fcntl(acceptfd, F_GETFL); if (flf == -1) die("fcntl:F_GETFD"); flf_pass = ((flf & O_NONBLOCK) != 0) == ((nonblock_flag & SOCK_NONBLOCK) !=0); printf("nonblock flag is %sset (%s)\n", (flf & O_NONBLOCK) ? "" : "not ", flf_pass ? "OK" : "failed"); close(acceptfd); close(connfd); printf("Test result: %s\n", (fdf_pass && flf_pass) ? "PASS" : "FAIL"); return fdf_pass && flf_pass; } static int create_listening_socket(int port_num) { struct sockaddr_in svaddr; int lfd; int optval; memset(&svaddr, 0, sizeof(struct sockaddr_in)); svaddr.sin_family = AF_INET; svaddr.sin_addr.s_addr = htonl(INADDR_ANY); svaddr.sin_port = htons(port_num); lfd = socket(AF_INET, SOCK_STREAM, 0); if (lfd == -1) die("socket"); optval = 1; if (setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &optval, sizeof(optval)) == -1) die("setsockopt"); if (bind(lfd, (struct sockaddr *) &svaddr, sizeof(struct sockaddr_in)) == -1) die("bind"); if (listen(lfd, 5) == -1) die("listen"); return lfd; } int main(int argc, char *argv[]) { struct sockaddr_in conn_addr; int lfd; int port_num; int passed; passed = 1; port_num = (argc > 1) ? atoi(argv[1]) : PORT_NUM; memset(&conn_addr, 0, sizeof(struct sockaddr_in)); conn_addr.sin_family = AF_INET; conn_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); conn_addr.sin_port = htons(port_num); lfd = create_listening_socket(port_num); if (!do_test(lfd, &conn_addr, 0, 0)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, 0)) passed = 0; if (!do_test(lfd, &conn_addr, 0, SOCK_NONBLOCK)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, SOCK_NONBLOCK)) passed = 0; close(lfd); exit(passed ? EXIT_SUCCESS : EXIT_FAILURE); } [mtk.manpages@gmail.com: rewrote changelog, updated test program] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Tested-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-19 23:36:14 +00:00
cond_syscall(sys_accept4);
cond_syscall(sys_connect);
cond_syscall(sys_getsockname);
cond_syscall(sys_getpeername);
cond_syscall(sys_sendto);
cond_syscall(sys_send);
cond_syscall(sys_recvfrom);
cond_syscall(sys_recv);
cond_syscall(sys_socket);
cond_syscall(sys_setsockopt);
cond_syscall(compat_sys_setsockopt);
cond_syscall(sys_getsockopt);
cond_syscall(compat_sys_getsockopt);
cond_syscall(sys_shutdown);
cond_syscall(sys_sendmsg);
cond_syscall(compat_sys_sendmsg);
cond_syscall(sys_recvmsg);
cond_syscall(compat_sys_recvmsg);
cond_syscall(sys_socketcall);
cond_syscall(sys_futex);
cond_syscall(compat_sys_futex);
cond_syscall(sys_set_robust_list);
cond_syscall(compat_sys_set_robust_list);
cond_syscall(sys_get_robust_list);
cond_syscall(compat_sys_get_robust_list);
cond_syscall(sys_epoll_create);
cond_syscall(sys_epoll_create1);
cond_syscall(sys_epoll_ctl);
cond_syscall(sys_epoll_wait);
cond_syscall(sys_epoll_pwait);
cond_syscall(compat_sys_epoll_pwait);
cond_syscall(sys_semget);
cond_syscall(sys_semop);
cond_syscall(sys_semtimedop);
cond_syscall(sys_semctl);
cond_syscall(sys_msgget);
cond_syscall(sys_msgsnd);
cond_syscall(sys_msgrcv);
cond_syscall(sys_msgctl);
cond_syscall(sys_shmget);
cond_syscall(sys_shmat);
cond_syscall(sys_shmdt);
cond_syscall(sys_shmctl);
cond_syscall(sys_mq_open);
cond_syscall(sys_mq_unlink);
cond_syscall(sys_mq_timedsend);
cond_syscall(sys_mq_timedreceive);
cond_syscall(sys_mq_notify);
cond_syscall(sys_mq_getsetattr);
cond_syscall(compat_sys_mq_open);
cond_syscall(compat_sys_mq_timedsend);
cond_syscall(compat_sys_mq_timedreceive);
cond_syscall(compat_sys_mq_notify);
cond_syscall(compat_sys_mq_getsetattr);
cond_syscall(sys_mbind);
cond_syscall(sys_get_mempolicy);
cond_syscall(sys_set_mempolicy);
cond_syscall(compat_sys_mbind);
cond_syscall(compat_sys_get_mempolicy);
cond_syscall(compat_sys_set_mempolicy);
cond_syscall(sys_add_key);
cond_syscall(sys_request_key);
cond_syscall(sys_keyctl);
cond_syscall(compat_sys_keyctl);
cond_syscall(compat_sys_socketcall);
cond_syscall(sys_inotify_init);
