From e11d4284e2f4de5048c6d1787c82226f0a198292 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 18 Apr 2018 13:43:52 +0200 Subject: y2038: socket: Add compat_sys_recvmmsg_time64 recvmmsg() takes two arguments to pointers of structures that differ between 32-bit and 64-bit architectures: mmsghdr and timespec. For y2038 compatbility, we are changing the native system call from timespec to __kernel_timespec with a 64-bit time_t (in another patch), and use the existing compat system call on both 32-bit and 64-bit architectures for compatibility with traditional 32-bit user space. As we now have two variants of recvmmsg() for 32-bit tasks that are both different from the variant that we use on 64-bit tasks, this means we also require two compat system calls! The solution I picked is to flip things around: The existing compat_sys_recvmmsg() call gets moved from net/compat.c into net/socket.c and now handles the case for old user space on all architectures that have set CONFIG_COMPAT_32BIT_TIME. A new compat_sys_recvmmsg_time64() call gets added in the old place for 64-bit architectures only, this one handles the case of a compat mmsghdr structure combined with __kernel_timespec. In the indirect sys_socketcall(), we now need to call either do_sys_recvmmsg() or __compat_sys_recvmmsg(), depending on what kind of architecture we are on. For compat_sys_socketcall(), no such change is needed, we always call __compat_sys_recvmmsg(). I decided to not add a new SYS_RECVMMSG_TIME64 socketcall: Any libc implementation for 64-bit time_t will need significant changes including an updated asm/unistd.h, and it seems better to consistently use the separate syscalls that configuration, leaving the socketcall only for backward compatibility with 32-bit time_t based libc. The naming is asymmetric for the moment, so both existing syscalls entry points keep their names, while the new ones are recvmmsg_time32 and compat_recvmmsg_time64 respectively. I expect that we will rename the compat syscalls later as we start using generated syscall tables everywhere and add these entry points. Signed-off-by: Arnd Bergmann --- include/linux/socket.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux/socket.h') diff --git a/include/linux/socket.h b/include/linux/socket.h index 8b571e9b9f76..333b5df8a1b2 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -348,7 +348,8 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); -struct timespec64; +struct __kernel_timespec; +struct old_timespec32; /* The __sys_...msg variants allow MSG_CMSG_COMPAT iff * forbid_cmsg_compat==false @@ -357,8 +358,10 @@ extern long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat); extern long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat); -extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags, struct timespec64 *timeout); +extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, + unsigned int vlen, unsigned int flags, + struct __kernel_timespec __user *timeout, + struct old_timespec32 __user *timeout32); extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat); -- cgit v1.2.3 From 0608c69c9a805c6264689d7eab4203eab88cf1da Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Thu, 20 Dec 2018 11:35:35 -0800 Subject: bpf: sk_msg, sock{map|hash} redirect through ULP A sockmap program that redirects through a kTLS ULP enabled socket will not work correctly because the ULP layer is skipped. This fixes the behavior to call through the ULP layer on redirect to ensure any operations required on the data stream at the ULP layer continue to be applied. To do this we add an internal flag MSG_SENDPAGE_NOPOLICY to avoid calling the BPF layer on a redirected message. This is required to avoid calling the BPF layer multiple times (possibly recursively) which is not the current/expected behavior without ULPs. In the future we may add a redirect flag if users _do_ want the policy applied again but this would need to work for both ULP and non-ULP sockets and be opt-in to avoid breaking existing programs. Also to avoid polluting the flag space with an internal flag we reuse the flag space overlapping MSG_SENDPAGE_NOPOLICY with MSG_WAITFORONE. Here WAITFORONE is specific to recv path and SENDPAGE_NOPOLICY is only used for sendpage hooks. The last thing to verify is user space API is masked correctly to ensure the flag can not be set by user. (Note this needs to be true regardless because we have internal flags already in-use that user space should not be able to set). But for completeness we have two UAPI paths into sendpage, sendfile and splice. In the sendfile case the function do_sendfile() zero's flags, ./fs/read_write.c: static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { ... fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif file_start_write(out.file); retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); } In the splice case the pipe_to_sendpage "actor" is used which masks flags with SPLICE_F_MORE. ./fs/splice.c: static int pipe_to_sendpage(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) { ... more = (sd->flags & SPLICE_F_MORE) ? MSG_MORE : 0; ... } Confirming what we expect that internal flags are in fact internal to socket side. Fixes: d3b18ad31f93 ("tls: add bpf support to sk_msg handling") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/socket.h') diff --git a/include/linux/socket.h b/include/linux/socket.h index 8b571e9b9f76..84c48a3c0227 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -286,6 +286,7 @@ struct ucred { #define MSG_NOSIGNAL 0x4000 /* Do not generate SIGPIPE */ #define MSG_MORE 0x8000 /* Sender will send more */ #define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ +#define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */ #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN -- cgit v1.2.3