flag parameters: inotify_init This patch introduces the new syscall inotify_init1 (note: the 1 stands for the one parameter the syscall takes, as opposed to no parameter before). The values accepted for this parameter are function-specific and defined in the inotify.h header. Here the values must match the O_* flags, though. In this patch CLOEXEC support is introduced. The following test must be adjusted for architectures other than x86 and x86-64 and in case the syscall numbers changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_inotify_init1 # ifdef __x86_64__ # define __NR_inotify_init1 294 # elif defined __i386__ # define __NR_inotify_init1 332 # else # error "need __NR_inotify_init1" # endif #endif #define IN_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = syscall (__NR_inotify_init1, 0); if (fd == -1) { puts ("inotify_init1(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("inotify_init1(0) set close-on-exit"); return 1; } close (fd); fd = syscall (__NR_inotify_init1, IN_CLOEXEC); if (fd == -1) { puts ("inotify_init1(IN_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("inotify_init1(O_CLOEXEC) does not set close-on-exit"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:32 +00:00
cond_syscall(sys_inotify_init1);
cond_syscall(sys_inotify_add_watch);
cond_syscall(sys_inotify_rm_watch);
[PATCH] Swap Migration V5: sys_migrate_pages interface sys_migrate_pages implementation using swap based page migration This is the original API proposed by Ray Bryant in his posts during the first half of 2005 on linux-mm@kvack.org and linux-kernel@vger.kernel.org. The intent of sys_migrate is to migrate memory of a process. A process may have migrated to another node. Memory was allocated optimally for the prior context. sys_migrate_pages allows to shift the memory to the new node. sys_migrate_pages is also useful if the processes available memory nodes have changed through cpuset operations to manually move the processes memory. Paul Jackson is working on an automated mechanism that will allow an automatic migration if the cpuset of a process is changed. However, a user may decide to manually control the migration. This implementation is put into the policy layer since it uses concepts and functions that are also needed for mbind and friends. The patch also provides a do_migrate_pages function that may be useful for cpusets to automatically move memory. sys_migrate_pages does not modify policies in contrast to Ray's implementation. The current code here is based on the swap based page migration capability and thus is not able to preserve the physical layout relative to it containing nodeset (which may be a cpuset). When direct page migration becomes available then the implementation needs to be changed to do a isomorphic move of pages between different nodesets. The current implementation simply evicts all pages in source nodeset that are not in the target nodeset. Patch supports ia64, i386 and x86_64. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-08 09:00:51 +00:00
cond_syscall(sys_migrate_pages);
[PATCH] page migration: sys_move_pages(): support moving of individual pages move_pages() is used to move individual pages of a process. The function can be used to determine the location of pages and to move them onto the desired node. move_pages() returns status information for each page. long move_pages(pid, number_of_pages_to_move, addresses_of_pages[], nodes[] or NULL, status[], flags); The addresses of pages is an array of void * pointing to the pages to be moved. The nodes array contains the node numbers that the pages should be moved to. If a NULL is passed instead of an array then no pages are moved but the status array is updated. The status request may be used to determine the page state before issuing another move_pages() to move pages. The status array will contain the state of all individual page migration attempts when the function terminates. The status array is only valid if move_pages() completed successfullly. Possible page states in status[]: 0..MAX_NUMNODES The page is now on the indicated node. -ENOENT Page is not present -EACCES Page is mapped by multiple processes and can only be moved if MPOL_MF_MOVE_ALL is specified. -EPERM The page has been mlocked by a process/driver and cannot be moved. -EBUSY Page is busy and cannot be moved. Try again later. -EFAULT Invalid address (no VMA or zero page). -ENOMEM Unable to allocate memory on target node. -EIO Unable to write back page. The page must be written back in order to move it since the page is dirty and the filesystem does not provide a migration function that would allow the moving of dirty pages. -EINVAL A dirty page cannot be moved. The filesystem does not provide a migration function and has no ability to write back pages. The flags parameter indicates what types of pages to move: MPOL_MF_MOVE Move pages that are only mapped by the process. MPOL_MF_MOVE_ALL Also move pages that are mapped by multiple processes. Requires sufficient capabilities. Possible return codes from move_pages() -ENOENT No pages found that would require moving. All pages are either already on the target node, not present, had an invalid address or could not be moved because they were mapped by multiple processes. -EINVAL Flags other than MPOL_MF_MOVE(_ALL) specified or an attempt to migrate pages in a kernel thread. -EPERM MPOL_MF_MOVE_ALL specified without sufficient priviledges. or an attempt to move a process belonging to another user. -EACCES One of the target nodes is not allowed by the current cpuset. -ENODEV One of the target nodes is not online. -ESRCH Process does not exist. -E2BIG Too many pages to move. -ENOMEM Not enough memory to allocate control array. -EFAULT Parameters could not be accessed. A test program for move_pages() may be found with the patches on ftp.kernel.org:/pub/linux/kernel/people/christoph/pmig/patches-2.6.17-rc4-mm3 From: Christoph Lameter <clameter@sgi.com> Detailed results for sys_move_pages() Pass a pointer to an integer to get_new_page() that may be used to indicate where the completion status of a migration operation should be placed. This allows sys_move_pags() to report back exactly what happened to each page. Wish there would be a better way to do this. Looks a bit hacky. Signed-off-by: Christoph Lameter <clameter@sgi.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Jes Sorensen <jes@trained-monkey.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Andi Kleen <ak@muc.de> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 09:03:55 +00:00
cond_syscall(sys_move_pages);
cond_syscall(sys_chown16);
cond_syscall(sys_fchown16);
cond_syscall(sys_getegid16);
cond_syscall(sys_geteuid16);
cond_syscall(sys_getgid16);
cond_syscall(sys_getgroups16);
cond_syscall(sys_getresgid16);
cond_syscall(sys_getresuid16);
cond_syscall(sys_getuid16);
cond_syscall(sys_lchown16);
cond_syscall(sys_setfsgid16);
cond_syscall(sys_setfsuid16);
cond_syscall(sys_setgid16);
cond_syscall(sys_setgroups16);
cond_syscall(sys_setregid16);
cond_syscall(sys_setresgid16);
cond_syscall(sys_setresuid16);
cond_syscall(sys_setreuid16);
cond_syscall(sys_setuid16);
cond_syscall(sys_vm86old);
cond_syscall(sys_vm86);
cond_syscall(compat_sys_ipc);
cond_syscall(compat_sys_sysctl);
cond_syscall(sys_flock);
cond_syscall(sys_io_setup);
cond_syscall(sys_io_destroy);
cond_syscall(sys_io_submit);
cond_syscall(sys_io_cancel);
cond_syscall(sys_io_getevents);
cond_syscall(sys_syslog);
/* arch-specific weak syscall entries */
cond_syscall(sys_pciconfig_read);
cond_syscall(sys_pciconfig_write);
cond_syscall(sys_pciconfig_iobase);
cond_syscall(sys32_ipc);
cond_syscall(sys32_sysctl);
cond_syscall(ppc_rtas);
cond_syscall(sys_spu_run);
cond_syscall(sys_spu_create);
[POWERPC] Provide a way to protect 4k subpages when using 64k pages Using 64k pages on 64-bit PowerPC systems makes life difficult for emulators that are trying to emulate an ISA, such as x86, which use a smaller page size, since the emulator can no longer use the MMU and the normal system calls for controlling page protections. Of course, the emulator can emulate the MMU by checking and possibly remapping the address for each memory access in software, but that is pretty slow. This provides a facility for such programs to control the access permissions on individual 4k sub-pages of 64k pages. The idea is that the emulator supplies an array of protection masks to apply to a specified range of virtual addresses. These masks are applied at the level where hardware PTEs are inserted into the hardware page table based on the Linux PTEs, so the Linux PTEs are not affected. Note that this new mechanism does not allow any access that would otherwise be prohibited; it can only prohibit accesses that would otherwise be allowed. This new facility is only available on 64-bit PowerPC and only when the kernel is configured for 64k pages. The masks are supplied using a new subpage_prot system call, which takes a starting virtual address and length, and a pointer to an array of protection masks in memory. The array has a 32-bit word per 64k page to be protected; each 32-bit word consists of 16 2-bit fields, for which 0 allows any access (that is otherwise allowed), 1 prevents write accesses, and 2 or 3 prevent any access. Implicit in this is that the regions of the address space that are protected are switched to use 4k hardware pages rather than 64k hardware pages (on machines with hardware 64k page support). In fact the whole process is switched to use 4k hardware pages when the subpage_prot system call is used, but this could be improved in future to switch only the affected segments. The subpage protection bits are stored in a 3 level tree akin to the page table tree. The top level of this tree is stored in a structure that is appended to the top level of the page table tree, i.e., the pgd array. Since it will often only be 32-bit addresses (below 4GB) that are protected, the pointers to the first four bottom level pages are also stored in this structure (each bottom level page contains the protection bits for 1GB of address space), so the protection bits for addresses below 4GB can be accessed with one fewer loads than those for higher addresses. Signed-off-by: Paul Mackerras <paulus@samba.org>
2008-01-23 21:35:13 +00:00
cond_syscall(sys_subpage_prot);
/* mmu depending weak syscall entries */
cond_syscall(sys_mprotect);
cond_syscall(sys_msync);
cond_syscall(sys_mlock);
cond_syscall(sys_munlock);
cond_syscall(sys_mlockall);
cond_syscall(sys_munlockall);
cond_syscall(sys_mincore);
cond_syscall(sys_madvise);
cond_syscall(sys_mremap);
cond_syscall(sys_remap_file_pages);
cond_syscall(compat_sys_move_pages);
cond_syscall(compat_sys_migrate_pages);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
/* block-layer dependent */
cond_syscall(sys_bdflush);
cond_syscall(sys_ioprio_set);
cond_syscall(sys_ioprio_get);
signal/timer/event: signalfd core This patch series implements the new signalfd() system call. I took part of the original Linus code (and you know how badly it can be broken :), and I added even more breakage ;) Signals are fetched from the same signal queue used by the process, so signalfd will compete with standard kernel delivery in dequeue_signal(). If you want to reliably fetch signals on the signalfd file, you need to block them with sigprocmask(SIG_BLOCK). This seems to be working fine on my Dual Opteron machine. I made a quick test program for it: http://www.xmailserver.org/signafd-test.c The signalfd() system call implements signal delivery into a file descriptor receiver. The signalfd file descriptor if created with the following API: int signalfd(int ufd, const sigset_t *mask, size_t masksize); The "ufd" parameter allows to change an existing signalfd sigmask, w/out going to close/create cycle (Linus idea). Use "ufd" == -1 if you want a brand new signalfd file. The "mask" allows to specify the signal mask of signals that we are interested in. The "masksize" parameter is the size of "mask". The signalfd fd supports the poll(2) and read(2) system calls. The poll(2) will return POLLIN when signals are available to be dequeued. As a direct consequence of supporting the Linux poll subsystem, the signalfd fd can use used together with epoll(2) too. The read(2) system call will return a "struct signalfd_siginfo" structure in the userspace supplied buffer. The return value is the number of bytes copied in the supplied buffer, or -1 in case of error. The read(2) call can also return 0, in case the sighand structure to which the signalfd was attached, has been orphaned. The O_NONBLOCK flag is also supported, and read(2) will return -EAGAIN in case no signal is available. If the size of the buffer passed to read(2) is lower than sizeof(struct signalfd_siginfo), -EINVAL is returned. A read from the signalfd can also return -ERESTARTSYS in case a signal hits the process. The format of the struct signalfd_siginfo is, and the valid fields depends of the (->code & __SI_MASK) value, in the same way a struct siginfo would: struct signalfd_siginfo { __u32 signo; /* si_signo */ __s32 err; /* si_errno */ __s32 code; /* si_code */ __u32 pid; /* si_pid */ __u32 uid; /* si_uid */ __s32 fd; /* si_fd */ __u32 tid; /* si_fd */ __u32 band; /* si_band */ __u32 overrun; /* si_overrun */ __u32 trapno; /* si_trapno */ __s32 status; /* si_status */ __s32 svint; /* si_int */ __u64 svptr; /* si_ptr */ __u64 utime; /* si_utime */ __u64 stime; /* si_stime */ __u64 addr; /* si_addr */ }; [akpm@linux-foundation.org: fix signalfd_copyinfo() on i386] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-11 05:23:13 +00:00
/* New file descriptors */
cond_syscall(sys_signalfd);
flag parameters: signalfd This patch adds the new signalfd4 syscall. It extends the old signalfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is SFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name SFD_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 <fcntl.h> #include <signal.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_signalfd4 # ifdef __x86_64__ # define __NR_signalfd4 289 # elif defined __i386__ # define __NR_signalfd4 327 # else # error "need __NR_signalfd4" # endif #endif #define SFD_CLOEXEC O_CLOEXEC int main (void) { sigset_t ss; sigemptyset (&ss); sigaddset (&ss, SIGUSR1); int fd = syscall (__NR_signalfd4, -1, &ss, 8, 0); if (fd == -1) { puts ("signalfd4(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("signalfd4(0) set close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_signalfd4, -1, &ss, 8, SFD_CLOEXEC); if (fd == -1) { puts ("signalfd4(SFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("signalfd4(SFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:24 +00:00
cond_syscall(sys_signalfd4);
cond_syscall(compat_sys_signalfd);
cond_syscall(compat_sys_signalfd4);
timerfd: new timerfd API This is the new timerfd API as it is implemented by the following patch: int timerfd_create(int clockid, int flags); int timerfd_settime(int ufd, int flags, const struct itimerspec *utmr, struct itimerspec *otmr); int timerfd_gettime(int ufd, struct itimerspec *otmr); The timerfd_create() API creates an un-programmed timerfd fd. The "clockid" parameter can be either CLOCK_MONOTONIC or CLOCK_REALTIME. The timerfd_settime() API give new settings by the timerfd fd, by optionally retrieving the previous expiration time (in case the "otmr" parameter is not NULL). The time value specified in "utmr" is absolute, if the TFD_TIMER_ABSTIME bit is set in the "flags" parameter. Otherwise it's a relative time. The timerfd_gettime() API returns the next expiration time of the timer, or {0, 0} if the timerfd has not been set yet. Like the previous timerfd API implementation, read(2) and poll(2) are supported (with the same interface). Here's a simple test program I used to exercise the new timerfd APIs: http://www.xmailserver.org/timerfd-test2.c [akpm@linux-foundation.org: coding-style cleanups] [akpm@linux-foundation.org: fix ia64 build] [akpm@linux-foundation.org: fix m68k build] [akpm@linux-foundation.org: fix mips build] [akpm@linux-foundation.org: fix alpha, arm, blackfin, cris, m68k, s390, sparc and sparc64 builds] [heiko.carstens@de.ibm.com: fix s390] [akpm@linux-foundation.org: fix powerpc build] [akpm@linux-foundation.org: fix sparc64 more] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 06:27:26 +00:00
cond_syscall(sys_timerfd_create);
cond_syscall(sys_timerfd_settime);
cond_syscall(sys_timerfd_gettime);
cond_syscall(compat_sys_timerfd_settime);
cond_syscall(compat_sys_timerfd_gettime);
signal/timer/event: eventfd core This is a very simple and light file descriptor, that can be used as event wait/dispatch by userspace (both wait and dispatch) and by the kernel (dispatch only). It can be used instead of pipe(2) in all cases where those would simply be used to signal events. Their kernel overhead is much lower than pipes, and they do not consume two fds. When used in the kernel, it can offer an fd-bridge to enable, for example, functionalities like KAIO or syslets/threadlets to signal to an fd the completion of certain operations. But more in general, an eventfd can be used by the kernel to signal readiness, in a POSIX poll/select way, of interfaces that would otherwise be incompatible with it. The API is: int eventfd(unsigned int count); The eventfd API accepts an initial "count" parameter, and returns an eventfd fd. It supports poll(2) (POLLIN, POLLOUT, POLLERR), read(2) and write(2). The POLLIN flag is raised when the internal counter is greater than zero. The POLLOUT flag is raised when at least a value of "1" can be written to the internal counter. The POLLERR flag is raised when an overflow in the counter value is detected. The write(2) operation can never overflow the counter, since it blocks (unless O_NONBLOCK is set, in which case -EAGAIN is returned). But the eventfd_signal() function can do it, since it's supposed to not sleep during its operation. The read(2) function reads the __u64 counter value, and reset the internal value to zero. If the value read is equal to (__u64) -1, an overflow happened on the internal counter (due to 2^64 eventfd_signal() posts that has never been retired - unlickely, but possible). The write(2) call writes an __u64 count value, and adds it to the current counter. The eventfd fd supports O_NONBLOCK also. On the kernel side, we have: struct file *eventfd_fget(int fd); int eventfd_signal(struct file *file, unsigned int n); The eventfd_fget() should be called to get a struct file* from an eventfd fd (this is an fget() + check of f_op being an eventfd fops pointer). The kernel can then call eventfd_signal() every time it wants to post an event to userspace. The eventfd_signal() function can be called from any context. An eventfd() simple test and bench is available here: http://www.xmailserver.org/eventfd-bench.c This is the eventfd-based version of pipetest-4 (pipe(2) based): http://www.xmailserver.org/pipetest-4.c Not that performance matters much in the eventfd case, but eventfd-bench shows almost as double as performance than pipetest-4. [akpm@linux-foundation.org: fix i386 build] [akpm@linux-foundation.org: add sys_eventfd to sys_ni.c] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-11 05:23:19 +00:00
cond_syscall(sys_eventfd);
flag parameters: eventfd This patch adds the new eventfd2 syscall. It extends the old eventfd syscall by one parameter which is meant to hold a flag value. In this patch the only flag support is EFD_CLOEXEC which causes the close-on-exec flag for the returned file descriptor to be set. A new name EFD_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 <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/syscall.h> #ifndef __NR_eventfd2 # ifdef __x86_64__ # define __NR_eventfd2 290 # elif defined __i386__ # define __NR_eventfd2 328 # else # error "need __NR_eventfd2" # endif #endif #define EFD_CLOEXEC O_CLOEXEC int main (void) { int fd = syscall (__NR_eventfd2, 1, 0); if (fd == -1) { puts ("eventfd2(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("eventfd2(0) sets close-on-exec flag"); return 1; } close (fd); fd = syscall (__NR_eventfd2, 1, EFD_CLOEXEC); if (fd == -1) { puts ("eventfd2(EFD_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("eventfd2(EFD_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [akpm@linux-foundation.org: add sys_ni stub] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 04:29:25 +00:00
cond_syscall(sys_eventfd2);